Authors: Xiongjun Guan, Yongjie Duan, Jianjiang Feng, Jie Zhou
Abstract: Skin distortion is a long standing challenge in fingerprint matching, which causes false non-matches. Previous studies have shown that the recognition rate can be improved by estimating the distortion field from a distorted fingerprint and then rectifying it into a normal fingerprint. However, existing rectification methods are based on principal component representation of distortion fields, which is not accurate and are very sensitive to finger pose. In this paper, we propose a rectification method where a self-reference based network is utilized to directly estimate the dense distortion field of distorted fingerprint instead of its low dimensional representation. This method can output accurate distortion fields of distorted fingerprints with various finger poses and distortion patterns. We conducted experiments on FVC2004 DB1\_A, expanded Tsinghua Distorted Fingerprint database (with additional distorted fingerprints in diverse finger poses and distortion patterns) and a latent fingerprint database. Experimental results demonstrate that our proposed method achieves the state-of-the-art rectification performance in terms of distortion field estimation and rectified fingerprint matching.
Authors: Ian Huang, Guandao Yang, Leonidas Guibas
Abstract: Graphics design is important for various applications, including movie production and game design. To create a high-quality scene, designers usually need to spend hours in software like Blender, in which they might need to interleave and repeat operations, such as connecting material nodes, hundreds of times. Moreover, slightly different design goals may require completely different sequences, making automation difficult. In this paper, we propose a system that leverages Vision-Language Models (VLMs), like GPT-4V, to intelligently search the design action space to arrive at an answer that can satisfy a user's intent. Specifically, we design a vision-based edit generator and state evaluator to work together to find the correct sequence of actions to achieve the goal. Inspired by the role of visual imagination in the human design process, we supplement the visual reasoning capabilities of VLMs with "imagined" reference images from image-generation models, providing visual grounding of abstract language descriptions. In this paper, we provide empirical evidence suggesting our system can produce simple but tedious Blender editing sequences for tasks such as editing procedural materials from text and/or reference images, as well as adjusting lighting configurations for product renderings in complex scenes.
Authors: Longzhen Li, Guang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
Abstract: In this paper, we propose a new dataset distillation method that considers balancing global structure and local details when distilling the information from a large dataset into a generative model. Dataset distillation has been proposed to reduce the size of the required dataset when training models. The conventional dataset distillation methods face the problem of long redeployment time and poor cross-architecture performance. Moreover, previous methods focused too much on the high-level semantic attributes between the synthetic dataset and the original dataset while ignoring the local features such as texture and shape. Based on the above understanding, we propose a new method for distilling the original image dataset into a generative model. Our method involves using a conditional generative adversarial network to generate the distilled dataset. Subsequently, we ensure balancing global structure and local details in the distillation process, continuously optimizing the generator for more information-dense dataset generation.
Authors: Jingxue Huang, Xilai Li, Tianshu Tan, Xiaosong Li, Tao Ye
Abstract: Multi-modal image fusion (MMIF) maps useful information from various modalities into the same representation space, thereby producing an informative fused image. However, the existing fusion algorithms tend to symmetrically fuse the multi-modal images, causing the loss of shallow information or bias towards a single modality in certain regions of the fusion results. In this study, we analyzed the spatial distribution differences of information in different modalities and proved that encoding features within the same network is not conducive to achieving simultaneous deep feature space alignment for multi-modal images. To overcome this issue, a Multi-Modal Asymmetric UNet (MMA-UNet) was proposed. We separately trained specialized feature encoders for different modal and implemented a cross-scale fusion strategy to maintain the features from different modalities within the same representation space, ensuring a balanced information fusion process. Furthermore, extensive fusion and downstream task experiments were conducted to demonstrate the efficiency of MMA-UNet in fusing infrared and visible image information, producing visually natural and semantically rich fusion results. Its performance surpasses that of the state-of-the-art comparison fusion methods.
Authors: Chao Yi, Lu Ren, De-Chuan Zhan, Han-Jia Ye
Abstract: CLIP showcases exceptional cross-modal matching capabilities due to its training on image-text contrastive learning tasks. However, without specific optimization for unimodal scenarios, its performance in single-modality feature extraction might be suboptimal. Despite this, some studies have directly used CLIP's image encoder for tasks like few-shot classification, introducing a misalignment between its pre-training objectives and feature extraction methods. This inconsistency can diminish the quality of the image's feature representation, adversely affecting CLIP's effectiveness in target tasks. In this paper, we view text features as precise neighbors of image features in CLIP's space and present a novel CrOss-moDal nEighbor Representation(CODER) based on the distance structure between images and their neighbor texts. This feature extraction method aligns better with CLIP's pre-training objectives, thereby fully leveraging CLIP's robust cross-modal capabilities. The key to construct a high-quality CODER lies in how to create a vast amount of high-quality and diverse texts to match with images. We introduce the Auto Text Generator(ATG) to automatically generate the required texts in a data-free and training-free manner. We apply CODER to CLIP's zero-shot and few-shot image classification tasks. Experiment results across various datasets and models confirm CODER's effectiveness. Code is available at:https://github.com/YCaigogogo/CVPR24-CODER.
Authors: Marina Fuster, Ignacio Vidaurreta
Abstract: In this paper we investigate the vulnerability that facial recognition systems present to adversarial examples by introducing a new methodology from the attacker perspective. The technique is based on the use of the autoencoder latent space, organized with principal component analysis. We intend to analyze the potential to craft adversarial examples suitable for both dodging and impersonation attacks, against state-of-the-art systems. Our initial hypothesis, which was not strongly favoured by the results, stated that it would be possible to separate between the "identity" and "facial expression" features to produce high-quality examples. Despite the findings not supporting it, the results sparked insights into adversarial examples generation and opened new research avenues in the area.
Authors: Puyi Wang, Wei Sun, Zicheng Zhang, Jun Jia, Yanwei Jiang, Zhichao Zhang, Xiongkuo Min, Guangtao Zhai
Abstract: Traditional deep neural network (DNN)-based image quality assessment (IQA) models leverage convolutional neural networks (CNN) or Transformer to learn the quality-aware feature representation, achieving commendable performance on natural scene images. However, when applied to AI-Generated images (AGIs), these DNN-based IQA models exhibit subpar performance. This situation is largely due to the semantic inaccuracies inherent in certain AGIs caused by uncontrollable nature of the generation process. Thus, the capability to discern semantic content becomes crucial for assessing the quality of AGIs. Traditional DNN-based IQA models, constrained by limited parameter complexity and training data, struggle to capture complex fine-grained semantic features, making it challenging to grasp the existence and coherence of semantic content of the entire image. To address the shortfall in semantic content perception of current IQA models, we introduce a large Multi-modality model Assisted AI-Generated Image Quality Assessment (MA-AGIQA) model, which utilizes semantically informed guidance to sense semantic information and extract semantic vectors through carefully designed text prompts. Moreover, it employs a mixture of experts (MoE) structure to dynamically integrate the semantic information with the quality-aware features extracted by traditional DNN-based IQA models. Comprehensive experiments conducted on two AI-generated content datasets, AIGCQA-20k and AGIQA-3k show that MA-AGIQA achieves state-of-the-art performance, and demonstrate its superior generalization capabilities on assessing the quality of AGIs. Code is available at https://github.com/wangpuyi/MA-AGIQA.
Authors: Yuhang Gan, Wenjie Xuan, Hang Chen, Juhua Liu, Bo Du
Abstract: Change Detection is a crucial but extremely challenging task of remote sensing image analysis, and much progress has been made with the rapid development of deep learning. However, most existing deep learning-based change detection methods mainly focus on intricate feature extraction and multi-scale feature fusion, while ignoring the insufficient utilization of features in the intermediate stages, thus resulting in sub-optimal results. To this end, we propose a novel framework, named RFL-CDNet, that utilizes richer feature learning to boost change detection performance. Specifically, we first introduce deep multiple supervision to enhance intermediate representations, thus unleashing the potential of backbone feature extractor at each stage. Furthermore, we design the Coarse-To-Fine Guiding (C2FG) module and the Learnable Fusion (LF) module to further improve feature learning and obtain more discriminative feature representations. The C2FG module aims to seamlessly integrate the side prediction from the previous coarse-scale into the current fine-scale prediction in a coarse-to-fine manner, while LF module assumes that the contribution of each stage and each spatial location is independent, thus designing a learnable module to fuse multiple predictions. Experiments on several benchmark datasets show that our proposed RFL-CDNet achieves state-of-the-art performance on WHU cultivated land dataset and CDD dataset, and the second-best performance on WHU building dataset. The source code and models are publicly available at https://github.com/Hhaizee/RFL-CDNet.
Authors: Xiao Jiang, Fei Zhou
Abstract: Dynamic Vision Sensors (DVS) have recently generated great interest because of the advantages of wide dynamic range and low latency compared with conventional frame-based cameras. However, the complicated behaviors in dim light conditions are still not clear, restricting the applications of DVS. In this paper, we analyze the typical DVS circuit, and find that there exists discontinuity of event triggering time. In dim light conditions, the discontinuity becomes prominent. We point out that the discontinuity depends exclusively on the changing speed of light intensity. Experimental results on real event data validate the analysis and the existence of discontinuity that reveals the non-first-order behaviors of DVS in dim light conditions.
Authors: Pinxuan Dai, Jiamin Xu, Wenxiang Xie, Xinguo Liu, Huamin Wang, Weiwei Xu
Abstract: We propose a novel point-based representation, Gaussian surfels, to combine the advantages of the flexible optimization procedure in 3D Gaussian points and the surface alignment property of surfels. This is achieved by directly setting the z-scale of 3D Gaussian points to 0, effectively flattening the original 3D ellipsoid into a 2D ellipse. Such a design provides clear guidance to the optimizer. By treating the local z-axis as the normal direction, it greatly improves optimization stability and surface alignment. While the derivatives to the local z-axis computed from the covariance matrix are zero in this setting, we design a self-supervised normal-depth consistency loss to remedy this issue. Monocular normal priors and foreground masks are incorporated to enhance the quality of the reconstruction, mitigating issues related to highlights and background. We propose a volumetric cutting method to aggregate the information of Gaussian surfels so as to remove erroneous points in depth maps generated by alpha blending. Finally, we apply screened Poisson reconstruction method to the fused depth maps to extract the surface mesh. Experimental results show that our method demonstrates superior performance in surface reconstruction compared to state-of-the-art neural volume rendering and point-based rendering methods.
Authors: Junyi Gu, Mauro Bellone, Tom\'a\v{s} Pivo\v{n}ka, Raivo Sell
Abstract: Critical research about camera-and-LiDAR-based semantic object segmentation for autonomous driving significantly benefited from the recent development of deep learning. Specifically, the vision transformer is the novel ground-breaker that successfully brought the multi-head-attention mechanism to computer vision applications. Therefore, we propose a vision-transformer-based network to carry out camera-LiDAR fusion for semantic segmentation applied to autonomous driving. Our proposal uses the novel progressive-assemble strategy of vision transformers on a double-direction network and then integrates the results in a cross-fusion strategy over the transformer decoder layers. Unlike other works in the literature, our camera-LiDAR fusion transformers have been evaluated in challenging conditions like rain and low illumination, showing robust performance. The paper reports the segmentation results over the vehicle and human classes in different modalities: camera-only, LiDAR-only, and camera-LiDAR fusion. We perform coherent controlled benchmark experiments of CLFT against other networks that are also designed for semantic segmentation. The experiments aim to evaluate the performance of CLFT independently from two perspectives: multimodal sensor fusion and backbone architectures. The quantitative assessments show our CLFT networks yield an improvement of up to 10\% for challenging dark-wet conditions when comparing with Fully-Convolutional-Neural-Network-based (FCN) camera-LiDAR fusion neural network. Contrasting to the network with transformer backbone but using single modality input, the all-around improvement is 5-10\%.
Authors: Zhongze Wang, Haitao Zhao, Jingchao Peng, Lujian Yao, Kaijie Zhao
Abstract: Unpaired image dehazing (UID) holds significant research importance due to the challenges in acquiring haze/clear image pairs with identical backgrounds. This paper proposes a novel method for UID named Orthogonal Decoupling Contrastive Regularization (ODCR). Our method is grounded in the assumption that an image consists of both haze-related features, which influence the degree of haze, and haze-unrelated features, such as texture and semantic information. ODCR aims to ensure that the haze-related features of the dehazing result closely resemble those of the clear image, while the haze-unrelated features align with the input hazy image. To accomplish the motivation, Orthogonal MLPs optimized geometrically on the Stiefel manifold are proposed, which can project image features into an orthogonal space, thereby reducing the relevance between different features. Furthermore, a task-driven Depth-wise Feature Classifier (DWFC) is proposed, which assigns weights to the orthogonal features based on the contribution of each channel's feature in predicting whether the feature source is hazy or clear in a self-supervised fashion. Finally, a Weighted PatchNCE (WPNCE) loss is introduced to achieve the pulling of haze-related features in the output image toward those of clear images, while bringing haze-unrelated features close to those of the hazy input. Extensive experiments demonstrate the superior performance of our ODCR method on UID.
Authors: Yiming Bao, Xu Zhao, Dahong Qian
Abstract: Temporal 3D human pose estimation from monocular videos is a challenging task in human-centered computer vision due to the depth ambiguity of 2D-to-3D lifting. To improve accuracy and address occlusion issues, inertial sensor has been introduced to provide complementary source of information. However, it remains challenging to integrate heterogeneous sensor data for producing physically rational 3D human poses. In this paper, we propose a novel framework, Real-time Optimization and Fusion (RTOF), to address this issue. We first incorporate sparse inertial orientations into a parametric human skeleton to refine 3D poses in kinematics. The poses are then optimized by energy functions built on both visual and inertial observations to reduce the temporal jitters. Our framework outputs smooth and biomechanically plausible human motion. Comprehensive experiments with ablation studies demonstrate its rationality and efficiency. On Total Capture dataset, the pose estimation error is significantly decreased compared to the baseline method.
Authors: Lichao Wang, Zhihao Yuan, Jinke Ren, Shuguang Cui, Zhen Li
Abstract: Text-to-point-cloud cross-modal localization is an emerging vision-language task critical for future robot-human collaboration. It seeks to localize a position from a city-scale point cloud scene based on a few natural language instructions. In this paper, we address two key limitations of existing approaches: 1) their reliance on ground-truth instances as input; and 2) their neglect of the relative positions among potential instances. Our proposed model follows a two-stage pipeline, including a coarse stage for text-cell retrieval and a fine stage for position estimation. In both stages, we introduce an instance query extractor, in which the cells are encoded by a 3D sparse convolution U-Net to generate the multi-scale point cloud features, and a set of queries iteratively attend to these features to represent instances. In the coarse stage, a row-column relative position-aware self-attention (RowColRPA) module is designed to capture the spatial relations among the instance queries. In the fine stage, a multi-modal relative position-aware cross-attention (RPCA) module is developed to fuse the text and point cloud features along with spatial relations for improving fine position estimation. Experiment results on the KITTI360Pose dataset demonstrate that our model achieves competitive performance with the state-of-the-art models without taking ground-truth instances as input.
Authors: Ziya Ata Yaz{\i}c{\i}, \.Ilkay \"Oks\"uz, Haz{\i}m Kemal Ekenel
Abstract: Convolutional Neural Networks (CNNs) have become widely adopted for medical image segmentation tasks, demonstrating promising performance. However, the inherent inductive biases in convolutional architectures limit their ability to model long-range dependencies and spatial correlations. While recent transformer-based architectures address these limitations by leveraging self-attention mechanisms to encode long-range dependencies and learn expressive representations, they often struggle to extract low-level features and are highly dependent on data availability. This motivated us for the development of GLIMS, a data-efficient attention-guided hybrid volumetric segmentation network. GLIMS utilizes Dilated Feature Aggregator Convolutional Blocks (DACB) to capture local-global feature correlations efficiently. Furthermore, the incorporated Swin Transformer-based bottleneck bridges the local and global features to improve the robustness of the model. Additionally, GLIMS employs an attention-guided segmentation approach through Channel and Spatial-Wise Attention Blocks (CSAB) to localize expressive features for fine-grained border segmentation. Quantitative and qualitative results on glioblastoma and multi-organ CT segmentation tasks demonstrate GLIMS' effectiveness in terms of complexity and accuracy. GLIMS demonstrated outstanding performance on BraTS2021 and BTCV datasets, surpassing the performance of Swin UNETR. Notably, GLIMS achieved this high performance with a significantly reduced number of trainable parameters. Specifically, GLIMS has 47.16M trainable parameters and 72.30G FLOPs, while Swin UNETR has 61.98M trainable parameters and 394.84G FLOPs. The code is publicly available on https://github.com/yaziciz/GLIMS.
Authors: Yuval Haitman, Oded Bialer
Abstract: Automotive radars have an important role in autonomous driving systems. The main challenge in automotive radar detection is the radar's wide point spread function (PSF) in the angular domain that causes blurriness and clutter in the radar image. Numerous studies suggest employing an 'end-to-end' learning strategy using a Deep Neural Network (DNN) to directly detect objects from radar images. This approach implicitly addresses the PSF's impact on objects of interest. In this paper, we propose an alternative approach, which we term "Boosting Radar Reflections" (BoostRad). In BoostRad, a first DNN is trained to narrow the PSF for all the reflection points in the scene. The output of the first DNN is a boosted reflection image with higher resolution and reduced clutter, resulting in a sharper and cleaner image. Subsequently, a second DNN is employed to detect objects within the boosted reflection image. We develop a novel method for training the boosting DNN that incorporates domain knowledge of radar's PSF characteristics. BoostRad's performance is evaluated using the RADDet and CARRADA datasets, revealing its superiority over reference methods.
Authors: Zitong Zhang, Yang Liu, Hao Sun
Abstract: Data-driven discovery of governing equations has kindled significant interests in many science and engineering areas. Existing studies primarily focus on uncovering equations that govern nonlinear dynamics based on direct measurement of the system states (e.g., trajectories). Limited efforts have been placed on distilling governing laws of dynamics directly from videos for moving targets in a 3D space. To this end, we propose a vision-based approach to automatically uncover governing equations of nonlinear dynamics for 3D moving targets via raw videos recorded by a set of cameras. The approach is composed of three key blocks: (1) a target tracking module that extracts plane pixel motions of the moving target in each video, (2) a Rodrigues' rotation formula-based coordinate transformation learning module that reconstructs the 3D coordinates with respect to a predefined reference point, and (3) a spline-enhanced library-based sparse regressor that uncovers the underlying governing law of dynamics. This framework is capable of effectively handling the challenges associated with measurement data, e.g., noise in the video, imprecise tracking of the target that causes data missing, etc. The efficacy of our method has been demonstrated through multiple sets of synthetic videos considering different nonlinear dynamics.
Authors: Xiaoshuai Wu, Xin Liao, Bo Ou, Yuling Liu, Zheng Qin
Abstract: AI-generated content has accelerated the topic of media synthesis, particularly Deepfake, which can manipulate our portraits for positive or malicious purposes. Before releasing these threatening face images, one promising forensics solution is the injection of robust watermarks to track their own provenance. However, we argue that current watermarking models, originally devised for genuine images, may harm the deployed Deepfake detectors when directly applied to forged images, since the watermarks are prone to overlap with the forgery signals used for detection. To bridge this gap, we thus propose AdvMark, on behalf of proactive forensics, to exploit the adversarial vulnerability of passive detectors for good. Specifically, AdvMark serves as a plug-and-play procedure for fine-tuning any robust watermarking into adversarial watermarking, to enhance the forensic detectability of watermarked images; meanwhile, the watermarks can still be extracted for provenance tracking. Extensive experiments demonstrate the effectiveness of the proposed AdvMark, leveraging robust watermarking to fool Deepfake detectors, which can help improve the accuracy of downstream Deepfake detection without tuning the in-the-wild detectors. We believe this work will shed some light on the harmless proactive forensics against Deepfake.
Authors: Weifeng Wei, Jie Wang
Abstract: We introduce a high-fidelity neural implicit dense visual Simultaneous Localization and Mapping (SLAM) system, termed DF-SLAM. In our work, we employ dictionary factors for scene representation, encoding the geometry and appearance information of the scene as a combination of basis and coefficient factors. Compared to neural implicit SLAM methods that directly encode scene information as features, our method exhibits superior scene detail reconstruction capabilities and more efficient memory usage, while our model size is insensitive to the size of the scene map, making our method more suitable for large-scale scenes. Additionally, we employ feature integration rendering to accelerate color rendering speed while ensuring color rendering quality, further enhancing the real-time performance of our neural SLAM method. Extensive experiments on synthetic and real-world datasets demonstrate that our method is competitive with existing state-of-the-art neural implicit SLAM methods in terms of real-time performance, localization accuracy, and scene reconstruction quality. Our source code is available at https://github.com/funcdecl/DF-SLAM.
Authors: Zhixiong Huang, Xinying Wang, Jinjiang Li, Shenglan Liu, Lin Feng
Abstract: Underwater scenes intrinsically involve degradation problems owing to heterogeneous ocean elements. Prevailing underwater image enhancement (UIE) methods stick to straightforward feature modeling to learn the mapping function, which leads to limited vision gain as it lacks more explicit physical cues (e.g., depth). In this work, we investigate injecting the depth prior into the deep UIE model for more precise scene enhancement capability. To this end, we present a novel depth-guided perception UIE framework, dubbed underwater variable zoom (UVZ). Specifically, UVZ resorts to a two-stage pipeline. First, a depth estimation network is designed to generate critical depth maps, combined with an auxiliary supervision network introduced to suppress estimation differences during training. Second, UVZ parses near-far scenarios by harnessing the predicted depth maps, enabling local and non-local perceiving in different regions. Extensive experiments on five benchmark datasets demonstrate that UVZ achieves superior visual gain and delivers promising quantitative metrics. Besides, UVZ is confirmed to exhibit good generalization in some visual tasks, especially in unusual lighting conditions. The code, models and results are available at: https://github.com/WindySprint/UVZ.
Authors: Tahira Shehzadi, Didier Stricker, Muhammad Zeshan Afzal
Abstract: Document layout analysis involves understanding the arrangement of elements within a document. This paper navigates the complexities of understanding various elements within document images, such as text, images, tables, and headings. The approach employs an advanced Transformer-based object detection network as an innovative graphical page object detector for identifying tables, figures, and displayed elements. We introduce a query encoding mechanism to provide high-quality object queries for contrastive learning, enhancing efficiency in the decoder phase. We also present a hybrid matching scheme that integrates the decoder's original one-to-one matching strategy with the one-to-many matching strategy during the training phase. This approach aims to improve the model's accuracy and versatility in detecting various graphical elements on a page. Our experiments on PubLayNet, DocLayNet, and PubTables benchmarks show that our approach outperforms current state-of-the-art methods. It achieves an average precision of 97.3% on PubLayNet, 81.6% on DocLayNet, and 98.6 on PubTables, demonstrating its superior performance in layout analysis. These advancements not only enhance the conversion of document images into editable and accessible formats but also streamline information retrieval and data extraction processes.
Authors: Like Xin, Wanqi Yang, Lei Wang, Ming Yang
Abstract: This paper focuses on unpaired multi-view clustering (UMC), a challenging problem where paired observed samples are unavailable across multiple views. The goal is to perform effective joint clustering using the unpaired observed samples in all views. In incomplete multi-view clustering, existing methods typically rely on sample pairing between views to capture their complementary. However, that is not applicable in the case of UMC. Hence, we aim to extract the consistent cluster structure across views. In UMC, two challenging issues arise: uncertain cluster structure due to lack of label and uncertain pairing relationship due to absence of paired samples. We assume that the view with a good cluster structure is the reliable view, which acts as a supervisor to guide the clustering of the other views. With the guidance of reliable views, a more certain cluster structure of these views is obtained while achieving alignment between reliable views and other views. Then we propose Reliable view Guidance with one reliable view (RG-UMC) and multiple reliable views (RGs-UMC) for UMC. Specifically, we design alignment modules with one reliable view and multiple reliable views, respectively, to adaptively guide the optimization process. Also, we utilize the compactness module to enhance the relationship of samples within the same cluster. Meanwhile, an orthogonal constraint is applied to latent representation to obtain discriminate features. Extensive experiments show that both RG-UMC and RGs-UMC outperform the best state-of-the-art method by an average of 24.14\% and 29.42\% in NMI, respectively.
Authors: Di Wu, Shicai Fan, Xue Zhou, Li Yu, Yuzhong Deng, Jianxiao Zou, Baihong Lin
Abstract: Reconstruction-based methods have been commonly used for unsupervised anomaly detection, in which a normal image is reconstructed and compared with the given test image to detect and locate anomalies. Recently, diffusion models have shown promising applications for anomaly detection due to their powerful generative ability. However, these models lack strict mathematical support for normal image reconstruction and unexpectedly suffer from low reconstruction quality. To address these issues, this paper proposes a novel and highly-interpretable method named Masked Diffusion Posterior Sampling (MDPS). In MDPS, the problem of normal image reconstruction is mathematically modeled as multiple diffusion posterior sampling for normal images based on the devised masked noisy observation model and the diffusion-based normal image prior under Bayesian framework. Using a metric designed from pixel-level and perceptual-level perspectives, MDPS can effectively compute the difference map between each normal posterior sample and the given test image. Anomaly scores are obtained by averaging all difference maps for multiple posterior samples. Exhaustive experiments on MVTec and BTAD datasets demonstrate that MDPS can achieve state-of-the-art performance in normal image reconstruction quality as well as anomaly detection and localization.
Authors: Farzad Nozarian, Shashank Agarwal, Farzaneh Rezaeianaran, Danish Shahzad, Atanas Poibrenski, Christian M\"uller, Philipp Slusallek
Abstract: Semi-supervised 3D object detection can benefit from the promising pseudo-labeling technique when labeled data is limited. However, recent approaches have overlooked the impact of noisy pseudo-labels during training, despite efforts to enhance pseudo-label quality through confidence-based filtering. In this paper, we examine the impact of noisy pseudo-labels on IoU-based target assignment and propose the Reliable Student framework, which incorporates two complementary approaches to mitigate errors. First, it involves a class-aware target assignment strategy that reduces false negative assignments in difficult classes. Second, it includes a reliability weighting strategy that suppresses false positive assignment errors while also addressing remaining false negatives from the first step. The reliability weights are determined by querying the teacher network for confidence scores of the student-generated proposals. Our work surpasses the previous state-of-the-art on KITTI 3D object detection benchmark on point clouds in the semi-supervised setting. On 1% labeled data, our approach achieves a 6.2% AP improvement for the pedestrian class, despite having only 37 labeled samples available. The improvements become significant for the 2% setting, achieving 6.0% AP and 5.7% AP improvements for the pedestrian and cyclist classes, respectively.
Authors: Mirza Tanzim Sami, Da Yan, Saugat Adhikari, Lyuheng Yuan, Jiao Han, Zhe Jiang, Jalal Khalil, Yang Zhou
Abstract: Accurate and timely mapping of flood extent from high-resolution satellite imagery plays a crucial role in disaster management such as damage assessment and relief activities. However, current state-of-the-art solutions are based on U-Net, which can-not segment the flood pixels accurately due to the ambiguous pixels (e.g., tree canopies, clouds) that prevent a direct judgement from only the spectral features. Thanks to the digital elevation model (DEM) data readily available from sources such as United States Geological Survey (USGS), this work explores the use of an elevation map to improve flood extent mapping. We propose, EvaNet, an elevation-guided segmentation model based on the encoder-decoder architecture with two novel techniques: (1) a loss function encoding the physical law of gravity that if a location is flooded (resp. dry), then its adjacent locations with a lower (resp. higher) elevation must also be flooded (resp. dry); (2) a new (de)convolution operation that integrates the elevation map by a location sensitive gating mechanism to regulate how much spectral features flow through adjacent layers. Extensive experiments show that EvaNet significantly outperforms the U-Net baselines, and works as a perfect drop-in replacement for U-Net in existing solutions to flood extent mapping.
Authors: Laksh Nanwani, Kumaraditya Gupta, Aditya Mathur, Swayam Agrawal, A. H. Abdul Hafez, K. Madhava Krishna
Abstract: Humans excel at forming mental maps of their surroundings, equipping them to understand object relationships and navigate based on language queries. Our previous work SI Maps [1] showed that having instance-level information and the semantic understanding of an environment helps significantly improve performance for language-guided tasks. We extend this instance-level approach to 3D while increasing the pipeline's robustness and improving quantitative and qualitative results. Our method leverages foundational models for object recognition, image segmentation, and feature extraction. We propose a representation that results in a 3D point cloud map with instance-level embeddings, which bring in the semantic understanding that natural language commands can query. Quantitatively, the work improves upon the success rate of language-guided tasks. At the same time, we qualitatively observe the ability to identify instances more clearly and leverage the foundational models and language and image-aligned embeddings to identify objects that, otherwise, a closed-set approach wouldn't be able to identify.
Authors: Xiao Wang, Qian Zhu, Jiandong Jin, Jun Zhu, Futian Wang, Bo Jiang, Yaowei Wang, Yonghong Tian
Abstract: Existing pedestrian attribute recognition (PAR) algorithms are mainly developed based on a static image, however, the performance is unreliable in challenging scenarios, such as heavy occlusion, motion blur, etc. In this work, we propose to understand human attributes using video frames that can fully use temporal information by fine-tuning a pre-trained multi-modal foundation model efficiently. Specifically, we formulate the video-based PAR as a vision-language fusion problem and adopt a pre-trained foundation model CLIP to extract the visual features. More importantly, we propose a novel spatiotemporal side-tuning strategy to achieve parameter-efficient optimization of the pre-trained vision foundation model. To better utilize the semantic information, we take the full attribute list that needs to be recognized as another input and transform the attribute words/phrases into the corresponding sentence via split, expand, and prompt operations. Then, the text encoder of CLIP is utilized for embedding processed attribute descriptions. The averaged visual tokens and text tokens are concatenated and fed into a fusion Transformer for multi-modal interactive learning. The enhanced tokens will be fed into a classification head for pedestrian attribute prediction. Extensive experiments on two large-scale video-based PAR datasets fully validated the effectiveness of our proposed framework. The source code of this paper is available at https://github.com/Event-AHU/OpenPAR.
Authors: Beno\^it G\'erin, Ana\"is Halin, Anthony Cioppa, Maxim Henry, Bernard Ghanem, Beno\^it Macq, Christophe De Vleeschouwer, Marc Van Droogenbroeck
Abstract: In the era of the Internet of Things (IoT), objects connect through a dynamic network, empowered by technologies like 5G, enabling real-time data sharing. However, smart objects, notably autonomous vehicles, face challenges in critical local computations due to limited resources. Lightweight AI models offer a solution but struggle with diverse data distributions. To address this limitation, we propose a novel Multi-Stream Cellular Test-Time Adaptation (MSC-TTA) setup where models adapt on the fly to a dynamic environment divided into cells. Then, we propose a real-time adaptive student-teacher method that leverages the multiple streams available in each cell to quickly adapt to changing data distributions. We validate our methodology in the context of autonomous vehicles navigating across cells defined based on location and weather conditions. To facilitate future benchmarking, we release a new multi-stream large-scale synthetic semantic segmentation dataset, called DADE, and show that our multi-stream approach outperforms a single-stream baseline. We believe that our work will open research opportunities in the IoT and 5G eras, offering solutions for real-time model adaptation.
Authors: Zheng Cheng, Guodong Fan, Jingchun Zhou, Min Gan, C. L. Philip Chen
Abstract: Underwater images often suffer from various issues such as low brightness, color shift, blurred details, and noise due to light absorption and scattering caused by water and suspended particles. Previous underwater image enhancement (UIE) methods have primarily focused on spatial domain enhancement, neglecting the frequency domain information inherent in the images. However, the degradation factors of underwater images are closely intertwined in the spatial domain. Although certain methods focus on enhancing images in the frequency domain, they overlook the inherent relationship between the image degradation factors and the information present in the frequency domain. As a result, these methods frequently enhance certain attributes of the improved image while inadequately addressing or even exacerbating other attributes. Moreover, many existing methods heavily rely on prior knowledge to address color shift problems in underwater images, limiting their flexibility and robustness. In order to overcome these limitations, we propose the Embedding Frequency and Dual Color Encoder Network (FDCE-Net) in our paper. The FDCE-Net consists of two main structures: (1) Frequency Spatial Network (FS-Net) aims to achieve initial enhancement by utilizing our designed Frequency Spatial Residual Block (FSRB) to decouple image degradation factors in the frequency domain and enhance different attributes separately. (2) To tackle the color shift issue, we introduce the Dual-Color Encoder (DCE). The DCE establishes correlations between color and semantic representations through cross-attention and leverages multi-scale image features to guide the optimization of adaptive color query. The final enhanced images are generated by combining the outputs of FS-Net and DCE through a fusion network. These images exhibit rich details, clear textures, low noise and natural colors.
Authors: Zelong Zeng, Kaname Tomite
Abstract: In anomaly segmentation for complex driving scenes, state-of-the-art approaches utilize anomaly scoring functions to calculate anomaly scores. For these functions, accurately predicting the logits of inlier classes for each pixel is crucial for precisely inferring the anomaly score. However, in real-world driving scenarios, the diversity of scenes often results in distorted manifolds of pixel embeddings in embedding space. This effect is not conducive to directly using the pixel embeddings for the logit prediction during inference, a concern overlooked by existing methods. To address this problem, we propose a novel method called Random Walk on Pixel Manifolds (RWPM). RWPM utilizes random walks to reveal the intrinsic relationships among pixels to refine the pixel embeddings. The refined pixel embeddings alleviate the distortion of manifolds, improving the accuracy of anomaly scores. Our extensive experiments show that RWPM consistently improve the performance of the existing anomaly segmentation methods and achieve the best results. Code: \url{https://github.com/ZelongZeng/RWPM}.
Authors: Krithika Iyer, Jadie Adams, Shireen Y. Elhabian
Abstract: Statistical shape modeling (SSM) is a powerful computational framework for quantifying and analyzing the geometric variability of anatomical structures, facilitating advancements in medical research, diagnostics, and treatment planning. Traditional methods for shape modeling from imaging data demand significant manual and computational resources. Additionally, these methods necessitate repeating the entire modeling pipeline to derive shape descriptors (e.g., surface-based point correspondences) for new data. While deep learning approaches have shown promise in streamlining the construction of SSMs on new data, they still rely on traditional techniques to supervise the training of the deep networks. Moreover, the predominant linearity assumption of traditional approaches restricts their efficacy, a limitation also inherited by deep learning models trained using optimized/established correspondences. Consequently, representing complex anatomies becomes challenging. To address these limitations, we introduce SCorP, a novel framework capable of predicting surface-based correspondences directly from unsegmented images. By leveraging the shape prior learned directly from surface meshes in an unsupervised manner, the proposed model eliminates the need for an optimized shape model for training supervision. The strong shape prior acts as a teacher and regularizes the feature learning of the student network to guide it in learning image-based features that are predictive of surface correspondences. The proposed model streamlines the training and inference phases by removing the supervision for the correspondence prediction task while alleviating the linearity assumption.
Authors: Michael Majurski, Sumeet Menon, Parniyan Farvardin, David Chapman
Abstract: Discriminative deep learning models with a linear+softmax final layer have a problem: the latent space only predicts the conditional probabilities $p(Y|X)$ but not the full joint distribution $p(Y,X)$, which necessitates a generative approach. The conditional probability cannot detect outliers, causing outlier sensitivity in softmax networks. This exacerbates model over-confidence impacting many problems, such as hallucinations, confounding biases, and dependence on large datasets. To address this we introduce a novel embedding constraint based on the Method of Moments (MoM). We investigate the use of polynomial moments ranging from 1st through 4th order hyper-covariance matrices. Furthermore, we use this embedding constraint to train an Axis-Aligned Gaussian Mixture Model (AAGMM) final layer, which learns not only the conditional, but also the joint distribution of the latent space. We apply this method to the domain of semi-supervised image classification by extending FlexMatch with our technique. We find our MoM constraint with the AAGMM layer is able to match the reported FlexMatch accuracy, while also modeling the joint distribution, thereby reducing outlier sensitivity. We also present a preliminary outlier detection strategy based on Mahalanobis distance and discuss future improvements to this strategy. Code is available at: \url{https://github.com/mmajurski/ssl-gmm}
Authors: Diana Sungatullina, Tomas Pajdla
Abstract: We present an approach to backpropagating through minimal problem solvers in end-to-end neural network training. Traditional methods relying on manually constructed formulas, finite differences, and autograd are laborious, approximate, and unstable for complex minimal problem solvers. We show that using the Implicit function theorem to calculate derivatives to backpropagate through the solution of a minimal problem solver is simple, fast, and stable. We compare our approach to (i) using the standard autograd on minimal problem solvers and relate it to existing backpropagation formulas through SVD-based and Eig-based solvers and (ii) implementing the backprop with an existing PyTorch Deep Declarative Networks (DDN) framework. We demonstrate our technique on a toy example of training outlier-rejection weights for 3D point registration and on a real application of training an outlier-rejection and RANSAC sampling network in image matching. Our method provides $100\%$ stability and is 10 times faster compared to autograd, which is unstable and slow, and compared to DDN, which is stable but also slow.
Authors: Maria Mihaela Trusca, Tinne Tuytelaars, Marie-Francine Moens
Abstract: Text-based semantic image editing assumes the manipulation of an image using a natural language instruction. Although recent works are capable of generating creative and qualitative images, the problem is still mostly approached as a black box sensitive to generating unexpected outputs. Therefore, we propose a novel model to enhance the text-based control of an image editor by explicitly reasoning about which parts of the image to alter or preserve. It relies on word alignments between a description of the original source image and the instruction that reflects the needed updates, and the input image. The proposed Diffusion Masking with word Alignments (DM-Align) allows the editing of an image in a transparent and explainable way. It is evaluated on a subset of the Bison dataset and a self-defined dataset dubbed Dream. When comparing to state-of-the-art baselines, quantitative and qualitative results show that DM-Align has superior performance in image editing conditioned on language instructions, well preserves the background of the image and can better cope with long text instructions.
Authors: Rong Zou, Marc Pollefeys, Denys Rozumnyi
Abstract: Moving objects are frequently seen in daily life and usually appear blurred in images due to their motion. While general object retrieval is a widely explored area in computer vision, it primarily focuses on sharp and static objects, and retrieval of motion-blurred objects in large image collections remains unexplored. We propose a method for object retrieval in images that are affected by motion blur. The proposed method learns a robust representation capable of matching blurred objects to their deblurred versions and vice versa. To evaluate our approach, we present the first large-scale datasets for blurred object retrieval, featuring images with objects exhibiting varying degrees of blur in various poses and scales. We conducted extensive experiments, showing that our method outperforms state-of-the-art retrieval methods on the new blur-retrieval datasets, which validates the effectiveness of the proposed approach.
Authors: Mingzhen Huang, Shan Jia, Zhou Zhou, Yan Ju, Jialing Cai, Siwei Lyu
Abstract: In the battle against widespread online misinformation, a growing problem is text-image inconsistency, where images are misleadingly paired with texts with different intent or meaning. Existing classification-based methods for text-image inconsistency can identify contextual inconsistencies but fail to provide explainable justifications for their decisions that humans can understand. Although more nuanced, human evaluation is impractical at scale and susceptible to errors. To address these limitations, this study introduces D-TIIL (Diffusion-based Text-Image Inconsistency Localization), which employs text-to-image diffusion models to localize semantic inconsistencies in text and image pairs. These models, trained on large-scale datasets act as ``omniscient" agents that filter out irrelevant information and incorporate background knowledge to identify inconsistencies. In addition, D-TIIL uses text embeddings and modified image regions to visualize these inconsistencies. To evaluate D-TIIL's efficacy, we introduce a new TIIL dataset containing 14K consistent and inconsistent text-image pairs. Unlike existing datasets, TIIL enables assessment at the level of individual words and image regions and is carefully designed to represent various inconsistencies. D-TIIL offers a scalable and evidence-based approach to identifying and localizing text-image inconsistency, providing a robust framework for future research combating misinformation.
Authors: Yong Dai, Xiaopeng Hong, Yabin Wang, Zhiheng Ma, Dongmei Jiang, Yaowei Wang
Abstract: Contemporary continual learning approaches typically select prompts from a pool, which function as supplementary inputs to a pre-trained model. However, this strategy is hindered by the inherent noise of its selection approach when handling increasing tasks. In response to these challenges, we reformulate the prompting approach for continual learning and propose the prompt customization (PC) method. PC mainly comprises a prompt generation module (PGM) and a prompt modulation module (PMM). In contrast to conventional methods that employ hard prompt selection, PGM assigns different coefficients to prompts from a fixed-sized pool of prompts and generates tailored prompts. Moreover, PMM further modulates the prompts by adaptively assigning weights according to the correlations between input data and corresponding prompts. We evaluate our method on four benchmark datasets for three diverse settings, including the class, domain, and task-agnostic incremental learning tasks. Experimental results demonstrate consistent improvement (by up to 16.2\%), yielded by the proposed method, over the state-of-the-art (SOTA) techniques.
Authors: Md Alif Rahman Ridoy, M Mahmud Hasan, Shovon Bhowmick
Abstract: In today's world, image processing plays a crucial role across various fields, from scientific research to industrial applications. But one particularly exciting application is image captioning. The potential impact of effective image captioning is vast. It can significantly boost the accuracy of search engines, making it easier to find relevant information. Moreover, it can greatly enhance accessibility for visually impaired individuals, providing them with a more immersive experience of digital content. However, despite its promise, image captioning presents several challenges. One major hurdle is extracting meaningful visual information from images and transforming it into coherent language. This requires bridging the gap between the visual and linguistic domains, a task that demands sophisticated algorithms and models. Our project is focused on addressing these challenges by developing an automatic image captioning architecture that combines the strengths of convolutional neural networks (CNNs) and encoder-decoder models. The CNN model is used to extract the visual features from images, and later, with the help of the encoder-decoder framework, captions are generated. We also did a performance comparison where we delved into the realm of pre-trained CNN models, experimenting with multiple architectures to understand their performance variations. In our quest for optimization, we also explored the integration of frequency regularization techniques to compress the "AlexNet" and "EfficientNetB0" model. We aimed to see if this compressed model could maintain its effectiveness in generating image captions while being more resource-efficient.
Authors: Xiaolong Li, Jiawei Mo, Ying Wang, Chethan Parameshwara, Xiaohan Fei, Ashwin Swaminathan, CJ Taylor, Zhuowen Tu, Paolo Favaro, Stefano Soatto
Abstract: In this paper, we propose an effective two-stage approach named Grounded-Dreamer to generate 3D assets that can accurately follow complex, compositional text prompts while achieving high fidelity by using a pre-trained multi-view diffusion model. Multi-view diffusion models, such as MVDream, have shown to generate high-fidelity 3D assets using score distillation sampling (SDS). However, applied naively, these methods often fail to comprehend compositional text prompts, and may often entirely omit certain subjects or parts. To address this issue, we first advocate leveraging text-guided 4-view images as the bottleneck in the text-to-3D pipeline. We then introduce an attention refocusing mechanism to encourage text-aligned 4-view image generation, without the necessity to re-train the multi-view diffusion model or craft a high-quality compositional 3D dataset. We further propose a hybrid optimization strategy to encourage synergy between the SDS loss and the sparse RGB reference images. Our method consistently outperforms previous state-of-the-art (SOTA) methods in generating compositional 3D assets, excelling in both quality and accuracy, and enabling diverse 3D from the same text prompt.
Authors: Daming Gao, Yang Bai, Min Cao, Hao Dou, Mang Ye, Min Zhang
Abstract: Text-based person search (TBPS) aims to retrieve images of a specific person from a large image gallery based on a natural language description. Existing methods rely on massive annotated image-text data to achieve satisfactory performance in fully-supervised learning. It poses a significant challenge in practice, as acquiring person images from surveillance videos is relatively easy, while obtaining annotated texts is challenging. The paper undertakes a pioneering initiative to explore TBPS under the semi-supervised setting, where only a limited number of person images are annotated with textual descriptions while the majority of images lack annotations. We present a two-stage basic solution based on generation-then-retrieval for semi-supervised TBPS. The generation stage enriches annotated data by applying an image captioning model to generate pseudo-texts for unannotated images. Later, the retrieval stage performs fully-supervised retrieval learning using the augmented data. Significantly, considering the noise interference of the pseudo-texts on retrieval learning, we propose a noise-robust retrieval framework that enhances the ability of the retrieval model to handle noisy data. The framework integrates two key strategies: Hybrid Patch-Channel Masking (PC-Mask) to refine the model architecture, and Noise-Guided Progressive Training (NP-Train) to enhance the training process. PC-Mask performs masking on the input data at both the patch-level and the channel-level to prevent overfitting noisy supervision. NP-Train introduces a progressive training schedule based on the noise level of pseudo-texts to facilitate noise-robust learning. Extensive experiments on multiple TBPS benchmarks show that the proposed framework achieves promising performance under the semi-supervised setting.
Authors: Ruitao Xie, Connor Qiu, Guoping Qiu
Abstract: This paper explores how artificial intelligence (AI) technology can contribute to achieve progress on good health and well-being, one of the United Nations' 17 Sustainable Development Goals. It is estimated that one in ten of the global population lived with a mental disorder. Inspired by studies showing that engaging and viewing beautiful natural images can make people feel happier and less stressful, lead to higher emotional well-being, and can even have therapeutic values, we explore how AI can help to promote mental health by developing automatic algorithms for finding beautiful and happy images. We first construct a large image database consisting of nearly 20K very high resolution colour photographs of natural scenes where each image is labelled with beautifulness and happiness scores by about 10 observers. Statistics of the database shows that there is a good correlation between the beautifulness and happiness scores which provides anecdotal evidence to corroborate that engaging beautiful natural images can potentially benefit mental well-being. Building on this unique database, the very first of its kind, we have developed a deep learning based model for automatically predicting the beautifulness and happiness scores of natural images. Experimental results are presented to show that it is possible to develop AI algorithms to automatically assess an image's beautifulness and happiness values which can in turn be used to develop applications for promoting mental health and well-being.
Authors: Nuo Xu, Jianfeng Liao, Qiwei Meng, Wei Song
Abstract: Efficient waste management and recycling heavily rely on garbage exploration and identification. In this study, we propose GSA2Seg (Garbage Segmentation and Attribute Analysis), a novel visual approach that utilizes quadruped robotic dogs as autonomous agents to address waste management and recycling challenges in diverse indoor and outdoor environments. Equipped with advanced visual perception system, including visual sensors and instance segmentators, the robotic dogs adeptly navigate their surroundings, diligently searching for common garbage items. Inspired by open-vocabulary algorithms, we introduce an innovative method for object attribute analysis. By combining garbage segmentation and attribute analysis techniques, the robotic dogs accurately determine the state of the trash, including its position and placement properties. This information enhances the robotic arm's grasping capabilities, facilitating successful garbage retrieval. Additionally, we contribute an image dataset, named GSA2D, to support evaluation. Through extensive experiments on GSA2D, this paper provides a comprehensive analysis of GSA2Seg's effectiveness. Dataset available: \href{https://www.kaggle.com/datasets/hellob/gsa2d-2024}{https://www.kaggle.com/datasets/hellob/gsa2d-2024}.
URLs: https://www.kaggle.com/datasets/hellob/gsa2d-2024, https://www.kaggle.com/datasets/hellob/gsa2d-2024
Authors: Haiwen Diao, Ying Zhang, Shang Gao, Xiang Ruan, Huchuan Lu
Abstract: Image-text matching remains a challenging task due to heterogeneous semantic diversity across modalities and insufficient distance separability within triplets. Different from previous approaches focusing on enhancing multi-modal representations or exploiting cross-modal correspondence for more accurate retrieval, in this paper we aim to leverage the knowledge transfer between peer branches in a boosting manner to seek a more powerful matching model. Specifically, we propose a brand-new Deep Boosting Learning (DBL) algorithm, where an anchor branch is first trained to provide insights into the data properties, with a target branch gaining more advanced knowledge to develop optimal features and distance metrics. Concretely, an anchor branch initially learns the absolute or relative distance between positive and negative pairs, providing a foundational understanding of the particular network and data distribution. Building upon this knowledge, a target branch is concurrently tasked with more adaptive margin constraints to further enlarge the relative distance between matched and unmatched samples. Extensive experiments validate that our DBL can achieve impressive and consistent improvements based on various recent state-of-the-art models in the image-text matching field, and outperform related popular cooperative strategies, e.g., Conventional Distillation, Mutual Learning, and Contrastive Learning. Beyond the above, we confirm that DBL can be seamlessly integrated into their training scenarios and achieve superior performance under the same computational costs, demonstrating the flexibility and broad applicability of our proposed method. Our code is publicly available at: https://github.com/Paranioar/DBL.
Authors: Dunyun Chen, Xin Liao, Xiaoshuai Wu, Shiwei Chen
Abstract: Existing image inpainting methods have achieved remarkable accomplishments in generating visually appealing results, often accompanied by a trend toward creating more intricate structural textures. However, while these models excel at creating more realistic image content, they often leave noticeable traces of tampering, posing a significant threat to security. In this work, we take the anti-forensic capabilities into consideration, firstly proposing an end-to-end training framework for anti-forensic image inpainting named SafePaint. Specifically, we innovatively formulated image inpainting as two major tasks: semantically plausible content completion and region-wise optimization. The former is similar to current inpainting methods that aim to restore the missing regions of corrupted images. The latter, through domain adaptation, endeavors to reconcile the discrepancies between the inpainted region and the unaltered area to achieve anti-forensic goals. Through comprehensive theoretical analysis, we validate the effectiveness of domain adaptation for anti-forensic performance. Furthermore, we meticulously crafted a region-wise separated attention (RWSA) module, which not only aligns with our objective of anti-forensics but also enhances the performance of the model. Extensive qualitative and quantitative evaluations show our approach achieves comparable results to existing image inpainting methods while offering anti-forensic capabilities not available in other methods.
Authors: You Wu, Yuelong Wang, Yaxin Liao, Fuliang Wu, Hengzhou Ye, Shuiwang Li
Abstract: Tracking transforming objects holds significant importance in various fields due to the dynamic nature of many real-world scenarios. By enabling systems accurately represent transforming objects over time, tracking transforming objects facilitates advancements in areas such as autonomous systems, human-computer interaction, and security applications. Moreover, understanding the behavior of transforming objects provides valuable insights into complex interactions or processes, contributing to the development of intelligent systems capable of robust and adaptive perception in dynamic environments. However, current research in the field mainly focuses on tracking generic objects. In this study, we bridge this gap by collecting a novel dedicated Dataset for Tracking Transforming Objects, called DTTO, which contains 100 sequences, amounting to approximately 9.3K frames. We provide carefully hand-annotated bounding boxes for each frame within these sequences, making DTTO the pioneering benchmark dedicated to tracking transforming objects. We thoroughly evaluate 20 state-of-the-art trackers on the benchmark, aiming to comprehend the performance of existing methods and provide a comparison for future research on DTTO. With the release of DTTO, our goal is to facilitate further research and applications related to tracking transforming objects.
Authors: Zongmei Chen, Xin Liao, Xiaoshuai Wu, Yanxiang Chen
Abstract: The misuse of deepfake technology by malicious actors poses a potential threat to nations, societies, and individuals. However, existing methods for detecting deepfakes primarily focus on uncompressed videos, such as noise characteristics, local textures, or frequency statistics. When applied to compressed videos, these methods experience a decrease in detection performance and are less suitable for real-world scenarios. In this paper, we propose a deepfake video detection method based on 3D spatiotemporal trajectories. Specifically, we utilize a robust 3D model to construct spatiotemporal motion features, integrating feature details from both 2D and 3D frames to mitigate the influence of large head rotation angles or insufficient lighting within frames. Furthermore, we separate facial expressions from head movements and design a sequential analysis method based on phase space motion trajectories to explore the feature differences between genuine and fake faces in deepfake videos. We conduct extensive experiments to validate the performance of our proposed method on several compressed deepfake benchmarks. The robustness of the well-designed features is verified by calculating the consistent distribution of facial landmarks before and after video compression.Our method yields satisfactory results and showcases its potential for practical applications.
Authors: Oded Bialer, Yuval Haitman
Abstract: Object detection in radar imagery with neural networks shows great potential for improving autonomous driving. However, obtaining annotated datasets from real radar images, crucial for training these networks, is challenging, especially in scenarios with long-range detection and adverse weather and lighting conditions where radar performance excels. To address this challenge, we present RadSimReal, an innovative physical radar simulation capable of generating synthetic radar images with accompanying annotations for various radar types and environmental conditions, all without the need for real data collection. Remarkably, our findings demonstrate that training object detection models on RadSimReal data and subsequently evaluating them on real-world data produce performance levels comparable to models trained and tested on real data from the same dataset, and even achieves better performance when testing across different real datasets. RadSimReal offers advantages over other physical radar simulations that it does not necessitate knowledge of the radar design details, which are often not disclosed by radar suppliers, and has faster run-time. This innovative tool has the potential to advance the development of computer vision algorithms for radar-based autonomous driving applications.
Authors: Cl\'ement Grisi, Geert Litjens, Jeroen van der Laak
Abstract: Vision Transformers are at the heart of the current surge of interest in foundation models for histopathology. They process images by breaking them into smaller patches following a regular grid, regardless of their content. Yet, not all parts of an image are equally relevant for its understanding. This is particularly true in computational pathology where background is completely non-informative and may introduce artefacts that could mislead predictions. To address this issue, we propose a novel method that explicitly masks background in Vision Transformers' attention mechanism. This ensures tokens corresponding to background patches do not contribute to the final image representation, thereby improving model robustness and interpretability. We validate our approach using prostate cancer grading from whole-slide images as a case study. Our results demonstrate that it achieves comparable performance with plain self-attention while providing more accurate and clinically meaningful attention heatmaps.
Authors: Jinming Cao, Sicheng Shen, Qiu Zhou, Yifang Yin, Yangyan Li, Roger Zimmermann
Abstract: Photographing optoelectronic displays often introduces unwanted moir\'e patterns due to analog signal interference between the pixel grids of the display and the camera sensor arrays. This work identifies two problems that are largely ignored by existing image demoir\'eing approaches: 1) moir\'e patterns vary across different channels (RGB); 2) repetitive patterns are constantly observed. However, employing conventional convolutional (CNN) layers cannot address these problems. Instead, this paper presents the use of our recently proposed Shape concept. It was originally employed to model consistent features from fragmented regions, particularly when identical or similar objects coexist in an RGB-D image. Interestingly, we find that the Shape information effectively captures the moir\'e patterns in artifact images. Motivated by this discovery, we propose a ShapeMoir\'e method to aid in image demoir\'eing. Beyond modeling shape features at the patch-level, we further extend this to the global image-level and design a novel Shape-Architecture. Consequently, our proposed method, equipped with both ShapeConv and Shape-Architecture, can be seamlessly integrated into existing approaches without introducing additional parameters or computation overhead during inference. We conduct extensive experiments on four widely used datasets, and the results demonstrate that our ShapeMoir\'e achieves state-of-the-art performance, particularly in terms of the PSNR metric. We then apply our method across four popular architectures to showcase its generalization capabilities. Moreover, our ShapeMoir\'e is robust and viable under real-world demoir\'eing scenarios involving smartphone photographs.
Authors: Yuhan Liu, Yongjian Deng, Hao Chen, Bochen Xie, Youfu Li, Zhen Yang
Abstract: Video frame interpolation, the process of synthesizing intermediate frames between sequential video frames, has made remarkable progress with the use of event cameras. These sensors, with microsecond-level temporal resolution, fill information gaps between frames by providing precise motion cues. However, contemporary Event-Based Video Frame Interpolation (E-VFI) techniques often neglect the fact that event data primarily supply high-confidence features at scene edges during multi-modal feature fusion, thereby diminishing the role of event signals in optical flow (OF) estimation and warping refinement. To address this overlooked aspect, we introduce an end-to-end E-VFI learning method (referred to as EGMR) to efficiently utilize edge features from event signals for motion flow and warping enhancement. Our method incorporates an Edge Guided Attentive (EGA) module, which rectifies estimated video motion through attentive aggregation based on the local correlation of multi-modal features in a coarse-to-fine strategy. Moreover, given that event data can provide accurate visual references at scene edges between consecutive frames, we introduce a learned visibility map derived from event data to adaptively mitigate the occlusion problem in the warping refinement process. Extensive experiments on both synthetic and real datasets show the effectiveness of the proposed approach, demonstrating its potential for higher quality video frame interpolation.
Authors: Ju Huang, Shiao Wang, Shuai Wang, Zhe Wu, Xiao Wang, Bo Jiang
Abstract: RGB-Event based tracking is an emerging research topic, focusing on how to effectively integrate heterogeneous multi-modal data (synchronized exposure video frames and asynchronous pulse Event stream). Existing works typically employ Transformer based networks to handle these modalities and achieve decent accuracy through input-level or feature-level fusion on multiple datasets. However, these trackers require significant memory consumption and computational complexity due to the use of self-attention mechanism. This paper proposes a novel RGB-Event tracking framework, Mamba-FETrack, based on the State Space Model (SSM) to achieve high-performance tracking while effectively reducing computational costs and realizing more efficient tracking. Specifically, we adopt two modality-specific Mamba backbone networks to extract the features of RGB frames and Event streams. Then, we also propose to boost the interactive learning between the RGB and Event features using the Mamba network. The fused features will be fed into the tracking head for target object localization. Extensive experiments on FELT and FE108 datasets fully validated the efficiency and effectiveness of our proposed tracker. Specifically, our Mamba-based tracker achieves 43.5/55.6 on the SR/PR metric, while the ViT-S based tracker (OSTrack) obtains 40.0/50.9. The GPU memory cost of ours and ViT-S based tracker is 13.98GB and 15.44GB, which decreased about $9.5\%$. The FLOPs and parameters of ours/ViT-S based OSTrack are 59GB/1076GB and 7MB/60MB, which decreased about $94.5\%$ and $88.3\%$, respectively. We hope this work can bring some new insights to the tracking field and greatly promote the application of the Mamba architecture in tracking. The source code of this work will be released on \url{https://github.com/Event-AHU/Mamba_FETrack}.
Authors: Fares Bougourzi, Fadi Dornaika, Abdelmalik Taleb-Ahmed, Vinh Truong Hoang
Abstract: Inspired by the success of Transformers in Computer vision, Transformers have been widely investigated for medical imaging segmentation. However, most of Transformer architecture are using the recent transformer architectures as encoder or as parallel encoder with the CNN encoder. In this paper, we introduce a novel hybrid CNN-Transformer segmentation architecture (PAG-TransYnet) designed for efficiently building a strong CNN-Transformer encoder. Our approach exploits attention gates within a Dual Pyramid hybrid encoder. The contributions of this methodology can be summarized into three key aspects: (i) the utilization of Pyramid input for highlighting the prominent features at different scales, (ii) the incorporation of a PVT transformer to capture long-range dependencies across various resolutions, and (iii) the implementation of a Dual-Attention Gate mechanism for effectively fusing prominent features from both CNN and Transformer branches. Through comprehensive evaluation across different segmentation tasks including: abdominal multi-organs segmentation, infection segmentation (Covid-19 and Bone Metastasis), microscopic tissues segmentation (Gland and Nucleus). The proposed approach demonstrates state-of-the-art performance and exhibits remarkable generalization capabilities. This research represents a significant advancement towards addressing the pressing need for efficient and adaptable segmentation solutions in medical imaging applications.
Authors: Zicheng Zhang, Haoning Wu, Yingjie Zhou, Chunyi Li, Wei Sun, Chaofeng Chen, Xiongkuo Min, Xiaohong Liu, Weisi Lin, Guangtao Zhai
Abstract: Although large multi-modality models (LMMs) have seen extensive exploration and application in various quality assessment studies, their integration into Point Cloud Quality Assessment (PCQA) remains unexplored. Given LMMs' exceptional performance and robustness in low-level vision and quality assessment tasks, this study aims to investigate the feasibility of imparting PCQA knowledge to LMMs through text supervision. To achieve this, we transform quality labels into textual descriptions during the fine-tuning phase, enabling LMMs to derive quality rating logits from 2D projections of point clouds. To compensate for the loss of perception in the 3D domain, structural features are extracted as well. These quality logits and structural features are then combined and regressed into quality scores. Our experimental results affirm the effectiveness of our approach, showcasing a novel integration of LMMs into PCQA that enhances model understanding and assessment accuracy. We hope our contributions can inspire subsequent investigations into the fusion of LMMs with PCQA, fostering advancements in 3D visual quality analysis and beyond.
Authors: Cuiwei Liu, Youzhi Jiang, Chong Du, Zhaokui Li
Abstract: Skeleton-based action recognition is vital for comprehending human-centric videos and has applications in diverse domains. One of the challenges of skeleton-based action recognition is dealing with low-quality data, such as skeletons that have missing or inaccurate joints. This paper addresses the issue of enhancing action recognition using low-quality skeletons through a general knowledge distillation framework. The proposed framework employs a teacher-student model setup, where a teacher model trained on high-quality skeletons guides the learning of a student model that handles low-quality skeletons. To bridge the gap between heterogeneous high-quality and lowquality skeletons, we present a novel part-based skeleton matching strategy, which exploits shared body parts to facilitate local action pattern learning. An action-specific part matrix is developed to emphasize critical parts for different actions, enabling the student model to distill discriminative part-level knowledge. A novel part-level multi-sample contrastive loss achieves knowledge transfer from multiple high-quality skeletons to low-quality ones, which enables the proposed knowledge distillation framework to include training low-quality skeletons that lack corresponding high-quality matches. Comprehensive experiments conducted on the NTU-RGB+D, Penn Action, and SYSU 3D HOI datasets demonstrate the effectiveness of the proposed knowledge distillation framework.
Authors: Navve Wasserman, Noam Rotstein, Roy Ganz, Ron Kimmel
Abstract: Image editing has advanced significantly with the introduction of text-conditioned diffusion models. Despite this progress, seamlessly adding objects to images based on textual instructions without requiring user-provided input masks remains a challenge. We address this by leveraging the insight that removing objects (Inpaint) is significantly simpler than its inverse process of adding them (Paint), attributed to the utilization of segmentation mask datasets alongside inpainting models that inpaint within these masks. Capitalizing on this realization, by implementing an automated and extensive pipeline, we curate a filtered large-scale image dataset containing pairs of images and their corresponding object-removed versions. Using these pairs, we train a diffusion model to inverse the inpainting process, effectively adding objects into images. Unlike other editing datasets, ours features natural target images instead of synthetic ones; moreover, it maintains consistency between source and target by construction. Additionally, we utilize a large Vision-Language Model to provide detailed descriptions of the removed objects and a Large Language Model to convert these descriptions into diverse, natural-language instructions. We show that the trained model surpasses existing ones both qualitatively and quantitatively, and release the large-scale dataset alongside the trained models for the community.
Authors: Guanchun Wang, Xiangrong Zhang, Zelin Peng, Tianyang Zhang, Xiuping Jia, Licheng Jiao
Abstract: Land cover analysis using hyperspectral images (HSI) remains an open problem due to their low spatial resolution and complex spectral information. Recent studies are primarily dedicated to designing Transformer-based architectures for spatial-spectral long-range dependencies modeling, which is computationally expensive with quadratic complexity. Selective structured state space model (Mamba), which is efficient for modeling long-range dependencies with linear complexity, has recently shown promising progress. However, its potential in hyperspectral image processing that requires handling numerous spectral bands has not yet been explored. In this paper, we innovatively propose S$^2$Mamba, a spatial-spectral state space model for hyperspectral image classification, to excavate spatial-spectral contextual features, resulting in more efficient and accurate land cover analysis. In S$^2$Mamba, two selective structured state space models through different dimensions are designed for feature extraction, one for spatial, and the other for spectral, along with a spatial-spectral mixture gate for optimal fusion. More specifically, S$^2$Mamba first captures spatial contextual relations by interacting each pixel with its adjacent through a Patch Cross Scanning module and then explores semantic information from continuous spectral bands through a Bi-directional Spectral Scanning module. Considering the distinct expertise of the two attributes in homogenous and complicated texture scenes, we realize the Spatial-spectral Mixture Gate by a group of learnable matrices, allowing for the adaptive incorporation of representations learned across different dimensions. Extensive experiments conducted on HSI classification benchmarks demonstrate the superiority and prospect of S$^2$Mamba. The code will be available at: https://github.com/PURE-melo/S2Mamba.
Authors: Yanbing Bai, Zihao Yang, Jinze Yu, Rui-Yang Ju, Bin Yang, Erick Mas, Shunichi Koshimura
Abstract: With the escalating frequency of floods posing persistent threats to human life and property, satellite remote sensing has emerged as an indispensable tool for monitoring flood hazards. SpaceNet8 offers a unique opportunity to leverage cutting-edge artificial intelligence technologies to assess these hazards. A significant contribution of this research is its application of Apache Sedona, an advanced platform specifically designed for the efficient and distributed processing of large-scale geospatial data. This platform aims to enhance the efficiency of error analysis, a critical aspect of improving flood damage detection accuracy. Based on Apache Sedona, we introduce a novel approach that addresses the challenges associated with inaccuracies in flood damage detection. This approach involves the retrieval of cases from historical flood events, the adaptation of these cases to current scenarios, and the revision of the model based on clustering algorithms to refine its performance. Through the replication of both the SpaceNet8 baseline and its top-performing models, we embark on a comprehensive error analysis. This analysis reveals several main sources of inaccuracies. To address these issues, we employ data visual interpretation and histogram equalization techniques, resulting in significant improvements in model metrics. After these enhancements, our indicators show a notable improvement, with precision up by 5%, F1 score by 2.6%, and IoU by 4.5%. This work highlights the importance of advanced geospatial data processing tools, such as Apache Sedona. By improving the accuracy and efficiency of flood detection, this research contributes to safeguarding public safety and strengthening infrastructure resilience in flood-prone areas, making it a valuable addition to the field of remote sensing and disaster management.
Authors: Yanbing Bai, Rui-Yang Ju, Siao Li, Zihao Yang, Jinze Yu
Abstract: Illegal, unreported, and unregulated (IUU) fishing seriously affects various aspects of human life. However, current methods for detecting and monitoring IUU activities at sea have limitations. While Synthetic Aperture Radar (SAR) can complement existing vessel detection systems, extracting useful information from SAR images using traditional methods, especially for IUU fishing identification, poses challenges. This paper proposes a deep learning-based system for detecting fishing activities. We implemented this system on the xView3 dataset using six classical object detection models: Faster R-CNN, Cascade R-CNN, SSD, RetinaNet, FSAF, and FCOS. We applied improvement methods to enhance the performance of the Faster R-CNN model. Specifically, training the Faster R-CNN model using Online Hard Example Mining (OHEM) strategy improved the Avg-F1 value from 0.212 to 0.216, representing a 1.96% improvement.
Authors: Kaiyu Song, Hanjiang Lai
Abstract: Recently, the diffusion model with the training-free methods has succeeded in conditional image generation tasks. However, there is an efficiency problem because it requires calculating the gradient with high computational cost, and previous methods make strong assumptions to solve it, sacrificing generalization. In this work, we propose the Fisher information guided diffusion model (FIGD). Concretely, we introduce the Fisher information to estimate the gradient without making any additional assumptions to reduce computation cost. Meanwhile, we demonstrate that the Fisher information ensures the generalization of FIGD and provides new insights for training-free methods based on the information theory. The experimental results demonstrate that FIGD could achieve different conditional generations more quickly while maintaining high quality.
Authors: Tengjun Huang
Abstract: With the rise of Visual and Language Pretraining (VLP), an increasing number of downstream tasks are adopting the paradigm of pretraining followed by fine-tuning. Although this paradigm has demonstrated potential in various multimodal downstream tasks, its implementation in the remote sensing domain encounters some obstacles. Specifically, the tendency for same-modality embeddings to cluster together impedes efficient transfer learning. To tackle this issue, we review the aim of multimodal transfer learning for downstream tasks from a unified perspective, and rethink the optimization process based on three distinct objectives. We propose "Harmonized Transfer Learning and Modality Alignment (HarMA)", a method that simultaneously satisfies task constraints, modality alignment, and single-modality uniform alignment, while minimizing training overhead through parameter-efficient fine-tuning. Remarkably, without the need for external data for training, HarMA achieves state-of-the-art performance in two popular multimodal retrieval tasks in the field of remote sensing. Our experiments reveal that HarMA achieves competitive and even superior performance to fully fine-tuned models with only minimal adjustable parameters. Due to its simplicity, HarMA can be integrated into almost all existing multimodal pretraining models. We hope this method can facilitate the efficient application of large models to a wide range of downstream tasks while significantly reducing the resource consumption. Code is available at https://github.com/seekerhuang/HarMA.
Authors: Mar\'ia Alfaro-Contreras, Jorge Calvo-Zaragoza
Abstract: This paper serves to introduce the Align, Minimize and Diversify (AMD) method, a Source-Free Unsupervised Domain Adaptation approach for Handwritten Text Recognition (HTR). This framework decouples the adaptation process from the source data, thus not only sidestepping the resource-intensive retraining process but also making it possible to leverage the wealth of pre-trained knowledge encoded in modern Deep Learning architectures. Our method explicitly eliminates the need to revisit the source data during adaptation by incorporating three distinct regularization terms: the Align term, which reduces the feature distribution discrepancy between source and target data, ensuring the transferability of the pre-trained representation; the Minimize term, which encourages the model to make assertive predictions, pushing the outputs towards one-hot-like distributions in order to minimize prediction uncertainty, and finally, the Diversify term, which safeguards against the degeneracy in predictions by promoting varied and distinctive sequences throughout the target data, preventing informational collapse. Experimental results from several benchmarks demonstrated the effectiveness and robustness of AMD, showing it to be competitive and often outperforming DA methods in HTR.
Authors: Zesheng Hong, Yubiao Yue, Yubin Chen, Huanjie Lin, Yuanmei Luo, Mini Han Wang, Weidong Wang, Jialong Xu, Xiaoqi Yang, Zhenzhang Li, Sihong Xie
Abstract: Computer-aided diagnostics has benefited from the development of deep learning-based computer vision techniques in these years. Traditional supervised deep learning methods assume that the test sample is drawn from the identical distribution as the training data. However, it is possible to encounter out-of-distribution samples in real-world clinical scenarios, which may cause silent failure in deep learning-based medical image analysis tasks. Recently, research has explored various out-of-distribution (OOD) detection situations and techniques to enable a trustworthy medical AI system. In this survey, we systematically review the recent advances in OOD detection in medical image analysis. We first explore several factors that may cause a distributional shift when using a deep-learning-based model in clinic scenarios, with three different types of distributional shift well defined on top of these factors. Then a framework is suggested to categorize and feature existing solutions, while the previous studies are reviewed based on the methodology taxonomy. Our discussion also includes evaluation protocols and metrics, as well as the challenge and a research direction lack of exploration.
Authors: Zhiyao Zhang, Yunzhou Zhang, Yanmin Wu, Bin Zhao, Xingshuo Wang, Rui Tian
Abstract: With the emergence of Neural Radiance Fields (NeRF), neural implicit representations have gained widespread applications across various domains, including simultaneous localization and mapping. However, current neural implicit SLAM faces a challenging trade-off problem between performance and the number of parameters. To address this problem, we propose sparse tri-plane encoding, which efficiently achieves scene reconstruction at resolutions up to 512 using only 2~4% of the commonly used tri-plane parameters (reduced from 100MB to 2~4MB). On this basis, we design S3-SLAM to achieve rapid and high-quality tracking and mapping through sparsifying plane parameters and integrating orthogonal features of tri-plane. Furthermore, we develop hierarchical bundle adjustment to achieve globally consistent geometric structures and reconstruct high-resolution appearance. Experimental results demonstrate that our approach achieves competitive tracking and scene reconstruction with minimal parameters on three datasets. Source code will soon be available.
Authors: Rikathi Pal, Priya Saha, Somoballi Ghoshal, Amlan Chakrabarti, Susmita Sur-Kolay
Abstract: Segmentation and labeling of vertebrae in MRI images of the spine are critical for the diagnosis of illnesses and abnormalities. These steps are indispensable as MRI technology provides detailed information about the tissue structure of the spine. Both supervised and unsupervised segmentation methods exist, yet acquiring sufficient data remains challenging for achieving high accuracy. In this study, we propose an enhancing approach based on modified attention U-Net architecture for panoptic segmentation of 3D sliced MRI data of the lumbar spine. Our method achieves an impressive accuracy of 99.5\% by incorporating novel masking logic, thus significantly advancing the state-of-the-art in vertebral segmentation and labeling. This contributes to more precise and reliable diagnosis and treatment planning.
Authors: Paulina Tomaszewska, Przemys{\l}aw Biecek
Abstract: Does the stethoscope in the picture make the adjacent person a doctor or a patient? This, of course, depends on the contextual relationship of the two objects. If it is obvious, why don not explanation methods for vision models use contextual information? In this paper, we (1) review the most popular methods of explaining computer vision models by pointing out that they do not take into account context information, (2) provide examples of real-world use cases where spatial context plays a significant role, (3) propose new research directions that may lead to better use of context information in explaining computer vision models, (4) argue that a change in approach to explanations is needed from 'where' to 'how'.
Authors: Peihao Xiang, Chaohao Lin, Kaida Wu, Ou Bai
Abstract: This paper presents a novel approach to processing multimodal data for dynamic emotion recognition, named as the Multimodal Masked Autoencoder for Dynamic Emotion Recognition (MultiMAE-DER). The MultiMAE-DER leverages the closely correlated representation information within spatiotemporal sequences across visual and audio modalities. By utilizing a pre-trained masked autoencoder model, the MultiMAEDER is accomplished through simple, straightforward finetuning. The performance of the MultiMAE-DER is enhanced by optimizing six fusion strategies for multimodal input sequences. These strategies address dynamic feature correlations within cross-domain data across spatial, temporal, and spatiotemporal sequences. In comparison to state-of-the-art multimodal supervised learning models for dynamic emotion recognition, MultiMAE-DER enhances the weighted average recall (WAR) by 4.41% on the RAVDESS dataset and by 2.06% on the CREMAD. Furthermore, when compared with the state-of-the-art model of multimodal self-supervised learning, MultiMAE-DER achieves a 1.86% higher WAR on the IEMOCAP dataset.
Authors: Yang Xiao
Abstract: The complex information processing system of humans generates a lot of objective and subjective evaluations, making the exploration of human cognitive products of great cutting-edge theoretical value. In recent years, deep learning technologies, which are inspired by biological brain mechanisms, have made significant strides in the application of psychological or cognitive scientific research, particularly in the memorization and recognition of facial data. This paper investigates through experimental research how neural networks process and store facial expression data and associate these data with a range of psychological attributes produced by humans. Researchers utilized deep learning model VGG16, demonstrating that neural networks can learn and reproduce key features of facial data, thereby storing image memories. Moreover, the experimental results reveal the potential of deep learning models in understanding human emotions and cognitive processes and establish a manifold visualization interpretation of cognitive products or psychological attributes from a non-Euclidean space perspective, offering new insights into enhancing the explainability of AI. This study not only advances the application of AI technology in the field of psychology but also provides a new psychological theoretical understanding the information processing of the AI. The code is available in here: https://github.com/NKUShaw/Psychoinformatics.
Authors: Zhiming Chang, Boyang Liu, Yifei Xia, Youming Guo, Boxin Shi, He Sun
Abstract: This paper proposes a framework for the 3D reconstruction of satellites in low-Earth orbit, utilizing videos captured by small amateur telescopes. The video data obtained from these telescopes differ significantly from data for standard 3D reconstruction tasks, characterized by intense motion blur, atmospheric turbulence, pervasive background light pollution, extended focal length and constrained observational perspectives. To address these challenges, our approach begins with a comprehensive pre-processing workflow that encompasses deep learning-based image restoration, feature point extraction and camera pose initialization. We proceed with the application of an improved 3D Gaussian splatting algorithm for reconstructing the 3D model. Our technique supports simultaneous 3D Gaussian training and pose estimation, enabling the robust generation of intricate 3D point clouds from sparse, noisy data. The procedure is further bolstered by a post-editing phase designed to eliminate noise points inconsistent with our prior knowledge of a satellite's geometric constraints. We validate our approach using both synthetic datasets and actual observations of China's Space Station, showcasing its significant advantages over existing methods in reconstructing 3D space objects from ground-based observations.
Authors: Huy Quang Pham, Thang Kien-Bao Nguyen, Quan Van Nguyen, Dan Quang Tran, Nghia Hieu Nguyen, Kiet Van Nguyen, Ngan Luu-Thuy Nguyen
Abstract: Optical Character Recognition - Visual Question Answering (OCR-VQA) is the task of answering text information contained in images that have just been significantly developed in the English language in recent years. However, there are limited studies of this task in low-resource languages such as Vietnamese. To this end, we introduce a novel dataset, ViOCRVQA (Vietnamese Optical Character Recognition - Visual Question Answering dataset), consisting of 28,000+ images and 120,000+ question-answer pairs. In this dataset, all the images contain text and questions about the information relevant to the text in the images. We deploy ideas from state-of-the-art methods proposed for English to conduct experiments on our dataset, revealing the challenges and difficulties inherent in a Vietnamese dataset. Furthermore, we introduce a novel approach, called VisionReader, which achieved 0.4116 in EM and 0.6990 in the F1-score on the test set. Through the results, we found that the OCR system plays a very important role in VQA models on the ViOCRVQA dataset. In addition, the objects in the image also play a role in improving model performance. We open access to our dataset at link (https://github.com/qhnhynmm/ViOCRVQA.git) for further research in OCR-VQA task in Vietnamese.
Authors: Jinwon Ko, Dongkwon Jin, Chang-Su Kim
Abstract: A novel algorithm, called semantic line combination detector (SLCD), to find an optimal combination of semantic lines is proposed in this paper. It processes all lines in each line combination at once to assess the overall harmony of the lines. First, we generate various line combinations from reliable lines. Second, we estimate the score of each line combination and determine the best one. Experimental results demonstrate that the proposed SLCD outperforms existing semantic line detectors on various datasets. Moreover, it is shown that SLCD can be applied effectively to three vision tasks of vanishing point detection, symmetry axis detection, and composition-based image retrieval. Our codes are available at https://github.com/Jinwon-Ko/SLCD.
Authors: Lingbo Huang, Yushi Chen, Xin He
Abstract: Recently, deep learning models have achieved excellent performance in hyperspectral image (HSI) classification. Among the many deep models, Transformer has gradually attracted interest for its excellence in modeling the long-range dependencies of spatial-spectral features in HSI. However, Transformer has the problem of quadratic computational complexity due to the self-attention mechanism, which is heavier than other models and thus has limited adoption in HSI processing. Fortunately, the recently emerging state space model-based Mamba shows great computational efficiency while achieving the modeling power of Transformers. Therefore, in this paper, we make a preliminary attempt to apply the Mamba to HSI classification, leading to the proposed spectral-spatial Mamba (SS-Mamba). Specifically, the proposed SS-Mamba mainly consists of spectral-spatial token generation module and several stacked spectral-spatial Mamba blocks. Firstly, the token generation module converts any given HSI cube to spatial and spectral tokens as sequences. And then these tokens are sent to stacked spectral-spatial mamba blocks (SS-MB). Each SS-MB block consists of two basic mamba blocks and a spectral-spatial feature enhancement module. The spatial and spectral tokens are processed separately by the two basic mamba blocks, respectively. Besides, the feature enhancement module modulates spatial and spectral tokens using HSI sample's center region information. In this way, the spectral and spatial tokens cooperate with each other and achieve information fusion within each block. The experimental results conducted on widely used HSI datasets reveal that the proposed model achieves competitive results compared with the state-of-the-art methods. The Mamba-based method opens a new window for HSI classification.
Authors: Jiquan Yuan, Fanyi Yang, Jihe Li, Xinyan Cao, Jinming Che, Jinlong Lin, Xixin Cao
Abstract: In recent years, image generation technology has rapidly advanced, resulting in the creation of a vast array of AI-generated images (AIGIs). However, the quality of these AIGIs is highly inconsistent, with low-quality AIGIs severely impairing the visual experience of users. Due to the widespread application of AIGIs, the AI-generated image quality assessment (AIGIQA), aimed at evaluating the quality of AIGIs from the perspective of human perception, has garnered increasing interest among scholars. Nonetheless, current research has not yet fully explored this field. We have observed that existing databases are limited to images generated from single scenario settings. Databases such as AGIQA-1K, AGIQA-3K, and AIGCIQA2023, for example, only include images generated by text-to-image generative models. This oversight highlights a critical gap in the current research landscape, underscoring the need for dedicated databases catering to image-to-image scenarios, as well as more comprehensive databases that encompass a broader range of AI-generated image scenarios. Addressing these issues, we have established a large scale perceptual quality assessment database for both text-to-image and image-to-image AIGIs, named PKU-AIGIQA-4K. We then conduct a well-organized subjective experiment to collect quality labels for AIGIs and perform a comprehensive analysis of the PKU-AIGIQA-4K database. Regarding the use of image prompts during the training process, we propose three image quality assessment (IQA) methods based on pre-trained models that include a no-reference method NR-AIGCIQA, a full-reference method FR-AIGCIQA, and a partial-reference method PR-AIGCIQA. Finally, leveraging the PKU-AIGIQA-4K database, we conduct extensive benchmark experiments and compare the performance of the proposed methods and the current IQA methods.
Authors: Xinyu Ma, Xuebo Liu, Derek F. Wong, Jun Rao, Bei Li, Liang Ding, Lidia S. Chao, Dacheng Tao, Min Zhang
Abstract: Multimodal machine translation (MMT) is a challenging task that seeks to improve translation quality by incorporating visual information. However, recent studies have indicated that the visual information provided by existing MMT datasets is insufficient, causing models to disregard it and overestimate their capabilities. This issue presents a significant obstacle to the development of MMT research. This paper presents a novel solution to this issue by introducing 3AM, an ambiguity-aware MMT dataset comprising 26,000 parallel sentence pairs in English and Chinese, each with corresponding images. Our dataset is specifically designed to include more ambiguity and a greater variety of both captions and images than other MMT datasets. We utilize a word sense disambiguation model to select ambiguous data from vision-and-language datasets, resulting in a more challenging dataset. We further benchmark several state-of-the-art MMT models on our proposed dataset. Experimental results show that MMT models trained on our dataset exhibit a greater ability to exploit visual information than those trained on other MMT datasets. Our work provides a valuable resource for researchers in the field of multimodal learning and encourages further exploration in this area. The data, code and scripts are freely available at https://github.com/MaxyLee/3AM.
Authors: Jiajie Yuan, Linxiao Wu, Yulu Gong, Zhou Yu, Ziang Liu, Shuyao He
Abstract: This paper combines Struts and Hibernate two architectures together, using DAO (Data Access Object) to store and access data. Then a set of dual-mode humidity medical image library suitable for deep network is established, and a dual-mode medical image assisted diagnosis method based on the image is proposed. Through the test of various feature extraction methods, the optimal operating characteristic under curve product (AUROC) is 0.9985, the recall rate is 0.9814, and the accuracy is 0.9833. This method can be applied to clinical diagnosis, and it is a practical method. Any outpatient doctor can register quickly through the system, or log in to the platform to upload the image to obtain more accurate images. Through the system, each outpatient physician can quickly register or log in to the platform for image uploading, thus obtaining more accurate images. The segmentation of images can guide doctors in clinical departments. Then the image is analyzed to determine the location and nature of the tumor, so as to make targeted treatment.
Authors: Yeon-Ji Song, Suhyung Choi, Jaein Kim, Jin-Hwa Kim, Byoung-Tak Zhang
Abstract: Human perception involves discerning complex multi-object scenes into time-static object appearance (\ie, size, shape, color) and time-varying object motion (\ie, location, velocity, acceleration). This innate ability to unconsciously understand the environment is the motivation behind the success of dynamics modeling. Object-centric representations have emerged as a promising tool for dynamics prediction, yet they primarily focus on the objects' appearance, often overlooking other crucial attributes. In this paper, we propose Object-Centric Kinematics (OCK), a framework for dynamics prediction leveraging object-centric representations. Our model utilizes a novel component named object kinematics, which comprises low-level structured states of objects' position, velocity, and acceleration. The object kinematics are obtained via either implicit or explicit approaches, enabling comprehensive spatiotemporal object reasoning, and integrated through various transformer mechanisms, facilitating effective object-centric dynamics modeling. Our model demonstrates superior performance when handling objects and backgrounds in complex scenes characterized by a wide range of object attributes and dynamic movements. Moreover, our model demonstrates generalization capabilities across diverse synthetic environments, highlighting its potential for broad applicability in vision-related tasks.
Authors: Wenbin Guan, Zijiu Yang, Xiaohong Wu, Liqiong Chen, Feng Huang, Xiaohai He, Honggang Chen
Abstract: Presently, the task of few-shot object detection (FSOD) in remote sensing images (RSIs) has become a focal point of attention. Numerous few-shot detectors, particularly those based on two-stage detectors, face challenges when dealing with the multiscale complexities inherent in RSIs. Moreover, these detectors present impractical characteristics in real-world applications, mainly due to their unwieldy model parameters when handling large amount of data. In contrast, we recognize the advantages of one-stage detectors, including high detection speed and a global receptive field. Consequently, we choose the YOLOv7 one-stage detector as a baseline and subject it to a novel meta-learning training framework. This transformation allows the detector to adeptly address FSOD tasks while capitalizing on its inherent advantage of lightweight. Additionally, we thoroughly investigate the samples generated by the meta-learning strategy and introduce a novel meta-sampling approach to retain samples produced by our designed meta-detection head. Coupled with our devised meta-cross loss, we deliberately utilize ``negative samples" that are often overlooked to extract valuable knowledge from them. This approach serves to enhance detection accuracy and efficiently refine the overall meta-learning strategy. To validate the effectiveness of our proposed detector, we conducted performance comparisons with current state-of-the-art detectors using the DIOR and NWPU VHR-10.v2 datasets, yielding satisfactory results.
Authors: Zhuohao Li, Guoyang Xie, Guannan Jiang, Zhichao Lu
Abstract: Transformer recently emerged as the de facto model for computer vision tasks and has also been successfully applied to shadow removal. However, these existing methods heavily rely on intricate modifications to the attention mechanisms within the transformer blocks while using a generic patch embedding. As a result, it often leads to complex architectural designs requiring additional computation resources. In this work, we aim to explore the efficacy of incorporating shadow information within the early processing stage. Accordingly, we propose a transformer-based framework with a novel patch embedding that is tailored for shadow removal, dubbed ShadowMaskFormer. Specifically, we present a simple and effective mask-augmented patch embedding to integrate shadow information and promote the model's emphasis on acquiring knowledge for shadow regions. Extensive experiments conducted on the ISTD, ISTD+, and SRD benchmark datasets demonstrate the efficacy of our method against state-of-the-art approaches while using fewer model parameters.
Authors: Yunxuan Mao, Bingqi Shen, Yifei Yang, Kai Wang, Rong Xiong, Yiyi Liao, Yue Wang
Abstract: The joint optimization of the sensor trajectory and 3D map is a crucial characteristic of bundle adjustment (BA), essential for autonomous driving. This paper presents $\nu$-DBA, a novel framework implementing geometric dense bundle adjustment (DBA) using 3D neural implicit surfaces for map parametrization, which optimizes both the map surface and trajectory poses using geometric error guided by dense optical flow prediction. Additionally, we fine-tune the optical flow model with per-scene self-supervision to further improve the quality of the dense mapping. Our experimental results on multiple driving scene datasets demonstrate that our method achieves superior trajectory optimization and dense reconstruction accuracy. We also investigate the influences of photometric error and different neural geometric priors on the performance of surface reconstruction and novel view synthesis. Our method stands as a significant step towards leveraging neural implicit representations in dense bundle adjustment for more accurate trajectories and detailed environmental mapping.
Authors: Chaewon Lee, Seon-Ho Lee, Chang-Su Kim
Abstract: In recent interactive segmentation algorithms, previous probability maps are used as network input to help predictions in the current segmentation round. However, despite the utilization of previous masks, useful information contained in the probability maps is not well propagated to the current predictions. In this paper, to overcome this limitation, we propose a novel and effective algorithm for click-based interactive image segmentation, called MFP, which attempts to make full use of probability maps. We first modulate previous probability maps to enhance their representations of user-specified objects. Then, we feed the modulated probability maps as additional input to the segmentation network. We implement the proposed MFP algorithm based on the ResNet-34, HRNet-18, and ViT-B backbones and assess the performance extensively on various datasets. It is demonstrated that MFP meaningfully outperforms the existing algorithms using identical backbones. The source codes are available at \href{https://github.com/cwlee00/MFP}{https://github.com/cwlee00/MFP}.
URLs: https://github.com/cwlee00/MFP, https://github.com/cwlee00/MFP
Authors: Keyang Ye, Qiming Hou, Kun Zhou
Abstract: The advent of neural and Gaussian-based radiance field methods have achieved great success in the field of novel view synthesis. However, specular reflection remains non-trivial, as the high frequency radiance field is notoriously difficult to fit stably and accurately. We present a deferred shading method to effectively render specular reflection with Gaussian splatting. The key challenge comes from the environment map reflection model, which requires accurate surface normal while simultaneously bottlenecks normal estimation with discontinuous gradients. We leverage the per-pixel reflection gradients generated by deferred shading to bridge the optimization process of neighboring Gaussians, allowing nearly correct normal estimations to gradually propagate and eventually spread over all reflective objects. Our method significantly outperforms state-of-the-art techniques and concurrent work in synthesizing high-quality specular reflection effects, demonstrating a consistent improvement of peak signal-to-noise ratio (PSNR) for both synthetic and real-world scenes, while running at a frame rate almost identical to vanilla Gaussian splatting.
Authors: Donggyun Kim, Seongwoong Cho, Semin Kim, Chong Luo, Seunghoon Hong
Abstract: Large language models have evolved data-efficient generalists, benefiting from the universal language interface and large-scale pre-training. However, constructing a data-efficient generalist for dense visual prediction presents a distinct challenge due to the variation in label structures across different tasks. Consequently, generalization to unseen dense prediction tasks in the low-data regime is not straightforward and has received less attention from previous vision generalists. In this study, we explore a universal model that can flexibly adapt to unseen dense label structures with a few examples, enabling it to serve as a data-efficient vision generalist in diverse real-world scenarios. To this end, we base our method on a powerful meta-learning framework and explore several axes to improve its performance and versatility for real-world problems, such as flexible adaptation mechanisms and scalability. We evaluate our model across a spectrum of unseen real-world scenarios where low-shot learning is desirable, including video, 3D, medical, biological, and user-interactive tasks. Equipped with a generic architecture and an effective adaptation mechanism, our model flexibly adapts to all of these tasks with at most 50 labeled images, showcasing a significant advancement over existing data-efficient generalist approaches. Codes are available at https://github.com/GitGyun/chameleon.
Authors: Chaewon Lee, Chang-Su Kim
Abstract: For click-based interactive segmentation methods, reducing the number of clicks required to obtain a desired segmentation result is essential. Although recent click-based methods yield decent segmentation results, we observe that substantial amount of clicks are required to segment elongated regions. To reduce the amount of user-effort required, we propose using lines instead of clicks for such cases. In this paper, an interactive segmentation algorithm which adaptively adopts either clicks or lines as input is proposed. Experimental results demonstrate that using lines can generate better segmentation results than clicks for several cases.
Authors: Chuni Liu, Boyuan Ma, Xiaojuan Ban, Yujie Xie, Hao Wang, Weihua Xue, Jingchao Ma, Ke Xu
Abstract: Topological consistency plays a crucial role in the task of boundary segmentation for reticular images, such as cell membrane segmentation in neuron electron microscopic images, grain boundary segmentation in material microscopic images and road segmentation in aerial images. In these fields, topological changes in segmentation results have a serious impact on the downstream tasks, which can even exceed the misalignment of the boundary itself. To enhance the topology accuracy in segmentation results, we propose the Skea-Topo Aware loss, which is a novel loss function that takes into account the shape of each object and topological significance of the pixels. It consists of two components. First, the skeleton-aware weighted loss improves the segmentation accuracy by better modeling the object geometry with skeletons. Second, a boundary rectified term effectively identifies and emphasizes topological critical pixels in the prediction errors using both foreground and background skeletons in the ground truth and predictions. Experiments prove that our method improves topological consistency by up to 7 points in VI compared to 13 state-of-art methods, based on objective and subjective assessments across three different boundary segmentation datasets. The code is available at https://github.com/clovermini/Skea_topo.
Authors: Manos Schinas, Symeon Papadopoulos
Abstract: The generative AI technology offers an increasing variety of tools for generating entirely synthetic images that are increasingly indistinguishable from real ones. Unlike methods that alter portions of an image, the creation of completely synthetic images presents a unique challenge and several Synthetic Image Detection (SID) methods have recently appeared to tackle it. Yet, there is often a large gap between experimental results on benchmark datasets and the performance of methods in the wild. To better address the evaluation needs of SID and help close this gap, this paper introduces a benchmarking framework that integrates several state-of-the-art SID models. Our selection of integrated models was based on the utilization of varied input features, and different network architectures, aiming to encompass a broad spectrum of techniques. The framework leverages recent datasets with a diverse set of generative models, high level of photo-realism and resolution, reflecting the rapid improvements in image synthesis technology. Additionally, the framework enables the study of how image transformations, common in assets shared online, such as JPEG compression, affect detection performance. SIDBench is available on https://github.com/mever-team/sidbench and is designed in a modular manner to enable easy inclusion of new datasets and SID models.
Authors: Maximilian Bernhard, Tanveer Hannan, Niklas Strau{\ss}, Matthias Schubert
Abstract: Remote sensing projects typically generate large amounts of imagery that can be used to train powerful deep neural networks. However, the amount of labeled images is often small, as remote sensing applications generally require expert labelers. Thus, semi-supervised learning (SSL), i.e., learning with a small pool of labeled and a larger pool of unlabeled data, is particularly useful in this domain. Current SSL approaches generate pseudo-labels from model predictions for unlabeled samples. As the quality of these pseudo-labels is crucial for performance, utilizing additional information to improve pseudo-label quality yields a promising direction. For remote sensing images, geolocation and recording time are generally available and provide a valuable source of information as semantic concepts, such as land cover, are highly dependent on spatiotemporal context, e.g., due to seasonal effects and vegetation zones. In this paper, we propose to exploit spatiotemporal metainformation in SSL to improve the quality of pseudo-labels and, therefore, the final model performance. We show that directly adding the available metadata to the input of the predictor at test time degenerates the prediction quality for metadata outside the spatiotemporal distribution of the training set. Thus, we propose a teacher-student SSL framework where only the teacher network uses metainformation to improve the quality of pseudo-labels on the training set. Correspondingly, our student network benefits from the improved pseudo-labels but does not receive metadata as input, making it invariant to spatiotemporal shifts at test time. Furthermore, we propose methods for encoding and injecting spatiotemporal information into the model and introduce a novel distillation mechanism to enhance the knowledge transfer between teacher and student. Our framework dubbed Spatiotemporal SSL can be easily combined with several stat...
Authors: Abhishek Kumar Singh, Ioannis Patras
Abstract: The rapid evolution of the fashion industry increasingly intersects with technological advancements, particularly through the integration of generative AI. This study introduces a novel generative pipeline designed to transform the fashion design process by employing latent diffusion models. Utilizing ControlNet and LoRA fine-tuning, our approach generates high-quality images from multimodal inputs such as text and sketches. We leverage and enhance state-of-the-art virtual try-on datasets, including Multimodal Dress Code and VITON-HD, by integrating sketch data. Our evaluation, utilizing metrics like FID, CLIP Score, and KID, demonstrates that our model significantly outperforms traditional stable diffusion models. The results not only highlight the effectiveness of our model in generating fashion-appropriate outputs but also underscore the potential of diffusion models in revolutionizing fashion design workflows. This research paves the way for more interactive, personalized, and technologically enriched methodologies in fashion design and representation, bridging the gap between creative vision and practical application.
Authors: Tianyidan Xie, Rui Ma, Qian Wang, Xiaoqian Ye, Feixuan Liu, Ying Tai, Zhenyu Zhang, Zili Yi
Abstract: Recent advancements in image inpainting, particularly through diffusion modeling, have yielded promising outcomes. However, when tested in scenarios involving the completion of images based on the foreground objects, current methods that aim to inpaint an image in an end-to-end manner encounter challenges such as "over-imagination", inconsistency between foreground and background, and limited diversity. In response, we introduce Anywhere, a pioneering multi-agent framework designed to address these issues. Anywhere utilizes a sophisticated pipeline framework comprising various agents such as Visual Language Model (VLM), Large Language Model (LLM), and image generation models. This framework consists of three principal components: the prompt generation module, the image generation module, and the outcome analyzer. The prompt generation module conducts a semantic analysis of the input foreground image, leveraging VLM to predict relevant language descriptions and LLM to recommend optimal language prompts. In the image generation module, we employ a text-guided canny-to-image generation model to create a template image based on the edge map of the foreground image and language prompts, and an image refiner to produce the outcome by blending the input foreground and the template image. The outcome analyzer employs VLM to evaluate image content rationality, aesthetic score, and foreground-background relevance, triggering prompt and image regeneration as needed. Extensive experiments demonstrate that our Anywhere framework excels in foreground-conditioned image inpainting, mitigating "over-imagination", resolving foreground-background discrepancies, and enhancing diversity. It successfully elevates foreground-conditioned image inpainting to produce more reliable and diverse results.
Authors: Xiangyu Liang, Wenlin Zhuang, Tianyong Wang, Guangxing Geng, Guangyue Geng, Haifeng Xia, Siyu Xia
Abstract: Speech-driven 3D facial animation technology has been developed for years, but its practical application still lacks expectations. The main challenges lie in data limitations, lip alignment, and the naturalness of facial expressions. Although lip alignment has seen many related studies, existing methods struggle to synthesize natural and realistic expressions, resulting in a mechanical and stiff appearance of facial animations. Even with some research extracting emotional features from speech, the randomness of facial movements limits the effective expression of emotions. To address this issue, this paper proposes a method called CSTalk (Correlation Supervised) that models the correlations among different regions of facial movements and supervises the training of the generative model to generate realistic expressions that conform to human facial motion patterns. To generate more intricate animations, we employ a rich set of control parameters based on the metahuman character model and capture a dataset for five different emotions. We train a generative network using an autoencoder structure and input an emotion embedding vector to achieve the generation of user-control expressions. Experimental results demonstrate that our method outperforms existing state-of-the-art methods.
Authors: Yunshuang Yuan, Monika Sester
Abstract: Collective Perception has attracted significant attention in recent years due to its advantage for mitigating occlusion and expanding the field-of-view, thereby enhancing reliability, efficiency, and, most crucially, decision-making safety. However, developing collective perception models is highly resource demanding due to extensive requirements of processing input data for many agents, usually dozens of images and point clouds for a single frame. This not only slows down the model development process for collective perception but also impedes the utilization of larger models. In this paper, we propose an agent-based training framework that handles the deep learning modules and agent data separately to have a cleaner data flow structure. This framework not only provides an API for flexibly prototyping the data processing pipeline and defining the gradient calculation for each agent, but also provides the user interface for interactive training, testing and data visualization. Training experiment results of four collective object detection models on the prominent collective perception benchmark OPV2V show that the agent-based training can significantly reduce the GPU memory consumption and training time while retaining inference performance. The framework and model implementations are available at \url{https://github.com/YuanYunshuang/CoSense3D}
Authors: Yichen Ouyang, jianhao Yuan, Hao Zhao, Gaoang Wang, Bo zhao
Abstract: Generating long and consistent videos has emerged as a significant yet challenging problem. While most existing diffusion-based video generation models, derived from image generation models, demonstrate promising performance in generating short videos, their simple conditioning mechanism and sampling strategy-originally designed for image generation-cause severe performance degradation when adapted to long video generation. This results in prominent temporal inconsistency and overexposure. Thus, in this work, we introduce FlexiFilm, a new diffusion model tailored for long video generation. Our framework incorporates a temporal conditioner to establish a more consistent relationship between generation and multi-modal conditions, and a resampling strategy to tackle overexposure. Empirical results demonstrate FlexiFilm generates long and consistent videos, each over 30 seconds in length, outperforming competitors in qualitative and quantitative analyses. Project page: https://y-ichen.github.io/FlexiFilm-Page/
Authors: Antoine Maiorca, Seyed Abolfazl Ghasemzadeh, Thierry Ravet, Fran\c{c}ois Cresson, Thierry Dutoit, Christophe De Vleeschouwer
Abstract: Virtual Reality (VR) applications have revolutionized user experiences by immersing individuals in interactive 3D environments. These environments find applications in numerous fields, including healthcare, education, or architecture. A significant aspect of VR is the inclusion of self-avatars, representing users within the virtual world, which enhances interaction and embodiment. However, generating lifelike full-body self-avatar animations remains challenging, particularly in consumer-grade VR systems, where lower-body tracking is often absent. One method to tackle this problem is by providing an external source of motion information that includes lower body information such as full Cartesian positions estimated from RGB(D) cameras. Nevertheless, the limitations of these systems are multiples: the desynchronization between the two motion sources and occlusions are examples of significant issues that hinder the implementations of such systems. In this paper, we aim to measure the impact on the reconstruction of the articulated self-avatar's full-body pose of (1) the latency between the VR motion features and estimated positions, (2) the data acquisition rate, (3) occlusions, and (4) the inaccuracy of the position estimation algorithm. In addition, we analyze the motion reconstruction errors using ground truth and 3D Cartesian coordinates estimated from \textit{YOLOv8} pose estimation. These analyzes show that the studied methods are significantly sensitive to any degradation tested, especially regarding the velocity reconstruction error.
Authors: Wenbo Wang, Hsuan-I Ho, Chen Guo, Boxiang Rong, Artur Grigorev, Jie Song, Juan Jose Zarate, Otmar Hilliges
Abstract: The studies of human clothing for digital avatars have predominantly relied on synthetic datasets. While easy to collect, synthetic data often fall short in realism and fail to capture authentic clothing dynamics. Addressing this gap, we introduce 4D-DRESS, the first real-world 4D dataset advancing human clothing research with its high-quality 4D textured scans and garment meshes. 4D-DRESS captures 64 outfits in 520 human motion sequences, amounting to 78k textured scans. Creating a real-world clothing dataset is challenging, particularly in annotating and segmenting the extensive and complex 4D human scans. To address this, we develop a semi-automatic 4D human parsing pipeline. We efficiently combine a human-in-the-loop process with automation to accurately label 4D scans in diverse garments and body movements. Leveraging precise annotations and high-quality garment meshes, we establish several benchmarks for clothing simulation and reconstruction. 4D-DRESS offers realistic and challenging data that complements synthetic sources, paving the way for advancements in research of lifelike human clothing. Website: https://ait.ethz.ch/4d-dress.
Authors: Zhaobo Qi, Shuhui Wang, Weigang Zhang, Qingming Huang
Abstract: Video activity anticipation aims to predict what will happen in the future, embracing a broad application prospect ranging from robot vision and autonomous driving. Despite the recent progress, the data uncertainty issue, reflected as the content evolution process and dynamic correlation in event labels, has been somehow ignored. This reduces the model generalization ability and deep understanding on video content, leading to serious error accumulation and degraded performance. In this paper, we address the uncertainty learning problem and propose an uncertainty-boosted robust video activity anticipation framework, which generates uncertainty values to indicate the credibility of the anticipation results. The uncertainty value is used to derive a temperature parameter in the softmax function to modulate the predicted target activity distribution. To guarantee the distribution adjustment, we construct a reasonable target activity label representation by incorporating the activity evolution from the temporal class correlation and the semantic relationship. Moreover, we quantify the uncertainty into relative values by comparing the uncertainty among sample pairs and their temporal-lengths. This relative strategy provides a more accessible way in uncertainty modeling than quantifying the absolute uncertainty values on the whole dataset. Experiments on multiple backbones and benchmarks show our framework achieves promising performance and better robustness/interpretability. Source codes are available at https://github.com/qzhb/UbRV2A.
Authors: Konstantinos Tsigos, Evlampios Apostolidis, Spyridon Baxevanakis, Symeon Papadopoulos, Vasileios Mezaris
Abstract: In this paper we propose a new framework for evaluating the performance of explanation methods on the decisions of a deepfake detector. This framework assesses the ability of an explanation method to spot the regions of a fake image with the biggest influence on the decision of the deepfake detector, by examining the extent to which these regions can be modified through a set of adversarial attacks, in order to flip the detector's prediction or reduce its initial prediction; we anticipate a larger drop in deepfake detection accuracy and prediction, for methods that spot these regions more accurately. Based on this framework, we conduct a comparative study using a state-of-the-art model for deepfake detection that has been trained on the FaceForensics++ dataset, and five explanation methods from the literature. The findings of our quantitative and qualitative evaluations document the advanced performance of the LIME explanation method against the other compared ones, and indicate this method as the most appropriate for explaining the decisions of the utilized deepfake detector.
Authors: Thomas Guerneve, Stephanos Loizou, Andrea Munafo, Pierre-Yves Mignotte
Abstract: The performance of Automated Recognition (ATR) algorithms on side-scan sonar imagery has shown to degrade rapidly when deployed on non benign environments. Complex seafloors and acoustic artefacts constitute distractors in the form of strong textural patterns, creating false detections or preventing detections of true objects. This paper presents two online seafloor characterisation techniques to improve explainability during Autonomous Underwater Vehicles (AUVs) missions. Importantly and as opposed to previous work in the domain, these techniques are not based on a model and require limited input from human operators, making it suitable for real-time onboard processing. Both techniques rely on an unsupervised machine learning approach to extract terrain features which relate to the human understanding of terrain complexity. The first technnique provides a quantitative, application-driven terrain characterisation metric based on the performance of an ATR algorithm. The second method provides a way to incorporate subject matter expertise and enables contextualisation and explainability in support for scenario-dependent subjective terrain characterisation. The terrain complexity matches the expectation of seasoned users making this tool desirable and trustworthy in comparison to traditional unsupervised approaches. We finally detail an application of these techniques to repair a Mine Countermeasures (MCM) mission carried with SeeByte autonomy framework Neptune.
Authors: David Villanova-Aparisi, Sol\`ene Tarride, Carlos-D. Mart\'inez-Hinarejos, Ver\'onica Romero, Christopher Kermorvant, Mois\'es Pastor-Gadea
Abstract: Information Extraction processes in handwritten documents tend to rely on obtaining an automatic transcription and performing Named Entity Recognition (NER) over such transcription. For this reason, in publicly available datasets, the performance of the systems is usually evaluated with metrics particular to each dataset. Moreover, most of the metrics employed are sensitive to reading order errors. Therefore, they do not reflect the expected final application of the system and introduce biases in more complex documents. In this paper, we propose and publicly release a set of reading order independent metrics tailored to Information Extraction evaluation in handwritten documents. In our experimentation, we perform an in-depth analysis of the behavior of the metrics to recommend what we consider to be the minimal set of metrics to evaluate a task correctly.
Authors: Rajat K. Doshi
Abstract: This study investigates the application of PointNet and PointNet++ in the classification of LiDAR-generated point cloud data, a critical component for achieving fully autonomous vehicles. Utilizing a modified dataset from the Lyft 3D Object Detection Challenge, we examine the models' capabilities to handle dynamic and complex environments essential for autonomous navigation. Our analysis shows that PointNet and PointNet++ achieved accuracy rates of 79.53% and 84.24%, respectively. These results underscore the models' robustness in interpreting intricate environmental data, which is pivotal for the safety and efficiency of autonomous vehicles. Moreover, the enhanced detection accuracy, particularly in distinguishing pedestrians from other objects, highlights the potential of these models to contribute substantially to the advancement of autonomous vehicle technology.
Authors: Liying Gao, Bingliang Jiao, Peng Wang, Shizhou Zhang, Hanwang Zhang, Yanning Zhang
Abstract: Sketch-based image retrieval (SBIR) associates hand-drawn sketches with their corresponding realistic images. In this study, we aim to tackle two major challenges of this task simultaneously: i) zero-shot, dealing with unseen categories, and ii) fine-grained, referring to intra-category instance-level retrieval. Our key innovation lies in the realization that solely addressing this cross-category and fine-grained recognition task from the generalization perspective may be inadequate since the knowledge accumulated from limited seen categories might not be fully valuable or transferable to unseen target categories. Inspired by this, in this work, we propose a dual-modal prompting CLIP (DP-CLIP) network, in which an adaptive prompting strategy is designed. Specifically, to facilitate the adaptation of our DP-CLIP toward unpredictable target categories, we employ a set of images within the target category and the textual category label to respectively construct a set of category-adaptive prompt tokens and channel scales. By integrating the generated guidance, DP-CLIP could gain valuable category-centric insights, efficiently adapting to novel categories and capturing unique discriminative clues for effective retrieval within each target category. With these designs, our DP-CLIP outperforms the state-of-the-art fine-grained zero-shot SBIR method by 7.3% in Acc.@1 on the Sketchy dataset. Meanwhile, in the other two category-level zero-shot SBIR benchmarks, our method also achieves promising performance.
Authors: M\'elodie Boillet, Sol\`ene Tarride, Yoann Schneider, Bastien Abadie, Lionel Kesztenbaum, Christopher Kermorvant
Abstract: This paper presents a complete processing workflow for extracting information from French census lists from 1836 to 1936. These lists contain information about individuals living in France and their households. We aim at extracting all the information contained in these tables using automatic handwritten table recognition. At the end of the Socface project, in which our work is taking place, the extracted information will be redistributed to the departmental archives, and the nominative lists will be freely available to the public, allowing anyone to browse hundreds of millions of records. The extracted data will be used by demographers to analyze social change over time, significantly improving our understanding of French economic and social structures. For this project, we developed a complete processing workflow: large-scale data collection from French departmental archives, collaborative annotation of documents, training of handwritten table text and structure recognition models, and mass processing of millions of images. We present the tools we have developed to easily collect and process millions of pages. We also show that it is possible to process such a wide variety of tables with a single table recognition model that uses the image of the entire page to recognize information about individuals, categorize them and automatically group them into households. The entire process has been successfully used to process the documents of a departmental archive, representing more than 450,000 images.
Authors: Sol\`ene Tarride, Yoann Schneider, Marie Generali-Lince, M\'elodie Boillet, Bastien Abadie, Christopher Kermorvant
Abstract: PyLaia is one of the most popular open-source software for Automatic Text Recognition (ATR), delivering strong performance in terms of speed and accuracy. In this paper, we outline our recent contributions to the PyLaia library, focusing on the incorporation of reliable confidence scores and the integration of statistical language modeling during decoding. Our implementation provides an easy way to combine PyLaia with n-grams language models at different levels. One of the highlights of this work is that language models are completely auto-tuned: they can be built and used easily without any expert knowledge, and without requiring any additional data. To demonstrate the significance of our contribution, we evaluate PyLaia's performance on twelve datasets, both with and without language modelling. The results show that decoding with small language models improves the Word Error Rate by 13% and the Character Error Rate by 12% in average. Additionally, we conduct an analysis of confidence scores and highlight the importance of calibration techniques. Our implementation is publicly available in the official PyLaia repository at https://gitlab.teklia.com/atr/pylaia, and twelve open-source models are released on Hugging Face.
Authors: Halid Ziya Yerebakan, Yoshihisa Shinagawa, Gerardo Hermosillo Valadez
Abstract: Organ segmentation is a fundamental task in medical imaging, and it is useful for many clinical automation pipelines. Typically, the process involves segmenting the entire volume, which can be unnecessary when the points of interest are limited. In those cases, a classifier could be used instead of segmentation. However, there is an inherent trade-off between the context size and the speed of classifiers. To address this issue, we propose a new method that employs a data selection strategy with sparse sampling across a wide field of view without image resampling. This sparse sampling strategy makes it possible to classify voxels into multiple organs in real time without using accelerators. Although our method is an independent classifier, it can generate full segmentation by querying grid locations at any resolution. We have compared our method with existing segmentation techniques, demonstrating its potential for superior runtime in practical applications in medical imaging.
Authors: Shanle Yao, Ghazal Alinezhad Noghre, Armin Danesh Pazho, Hamed Tabkhi
Abstract: Video Anomaly Detection (VAD) identifies unusual activities in video streams, a key technology with broad applications ranging from surveillance to healthcare. Tackling VAD in real-life settings poses significant challenges due to the dynamic nature of human actions, environmental variations, and domain shifts. Many research initiatives neglect these complexities, often concentrating on traditional testing methods that fail to account for performance on unseen datasets, creating a gap between theoretical models and their real-world utility. Online learning is a potential strategy to mitigate this issue by allowing models to adapt to new information continuously. This paper assesses how well current VAD algorithms can adjust to real-life conditions through an online learning framework, particularly those based on pose analysis, for their efficiency and privacy advantages. Our proposed framework enables continuous model updates with streaming data from novel environments, thus mirroring actual world challenges and evaluating the models' ability to adapt in real-time while maintaining accuracy. We investigate three state-of-the-art models in this setting, focusing on their adaptability across different domains. Our findings indicate that, even under the most challenging conditions, our online learning approach allows a model to preserve 89.39% of its original effectiveness compared to its offline-trained counterpart in a specific target domain.
Authors: Peter Mortimer, Mirko Maehlisch
Abstract: Perception is an essential component of pipelines in field robotics. In this survey, we quantitatively compare publicly available datasets available in unstructured outdoor environments. We focus on datasets for common perception tasks in field robotics. Our survey categorizes and compares available research datasets. This survey also reports on relevant dataset characteristics to help practitioners determine which dataset fits best for their own application. We believe more consideration should be taken in choosing compatible annotation policies across the datasets in unstructured outdoor environments.
Authors: Liyuan Wang, Yan Jin, Zhen Chen, Jinlin Wu, Mengke Li, Yang Lu, Hanzi Wang
Abstract: The vision-language pre-training has enabled deep models to make a huge step forward in generalizing across unseen domains. The recent learning method based on the vision-language pre-training model is a great tool for domain generalization and can solve this problem to a large extent. However, there are still some issues that an advancement still suffers from trading-off between domain invariance and class separability, which are crucial in current DG problems. However, there are still some issues that an advancement still suffers from trading-off between domain invariance and class separability, which are crucial in current DG problems. In this paper, we introduce a novel prompt learning strategy that leverages deep vision prompts to address domain invariance while utilizing language prompts to ensure class separability, coupled with adaptive weighting mechanisms to balance domain invariance and class separability. Extensive experiments demonstrate that deep vision prompts effectively extract domain-invariant features, significantly improving the generalization ability of deep models and achieving state-of-the-art performance on three datasets.
Authors: Hanxiao Tan
Abstract: Although point cloud models have gained significant improvements in prediction accuracy over recent years, their trustworthiness is still not sufficiently investigated. In terms of global explainability, Activation Maximization (AM) techniques in the image domain are not directly transplantable due to the special structure of the point cloud models. Existing studies exploit generative models to yield global explanations that can be perceived by humans. However, the opacity of the generative models themselves and the introduction of additional priors call into question the plausibility and fidelity of the explanations. In this work, we demonstrate that when the classifier predicts different types of instances, the intermediate layer activations are differently activated, known as activation flows. Based on this property, we propose an activation flow-based AM method that generates global explanations that can be perceived without incorporating any generative model. Furthermore, we reveal that AM based on generative models fails the sanity checks and thus lack of fidelity. Extensive experiments show that our approach dramatically enhances the perceptibility of explanations compared to other AM methods that are not based on generative models. Our code is available at: https://github.com/Explain3D/FlowAM
Authors: Thomas Rochefort-Beaudoin, Aurelian Vadean, Sofiane Achiche, Niels Aage
Abstract: This paper introduces YOLOv8-TO, a novel approach for reverse engineering of topology-optimized structures into interpretable geometric parameters using the YOLOv8 instance segmentation model. Density-based topology optimization methods require post-processing to convert the optimal density distribution into a parametric representation for design exploration and integration with CAD tools. Traditional methods such as skeletonization struggle with complex geometries and require manual intervention. YOLOv8-TO addresses these challenges by training a custom YOLOv8 model to automatically detect and reconstruct structural components from binary density distributions. The model is trained on a diverse dataset of both optimized and random structures generated using the Moving Morphable Components method. A custom reconstruction loss function based on the dice coefficient of the predicted geometry is used to train the new regression head of the model via self-supervised learning. The method is evaluated on test sets generated from different topology optimization methods, including out-of-distribution samples, and compared against a skeletonization approach. Results show that YOLOv8-TO significantly outperforms skeletonization in reconstructing visually and structurally similar designs. The method showcases an average improvement of 13.84% in the Dice coefficient, with peak enhancements reaching 20.78%. The method demonstrates good generalization to complex geometries and fast inference times, making it suitable for integration into design workflows using regular workstations. Limitations include the sensitivity to non-max suppression thresholds. YOLOv8-TO represents a significant advancement in topology optimization post-processing, enabling efficient and accurate reverse engineering of optimized structures for design exploration and manufacturing.
Authors: Gustaw Opie{\l}ka, Jessica Loke, Steven Scholte
Abstract: Deep learning algorithms lack human-interpretable accounts of how they transform raw visual input into a robust semantic understanding, which impedes comparisons between different architectures, training objectives, and the human brain. In this work, we take inspiration from neuroscience and employ representational approaches to shed light on how neural networks encode information at low (visual saliency) and high (semantic similarity) levels of abstraction. Moreover, we introduce a custom image dataset where we systematically manipulate salient and semantic information. We find that ResNets are more sensitive to saliency information than ViTs, when trained with object classification objectives. We uncover that networks suppress saliency in early layers, a process enhanced by natural language supervision (CLIP) in ResNets. CLIP also enhances semantic encoding in both architectures. Finally, we show that semantic encoding is a key factor in aligning AI with human visual perception, while saliency suppression is a non-brain-like strategy.
Authors: Vishal Purohit, Wenxin Jiang, Akshath R. Ravikiran, James C. Davis
Abstract: This paper undertakes the task of replicating the MaskFormer model a universal image segmentation model originally developed using the PyTorch framework, within the TensorFlow ecosystem, specifically optimized for execution on Tensor Processing Units (TPUs). Our implementation exploits the modular constructs available within the TensorFlow Model Garden (TFMG), encompassing elements such as the data loader, training orchestrator, and various architectural components, tailored and adapted to meet the specifications of the MaskFormer model. We address key challenges encountered during the replication, non-convergence issues, slow training, adaptation of loss functions, and the integration of TPU-specific functionalities. We verify our reproduced implementation and present qualitative results on the COCO dataset. Although our implementation meets some of the objectives for end-to-end reproducibility, we encountered challenges in replicating the PyTorch version of MaskFormer in TensorFlow. This replication process is not straightforward and requires substantial engineering efforts. Specifically, it necessitates the customization of various components within the TFMG, alongside thorough verification and hyper-parameter tuning. The replication is available at: https://github.com/PurdueDualityLab/tf-maskformer/tree/main/official/projects/maskformer
URLs: https://github.com/PurdueDualityLab/tf-maskformer/tree/main/official/projects/maskformer
Authors: Hong Nguyen, Hoang Nguyen, Melinda Chang, Hieu Pham, Shrikanth Narayanan, Michael Pazzani
Abstract: Understanding the severity of conditions shown in images in medical diagnosis is crucial, serving as a key guide for clinical assessment, treatment, as well as evaluating longitudinal progression. This paper proposes Con- PrO: a novel representation learning method for severity assessment in medical images using Contrastive learningintegrated Preference Optimization. Different from conventional contrastive learning methods that maximize the distance between classes, ConPrO injects into the latent vector the distance preference knowledge between various severity classes and the normal class. We systematically examine the key components of our framework to illuminate how contrastive prediction tasks acquire valuable representations. We show that our representation learning framework offers valuable severity ordering in the feature space while outperforming previous state-of-the-art methods on classification tasks. We achieve a 6% and 20% relative improvement compared to a supervised and a self-supervised baseline, respectively. In addition, we derived discussions on severity indicators and related applications of preference comparison in the medical domain.
Authors: Kathryn Knight, Ioana Danciu, Olga Ovchinnikova, Jacob Hinkle, Mayanka Chandra Shekar, Debangshu Mukherjee, Eileen McAllister, Caitlin Rizy, Kelly Cho, Amy C. Justice, Joseph Erdos, Peter Kuzmak, Lauren Costa, Yuk-Lam Ho, Reddy Madipadga, Suzanne Tamang, Ian Goethert
Abstract: The compilation and analysis of radiological images poses numerous challenges for researchers. The sheer volume of data as well as the computational needs of algorithms capable of operating on images are extensive. Additionally, the assembly of these images alone is difficult, as these exams may differ widely in terms of clinical context, structured annotation available for model training, modality, and patient identifiers. In this paper, we describe our experiences and challenges in establishing a trusted collection of radiology images linked to the United States Department of Veterans Affairs (VA) electronic health record database. We also discuss implications in making this repository research-ready for medical investigators. Key insights include uncovering the specific procedures required for transferring images from a clinical to a research-ready environment, as well as roadblocks and bottlenecks in this process that may hinder future efforts at automation.
Authors: Heitor R. Medeiros, David Latortue, Fidel Guerrero Pena, Eric Granger, Marco Pedersoli
Abstract: In this paper, we present a different way to use two modalities, in which either one modality or the other is seen by a single model. This can be useful when adapting an unimodal model to leverage more information while respecting a limited computational budget. This would mean having a single model that is able to deal with any modalities. To describe this, we coined the term anymodal learning. An example of this, is a use case where, surveillance in a room when the lights are off would be much more valuable using an infrared modality while a visible one would provide more discriminative information when lights are on. This work investigates how to efficiently leverage visible and infrared/thermal modalities for transformer-based object detection backbone to create an anymodal architecture. Our work does not create any inference overhead during the testing while exploring an effective way to exploit the two modalities during the training. To accomplish such a task, we introduce the novel anymodal training technique: Mixed Patches (MiPa), in conjunction with a patch-wise domain agnostic module, which is responsible of learning the best way to find a common representation of both modalities. This approach proves to be able to balance modalities by reaching competitive results on individual modality benchmarks with the alternative of using an unimodal architecture on three different visible-infrared object detection datasets. Finally, our proposed method, when used as a regularization for the strongest modality, can beat the performance of multimodal fusion methods while only requiring a single modality during inference. Notably, MiPa became the state-of-the-art on the LLVIP visible/infrared benchmark. Code: https://github.com/heitorrapela/MiPa
Authors: Rui Xu, Shu Yang, Yihui Wang, Bo Du, Hao Chen
Abstract: Mamba, a recent selective structured state space model, performs excellently on long sequence modeling tasks. Mamba mitigates the modeling constraints of convolutional neural networks and offers advanced modeling capabilities similar to those of Transformers, through global receptive fields and dynamic weighting. Crucially, it achieves this without incurring the quadratic computational complexity typically associated with Transformers. Due to its advantages over the former two mainstream foundation models, Mamba exhibits great potential to be a visual foundation model. Researchers are actively applying Mamba to various computer vision tasks, leading to numerous emerging works. To help keep pace with the rapid advancements in computer vision, this paper aims to provide a comprehensive review of visual Mamba approaches. This paper begins by delineating the formulation of the original Mamba model. Subsequently, our review of visual Mamba delves into several representative backbone networks to elucidate the core insights of the visual Mamba. We then categorize related works using different modalities, including image, video, point cloud, multi-modal, and others. Specifically, for image applications, we further organize them into distinct tasks to facilitate a more structured discussion. Finally, we discuss the challenges and future research directions for visual Mamba, providing insights for future research in this quickly evolving area. A comprehensive list of visual Mamba models reviewed in this work is available at https://github.com/Ruixxxx/Awesome-Vision-Mamba-Models.
URLs: https://github.com/Ruixxxx/Awesome-Vision-Mamba-Models.
Authors: Guillaume Astruc, Nicolas Dufour, Ioannis Siglidis, Constantin Aronssohn, Nacim Bouia, Stephanie Fu, Romain Loiseau, Van Nguyen Nguyen, Charles Raude, Elliot Vincent, Lintao XU, Hongyu Zhou, Loic Landrieu
Abstract: Determining the location of an image anywhere on Earth is a complex visual task, which makes it particularly relevant for evaluating computer vision algorithms. Yet, the absence of standard, large-scale, open-access datasets with reliably localizable images has limited its potential. To address this issue, we introduce OpenStreetView-5M, a large-scale, open-access dataset comprising over 5.1 million geo-referenced street view images, covering 225 countries and territories. In contrast to existing benchmarks, we enforce a strict train/test separation, allowing us to evaluate the relevance of learned geographical features beyond mere memorization. To demonstrate the utility of our dataset, we conduct an extensive benchmark of various state-of-the-art image encoders, spatial representations, and training strategies. All associated codes and models can be found at https://github.com/gastruc/osv5m.
Authors: Cristiano B. de Oliveira, Joao C. Neves, Rafael O. Ribeiro, David Menotti
Abstract: The Pal\'acio do Planalto, office of the President of Brazil, was invaded by protesters on January 8, 2023. Surveillance videos taken from inside the building were subsequently released by the Brazilian Supreme Court for public scrutiny. We used segments of such footage to create the UFPR-Planalto801 dataset for people tracking and re-identification in a real-world scenario. This dataset consists of more than 500,000 images. This paper presents a tracking approach targeting this dataset. The method proposed in this paper relies on the use of known state-of-the-art trackers combined in a multilevel hierarchy to correct the ID association over the trajectories. We evaluated our method using IDF1, MOTA, MOTP and HOTA metrics. The results show improvements for every tracker used in the experiments, with IDF1 score increasing by a margin up to 9.5%.
Authors: Yuguang Yao, Steven Grosz, Sijia Liu, Anil Jain
Abstract: The recent progress in generative models has revolutionized the synthesis of highly realistic images, including face images. This technological development has undoubtedly helped face recognition, such as training data augmentation for higher recognition accuracy and data privacy. However, it has also introduced novel challenges concerning the responsible use and proper attribution of computer generated images. We investigate the impact of digital watermarking, a technique for embedding ownership signatures into images, on the effectiveness of face recognition models. We propose a comprehensive pipeline that integrates face image generation, watermarking, and face recognition to systematically examine this question. The proposed watermarking scheme, based on an encoder-decoder architecture, successfully embeds and recovers signatures from both real and synthetic face images while preserving their visual fidelity. Through extensive experiments, we unveil that while watermarking enables robust image attribution, it results in a slight decline in face recognition accuracy, particularly evident for face images with challenging poses and expressions. Additionally, we find that directly training face recognition models on watermarked images offers only a limited alleviation of this performance decline. Our findings underscore the intricate trade off between watermarking and face recognition accuracy. This work represents a pivotal step towards the responsible utilization of generative models in face recognition and serves to initiate discussions regarding the broader implications of watermarking in biometrics.
Authors: Kebin Wu, Wenbin Li, Xiaofei Xiao
Abstract: The scarcity of labeled data in real-world scenarios is a critical bottleneck of deep learning's effectiveness. Semi-supervised semantic segmentation has been a typical solution to achieve a desirable tradeoff between annotation cost and segmentation performance. However, previous approaches, whether based on consistency regularization or self-training, tend to neglect the contextual knowledge embedded within inter-pixel relations. This negligence leads to suboptimal performance and limited generalization. In this paper, we propose a novel approach IPixMatch designed to mine the neglected but valuable Inter-Pixel information for semi-supervised learning. Specifically, IPixMatch is constructed as an extension of the standard teacher-student network, incorporating additional loss terms to capture inter-pixel relations. It shines in low-data regimes by efficiently leveraging the limited labeled data and extracting maximum utility from the available unlabeled data. Furthermore, IPixMatch can be integrated seamlessly into most teacher-student frameworks without the need of model modification or adding additional components. Our straightforward IPixMatch method demonstrates consistent performance improvements across various benchmark datasets under different partitioning protocols.
Authors: Chenyang Liu, Keyan Chen, Bowen Chen, Haotian Zhang, Zhengxia Zou, Zhenwei Shi
Abstract: Remote Sensing Image Change Captioning (RSICC) aims to identify surface changes in multi-temporal remote sensing images and describe them in natural language. Current methods typically rely on an encoder-decoder architecture and focus on designing a sophisticated neck to process bi-temporal features extracted by the backbone. Recently, State Space Models (SSMs), especially Mamba, have demonstrated outstanding performance in many fields, owing to their efficient feature-selective modelling capability. However, their potential in the RSICC task remains unexplored. In this paper, we introduce Mamba into RSICC and propose a novel approach called RSCaMa (Remote Sensing Change Captioning Mamba). Specifically, we utilize Siamese backbones to extract bi-temporal features, which are then processed through multiple CaMa layers consisting of Spatial Difference-guided SSM (SD-SSM) and Temporal Traveling SSM (TT-SSM). SD-SSM uses differential features to enhance change perception, while TT-SSM promotes bitemporal interactions in a token-wise cross-scanning manner. Experimental results validate the effectiveness of CaMa layers and demonstrate the superior performance of RSCaMa, as well as the potential of Mamba in the RSICC task. Additionally, we systematically compare the effects of three language decoders, including Mamba, GPT-style decoder with causal attention mechanism, and Transformer decoder with cross-attention mechanism. This provides valuable insights for future RSICC research. The code will be available at https://github.com/Chen-Yang-Liu/RSCaMa
Authors: Junhao Cheng, Baiqiao Yin, Kaixin Cai, Minbin Huang, Hanhui Li, Yuxin He, Xi Lu, Yue Li, Yifei Li, Yuhao Cheng, Yiqiang Yan, Xiaodan Liang
Abstract: Recent advances in diffusion models can generate high-quality and stunning images from text. However, multi-turn image generation, which is of high demand in real-world scenarios, still faces challenges in maintaining semantic consistency between images and texts, as well as contextual consistency of the same subject across multiple interactive turns. To address this issue, we introduce TheaterGen, a training-free framework that integrates large language models (LLMs) and text-to-image (T2I) models to provide the capability of multi-turn image generation. Within this framework, LLMs, acting as a "Screenwriter", engage in multi-turn interaction, generating and managing a standardized prompt book that encompasses prompts and layout designs for each character in the target image. Based on these, Theatergen generate a list of character images and extract guidance information, akin to the "Rehearsal". Subsequently, through incorporating the prompt book and guidance information into the reverse denoising process of T2I diffusion models, Theatergen generate the final image, as conducting the "Final Performance". With the effective management of prompt books and character images, TheaterGen significantly improves semantic and contextual consistency in synthesized images. Furthermore, we introduce a dedicated benchmark, CMIGBench (Consistent Multi-turn Image Generation Benchmark) with 8000 multi-turn instructions. Different from previous multi-turn benchmarks, CMIGBench does not define characters in advance. Both the tasks of story generation and multi-turn editing are included on CMIGBench for comprehensive evaluation. Extensive experimental results show that TheaterGen outperforms state-of-the-art methods significantly. It raises the performance bar of the cutting-edge Mini DALLE 3 model by 21% in average character-character similarity and 19% in average text-image similarity.
Authors: Leonardo Rossi, Vittorio Bernuzzi, Tomaso Fontanini, Massimo Bertozzi, Andrea Prati
Abstract: Due to the limitations of current optical and sensor technologies and the high cost of updating them, the spectral and spatial resolution of satellites may not always meet desired requirements. For these reasons, Remote-Sensing Single-Image Super-Resolution (RS-SISR) techniques have gained significant interest. In this paper, we propose Swin2-MoSE model, an enhanced version of Swin2SR. Our model introduces MoE-SM, an enhanced Mixture-of-Experts (MoE) to replace the Feed-Forward inside all Transformer block. MoE-SM is designed with Smart-Merger, and new layer for merging the output of individual experts, and with a new way to split the work between experts, defining a new per-example strategy instead of the commonly used per-token one. Furthermore, we analyze how positional encodings interact with each other, demonstrating that per-channel bias and per-head bias can positively cooperate. Finally, we propose to use a combination of Normalized-Cross-Correlation (NCC) and Structural Similarity Index Measure (SSIM) losses, to avoid typical MSE loss limitations. Experimental results demonstrate that Swin2-MoSE outperforms SOTA by up to 0.377 ~ 0.958 dB (PSNR) on task of 2x, 3x and 4x resolution-upscaling (Sen2Venus and OLI2MSI datasets). We show the efficacy of Swin2-MoSE, applying it to a semantic segmentation task (SeasoNet dataset). Code and pretrained are available on https://github.com/IMPLabUniPr/swin2-mose/tree/official_code
URLs: https://github.com/IMPLabUniPr/swin2-mose/tree/official_code
Authors: Michael Luo, Justin Wong, Brandon Trabucco, Yanping Huang, Joseph E. Gonzalez, Zhifeng Chen, Ruslan Salakhutdinov, Ion Stoica
Abstract: Beyond scaling base models with more data or parameters, fine-tuned adapters provide an alternative way to generate high fidelity, custom images at reduced costs. As such, adapters have been widely adopted by open-source communities, accumulating a database of over 100K adapters-most of which are highly customized with insufficient descriptions. This paper explores the problem of matching the prompt to a set of relevant adapters, built on recent work that highlight the performance gains of composing adapters. We introduce Stylus, which efficiently selects and automatically composes task-specific adapters based on a prompt's keywords. Stylus outlines a three-stage approach that first summarizes adapters with improved descriptions and embeddings, retrieves relevant adapters, and then further assembles adapters based on prompts' keywords by checking how well they fit the prompt. To evaluate Stylus, we developed StylusDocs, a curated dataset featuring 75K adapters with pre-computed adapter embeddings. In our evaluation on popular Stable Diffusion checkpoints, Stylus achieves greater CLIP-FID Pareto efficiency and is twice as preferred, with humans and multimodal models as evaluators, over the base model. See stylus-diffusion.github.io for more.
Authors: Minghao Chen, Iro Laina, Andrea Vedaldi
Abstract: We consider the problem of editing 3D objects and scenes based on open-ended language instructions. The established paradigm to solve this problem is to use a 2D image generator or editor to guide the 3D editing process. However, this is often slow as it requires do update a computationally expensive 3D representations such as a neural radiance field, and to do so by using contradictory guidance from a 2D model which is inherently not multi-view consistent. We thus introduce the Direct Gaussian Editor (DGE), a method that addresses these issues in two ways. First, we modify a given high-quality image editor like InstructPix2Pix to be multi-view consistent. We do so by utilizing a training-free approach which integrates cues from the underlying 3D geometry of the scene. Second, given a multi-view consistent edited sequence of images of the object, we directly and efficiently optimize the 3D object representation, which is based on 3D Gaussian Splatting. Because it does not require to apply edits incrementally and iteratively, DGE is significantly more efficient than existing approaches, and comes with other perks such as allowing selective editing of parts of the scene.
Authors: Zechen Bai, Pichao Wang, Tianjun Xiao, Tong He, Zongbo Han, Zheng Zhang, Mike Zheng Shou
Abstract: This survey presents a comprehensive analysis of the phenomenon of hallucination in multimodal large language models (MLLMs), also known as Large Vision-Language Models (LVLMs), which have demonstrated significant advancements and remarkable abilities in multimodal tasks. Despite these promising developments, MLLMs often generate outputs that are inconsistent with the visual content, a challenge known as hallucination, which poses substantial obstacles to their practical deployment and raises concerns regarding their reliability in real-world applications. This problem has attracted increasing attention, prompting efforts to detect and mitigate such inaccuracies. We review recent advances in identifying, evaluating, and mitigating these hallucinations, offering a detailed overview of the underlying causes, evaluation benchmarks, metrics, and strategies developed to address this issue. Additionally, we analyze the current challenges and limitations, formulating open questions that delineate potential pathways for future research. By drawing the granular classification and landscapes of hallucination causes, evaluation benchmarks, and mitigation methods, this survey aims to deepen the understanding of hallucinations in MLLMs and inspire further advancements in the field. Through our thorough and in-depth review, we contribute to the ongoing dialogue on enhancing the robustness and reliability of MLLMs, providing valuable insights and resources for researchers and practitioners alike. Resources are available at: https://github.com/showlab/Awesome-MLLM-Hallucination.
URLs: https://github.com/showlab/Awesome-MLLM-Hallucination.
Authors: Liming Xu, Dave Towey, Andrew P. French, Steve Benford
Abstract: The recent release of the Apple Vision Pro has reignited interest in the metaverse, showcasing the intensified efforts of technology giants in developing platforms and devices to facilitate its growth. As the metaverse continues to proliferate, it is foreseeable that everyday environments will become increasingly saturated with its presence. Consequently, uncovering links to these metaverse items will be a crucial first step to interacting with this new augmented world. In this paper, we address the problem of establishing connections with virtual worlds within everyday environments, especially those that are not readily discernible through direct visual inspection. We introduce a vision-based approach leveraging Artcode visual markers to uncover hidden metaverse links embedded in our ambient surroundings. This approach progressively localises the access points to the metaverse, transitioning from coarse to fine localisation, thus facilitating an exploratory interaction process. Detailed experiments are conducted to study the performance of the proposed approach, demonstrating its effectiveness in Artcode localisation and enabling new interaction opportunities.
Authors: Tao Liu, Yuhang Zhang, Zhu Feng, Zhiqin Yang, Chen Xu, Dapeng Man, Wu Yang
Abstract: Backdoors on federated learning will be diluted by subsequent benign updates. This is reflected in the significant reduction of attack success rate as iterations increase, ultimately failing. We use a new metric to quantify the degree of this weakened backdoor effect, called attack persistence. Given that research to improve this performance has not been widely noted,we propose a Full Combination Backdoor Attack (FCBA) method. It aggregates more combined trigger information for a more complete backdoor pattern in the global model. Trained backdoored global model is more resilient to benign updates, leading to a higher attack success rate on the test set. We test on three datasets and evaluate with two models across various settings. FCBA's persistence outperforms SOTA federated learning backdoor attacks. On GTSRB, postattack 120 rounds, our attack success rate rose over 50% from baseline. The core code of our method is available at https://github.com/PhD-TaoLiu/FCBA.
Authors: Jiahong Wang, Yinwei Du, Stelian Coros, Bernhard Thomaszewski
Abstract: We propose a self-supervised approach for learning physics-based subspaces for real-time simulation. Existing learning-based methods construct subspaces by approximating pre-defined simulation data in a purely geometric way. However, this approach tends to produce high-energy configurations, leads to entangled latent space dimensions, and generalizes poorly beyond the training set. To overcome these limitations, we propose a self-supervised approach that directly minimizes the system's mechanical energy during training. We show that our method leads to learned subspaces that reflect physical equilibrium constraints, resolve overfitting issues of previous methods, and offer interpretable latent space parameters.
Authors: Aya Ghoul, Jiazhen Pan, Andreas Lingg, Jens K\"ubler, Patrick Krumm, Kerstin Hammernik, Daniel Rueckert, Sergios Gatidis, Thomas K\"ustner
Abstract: Accurate motion estimation at high acceleration factors enables rapid motion-compensated reconstruction in Magnetic Resonance Imaging (MRI) without compromising the diagnostic image quality. In this work, we introduce an attention-aware deep learning-based framework that can perform non-rigid pairwise registration for fully sampled and accelerated MRI. We extract local visual representations to build similarity maps between the registered image pairs at multiple resolution levels and additionally leverage long-range contextual information using a transformer-based module to alleviate ambiguities in the presence of artifacts caused by undersampling. We combine local and global dependencies to perform simultaneous coarse and fine motion estimation. The proposed method was evaluated on in-house acquired fully sampled and accelerated data of 101 patients and 62 healthy subjects undergoing cardiac and thoracic MRI. The impact of motion estimation accuracy on the downstream task of motion-compensated reconstruction was analyzed. We demonstrate that our model derives reliable and consistent motion fields across different sampling trajectories (Cartesian and radial) and acceleration factors of up to 16x for cardiac motion and 30x for respiratory motion and achieves superior image quality in motion-compensated reconstruction qualitatively and quantitatively compared to conventional and recent deep learning-based approaches. The code is publicly available at https://github.com/lab-midas/GMARAFT.
Authors: Santtu Keskinen
Abstract: In class incremental learning, neural networks typically suffer from catastrophic forgetting. We show that an MLP featuring a sparse activation function and an adaptive learning rate optimizer can compete with established regularization techniques in the Split-MNIST task. We highlight the effectiveness of the Adaptive SwisH (ASH) activation function in this context and introduce a novel variant, Hard Adaptive SwisH (Hard ASH) to further enhance the learning retention.
Authors: Brian B. Moser, Ahmed Anwar, Federico Raue, Stanislav Frolov, Andreas Dengel
Abstract: Traditional blind image SR methods need to model real-world degradations precisely. Consequently, current research struggles with this dilemma by assuming idealized degradations, which leads to limited applicability to actual user data. Moreover, the ideal scenario - training models on data from the targeted user base - presents significant privacy concerns. To address both challenges, we propose to fuse image SR with federated learning, allowing real-world degradations to be directly learned from users without invading their privacy. Furthermore, it enables optimization across many devices without data centralization. As this fusion is underexplored, we introduce new benchmarks specifically designed to evaluate new SR methods in this federated setting. By doing so, we employ known degradation modeling techniques from SR research. However, rather than aiming to mirror real degradations, our benchmarks use these degradation models to simulate the variety of degradations found across clients within a distributed user base. This distinction is crucial as it circumvents the need to precisely model real-world degradations, which limits contemporary blind image SR research. Our proposed benchmarks investigate blind image SR under new aspects, namely differently distributed degradation types among users and varying user numbers. We believe new methods tested within these benchmarks will perform more similarly in an application, as the simulated scenario addresses the variety while federated learning enables the training on actual degradations.
Authors: Thomas Billington, Ansh Gwash, Aadi Kothari, Lucas Izquierdo, Timothy Talty
Abstract: In the rapidly advancing landscape of connected and automated vehicles (CAV), the integration of Vehicle-to-Everything (V2X) communication in traditional fusion systems presents a promising avenue for enhancing vehicle perception. Addressing current limitations with vehicle sensing, this paper proposes a novel Vehicle-to-Vehicle (V2V) enabled track management system that leverages the synergy between V2V signals and detections from radar and camera sensors. The core innovation lies in the creation of independent priority track lists, consisting of fused detections validated through V2V communication. This approach enables more flexible and resilient thresholds for track management, particularly in scenarios with numerous occlusions where the tracked objects move outside the field of view of the perception sensors. The proposed system considers the implications of falsification of V2X signals which is combated through an initial vehicle identification process using detection from perception sensors. Presented are the fusion algorithm, simulated environments, and validation mechanisms. Experimental results demonstrate the improved accuracy and robustness of the proposed system in common driving scenarios, highlighting its potential to advance the reliability and efficiency of autonomous vehicles.
Authors: Francis Ogoke, Peter Myung-Won Pak, Alexander Myers, Guadalupe Quirarte, Jack Beuth, Jonathan Malen, Amir Barati Farimani
Abstract: Insufficient overlap between the melt pools produced during Laser Powder Bed Fusion (L-PBF) can lead to lack-of-fusion defects and deteriorated mechanical and fatigue performance. In-situ monitoring of the melt pool subsurface morphology requires specialized equipment that may not be readily accessible or scalable. Therefore, we introduce a machine learning framework to correlate in-situ two-color thermal images observed via high-speed color imaging to the two-dimensional profile of the melt pool cross-section. Specifically, we employ a hybrid CNN-Transformer architecture to establish a correlation between single bead off-axis thermal image sequences and melt pool cross-section contours measured via optical microscopy. In this architecture, a ResNet model embeds the spatial information contained within the thermal images to a latent vector, while a Transformer model correlates the sequence of embedded vectors to extract temporal information. Our framework is able to model the curvature of the subsurface melt pool structure, with improved performance in high energy density regimes compared to analytical melt pool models. The performance of this model is evaluated through dimensional and geometric comparisons to the corresponding experimental melt pool observations.
Authors: Areej Alsaafin, Peyman Nejat, Abubakr Shafique, Jibran Khan, Saghir Alfasly, Ghazal Alabtah, H. R. Tizhoosh
Abstract: Digital pathology and the integration of artificial intelligence (AI) models have revolutionized histopathology, opening new opportunities. With the increasing availability of Whole Slide Images (WSIs), there's a growing demand for efficient retrieval, processing, and analysis of relevant images from vast biomedical archives. However, processing WSIs presents challenges due to their large size and content complexity. Full computer digestion of WSIs is impractical, and processing all patches individually is prohibitively expensive. In this paper, we propose an unsupervised patching algorithm, Sequential Patching Lattice for Image Classification and Enquiry (SPLICE). This novel approach condenses a histopathology WSI into a compact set of representative patches, forming a "collage" of WSI while minimizing redundancy. SPLICE prioritizes patch quality and uniqueness by sequentially analyzing a WSI and selecting non-redundant representative features. We evaluated SPLICE for search and match applications, demonstrating improved accuracy, reduced computation time, and storage requirements compared to existing state-of-the-art methods. As an unsupervised method, SPLICE effectively reduces storage requirements for representing tissue images by 50%. This reduction enables numerous algorithms in computational pathology to operate much more efficiently, paving the way for accelerated adoption of digital pathology.
Authors: Arun N. Sivakumar, Mateus V. Gasparino, Michael McGuire, Vitor A. H. Higuti, M. Ugur Akcal, Girish Chowdhary
Abstract: We present a vision-based navigation system for under-canopy agricultural robots using semantic keypoints. Autonomous under-canopy navigation is challenging due to the tight spacing between the crop rows ($\sim 0.75$ m), degradation in RTK-GPS accuracy due to multipath error, and noise in LiDAR measurements from the excessive clutter. Our system, CropFollow++, introduces modular and interpretable perception architecture with a learned semantic keypoint representation. We deployed CropFollow++ in multiple under-canopy cover crop planting robots on a large scale (25 km in total) in various field conditions and we discuss the key lessons learned from this.
Authors: Mingyu Yang, Bowen Liu, Boyang Wang, Hun-Seok Kim
Abstract: Deep learning-based joint source-channel coding (deep JSCC) has been demonstrated as an effective approach for wireless image transmission. Nevertheless, current research has concentrated on minimizing a standard distortion metric such as Mean Squared Error (MSE), which does not necessarily improve the perceptual quality. To address this issue, we propose DiffJSCC, a novel framework that leverages pre-trained text-to-image diffusion models to enhance the realism of images transmitted over the channel. The proposed DiffJSCC utilizes prior deep JSCC frameworks to deliver an initial reconstructed image at the receiver. Then, the spatial and textual features are extracted from the initial reconstruction, which, together with the channel state information (e.g., signal-to-noise ratio, SNR), are passed to a control module to fine-tune the pre-trained Stable Diffusion model. Extensive experiments on the Kodak dataset reveal that our method significantly surpasses both conventional methods and prior deep JSCC approaches on perceptual metrics such as LPIPS and FID scores, especially with poor channel conditions and limited bandwidth. Notably, DiffJSCC can achieve highly realistic reconstructions for 768x512 pixel Kodak images with only 3072 symbols (<0.008 symbols per pixel) under 1dB SNR. Our code will be released in https://github.com/mingyuyng/DiffJSCC.
Authors: Zheyuan Zhang, Ulas Bagci
Abstract: Current medical image segmentation relies on the region-based (Dice, F1-score) and boundary-based (Hausdorff distance, surface distance) metrics as the de-facto standard. While these metrics are widely used, they lack a unified interpretation, particularly regarding volume agreement. Clinicians often lack clear benchmarks to gauge the "goodness" of segmentation results based on these metrics. Recognizing the clinical relevance of volumetry, we utilize relative volume prediction error (vpe) to directly assess the accuracy of volume predictions derived from segmentation tasks. Our work integrates theoretical analysis and empirical validation across diverse datasets. We delve into the often-ambiguous relationship between segmentation quality (measured by Dice) and volumetric accuracy in clinical practice. Our findings highlight the critical role of incorporating volumetric prediction accuracy into segmentation evaluation. This approach empowers clinicians with a more nuanced understanding of segmentation performance, ultimately improving the interpretation and utility of these metrics in real-world healthcare settings.
Authors: Olivier Brochu Dufour, Abolfazl Mohebbi, Sofiane Achiche
Abstract: Drones are increasingly used in fields like industry, medicine, research, disaster relief, defense, and security. Technical challenges, such as navigation in GPS-denied environments, hinder further adoption. Research in visual odometry is advancing, potentially solving GPS-free navigation issues. Traditional visual odometry methods use geometry-based pipelines which, while popular, often suffer from error accumulation and high computational demands. Recent studies utilizing deep neural networks (DNNs) have shown improved performance, addressing these drawbacks. Deep visual odometry typically employs convolutional neural networks (CNNs) and sequence modeling networks like recurrent neural networks (RNNs) to interpret scenes and deduce visual odometry from video sequences. This paper presents a novel real-time monocular visual odometry model for drones, using a deep neural architecture with a self-attention module. It estimates the ego-motion of a camera on a drone, using consecutive video frames. An inference utility processes the live video feed, employing deep learning to estimate the drone's trajectory. The architecture combines a CNN for image feature extraction and a long short-term memory (LSTM) network with a multi-head attention module for video sequence modeling. Tested on two visual odometry datasets, this model converged 48% faster than a previous RNN model and showed a 22% reduction in mean translational drift and a 12% improvement in mean translational absolute trajectory error, demonstrating enhanced robustness to noise.
Authors: Dang Nguyen, Paymon Haddad, Eric Gan, Baharan Mirzasoleiman
Abstract: Can we modify the training data distribution to encourage the underlying optimization method toward finding solutions with superior generalization performance on in-distribution data? In this work, we approach this question for the first time by comparing the inductive bias of gradient descent (GD) with that of sharpness-aware minimization (SAM). By studying a two-layer CNN, we prove that SAM learns easy and difficult features more uniformly, particularly in early epochs. That is, SAM is less susceptible to simplicity bias compared to GD. Based on this observation, we propose USEFUL, an algorithm that clusters examples based on the network output early in training and upsamples examples with no easy features to alleviate the pitfalls of the simplicity bias. We show empirically that modifying the training data distribution in this way effectively improves the generalization performance on the original data distribution when training with (S)GD by mimicking the training dynamics of SAM. Notably, we demonstrate that our method can be combined with SAM and existing data augmentation strategies to achieve, to the best of our knowledge, state-of-the-art performance for training ResNet18 on CIFAR10, STL10, CINIC10, Tiny-ImageNet; ResNet34 on CIFAR100; and VGG19 and DenseNet121 on CIFAR10.
Authors: Qiuyi Chen, Mark Fuge
Abstract: This paper introduces Least Volume-a simple yet effective regularization inspired by geometric intuition-that can reduce the necessary number of latent dimensions needed by an autoencoder without requiring any prior knowledge of the intrinsic dimensionality of the dataset. We show that the Lipschitz continuity of the decoder is the key to making it work, provide a proof that PCA is just a linear special case of it, and reveal that it has a similar PCA-like importance ordering effect when applied to nonlinear models. We demonstrate the intuition behind the regularization on some pedagogical toy problems, and its effectiveness on several benchmark problems, including MNIST, CIFAR-10 and CelebA.
Authors: Nannan Wu, Zhuo Kuang, Zengqiang Yan, Li Yu
Abstract: Due to escalating privacy concerns, federated learning has been recognized as a vital approach for training deep neural networks with decentralized medical data. In practice, it is challenging to ensure consistent imaging quality across various institutions, often attributed to equipment malfunctions affecting a minority of clients. This imbalance in image quality can cause the federated model to develop an inherent bias towards higher-quality images, thus posing a severe fairness issue. In this study, we pioneer the identification and formulation of this new fairness challenge within the context of the imaging quality shift. Traditional methods for promoting fairness in federated learning predominantly focus on balancing empirical risks across diverse client distributions. This strategy primarily facilitates fair optimization across different training data distributions, yet neglects the crucial aspect of generalization. To address this, we introduce a solution termed Federated learning with Inter-client Sharpness Matching (FedISM). FedISM enhances both local training and global aggregation by incorporating sharpness-awareness, aiming to harmonize the sharpness levels across clients for fair generalization. Our empirical evaluations, conducted using the widely-used ICH and ISIC 2019 datasets, establish FedISM's superiority over current state-of-the-art federated learning methods in promoting fairness. Code is available at https://github.com/wnn2000/FFL4MIA.
Authors: Haifeng Yang, Chuanxing Geng, PongChi Yuen, Songcan Chen
Abstract: In open-set recognition, existing methods generally learn statically fixed decision boundaries using known classes to reject unknown classes. Though they have achieved promising results, such decision boundaries are evidently insufficient for universal unknown classes in dynamic and open scenarios as they can potentially appear at any position in the feature space. Moreover, these methods just simply reject unknown class samples during testing without any effective utilization for them. In fact, such samples completely can constitute the true instantiated representation of the unknown classes to further enhance the model's performance. To address these issues, this paper proposes a novel dynamic against dynamic idea, i.e., dynamic method against dynamic changing open-set world, where an open-set self-learning (OSSL) framework is correspondingly developed. OSSL starts with a good closed-set classifier trained by known classes and utilizes available test samples for model adaptation during testing, thus gaining the adaptability to changing data distributions. In particular, a novel self-matching module is designed for OSSL, which can achieve the adaptation in automatically identifying known class samples while rejecting unknown class samples which are further utilized to enhance the discriminability of the model as the instantiated representation of unknown classes. Our method establishes new performance milestones respectively in almost all standard and cross-data benchmarks.
Authors: Lie Cai, Andre Pfob
Abstract: Background: Using artificial intelligence (AI) techniques for computational medical image analysis has shown promising results. However, colored images are often not readily available for AI analysis because of different coloring thresholds used across centers and physicians as well as the removal of clinical annotations. We aimed to develop an open-source tool that can adapt different color thresholds of HSV-colored medical images and remove annotations with a simple click. Materials and Methods: We built a function using MATLAB and used multi-center international shear wave elastography data (NCT 02638935) to test the function. We provide step-by-step instructions with accompanying code lines. Results: We demonstrate that the newly developed pre-processing function successfully removed letters and adapted different color thresholds of HSV-colored medical images. Conclusion: We developed an open-source tool for removing letters and adapting different color thresholds in HSV-colored medical images. We hope this contributes to advancing medical image processing for developing robust computational imaging algorithms using diverse multi-center big data. The open-source Matlab tool is available at https://github.com/cailiemed/image-threshold-adapting.
URLs: https://github.com/cailiemed/image-threshold-adapting.
Authors: Chenhe Du, Xiyue Lin, Qing Wu, Xuanyu Tian, Ying Su, Zhe Luo, Hongjiang Wei, S. Kevin Zhou, Jingyi Yu, Yuyao Zhang
Abstract: Limited-angle and sparse-view computed tomography (LACT and SVCT) are crucial for expanding the scope of X-ray CT applications. However, they face challenges due to incomplete data acquisition, resulting in diverse artifacts in the reconstructed CT images. Emerging implicit neural representation (INR) techniques, such as NeRF, NeAT, and NeRP, have shown promise in under-determined CT imaging reconstruction tasks. However, the unsupervised nature of INR architecture imposes limited constraints on the solution space, particularly for the highly ill-posed reconstruction task posed by LACT and ultra-SVCT. In this study, we introduce the Diffusion Prior Driven Neural Representation (DPER), an advanced unsupervised framework designed to address the exceptionally ill-posed CT reconstruction inverse problems. DPER adopts the Half Quadratic Splitting (HQS) algorithm to decompose the inverse problem into data fidelity and distribution prior sub-problems. The two sub-problems are respectively addressed by INR reconstruction scheme and pre-trained score-based diffusion model. This combination initially preserves the implicit image local consistency prior from INR. Additionally, it effectively augments the feasibility of the solution space for the inverse problem through the generative diffusion model, resulting in increased stability and precision in the solutions. We conduct comprehensive experiments to evaluate the performance of DPER on LACT and ultra-SVCT reconstruction with two public datasets (AAPM and LIDC). The results show that our method outperforms the state-of-the-art reconstruction methods on in-domain datasets, while achieving significant performance improvements on out-of-domain datasets.
Authors: Xiao Wang, Yuehang Li, Wentao Wu, Jiandong Jin, Yao Rong, Bo Jiang, Chuanfu Li, Jin Tang
Abstract: Existing X-ray based pre-trained vision models are usually conducted on a relatively small-scale dataset (less than 500k samples) with limited resolution (e.g., 224 $\times$ 224). However, the key to the success of self-supervised pre-training large models lies in massive training data, and maintaining high resolution in the field of X-ray images is the guarantee of effective solutions to difficult miscellaneous diseases. In this paper, we address these issues by proposing the first high-definition (1280 $\times$ 1280) X-ray based pre-trained foundation vision model on our newly collected large-scale dataset which contains more than 1 million X-ray images. Our model follows the masked auto-encoder framework which takes the tokens after mask processing (with a high rate) is used as input, and the masked image patches are reconstructed by the Transformer encoder-decoder network. More importantly, we introduce a novel context-aware masking strategy that utilizes the chest contour as a boundary for adaptive masking operations. We validate the effectiveness of our model on two downstream tasks, including X-ray report generation and disease recognition. Extensive experiments demonstrate that our pre-trained medical foundation vision model achieves comparable or even new state-of-the-art performance on downstream benchmark datasets. The source code and pre-trained models of this paper will be released on https://github.com/Event-AHU/Medical_Image_Analysis.
Authors: Toshitaka Hayashi, Dalibor Cimr, Hamido Fujita, Richard Cimler
Abstract: This paper offers a comprehensive review of one-class classification (OCC), examining the technologies and methodologies employed in its implementation. It delves into various approaches utilized for OCC across diverse data types, such as feature data, image, video, time series, and others. Through a systematic review, this paper synthesizes promi-nent strategies used in OCC from its inception to its current advance-ments, with a particular emphasis on the promising application. Moreo-ver, the article criticizes the state-of-the-art (SOTA) image anomaly de-tection (AD) algorithms dominating one-class experiments. These algo-rithms include outlier exposure (binary classification) and pretrained model (multi-class classification), conflicting with the fundamental con-cept of learning from one class. Our investigation reveals that the top nine algorithms for one-class CIFAR10 benchmark are not OCC. We ar-gue that binary/multi-class classification algorithms should not be com-pared with OCC.
Authors: Shaofan Liu, Junbo Chen, Jianke Zhu
Abstract: Incremental scene reconstruction is essential to the navigation in robotics. Most of the conventional methods typically make use of either TSDF (truncated signed distance functions) volume or neural networks to implicitly represent the surface. Due to the voxel representation or involving with time-consuming sampling, they have difficulty in balancing speed, memory storage, and surface quality. In this paper, we propose a novel hybrid voxel-octree approach to effectively fuse octree with voxel structures so that we can take advantage of both implicit surface and explicit triangular mesh representation. Such sparse structure preserves triangular faces in the leaf nodes and produces partial meshes sequentially for incremental reconstruction. This storage scheme allows us to naturally optimize the mesh in explicit 3D space to achieve higher surface quality. We iteratively deform the mesh towards the target and recovers vertex colors by optimizing a shading model. Experimental results on several datasets show that our proposed approach is capable of quickly and accurately reconstructing a scene with realistic colors.
Authors: Nikolaos Stathoulopoulos, Bj\"orn Lindqvist, Anton Koval, Ali-akbar Agha-mohammadi, George Nikolakopoulos
Abstract: In this article, a novel approach for merging 3D point cloud maps in the context of egocentric multi-robot exploration is presented. Unlike traditional methods, the proposed approach leverages state-of-the-art place recognition and learned descriptors to efficiently detect overlap between maps, eliminating the need for the time-consuming global feature extraction and feature matching process. The estimated overlapping regions are used to calculate a homogeneous rigid transform, which serves as an initial condition for the GICP point cloud registration algorithm to refine the alignment between the maps. The advantages of this approach include faster processing time, improved accuracy, and increased robustness in challenging environments. Furthermore, the effectiveness of the proposed framework is successfully demonstrated through multiple field missions of robot exploration in a variety of different underground environments.
Authors: Weijie Bao, Yuantong Zhang, Jianghao Jia, Zhenzhong Chen, Shan Liu
Abstract: This paper presents the joint reference frame synthesis (RFS) and post-processing filter enhancement (PFE) for Versatile Video Coding (VVC), aiming to explore the combination of different neural network-based video coding (NNVC) tools to better utilize the hierarchical bi-directional coding structure of VVC. Both RFS and PFE utilize the Space-Time Enhancement Network (STENet), which receives two input frames with artifacts and produces two enhanced frames with suppressed artifacts, along with an intermediate synthesized frame. STENet comprises two pipelines, the synthesis pipeline and the enhancement pipeline, tailored for different purposes. During RFS, two reconstructed frames are sent into STENet's synthesis pipeline to synthesize a virtual reference frame, similar to the current to-be-coded frame. The synthesized frame serves as an additional reference frame inserted into the reference picture list (RPL). During PFE, two reconstructed frames are fed into STENet's enhancement pipeline to alleviate their artifacts and distortions, resulting in enhanced frames with reduced artifacts and distortions. To reduce inference complexity, we propose joint inference of RFS and PFE (JISE), achieved through a single execution of STENet. Integrated into the VVC reference software VTM-15.0, RFS, PFE, and JISE are coordinated within a novel Space-Time Enhancement Window (STEW) under Random Access (RA) configuration. The proposed method could achieve -7.34%/-17.21%/-16.65% PSNR-based BD-rate on average for three components under RA configuration.
Authors: Sai Sukruth Bezugam, Yihao Wu, JaeBum Yoo, Dmitri Strukov, Bongjin Kim
Abstract: In this study, we propose the first hardware implementation of a context-based recurrent spiking neural network (RSNN) emphasizing on integrating dual information streams within the neocortical pyramidal neurons specifically Context- Dependent Leaky Integrate and Fire (CLIF) neuron models, essential element in RSNN. We present a quantized version of the CLIF neuron (qCLIF), developed through a hardware-software codesign approach utilizing the sparse activity of RSNN. Implemented in a 45nm technology node, the qCLIF is compact (900um^2) and achieves a high accuracy of 90% despite 8 bit quantization on DVS gesture classification dataset. Our analysis spans a network configuration from 10 to 200 qCLIF neurons, supporting up to 82k synapses within a 1.86 mm^2 footprint, demonstrating scalability and efficiency
Authors: Zhiwei Huang, Yikang Zhang, Qijun Chen, Rui Fan
Abstract: LiDAR-camera extrinsic calibration (LCEC) is crucial for data fusion in intelligent vehicles. Offline, target-based approaches have long been the preferred choice in this field. However, they often demonstrate poor adaptability to real-world environments. This is largely because extrinsic parameters may change significantly due to moderate shocks or during extended operations in environments with vibrations. In contrast, online, target-free approaches provide greater adaptability yet typically lack robustness, primarily due to the challenges in cross-modal feature matching. Therefore, in this article, we unleash the full potential of large vision models (LVMs), which are emerging as a significant trend in the fields of computer vision and robotics, especially for embodied artificial intelligence, to achieve robust and accurate online, target-free LCEC across a variety of challenging scenarios. Our main contributions are threefold: we introduce a novel framework known as MIAS-LCEC, provide an open-source versatile calibration toolbox with an interactive visualization interface, and publish three real-world datasets captured from various indoor and outdoor environments. The cornerstone of our framework and toolbox is the cross-modal mask matching (C3M) algorithm, developed based on a state-of-the-art (SoTA) LVM and capable of generating sufficient and reliable matches. Extensive experiments conducted on these real-world datasets demonstrate the robustness of our approach and its superior performance compared to SoTA methods, particularly for the solid-state LiDARs with super-wide fields of view.
Authors: Xinrun Chen, Mei Shen, Haojian Ning, Mengzhan Zhang, Chengliang Wang, Shiying Li
Abstract: Segmenting specific targets or structures in optical coherence tomography angiography (OCTA) images is fundamental for conducting further pathological studies. The retinal vascular layers are rich and intricate, and such vascular with complex shapes can be captured by the widely-studied OCTA images. In this paper, we thus study how to use OCTA images with projection vascular layers to segment retinal structures. To this end, we propose the SSW-OCTA model, which integrates the advantages of deformable convolutions suited for tubular structures and the swin-transformer for global feature extraction, adapting to the characteristics of OCTA modality images. Our model underwent testing and comparison on the OCTA-500 dataset, achieving state-of-the-art performance. The code is available at: https://github.com/ShellRedia/Snake-SWin-OCTA.
Authors: Prashant Bhat, Bharath Renjith, Elahe Arani, Bahram Zonooz
Abstract: Continual learning (CL) remains one of the long-standing challenges for deep neural networks due to catastrophic forgetting of previously acquired knowledge. Although rehearsal-based approaches have been fairly successful in mitigating catastrophic forgetting, they suffer from overfitting on buffered samples and prior information loss, hindering generalization under low-buffer regimes. Inspired by how humans learn using strong inductive biases, we propose IMEX-Reg to improve the generalization performance of experience rehearsal in CL under low buffer regimes. Specifically, we employ a two-pronged implicit-explicit regularization approach using contrastive representation learning (CRL) and consistency regularization. To further leverage the global relationship between representations learned using CRL, we propose a regularization strategy to guide the classifier toward the activation correlations in the unit hypersphere of the CRL. Our results show that IMEX-Reg significantly improves generalization performance and outperforms rehearsal-based approaches in several CL scenarios. It is also robust to natural and adversarial corruptions with less task-recency bias. Additionally, we provide theoretical insights to support our design decisions further.
Authors: Simon Raviv, Gal Chechik
Abstract: Perceptual image quality assessment (IQA) is the task of predicting the visual quality of an image as perceived by a human observer. Current state-of-the-art techniques are based on deep representations trained in discriminative manner. Such representations may ignore visually important features, if they are not predictive of class labels. Recent generative models successfully learn low-dimensional representations using auto-encoding and have been argued to preserve better visual features. Here we leverage existing auto-encoders and propose VAE-QA, a simple and efficient method for predicting image quality in the presence of a full-reference. We evaluate our approach on four standard benchmarks and find that it significantly improves generalization across datasets, has fewer trainable parameters, a smaller memory footprint and faster run time.
Authors: Sreetama Das, Filippo Caruso
Abstract: The Symmetric group $S_{n}$ manifests itself in large classes of quantum systems as the invariance of certain characteristics of a quantum state with respect to permuting the qubits. The subgroups of $S_{n}$ arise, among many other contexts, to describe label symmetry of classical images with respect to spatial transformations, e.g. reflection or rotation. Equipped with the formalism of geometric quantum machine learning, in this work we propose the architectures of equivariant quantum convolutional neural networks (EQCNNs) adherent to $S_{n}$ and its subgroups. We demonstrate that a careful choice of pixel-to-qubit embedding order can facilitate easy construction of EQCNNs for small subgroups of $S_{n}$. Our novel EQCNN architecture corresponding to the full permutation group $S_{n}$ is built by applying all possible QCNNs with equal probability, which can also be conceptualized as a dropout strategy in quantum neural networks. For subgroups of $S_{n}$, our numerical results using MNIST datasets show better classification accuracy than non-equivariant QCNNs. The $S_{n}$-equivariant QCNN architecture shows significantly improved training and test performance than non-equivariant QCNN for classification of connected and non-connected graphs. When trained with sufficiently large number of data, the $S_{n}$-equivariant QCNN shows better average performance compared to $S_{n}$-equivariant QNN . These results contribute towards building powerful quantum machine learning architectures in permutation-symmetric systems.
Authors: Haoxiao Wang, Bo Peng, Jianhua Zhang, Xu Cheng
Abstract: Time series classification is one of the most critical and challenging problems in data mining, existing widely in various fields and holding significant research importance. Despite extensive research and notable achievements with successful real-world applications, addressing the challenge of capturing the appropriate receptive field (RF) size from one-dimensional or multi-dimensional time series of varying lengths remains a persistent issue, which greatly impacts performance and varies considerably across different datasets. In this paper, we propose an Adaptive and Effective Full-Scope Convolutional Neural Network (AdaFSNet) to enhance the accuracy of time series classification. This network includes two Dense Blocks. Particularly, it can dynamically choose a range of kernel sizes that effectively encompass the optimal RF size for various datasets by incorporating multiple prime numbers corresponding to the time series length. We also design a TargetDrop block, which can reduce redundancy while extracting a more effective RF. To assess the effectiveness of the AdaFSNet network, comprehensive experiments were conducted using the UCR and UEA datasets, which include one-dimensional and multi-dimensional time series data, respectively. Our model surpassed baseline models in terms of classification accuracy, underscoring the AdaFSNet network's efficiency and effectiveness in handling time series classification tasks.
Authors: Chunyi Li, Haoning Wu, Hongkun Hao, Zicheng Zhang, Tengchaun Kou, Chaofeng Chen, Lei Bai, Xiaohong Liu, Weisi Lin, Guangtao Zhai
Abstract: With the evolution of Text-to-Image (T2I) models, the quality defects of AI-Generated Images (AIGIs) pose a significant barrier to their widespread adoption. In terms of both perception and alignment, existing models cannot always guarantee high-quality results. To mitigate this limitation, we introduce G-Refine, a general image quality refiner designed to enhance low-quality images without compromising the integrity of high-quality ones. The model is composed of three interconnected modules: a perception quality indicator, an alignment quality indicator, and a general quality enhancement module. Based on the mechanisms of the Human Visual System (HVS) and syntax trees, the first two indicators can respectively identify the perception and alignment deficiencies, and the last module can apply targeted quality enhancement accordingly. Extensive experimentation reveals that when compared to alternative optimization methods, AIGIs after G-Refine outperform in 10+ quality metrics across 4 databases. This improvement significantly contributes to the practical application of contemporary T2I models, paving the way for their broader adoption. The code will be released on https://github.com/Q-Future/Q-Refine.
Authors: David Hall, Stephen Hausler, Sutharsan Mahendren, Peyman Moghadam
Abstract: Neural fields provide a continuous scene representation of 3D geometry and appearance in a way which has great promise for robotics applications. One functionality that unlocks unique use-cases for neural fields in robotics is object 6-DoF registration. In this paper, we provide an expanded analysis of the recent Reg-NF neural field registration method and its use-cases within a robotics context. We showcase the scenario of determining the 6-DoF pose of known objects within a scene using scene and object neural field models. We show how this may be used to better represent objects within imperfectly modelled scenes and generate new scenes by substituting object neural field models into the scene.
Authors: Mingi Jeong, Arihant Chadda, Ziang Ren, Luyang Zhao, Haowen Liu, Monika Roznere, Aiwei Zhang, Yitao Jiang, Sabriel Achong, Samuel Lensgraf, Alberto Quattrini Li
Abstract: This paper introduces the first publicly accessible multi-modal perception dataset for autonomous maritime navigation, focusing on in-water obstacles within the aquatic environment to enhance situational awareness for Autonomous Surface Vehicles (ASVs). This dataset, consisting of diverse objects encountered under varying environmental conditions, aims to bridge the research gap in marine robotics by providing a multi-modal, annotated, and ego-centric perception dataset, for object detection and classification. We also show the applicability of the proposed dataset's framework using deep learning-based open-source perception algorithms that have shown success. We expect that our dataset will contribute to development of the marine autonomy pipeline and marine (field) robotics. Please note this is a work-in-progress paper about our on-going research that we plan to release in full via future publication.
Authors: Khaled Saab, Tao Tu, Wei-Hung Weng, Ryutaro Tanno, David Stutz, Ellery Wulczyn, Fan Zhang, Tim Strother, Chunjong Park, Elahe Vedadi, Juanma Zambrano Chaves, Szu-Yeu Hu, Mike Schaekermann, Aishwarya Kamath, Yong Cheng, David G. T. Barrett, Cathy Cheung, Basil Mustafa, Anil Palepu, Daniel McDuff, Le Hou, Tomer Golany, Luyang Liu, Jean-baptiste Alayrac, Neil Houlsby, Nenad Tomasev, Jan Freyberg, Charles Lau, Jonas Kemp, Jeremy Lai, Shekoofeh Azizi, Kimberly Kanada, SiWai Man, Kavita Kulkarni, Ruoxi Sun, Siamak Shakeri, Luheng He, Ben Caine, Albert Webson, Natasha Latysheva, Melvin Johnson, Philip Mansfield, Jian Lu, Ehud Rivlin, Jesper Anderson, Bradley Green, Renee Wong, Jonathan Krause, Jonathon Shlens, Ewa Dominowska, S. M. Ali Eslami, Claire Cui, Oriol Vinyals, Koray Kavukcuoglu, James Manyika, Jeff Dean, Demis Hassabis, Yossi Matias, Dale Webster, Joelle Barral, Greg Corrado, Christopher Semturs, S. Sara Mahdavi, Juraj Gottweis, Alan Karthikesalingam, Vivek Natarajan
Abstract: Excellence in a wide variety of medical applications poses considerable challenges for AI, requiring advanced reasoning, access to up-to-date medical knowledge and understanding of complex multimodal data. Gemini models, with strong general capabilities in multimodal and long-context reasoning, offer exciting possibilities in medicine. Building on these core strengths of Gemini, we introduce Med-Gemini, a family of highly capable multimodal models that are specialized in medicine with the ability to seamlessly use web search, and that can be efficiently tailored to novel modalities using custom encoders. We evaluate Med-Gemini on 14 medical benchmarks, establishing new state-of-the-art (SoTA) performance on 10 of them, and surpass the GPT-4 model family on every benchmark where a direct comparison is viable, often by a wide margin. On the popular MedQA (USMLE) benchmark, our best-performing Med-Gemini model achieves SoTA performance of 91.1% accuracy, using a novel uncertainty-guided search strategy. On 7 multimodal benchmarks including NEJM Image Challenges and MMMU (health & medicine), Med-Gemini improves over GPT-4V by an average relative margin of 44.5%. We demonstrate the effectiveness of Med-Gemini's long-context capabilities through SoTA performance on a needle-in-a-haystack retrieval task from long de-identified health records and medical video question answering, surpassing prior bespoke methods using only in-context learning. Finally, Med-Gemini's performance suggests real-world utility by surpassing human experts on tasks such as medical text summarization, alongside demonstrations of promising potential for multimodal medical dialogue, medical research and education. Taken together, our results offer compelling evidence for Med-Gemini's potential, although further rigorous evaluation will be crucial before real-world deployment in this safety-critical domain.
Authors: Luzhe Huang, Yuzhu Li, Nir Pillar, Tal Keidar Haran, William Dean Wallace, Aydogan Ozcan
Abstract: Histopathological staining of human tissue is essential in the diagnosis of various diseases. The recent advances in virtual tissue staining technologies using AI alleviate some of the costly and tedious steps involved in the traditional histochemical staining process, permitting multiplexed rapid staining of label-free tissue without using staining reagents, while also preserving tissue. However, potential hallucinations and artifacts in these virtually stained tissue images pose concerns, especially for the clinical utility of these approaches. Quality assessment of histology images is generally performed by human experts, which can be subjective and depends on the training level of the expert. Here, we present an autonomous quality and hallucination assessment method (termed AQuA), mainly designed for virtual tissue staining, while also being applicable to histochemical staining. AQuA achieves 99.8% accuracy when detecting acceptable and unacceptable virtually stained tissue images without access to ground truth, also presenting an agreement of 98.5% with the manual assessments made by board-certified pathologists. Besides, AQuA achieves super-human performance in identifying realistic-looking, virtually stained hallucinatory images that would normally mislead human diagnosticians by deceiving them into diagnosing patients that never existed. We further demonstrate the wide adaptability of AQuA across various virtually and histochemically stained tissue images and showcase its strong external generalization to detect unseen hallucination patterns of virtual staining network models as well as artifacts observed in the traditional histochemical staining workflow. This framework creates new opportunities to enhance the reliability of virtual staining and will provide quality assurance for various image generation and transformation tasks in digital pathology and computational imaging.
Authors: Martin Tschaikner, Danja Brandt, Henning Schmidt, Felix Bie{\ss}mann, Teodor Chiaburu, Ilona Schrimpf, Thomas Schrimpf, Alexandra Stadel, Frank Hau{\ss}er, Ingeborg Beckers
Abstract: Insect populations are declining globally, making systematic monitoring essential for conservation. Most classical methods involve death traps and counter insect conservation. This paper presents a multisensor approach that uses AI-based data fusion for insect classification. The system is designed as low-cost setup and consists of a camera module and an optical wing beat sensor as well as environmental sensors to measure temperature, irradiance or daytime as prior information. The system has been tested in the laboratory and in the field. First tests on a small very unbalanced data set with 7 species show promising results for species classification. The multisensor system will support biodiversity and agriculture studies.
Authors: Dingjie Song, Shunian Chen, Guiming Hardy Chen, Fei Yu, Xiang Wan, Benyou Wang
Abstract: Despite the advancements and impressive performance of Multimodal Large Language Models (MLLMs) on benchmarks, their effectiveness in real-world, long-context, and multi-image tasks is unclear due to the benchmarks' limited scope. Existing benchmarks often focus on single-image and short-text samples, and when assessing multi-image tasks, they either limit the image count or focus on specific task (e.g time-series captioning), potentially obscuring the performance challenges of MLLMs. To address these limitations, we introduce MileBench, a pioneering benchmark designed to test the MultImodal Long-contExt capabilities of MLLMs. This benchmark comprises not only multimodal long contexts, but also multiple tasks requiring both comprehension and generation. We establish two distinct evaluation sets, diagnostic and realistic, to systematically assess MLLMs' long-context adaptation capacity and their ability to complete tasks in long-context scenarios. Our experimental results, obtained from testing 20 models, revealed that while the closed-source GPT-4(Vision) and Gemini 1.5 outperform others, most open-source MLLMs struggle in long-context situations. Interestingly, the performance gap tends to widen with an increase in the number of images. We strongly encourage an intensification of research efforts towards enhancing MLLMs' long-context capabilities, especially in scenarios involving multiple images.
Authors: Debayan Bhattacharya, Finn Behrendt, Benjamin Tobias Becker, Lennart Maack, Dirk Beyersdorff, Elina Petersen, Marvin Petersen, Bastian Cheng, Dennis Eggert, Christian Betz, Anna Sophie Hoffmann, Alexander Schlaefer
Abstract: Purpose: Paranasal anomalies, frequently identified in routine radiological screenings, exhibit diverse morphological characteristics. Due to the diversity of anomalies, supervised learning methods require large labelled dataset exhibiting diverse anomaly morphology. Self-supervised learning (SSL) can be used to learn representations from unlabelled data. However, there are no SSL methods designed for the downstream task of classifying paranasal anomalies in the maxillary sinus (MS). Methods: Our approach uses a 3D Convolutional Autoencoder (CAE) trained in an unsupervised anomaly detection (UAD) framework. Initially, we train the 3D CAE to reduce reconstruction errors when reconstructing normal maxillary sinus (MS) image. Then, this CAE is applied to an unlabelled dataset to generate coarse anomaly locations by creating residual MS images. Following this, a 3D Convolutional Neural Network (CNN) reconstructs these residual images, which forms our SSL task. Lastly, we fine-tune the encoder part of the 3D CNN on a labelled dataset of normal and anomalous MS images. Results: The proposed SSL technique exhibits superior performance compared to existing generic self-supervised methods, especially in scenarios with limited annotated data. When trained on just 10% of the annotated dataset, our method achieves an Area Under the Precision-Recall Curve (AUPRC) of 0.79 for the downstream classification task. This performance surpasses other methods, with BYOL attaining an AUPRC of 0.75, SimSiam at 0.74, SimCLR at 0.73 and Masked Autoencoding using SparK at 0.75. Conclusion: A self-supervised learning approach that inherently focuses on localizing paranasal anomalies proves to be advantageous, particularly when the subsequent task involves differentiating normal from anomalous maxillary sinuses. Access our code at https://github.com/mtec-tuhh/self-supervised-paranasal-anomaly
URLs: https://github.com/mtec-tuhh/self-supervised-paranasal-anomaly
Authors: Letitia Parcalabescu, Anette Frank
Abstract: Vision and language models (VLMs) are currently the most generally performant architectures on multimodal tasks. Next to their predictions, they can also produce explanations, either in post-hoc or CoT settings. However, it is not clear how much they use the vision and text modalities when generating predictions or explanations. In this work, we investigate if VLMs rely on modalities differently when generating explanations as opposed to when they provide answers. We also evaluate the self-consistency of VLM decoders in both post-hoc and CoT explanation settings, by extending existing tests and measures to VLM decoders. We find that VLMs are less self-consistent than LLMs. The text contributions in VL decoders are much larger than the image contributions across all measured tasks. And the contributions of the image are significantly larger for explanation generations than for answer generation. This difference is even larger in CoT compared to the post-hoc explanation setting. We also provide an up-to-date benchmarking of state-of-the-art VL decoders on the VALSE benchmark, which to date focused only on VL encoders. We find that VL decoders are still struggling with most phenomena tested by VALSE.
Authors: Yifei Gao, Jie Ou, Lei Wang, Jun Cheng
Abstract: Recent developments in neural rendering techniques have greatly enhanced the rendering of photo-realistic 3D scenes across both academic and commercial fields. The latest method, known as 3D Gaussian Splatting (3D-GS), has set new benchmarks for rendering quality and speed. Nevertheless, the limitations of 3D-GS become pronounced in synthesizing new viewpoints, especially for views that greatly deviate from those seen during training. Additionally, issues such as dilation and aliasing arise when zooming in or out. These challenges can all be traced back to a single underlying issue: insufficient sampling. In our paper, we present a bootstrapping method that significantly addresses this problem. This approach employs a diffusion model to enhance the rendering of novel views using trained 3D-GS, thereby streamlining the training process. Our results indicate that bootstrapping effectively reduces artifacts, as well as clear enhancements on the evaluation metrics. Furthermore, we show that our method is versatile and can be easily integrated, allowing various 3D reconstruction projects to benefit from our approach.
Authors: Pascal Fernsel, \v{Z}eljko Kereta, Alexander Denker
Abstract: The incorporation of generative models as regularisers within variational formulations for inverse problems has proven effective across numerous image reconstruction tasks. However, the resulting optimisation problem is often non-convex and challenging to solve. In this work, we show that score-based generative models (SGMs) can be used in a graduated optimisation framework to solve inverse problems. We show that the resulting graduated non-convexity flow converge to stationary points of the original problem and provide a numerical convergence analysis of a 2D toy example. We further provide experiments on computed tomography image reconstruction, where we show that this framework is able to recover high-quality images, independent of the initial value. The experiments highlight the potential of using SGMs in graduated optimisation frameworks.
Authors: Hongyi Zhu, Jia-Hong Huang, Stevan Rudinac, Evangelos Kanoulas
Abstract: Image search stands as a pivotal task in multimedia and computer vision, finding applications across diverse domains, ranging from internet search to medical diagnostics. Conventional image search systems operate by accepting textual or visual queries, retrieving the top-relevant candidate results from the database. However, prevalent methods often rely on single-turn procedures, introducing potential inaccuracies and limited recall. These methods also face the challenges, such as vocabulary mismatch and the semantic gap, constraining their overall effectiveness. To address these issues, we propose an interactive image retrieval system capable of refining queries based on user relevance feedback in a multi-turn setting. This system incorporates a vision language model (VLM) based image captioner to enhance the quality of text-based queries, resulting in more informative queries with each iteration. Moreover, we introduce a large language model (LLM) based denoiser to refine text-based query expansions, mitigating inaccuracies in image descriptions generated by captioning models. To evaluate our system, we curate a new dataset by adapting the MSR-VTT video retrieval dataset to the image retrieval task, offering multiple relevant ground truth images for each query. Through comprehensive experiments, we validate the effectiveness of our proposed system against baseline methods, achieving state-of-the-art performance with a notable 10\% improvement in terms of recall. Our contributions encompass the development of an innovative interactive image retrieval system, the integration of an LLM-based denoiser, the curation of a meticulously designed evaluation dataset, and thorough experimental validation.
Authors: Zhiyuan Li, Yanhui Zhou, Hao Wei, Chenyang Ge, Jingwen Jiang
Abstract: Compressing images at extremely low bitrates (below 0.1 bits per pixel (bpp)) is a significant challenge due to substantial information loss. Existing extreme image compression methods generally suffer from heavy compression artifacts or low-fidelity reconstructions. To address this problem, we propose a novel extreme image compression framework that combines compressive VAEs and pre-trained text-to-image diffusion models in an end-to-end manner. Specifically, we introduce a latent feature-guided compression module based on compressive VAEs. This module compresses images and initially decodes the compressed information into content variables. To enhance the alignment between content variables and the diffusion space, we introduce external guidance to modulate intermediate feature maps. Subsequently, we develop a conditional diffusion decoding module that leverages pre-trained diffusion models to further decode these content variables. To preserve the generative capability of pre-trained diffusion models, we keep their parameters fixed and use a control module to inject content information. We also design a space alignment loss to provide sufficient constraints for the latent feature-guided compression module. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches in terms of both visual performance and image fidelity at extremely low bitrates.
Authors: Nicholas S. Kersting, Yi Li, Aman Mohanty, Oyindamola Obisesan, Raphael Okochu
Abstract: We introduce Harmonic Robustness, a powerful and intuitive method to test the robustness of any machine-learning model either during training or in black-box real-time inference monitoring without ground-truth labels. It is based on functional deviation from the harmonic mean value property, indicating instability and lack of explainability. We show implementation examples in low-dimensional trees and feedforward NNs, where the method reliably identifies overfitting, as well as in more complex high-dimensional models such as ResNet-50 and Vision Transformer where it efficiently measures adversarial vulnerability across image classes.
Authors: Skand Peri, Iain Lee, Chanho Kim, Li Fuxin, Tucker Hermans, Stefan Lee
Abstract: Visual control policies can encounter significant performance degradation when visual conditions like lighting or camera position differ from those seen during training -- often exhibiting sharp declines in capability even for minor differences. In this work, we examine robustness to a suite of these types of visual changes for RGB-D and point cloud based visual control policies. To perform these experiments on both model-free and model-based reinforcement learners, we introduce a novel Point Cloud World Model (PCWM) and point cloud based control policies. Our experiments show that policies that explicitly encode point clouds are significantly more robust than their RGB-D counterparts. Further, we find our proposed PCWM significantly outperforms prior works in terms of sample efficiency during training. Taken together, these results suggest reasoning about the 3D scene through point clouds can improve performance, reduce learning time, and increase robustness for robotic learners. Project Webpage: https://pvskand.github.io/projects/PCWM
Authors: Kang Liao, Chunyu Lin, Yao Zhao
Abstract: Distortion is widely existed in the images captured by popular wide-angle cameras and fisheye cameras. Despite the long history of distortion rectification, accurately estimating the distortion parameters from a single distorted image is still challenging. The main reason is these parameters are implicit to image features, influencing the networks to fully learn the distortion information. In this work, we propose a novel distortion rectification approach that can obtain more accurate parameters with higher efficiency. Our key insight is that distortion rectification can be cast as a problem of learning an ordinal distortion from a single distorted image. To solve this problem, we design a local-global associated estimation network that learns the ordinal distortion to approximate the realistic distortion distribution. In contrast to the implicit distortion parameters, the proposed ordinal distortion have more explicit relationship with image features, and thus significantly boosts the distortion perception of neural networks. Considering the redundancy of distortion information, our approach only uses a part of distorted image for the ordinal distortion estimation, showing promising applications in the efficient distortion rectification. To our knowledge, we first unify the heterogeneous distortion parameters into a learning-friendly intermediate representation through ordinal distortion, bridging the gap between image feature and distortion rectification. The experimental results demonstrate that our approach outperforms the state-of-the-art methods by a significant margin, with approximately 23% improvement on the quantitative evaluation while displaying the best performance on visual appearance. The code is available at https://github.com/KangLiao929/OrdinalDistortion.
Authors: Lei Qi, Hongpeng Yang, Yinghuan Shi, Xin Geng
Abstract: Domain generalization (DG) aims at learning a model on source domains to well generalize on the unseen target domain. Although it has achieved great success, most of existing methods require the label information for all training samples in source domains, which is time-consuming and expensive in the real-world application. In this paper, we resort to solving the semi-supervised domain generalization (SSDG) task, where there are a few label information in each source domain. To address the task, we first analyze the theory of the multi-domain learning, which highlights that 1) mitigating the impact of domain gap and 2) exploiting all samples to train the model can effectively reduce the generalization error in each source domain so as to improve the quality of pseudo-labels. According to the analysis, we propose MultiMatch, i.e., extending FixMatch to the multi-task learning framework, producing the high-quality pseudo-label for SSDG. To be specific, we consider each training domain as a single task (i.e., local task) and combine all training domains together (i.e., global task) to train an extra task for the unseen test domain. In the multi-task framework, we utilize the independent BN and classifier for each task, which can effectively alleviate the interference from different domains during pseudo-labeling. Also, most of parameters in the framework are shared, which can be trained by all training samples sufficiently. Moreover, to further boost the pseudo-label accuracy and the model's generalization, we fuse the predictions from the global task and local task during training and testing, respectively. A series of experiments validate the effectiveness of the proposed method, and it outperforms the existing semi-supervised methods and the SSDG method on several benchmark DG datasets.
Authors: Zekun Qian, Ruize Han, Wei Feng, Feifan Wang, Song Wang
Abstract: We tackle a new problem of multi-view camera and subject registration in the bird's eye view (BEV) without pre-given camera calibration. This is a very challenging problem since its only input is several RGB images from different first-person views (FPVs) for a multi-person scene, without the BEV image and the calibration of the FPVs, while the output is a unified plane with the localization and orientation of both the subjects and cameras in a BEV. We propose an end-to-end framework solving this problem, whose main idea can be divided into following parts: i) creating a view-transform subject detection module to transform the FPV to a virtual BEV including localization and orientation of each pedestrian, ii) deriving a geometric transformation based method to estimate camera localization and view direction, i.e., the camera registration in a unified BEV, iii) making use of spatial and appearance information to aggregate the subjects into the unified BEV. We collect a new large-scale synthetic dataset with rich annotations for evaluation. The experimental results show the remarkable effectiveness of our proposed method.
Authors: Kunyu Peng, David Schneider, Alina Roitberg, Kailun Yang, Jiaming Zhang, Chen Deng, Kaiyu Zhang, M. Saquib Sarfraz, Rainer Stiefelhagen
Abstract: In this paper, we tackle the new task of video-based Activated Muscle Group Estimation (AMGE) aiming at identifying active muscle regions during physical activity in the wild. To this intent, we provide the MuscleMap dataset featuring >15K video clips with 135 different activities and 20 labeled muscle groups. This dataset opens the vistas to multiple video-based applications in sports and rehabilitation medicine under flexible environment constraints. The proposed MuscleMap dataset is constructed with YouTube videos, specifically targeting High-Intensity Interval Training (HIIT) physical exercise in the wild. To make the AMGE model applicable in real-life situations, it is crucial to ensure that the model can generalize well to numerous types of physical activities not present during training and involving new combinations of activated muscles. To achieve this, our benchmark also covers an evaluation setting where the model is exposed to activity types excluded from the training set. Our experiments reveal that the generalizability of existing architectures adapted for the AMGE task remains a challenge. Therefore, we also propose a new approach, TransM3E, which employs a multi-modality feature fusion mechanism between both the video transformer model and the skeleton-based graph convolution model with novel cross-modal knowledge distillation executed on multi-classification tokens. The proposed method surpasses all popular video classification models when dealing with both, previously seen and new types of physical activities. The contributed dataset and code will be publicly available at https://github.com/KPeng9510/MuscleMap.
Authors: Marwa Dhiaf, Mohamed Ali Souibgui, Kai Wang, Yuyang Liu, Yousri Kessentini, Alicia Forn\'es, Ahmed Cheikh Rouhou
Abstract: Self-supervised learning has recently emerged as a strong alternative in document analysis. These approaches are now capable of learning high-quality image representations and overcoming the limitations of supervised methods, which require a large amount of labeled data. However, these methods are unable to capture new knowledge in an incremental fashion, where data is presented to the model sequentially, which is closer to the realistic scenario. In this paper, we explore the potential of continual self-supervised learning to alleviate the catastrophic forgetting problem in handwritten text recognition, as an example of sequence recognition. Our method consists in adding intermediate layers called adapters for each task, and efficiently distilling knowledge from the previous model while learning the current task. Our proposed framework is efficient in both computation and memory complexity. To demonstrate its effectiveness, we evaluate our method by transferring the learned model to diverse text recognition downstream tasks, including Latin and non-Latin scripts. As far as we know, this is the first application of continual self-supervised learning for handwritten text recognition. We attain state-of-the-art performance on English, Italian and Russian scripts, whilst adding only a few parameters per task. The code and trained models will be publicly available.
Authors: Siming Yan, Yuqi Yang, Yuxiao Guo, Hao Pan, Peng-shuai Wang, Xin Tong, Yang Liu, Qixing Huang
Abstract: Masked autoencoders (MAE) have recently been introduced to 3D self-supervised pretraining for point clouds due to their great success in NLP and computer vision. Unlike MAEs used in the image domain, where the pretext task is to restore features at the masked pixels, such as colors, the existing 3D MAE works reconstruct the missing geometry only, i.e, the location of the masked points. In contrast to previous studies, we advocate that point location recovery is inessential and restoring intrinsic point features is much superior. To this end, we propose to ignore point position reconstruction and recover high-order features at masked points including surface normals and surface variations, through a novel attention-based decoder which is independent of the encoder design. We validate the effectiveness of our pretext task and decoder design using different encoder structures for 3D training and demonstrate the advantages of our pretrained networks on various point cloud analysis tasks.
Authors: Yingyan Li, Lue Fan, Yang Liu, Zehao Huang, Yuntao Chen, Naiyan Wang, Zhaoxiang Zhang
Abstract: Currently prevalent multimodal 3D detection methods are built upon LiDAR-based detectors that usually use dense Bird's-Eye-View (BEV) feature maps. However, the cost of such BEV feature maps is quadratic to the detection range, making it not suitable for long-range detection. Fully sparse architecture is gaining attention as they are highly efficient in long-range perception. In this paper, we study how to effectively leverage image modality in the emerging fully sparse architecture. Particularly, utilizing instance queries, our framework integrates the well-studied 2D instance segmentation into the LiDAR side, which is parallel to the 3D instance segmentation part in the fully sparse detector. This design achieves a uniform query-based fusion framework in both the 2D and 3D sides while maintaining the fully sparse characteristic. Extensive experiments showcase state-of-the-art results on the widely used nuScenes dataset and the long-range Argoverse 2 dataset. Notably, the inference speed of the proposed method under the long-range LiDAR perception setting is 2.7 $\times$ faster than that of other state-of-the-art multimodal 3D detection methods. Code will be released at \url{https://github.com/BraveGroup/FullySparseFusion}.
Authors: Kunyu Peng, Di Wen, David Schneider, Jiaming Zhang, Kailun Yang, M. Saquib Sarfraz, Rainer Stiefelhagen, Alina Roitberg
Abstract: Domain adaptation is essential for activity recognition to ensure accurate and robust performance across diverse environments, sensor types, and data sources. Unsupervised domain adaptation methods have been extensively studied, yet, they require large-scale unlabeled data from the target domain. In this work, we focus on Few-Shot Domain Adaptation for Activity Recognition (FSDA-AR), which leverages a very small amount of labeled target videos to achieve effective adaptation. This approach is appealing for applications because it only needs a few or even one labeled example per class in the target domain, ideal for recognizing rare but critical activities. However, the existing FSDA-AR works mostly focus on the domain adaptation on sports videos, where the domain diversity is limited. We propose a new FSDA-AR benchmark using five established datasets considering the adaptation on more diverse and challenging domains. Our results demonstrate that FSDA-AR performs comparably to unsupervised domain adaptation with significantly fewer labeled target domain samples. We further propose a novel approach, RelaMiX, to better leverage the few labeled target domain samples as knowledge guidance. RelaMiX encompasses a temporal relational attention network with relation dropout, alongside a cross-domain information alignment mechanism. Furthermore, it integrates a mechanism for mixing features within a latent space by using the few-shot target domain samples. The proposed RelaMiX solution achieves state-of-the-art performance on all datasets within the FSDA-AR benchmark. To encourage future research of few-shot domain adaptation for activity recognition, our code will be publicly available at https://github.com/KPeng9510/RelaMiX.
Authors: Chen Min, Liang Xiao, Dawei Zhao, Yiming Nie, Bin Dai
Abstract: Multi-camera 3D perception has emerged as a prominent research field in autonomous driving, offering a viable and cost-effective alternative to LiDAR-based solutions. The existing multi-camera algorithms primarily rely on monocular 2D pre-training. However, the monocular 2D pre-training overlooks the spatial and temporal correlations among the multi-camera system. To address this limitation, we propose the first multi-camera unified pre-training framework, called UniScene, which involves initially reconstructing the 3D scene as the foundational stage and subsequently fine-tuning the model on downstream tasks. Specifically, we employ Occupancy as the general representation for the 3D scene, enabling the model to grasp geometric priors of the surrounding world through pre-training. A significant benefit of UniScene is its capability to utilize a considerable volume of unlabeled image-LiDAR pairs for pre-training purposes. The proposed multi-camera unified pre-training framework demonstrates promising results in key tasks such as multi-camera 3D object detection and surrounding semantic scene completion. When compared to monocular pre-training methods on the nuScenes dataset, UniScene shows a significant improvement of about 2.0% in mAP and 2.0% in NDS for multi-camera 3D object detection, as well as a 3% increase in mIoU for surrounding semantic scene completion. By adopting our unified pre-training method, a 25% reduction in 3D training annotation costs can be achieved, offering significant practical value for the implementation of real-world autonomous driving. Codes are publicly available at https://github.com/chaytonmin/UniScene.
Authors: Quoc-Huy Tran, Muhammad Ahmed, Murad Popattia, M. Hassan Ahmed, Andrey Konin, M. Zeeshan Zia
Abstract: This paper presents a self-supervised temporal video alignment framework which is useful for several fine-grained human activity understanding applications. In contrast with the state-of-the-art method of CASA, where sequences of 3D skeleton coordinates are taken directly as input, our key idea is to use sequences of 2D skeleton heatmaps as input. Unlike CASA which performs self-attention in the temporal domain only, we feed 2D skeleton heatmaps to a video transformer which performs self-attention both in the spatial and temporal domains for extracting effective spatiotemporal and contextual features. In addition, we introduce simple heatmap augmentation techniques based on 2D skeletons for self-supervised learning. Despite the lack of 3D information, our approach achieves not only higher accuracy but also better robustness against missing and noisy keypoints than CASA. Furthermore, extensive evaluations on three public datasets, i.e., Penn Action, IKEA ASM, and H2O, demonstrate that our approach outperforms previous methods in different fine-grained human activity understanding tasks. Finally, fusing 2D skeleton heatmaps with RGB videos yields the state-of-the-art on all metrics and datasets. To our best knowledge, our work is the first to utilize 2D skeleton heatmap inputs and the first to explore multi-modality fusion for temporal video alignment.
Authors: Siming Yan, Chen Song, Youkang Kong, Qixing Huang
Abstract: A promising direction for pre-training 3D point clouds is to leverage the massive amount of data in 2D, whereas the domain gap between 2D and 3D creates a fundamental challenge. This paper proposes a novel approach to point-cloud pre-training that learns 3D representations by leveraging pre-trained 2D networks. Different from the popular practice of predicting 2D features first and then obtaining 3D features through dimensionality lifting, our approach directly uses a 3D network for feature extraction. We train the 3D feature extraction network with the help of the novel 2D knowledge transfer loss, which enforces the 2D projections of the 3D feature to be consistent with the output of pre-trained 2D networks. To prevent the feature from discarding 3D signals, we introduce the multi-view consistency loss that additionally encourages the projected 2D feature representations to capture pixel-wise correspondences across different views. Such correspondences induce 3D geometry and effectively retain 3D features in the projected 2D features. Experimental results demonstrate that our pre-trained model can be successfully transferred to various downstream tasks, including 3D shape classification, part segmentation, 3D object detection, and semantic segmentation, achieving state-of-the-art performance.
Authors: Madeline Chantry Schiappa, Shehreen Azad, Sachidanand VS, Yunhao Ge, Ondrej Miksik, Yogesh S. Rawat, Vibhav Vineet
Abstract: Due to the increase in computational resources and accessibility of data, an increase in large, deep learning models trained on copious amounts of multi-modal data using self-supervised or semi-supervised learning have emerged. These ``foundation'' models are often adapted to a variety of downstream tasks like classification, object detection, and segmentation with little-to-no training on the target dataset. In this work, we perform a robustness analysis of Visual Foundation Models (VFMs) for segmentation tasks and focus on robustness against real-world distribution shift inspired perturbations. We benchmark seven state-of-the-art segmentation architectures using 2 different perturbed datasets, MS COCO-P and ADE20K-P, with 17 different perturbations with 5 severity levels each. Our findings reveal several key insights: (1) VFMs exhibit vulnerabilities to compression-induced corruptions, (2) despite not outpacing all of unimodal models in robustness, multimodal models show competitive resilience in zero-shot scenarios, and (3) VFMs demonstrate enhanced robustness for certain object categories. These observations suggest that our robustness evaluation framework sets new requirements for foundational models, encouraging further advancements to bolster their adaptability and performance. The code and dataset is available at: \url{https://tinyurl.com/fm-robust}.
Authors: Lei Qi, Ziang Liu, Yinghuan Shi, Xin Geng
Abstract: Person Re-identification (Re-ID) is a crucial technique for public security and has made significant progress in supervised settings. However, the cross-domain (i.e., domain generalization) scene presents a challenge in Re-ID tasks due to unseen test domains and domain-shift between the training and test sets. To tackle this challenge, most existing methods aim to learn domain-invariant or robust features for all domains. In this paper, we observe that the data-distribution gap between the training and test sets is smaller in the sample-pair space than in the sample-instance space. Based on this observation, we propose a Generalizable Metric Network (GMN) to further explore sample similarity in the sample-pair space. Specifically, we add a Metric Network (M-Net) after the main network and train it on positive and negative sample-pair features, which is then employed during the test stage. Additionally, we introduce the Dropout-based Perturbation (DP) module to enhance the generalization capability of the metric network by enriching the sample-pair diversity. Moreover, we develop a Pair-Identity Center (PIC) loss to enhance the model's discrimination by ensuring that sample-pair features with the same pair-identity are consistent. We validate the effectiveness of our proposed method through a lot of experiments on multiple benchmark datasets and confirm the value of each module in our GMN.
Authors: Lars Schmarje, Vasco Grossmann, Claudius Zelenka, Johannes Br\"unger, Reinhard Koch
Abstract: In the field of image classification, existing methods often struggle with biased or ambiguous data, a prevalent issue in real-world scenarios. Current strategies, including semi-supervised learning and class blending, offer partial solutions but lack a definitive resolution. Addressing this gap, our paper introduces a novel strategy for generating high-quality labels in challenging datasets. Central to our approach is a clearly designed flowchart, based on a broad literature review, which enables the creation of reliable labels. We validate our methodology through a rigorous real-world test case in the biomedical field, specifically in deducing height reduction from vertebral imaging. Our empirical study, leveraging over 250,000 annotations, demonstrates the effectiveness of our strategies decisions compared to their alternatives.
Authors: Yuan Liu, Haodong Duan, Yuanhan Zhang, Bo Li, Songyang Zhang, Wangbo Zhao, Yike Yuan, Jiaqi Wang, Conghui He, Ziwei Liu, Kai Chen, Dahua Lin
Abstract: Large vision-language models have recently achieved remarkable progress, exhibiting great perception and reasoning abilities concerning visual information. However, how to effectively evaluate these large vision-language models remains a major obstacle, hindering future model development. Traditional benchmarks like VQAv2 or COCO Caption provide quantitative performance measurements but suffer from a lack of fine-grained ability assessment and non-robust evaluation metrics. Recent subjective benchmarks, such as OwlEval, offer comprehensive evaluations of a model's abilities by incorporating human labor, but they are not scalable and display significant bias. In response to these challenges, we propose MMBench, a novel multi-modality benchmark. MMBench methodically develops a comprehensive evaluation pipeline, primarily comprised of two elements. The first element is a meticulously curated dataset that surpasses existing similar benchmarks in terms of the number and variety of evaluation questions and abilities. The second element introduces a novel CircularEval strategy and incorporates the use of ChatGPT. This implementation is designed to convert free-form predictions into pre-defined choices, thereby facilitating a more robust evaluation of the model's predictions. MMBench is a systematically-designed objective benchmark for robustly evaluating the various abilities of vision-language models. We hope MMBench will assist the research community in better evaluating their models and encourage future advancements in this domain. Project page: https://opencompass.org.cn/mmbench.
Authors: Hao Qi, Xinghui Dong
Abstract: Underwater images normally suffer from degradation due to the transmission medium of water bodies. Both traditional prior-based approaches and deep learning-based methods have been used to address this problem. However, the inflexible assumption of the former often impairs their effectiveness in handling diverse underwater scenes, while the generalization of the latter to unseen images is usually weakened by insufficient data. In this study, we leverage both the physics-based underwater Image Formation Model (IFM) and deep learning techniques for Underwater Image Enhancement (UIE). To this end, we propose a novel Physics-Aware Dual-Stream Underwater Image Enhancement Network, i.e., PA-UIENet, which comprises a Transmission Estimation Steam (T-Stream) and an Ambient Light Estimation Stream (A-Stream). This network fulfills the UIE task by explicitly estimating the degradation parameters of the IFM. We also adopt an IFM-inspired semi-supervised learning framework, which exploits both the labeled and unlabeled images, to address the issue of insufficient data. Our method performs better than, or at least comparably to, eight baselines across five testing sets in the degradation estimation and UIE tasks. This should be due to the fact that it not only can model the degradation but also can learn the characteristics of diverse underwater scenes.
Authors: Jiucui Lu, Jiaran Zhou, Junyu Dong, Bin Li, Siwei Lyu, Yuezun Li
Abstract: The prominent progress in generative models has significantly improved the reality of generated faces, bringing serious concerns to society. Since recent GAN-generated faces are in high realism, the forgery traces have become more imperceptible, increasing the forensics challenge. To combat GAN-generated faces, many countermeasures based on Convolutional Neural Networks (CNNs) have been spawned due to their strong learning ability. In this paper, we rethink this problem and explore a new approach based on forest models instead of CNNs. Specifically, we describe a simple and effective forest-based method set called {\em ForensicsForest Family} to detect GAN-generate faces. The proposed ForensicsForest family is composed of three variants, which are {\em ForensicsForest}, {\em Hybrid ForensicsForest} and {\em Divide-and-Conquer ForensicsForest} respectively. ForenscisForest is a newly proposed Multi-scale Hierarchical Cascade Forest, which takes semantic, frequency and biology features as input, hierarchically cascades different levels of features for authenticity prediction, and then employs a multi-scale ensemble scheme that can comprehensively consider different levels of information to improve the performance further. Based on ForensicsForest, we develop Hybrid ForensicsForest, an extended version that integrates the CNN layers into models, to further refine the effectiveness of augmented features. Moreover, to reduce the memory cost in training, we propose Divide-and-Conquer ForensicsForest, which can construct a forest model using only a portion of training samplings. In the training stage, we train several candidate forest models using the subsets of training samples. Then a ForensicsForest is assembled by picking the suitable components from these candidate forest models...
Authors: Gaspard Goupy, Pierre Tirilly, Ioan Marius Bilasco
Abstract: Direct training of Spiking Neural Networks (SNNs) on neuromorphic hardware has the potential to significantly reduce the energy consumption of artificial neural network training. SNNs trained with Spike Timing-Dependent Plasticity (STDP) benefit from gradient-free and unsupervised local learning, which can be easily implemented on ultra-low-power neuromorphic hardware. However, classification tasks cannot be performed solely with unsupervised STDP. In this paper, we propose Stabilized Supervised STDP (S2-STDP), a supervised STDP learning rule to train the classification layer of an SNN equipped with unsupervised STDP for feature extraction. S2-STDP integrates error-modulated weight updates that align neuron spikes with desired timestamps derived from the average firing time within the layer. Then, we introduce a training architecture called Paired Competing Neurons (PCN) to further enhance the learning capabilities of our classification layer trained with S2-STDP. PCN associates each class with paired neurons and encourages neuron specialization toward target or non-target samples through intra-class competition. We evaluate our methods on image recognition datasets, including MNIST, Fashion-MNIST, and CIFAR-10. Results show that our methods outperform state-of-the-art supervised STDP learning rules, for comparable architectures and numbers of neurons. Further analysis demonstrates that the use of PCN enhances the performance of S2-STDP, regardless of the hyperparameter set and without introducing any additional hyperparameters.
Authors: Changkun Liu, Yukun Zhao, Tristan Braud
Abstract: Markerless Mobile Augmented Reality (AR) aims to anchor digital content in the physical world without using specific 2D or 3D objects. Absolute Pose Regressors (APR) are end-to-end machine learning solutions that infer the device's pose from a single monocular image. Thanks to their low computation cost, they can be directly executed on the constrained hardware of mobile AR devices. However, APR methods tend to yield significant inaccuracies for input images that are too distant from the training set. This paper introduces KS-APR, a pipeline that assesses the reliability of an estimated pose with minimal overhead by combining the inference results of the APR and the prior images in the training set. Mobile AR systems tend to rely upon visual-inertial odometry to track the relative pose of the device during the experience. As such, KS-APR favours reliability over frequency, discarding unreliable poses. This pipeline can integrate most existing APR methods to improve accuracy by filtering unreliable images with their pose estimates. We implement the pipeline on three types of APR models on indoor and outdoor datasets. The median error on position and orientation is reduced for all models, and the proportion of large errors is minimized across datasets. Our method enables state-of-the-art APRs such as DFNetdm to outperform single-image and sequential APR methods. These results demonstrate the scalability and effectiveness of KS-APR for visual localization tasks that do not require one-shot decisions.
Authors: Nazmus Sakib Ahmed, Saad Sakib Noor, Ashraful Islam Shanto Sikder, Abhijit Paul
Abstract: This paper focuses on enhancing Bengali Document Layout Analysis (DLA) using the YOLOv8 model and innovative post-processing techniques. We tackle challenges unique to the complex Bengali script by employing data augmentation for model robustness. After meticulous validation set evaluation, we fine-tune our approach on the complete dataset, leading to a two-stage prediction strategy for accurate element segmentation. Our ensemble model, combined with post-processing, outperforms individual base architectures, addressing issues identified in the BaDLAD dataset. By leveraging this approach, we aim to advance Bengali document analysis, contributing to improved OCR and document comprehension and BaDLAD serves as a foundational resource for this endeavor, aiding future research in the field. Furthermore, our experiments provided key insights to incorporate new strategies into the established solution.
Authors: Henry Hengyuan Zhao, Pichao Wang, Yuyang Zhao, Hao Luo, Fan Wang, Mike Zheng Shou
Abstract: Pre-trained vision transformers have strong representation benefits to various downstream tasks. Recently, many parameter-efficient fine-tuning (PEFT) methods have been proposed, and their experiments demonstrate that tuning only 1\% extra parameters could surpass full fine-tuning in low-data resource scenarios. However, these methods overlook the task-specific information when fine-tuning diverse downstream tasks. In this paper, we propose a simple yet effective method called "Salient Channel Tuning" (SCT) to leverage the task-specific information by forwarding the model with the task images to select partial channels in a feature map that enables us to tune only 1/8 channels leading to significantly lower parameter costs. Experiments on 19 visual transfer learning downstream tasks demonstrate that our SCT outperforms full fine-tuning on 18 out of 19 tasks by adding only 0.11M parameters of the ViT-B, which is 780$\times$ fewer than its full fine-tuning counterpart. Furthermore, experiments on domain generalization and few-shot classification further demonstrate the effectiveness and generic of our approach. The code is available at https://github.com/showlab/SCT.
Authors: Zhongyang Zhang, Shuyang Cui, Kaidong Chai, Haowen Yu, Subhasis Dasgupta, Upal Mahbub, Tauhidur Rahman
Abstract: Dynamic Vision Sensor (DVS)-based solutions have recently garnered significant interest across various computer vision tasks, offering notable benefits in terms of dynamic range, temporal resolution, and inference speed. However, as a relatively nascent vision sensor compared to Active Pixel Sensor (APS) devices such as RGB cameras, DVS suffers from a dearth of ample labeled datasets. Prior efforts to convert APS data into events often grapple with issues such as a considerable domain shift from real events, the absence of quantified validation, and layering problems within the time axis. In this paper, we present a novel method for video-to-events stream conversion from multiple perspectives, considering the specific characteristics of DVS. A series of carefully designed losses helps enhance the quality of generated event voxels significantly. We also propose a novel local dynamic-aware timestamp inference strategy to accurately recover event timestamps from event voxels in a continuous fashion and eliminate the temporal layering problem. Results from rigorous validation through quantified metrics at all stages of the pipeline establish our method unquestionably as the current state-of-the-art (SOTA).
Authors: Nadja Gruber, Johannes Schwab, No\'emie Debroux, Nicolas Papadakis, Markus Haltmeier
Abstract: We develop Self2Seg, a self-supervised method for the joint segmentation and denoising of a single image. To this end, we combine the advantages of variational segmentation with self-supervised deep learning. One major benefit of our method lies in the fact, that in contrast to data-driven methods, where huge amounts of labeled samples are necessary, Self2Seg segments an image into meaningful regions without any training database. Moreover, we demonstrate that self-supervised denoising itself is significantly improved through the region-specific learning of Self2Seg. Therefore, we introduce a novel self-supervised energy functional in which denoising and segmentation are coupled in a way that both tasks benefit from each other. We propose a unified optimisation strategy and numerically show that for noisy microscopy images our proposed joint approach outperforms its sequential counterpart as well as alternative methods focused purely on denoising or segmentation.
Authors: Yun Zhang, Wei Li, Simiao Li, Hanting Chen, Zhijun Tu, Wenjia Wang, Bingyi Jing, Shaohui Lin, Jie Hu
Abstract: Knowledge distillation (KD) compresses deep neural networks by transferring task-related knowledge from cumbersome pre-trained teacher models to compact student models. However, current KD methods for super-resolution (SR) networks overlook the nature of SR task that the outputs of the teacher model are noisy approximations to the ground-truth distribution of high-quality images (GT), which shades the teacher model's knowledge to result in limited KD effects. To utilize the teacher model beyond the GT upper-bound, we present the Data Upcycling Knowledge Distillation (DUKD), to transfer the teacher model's knowledge to the student model through the upcycled in-domain data derived from training data. Besides, we impose label consistency regularization to KD for SR by the paired invertible augmentations to improve the student model's performance and robustness. Comprehensive experiments demonstrate that the DUKD method significantly outperforms previous arts on several SR tasks.
Authors: Ji Qi, Kaixuan Ji, Jifan Yu, Duokang Wang, Bin Xu, Lei Hou, Juanzi Li
Abstract: Building models that comprehends videos and responds specific user instructions is a practical and challenging topic, as it requires mastery of both vision understanding and knowledge reasoning. Compared to language and image modalities, training efficiency remains a serious problem as existing studies train models on massive sparse videos paired with brief descriptions. In this paper, we introduce \textbf{VidCoM}, a fast adaptive framework that leverages Large Language Models (LLMs) to reason about videos using lightweight visual tools. Specifically, we reveal that the key to responding to specific instructions is focusing on relevant video events, and utilize two visual tools, structured scene graph generation and descriptive image caption generation, to gather and represent the event information. Thus, a LLM enriched with world knowledge is adopted as the reasoning agent to achieve the responses by performing multiple reasoning steps on specific video events. To address the difficulty of LLMs identifying video events, we further propose an Instruction-oriented Video Events Recognition (InsOVER) algorithm. This algorithm locates the corresponding video events based on an efficient Hungarian matching between decompositions of linguistic instructions and video events, thereby enabling LLMs to interact effectively with extended videos. Extensive experiments on two typical video comprehension tasks show that the proposed tuning-free framework outperforms the pre-trained models including Flamingo-80B, to achieve the state-of-the-art performance. Our source code and system will be publicly available.
Authors: Yu Hao, Fan Yang, Hao Huang, Shuaihang Yuan, Sundeep Rangan, John-Ross Rizzo, Yao Wang, Yi Fang
Abstract: People with blindness and low vision (pBLV) encounter substantial challenges when it comes to comprehensive scene recognition and precise object identification in unfamiliar environments. Additionally, due to the vision loss, pBLV have difficulty in accessing and identifying potential tripping hazards on their own. In this paper, we present a pioneering approach that leverages a large vision-language model to enhance visual perception for pBLV, offering detailed and comprehensive descriptions of the surrounding environments and providing warnings about the potential risks. Our method begins by leveraging a large image tagging model (i.e., Recognize Anything (RAM)) to identify all common objects present in the captured images. The recognition results and user query are then integrated into a prompt, tailored specifically for pBLV using prompt engineering. By combining the prompt and input image, a large vision-language model (i.e., InstructBLIP) generates detailed and comprehensive descriptions of the environment and identifies potential risks in the environment by analyzing the environmental objects and scenes, relevant to the prompt. We evaluate our approach through experiments conducted on both indoor and outdoor datasets. Our results demonstrate that our method is able to recognize objects accurately and provide insightful descriptions and analysis of the environment for pBLV.
Authors: Heejoon Koo
Abstract: Medical image segmentation, which is essential for many clinical applications, has achieved almost human-level performance via data-driven deep learning technologies. Nevertheless, its performance is predicated upon the costly process of manually annotating a vast amount of medical images. To this end, we propose a novel framework for robust semi-supervised medical image segmentation using diagonal hierarchical consistency learning (DiHC-Net). First, it is composed of multiple sub-models with identical multi-scale architecture but with distinct sub-layers, such as up-sampling and normalisation layers. Second, with mutual consistency, a novel consistency regularisation is enforced between one model's intermediate and final prediction and soft pseudo labels from other models in a diagonal hierarchical fashion. A series of experiments verifies the efficacy of our simple framework, outperforming all previous approaches on public benchmark dataset covering organ and tumour.
Authors: Yunlong Zhang, Honglin Li, Yuxuan Sun, Sunyi Zheng, Chenglu Zhu, Lin Yang
Abstract: In the application of Multiple Instance Learning (MIL) methods for Whole Slide Image (WSI) classification, attention mechanisms often focus on a subset of discriminative instances, which are closely linked to overfitting. To mitigate overfitting, we present Attention-Challenging MIL (ACMIL). ACMIL combines two techniques based on separate analyses for attention value concentration. Firstly, UMAP of instance features reveals various patterns among discriminative instances, with existing attention mechanisms capturing only some of them. To remedy this, we introduce Multiple Branch Attention (MBA) to capture more discriminative instances using multiple attention branches. Secondly, the examination of the cumulative value of Top-K attention scores indicates that a tiny number of instances dominate the majority of attention. In response, we present Stochastic Top-K Instance Masking (STKIM), which masks out a portion of instances with Top-K attention values and allocates their attention values to the remaining instances. The extensive experimental results on three WSI datasets with two pre-trained backbones reveal that our ACMIL outperforms state-of-the-art methods. Additionally, through heatmap visualization and UMAP visualization, this paper extensively illustrates ACMIL's effectiveness in suppressing attention value concentration and overcoming the overfitting challenge. The source code is available at \url{https://github.com/dazhangyu123/ACMIL}.
Authors: Ming Li, Pan Zhou, Jia-Wei Liu, Jussi Keppo, Min Lin, Shuicheng Yan, Xiangyu Xu
Abstract: Text-to-3D generation has attracted much attention from the computer vision community. Existing methods mainly optimize a neural field from scratch for each text prompt, relying on heavy and repetitive training cost which impedes their practical deployment. In this paper, we propose a novel framework for fast text-to-3D generation, dubbed Instant3D. Once trained, Instant3D is able to create a 3D object for an unseen text prompt in less than one second with a single run of a feedforward network. We achieve this remarkable speed by devising a new network that directly constructs a 3D triplane from a text prompt. The core innovation of our Instant3D lies in our exploration of strategies to effectively inject text conditions into the network. In particular, we propose to combine three key mechanisms: cross-attention, style injection, and token-to-plane transformation, which collectively ensure precise alignment of the output with the input text. Furthermore, we propose a simple yet effective activation function, the scaled-sigmoid, to replace the original sigmoid function, which speeds up the training convergence by more than ten times. Finally, to address the Janus (multi-head) problem in 3D generation, we propose an adaptive Perp-Neg algorithm that can dynamically adjust its concept negation scales according to the severity of the Janus problem during training, effectively reducing the multi-head effect. Extensive experiments on a wide variety of benchmark datasets demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods both qualitatively and quantitatively, while achieving significantly better efficiency. The code, data, and models are available at https://github.com/ming1993li/Instant3DCodes.
Authors: Yixin Liu, Chenrui Fan, Yutong Dai, Xun Chen, Pan Zhou, Lichao Sun
Abstract: Text-to-image diffusion models allow seamless generation of personalized images from scant reference photos. Yet, these tools, in the wrong hands, can fabricate misleading or harmful content, endangering individuals. To address this problem, existing poisoning-based approaches perturb user images in an imperceptible way to render them "unlearnable" from malicious uses. We identify two limitations of these defending approaches: i) sub-optimal due to the hand-crafted heuristics for solving the intractable bilevel optimization and ii) lack of robustness against simple data transformations like Gaussian filtering. To solve these challenges, we propose MetaCloak, which solves the bi-level poisoning problem with a meta-learning framework with an additional transformation sampling process to craft transferable and robust perturbation. Specifically, we employ a pool of surrogate diffusion models to craft transferable and model-agnostic perturbation. Furthermore, by incorporating an additional transformation process, we design a simple denoising-error maximization loss that is sufficient for causing transformation-robust semantic distortion and degradation in a personalized generation. Extensive experiments on the VGGFace2 and CelebA-HQ datasets show that MetaCloak outperforms existing approaches. Notably, MetaCloak can successfully fool online training services like Replicate, in a black-box manner, demonstrating the effectiveness of MetaCloak in real-world scenarios. Our code is available at https://github.com/liuyixin-louis/MetaCloak.
Authors: Yichao Cai, Yuhang Liu, Zhen Zhang, Javen Qinfeng Shi
Abstract: Contrastive vision-language models, such as CLIP, have garnered considerable attention for various dowmsteam tasks, mainly due to the remarkable ability of the learned features for generalization. However, the features they learned often blend content and style information, which somewhat limits their generalization capabilities under distribution shifts. To address this limitation, we adopt a causal generative perspective for multimodal data and propose contrastive learning with data augmentation to disentangle content features from the original representations. To achieve this, we begins with exploring image augmentation techniques and develop a method to seamlessly integrate them into pre-trained CLIP-like models to extract pure content features. Taking a step further, recognizing the inherent semantic richness and logical structure of text data, we explore the use of text augmentation to isolate latent content from style features. This enables CLIP-like model's encoders to concentrate on latent content information, refining the learned representations by pre-trained CLIP-like models. Our extensive experiments across diverse datasets demonstrate significant improvements in zero-shot and few-shot classification tasks, alongside enhanced robustness to various perturbations. These results underscore the effectiveness of our proposed methods in refining vision-language representations and advancing the state-of-the-art in multimodal learning.
Authors: Maximilian Dreyer, Reduan Achtibat, Wojciech Samek, Sebastian Lapuschkin
Abstract: Ensuring both transparency and safety is critical when deploying Deep Neural Networks (DNNs) in high-risk applications, such as medicine. The field of explainable AI (XAI) has proposed various methods to comprehend the decision-making processes of opaque DNNs. However, only few XAI methods are suitable of ensuring safety in practice as they heavily rely on repeated labor-intensive and possibly biased human assessment. In this work, we present a novel post-hoc concept-based XAI framework that conveys besides instance-wise (local) also class-wise (global) decision-making strategies via prototypes. What sets our approach apart is the combination of local and global strategies, enabling a clearer understanding of the (dis-)similarities in model decisions compared to the expected (prototypical) concept use, ultimately reducing the dependence on human long-term assessment. Quantifying the deviation from prototypical behavior not only allows to associate predictions with specific model sub-strategies but also to detect outlier behavior. As such, our approach constitutes an intuitive and explainable tool for model validation. We demonstrate the effectiveness of our approach in identifying out-of-distribution samples, spurious model behavior and data quality issues across three datasets (ImageNet, CUB-200, and CIFAR-10) utilizing VGG, ResNet, and EfficientNet architectures. Code is available on https://github.com/maxdreyer/pcx.
Authors: Shen Zhang, Zhaowei Chen, Zhenyu Zhao, Yuhao Chen, Yao Tang, Jiajun Liang
Abstract: Diffusion models have become a mainstream approach for high-resolution image synthesis. However, directly generating higher-resolution images from pretrained diffusion models will encounter unreasonable object duplication and exponentially increase the generation time. In this paper, we discover that object duplication arises from feature duplication in the deep blocks of the U-Net. Concurrently, We pinpoint the extended generation times to self-attention redundancy in U-Net's top blocks. To address these issues, we propose a tuning-free higher-resolution framework named HiDiffusion. Specifically, HiDiffusion contains Resolution-Aware U-Net (RAU-Net) that dynamically adjusts the feature map size to resolve object duplication and engages Modified Shifted Window Multi-head Self-Attention (MSW-MSA) that utilizes optimized window attention to reduce computations. we can integrate HiDiffusion into various pretrained diffusion models to scale image generation resolutions even to 4096x4096 at 1.5-6x the inference speed of previous methods. Extensive experiments demonstrate that our approach can address object duplication and heavy computation issues, achieving state-of-the-art performance on higher-resolution image synthesis tasks.
Authors: Ziqiao Peng, Wentao Hu, Yue Shi, Xiangyu Zhu, Xiaomei Zhang, Hao Zhao, Jun He, Hongyan Liu, Zhaoxin Fan
Abstract: Achieving high synchronization in the synthesis of realistic, speech-driven talking head videos presents a significant challenge. Traditional Generative Adversarial Networks (GAN) struggle to maintain consistent facial identity, while Neural Radiance Fields (NeRF) methods, although they can address this issue, often produce mismatched lip movements, inadequate facial expressions, and unstable head poses. A lifelike talking head requires synchronized coordination of subject identity, lip movements, facial expressions, and head poses. The absence of these synchronizations is a fundamental flaw, leading to unrealistic and artificial outcomes. To address the critical issue of synchronization, identified as the "devil" in creating realistic talking heads, we introduce SyncTalk. This NeRF-based method effectively maintains subject identity, enhancing synchronization and realism in talking head synthesis. SyncTalk employs a Face-Sync Controller to align lip movements with speech and innovatively uses a 3D facial blendshape model to capture accurate facial expressions. Our Head-Sync Stabilizer optimizes head poses, achieving more natural head movements. The Portrait-Sync Generator restores hair details and blends the generated head with the torso for a seamless visual experience. Extensive experiments and user studies demonstrate that SyncTalk outperforms state-of-the-art methods in synchronization and realism. We recommend watching the supplementary video: https://ziqiaopeng.github.io/synctalk
Authors: Kristen Grauman, Andrew Westbury, Lorenzo Torresani, Kris Kitani, Jitendra Malik, Triantafyllos Afouras, Kumar Ashutosh, Vijay Baiyya, Siddhant Bansal, Bikram Boote, Eugene Byrne, Zach Chavis, Joya Chen, Feng Cheng, Fu-Jen Chu, Sean Crane, Avijit Dasgupta, Jing Dong, Maria Escobar, Cristhian Forigua, Abrham Gebreselasie, Sanjay Haresh, Jing Huang, Md Mohaiminul Islam, Suyog Jain, Rawal Khirodkar, Devansh Kukreja, Kevin J Liang, Jia-Wei Liu, Sagnik Majumder, Yongsen Mao, Miguel Martin, Effrosyni Mavroudi, Tushar Nagarajan, Francesco Ragusa, Santhosh Kumar Ramakrishnan, Luigi Seminara, Arjun Somayazulu, Yale Song, Shan Su, Zihui Xue, Edward Zhang, Jinxu Zhang, Angela Castillo, Changan Chen, Xinzhu Fu, Ryosuke Furuta, Cristina Gonzalez, Prince Gupta, Jiabo Hu, Yifei Huang, Yiming Huang, Weslie Khoo, Anush Kumar, Robert Kuo, Sach Lakhavani, Miao Liu, Mi Luo, Zhengyi Luo, Brighid Meredith, Austin Miller, Oluwatumininu Oguntola, Xiaqing Pan, Penny Peng, Shraman Pramanick, Merey Ramazanova, Fiona Ryan, Wei Shan, Kiran Somasundaram, Chenan Song, Audrey Southerland, Masatoshi Tateno, Huiyu Wang, Yuchen Wang, Takuma Yagi, Mingfei Yan, Xitong Yang, Zecheng Yu, Shengxin Cindy Zha, Chen Zhao, Ziwei Zhao, Zhifan Zhu, Jeff Zhuo, Pablo Arbelaez, Gedas Bertasius, David Crandall, Dima Damen, Jakob Engel, Giovanni Maria Farinella, Antonino Furnari, Bernard Ghanem, Judy Hoffman, C. V. Jawahar, Richard Newcombe, Hyun Soo Park, James M. Rehg, Yoichi Sato, Manolis Savva, Jianbo Shi, Mike Zheng Shou, Michael Wray
Abstract: We present Ego-Exo4D, a diverse, large-scale multimodal multiview video dataset and benchmark challenge. Ego-Exo4D centers around simultaneously-captured egocentric and exocentric video of skilled human activities (e.g., sports, music, dance, bike repair). 740 participants from 13 cities worldwide performed these activities in 123 different natural scene contexts, yielding long-form captures from 1 to 42 minutes each and 1,286 hours of video combined. The multimodal nature of the dataset is unprecedented: the video is accompanied by multichannel audio, eye gaze, 3D point clouds, camera poses, IMU, and multiple paired language descriptions -- including a novel "expert commentary" done by coaches and teachers and tailored to the skilled-activity domain. To push the frontier of first-person video understanding of skilled human activity, we also present a suite of benchmark tasks and their annotations, including fine-grained activity understanding, proficiency estimation, cross-view translation, and 3D hand/body pose. All resources are open sourced to fuel new research in the community. Project page: http://ego-exo4d-data.org/
Authors: Davide Cozzolino, Giovanni Poggi, Riccardo Corvi, Matthias Nie{\ss}ner, Luisa Verdoliva
Abstract: The aim of this work is to explore the potential of pre-trained vision-language models (VLMs) for universal detection of AI-generated images. We develop a lightweight detection strategy based on CLIP features and study its performance in a wide variety of challenging scenarios. We find that, contrary to previous beliefs, it is neither necessary nor convenient to use a large domain-specific dataset for training. On the contrary, by using only a handful of example images from a single generative model, a CLIP-based detector exhibits surprising generalization ability and high robustness across different architectures, including recent commercial tools such as Dalle-3, Midjourney v5, and Firefly. We match the state-of-the-art (SoTA) on in-distribution data and significantly improve upon it in terms of generalization to out-of-distribution data (+6% AUC) and robustness to impaired/laundered data (+13%). Our project is available at https://grip-unina.github.io/ClipBased-SyntheticImageDetection/
URLs: https://grip-unina.github.io/ClipBased-SyntheticImageDetection/
Authors: Mu Cai, Haotian Liu, Dennis Park, Siva Karthik Mustikovela, Gregory P. Meyer, Yuning Chai, Yong Jae Lee
Abstract: While existing large vision-language multimodal models focus on whole image understanding, there is a prominent gap in achieving region-specific comprehension. Current approaches that use textual coordinates or spatial encodings often fail to provide a user-friendly interface for visual prompting. To address this challenge, we introduce a novel multimodal model capable of decoding arbitrary visual prompts. This allows users to intuitively mark images and interact with the model using natural cues like a "red bounding box" or "pointed arrow". Our simple design directly overlays visual markers onto the RGB image, eliminating the need for complex region encodings, yet achieves state-of-the-art performance on region-understanding tasks like Visual7W, PointQA, and Visual Commonsense Reasoning benchmark. Furthermore, we present ViP-Bench, a comprehensive benchmark to assess the capability of models in understanding visual prompts across multiple dimensions, enabling future research in this domain. Code, data, and model are publicly available.
Authors: Lisa Dunlap, Yuhui Zhang, Xiaohan Wang, Ruiqi Zhong, Trevor Darrell, Jacob Steinhardt, Joseph E. Gonzalez, Serena Yeung-Levy
Abstract: How do two sets of images differ? Discerning set-level differences is crucial for understanding model behaviors and analyzing datasets, yet manually sifting through thousands of images is impractical. To aid in this discovery process, we explore the task of automatically describing the differences between two $\textbf{sets}$ of images, which we term Set Difference Captioning. This task takes in image sets $D_A$ and $D_B$, and outputs a description that is more often true on $D_A$ than $D_B$. We outline a two-stage approach that first proposes candidate difference descriptions from image sets and then re-ranks the candidates by checking how well they can differentiate the two sets. We introduce VisDiff, which first captions the images and prompts a language model to propose candidate descriptions, then re-ranks these descriptions using CLIP. To evaluate VisDiff, we collect VisDiffBench, a dataset with 187 paired image sets with ground truth difference descriptions. We apply VisDiff to various domains, such as comparing datasets (e.g., ImageNet vs. ImageNetV2), comparing classification models (e.g., zero-shot CLIP vs. supervised ResNet), summarizing model failure modes (supervised ResNet), characterizing differences between generative models (e.g., StableDiffusionV1 and V2), and discovering what makes images memorable. Using VisDiff, we are able to find interesting and previously unknown differences in datasets and models, demonstrating its utility in revealing nuanced insights.
Authors: Muhammad Osama Zeeshan, Muhammad Haseeb Aslam, Soufiane Belharbi, Alessandro Lameiras Koerich, Marco Pedersoli, Simon Bacon, Eric Granger
Abstract: Adapting a deep learning model to a specific target individual is a challenging facial expression recognition (FER) task that may be achieved using unsupervised domain adaptation (UDA) methods. Although several UDA methods have been proposed to adapt deep FER models across source and target data sets, multiple subject-specific source domains are needed to accurately represent the intra- and inter-person variability in subject-based adaption. This paper considers the setting where domains correspond to individuals, not entire datasets. Unlike UDA, multi-source domain adaptation (MSDA) methods can leverage multiple source datasets to improve the accuracy and robustness of the target model. However, previous methods for MSDA adapt image classification models across datasets and do not scale well to a more significant number of source domains. This paper introduces a new MSDA method for subject-based domain adaptation in FER. It efficiently leverages information from multiple source subjects (labeled source domain data) to adapt a deep FER model to a single target individual (unlabeled target domain data). During adaptation, our subject-based MSDA first computes a between-source discrepancy loss to mitigate the domain shift among data from several source subjects. Then, a new strategy is employed to generate augmented confident pseudo-labels for the target subject, allowing a reduction in the domain shift between source and target subjects. Experiments performed on the challenging BioVid heat and pain dataset with 87 subjects and the UNBC-McMaster shoulder pain dataset with 25 subjects show that our subject-based MSDA can outperform state-of-the-art methods yet scale well to multiple subject-based source domains.
Authors: Kangneng Zhou, Daiheng Gao, Xuan Wang, Jie Zhang, Peng Zhang, Xusen Sun, Longhao Zhang, Shiqi Yang, Bang Zhang, Liefeng Bo, Yaxing Wang, Ming-Ming Cheng
Abstract: 3D-aware portrait editing has a wide range of applications in multiple fields. However, current approaches are limited due that they can only perform mask-guided or text-based editing. Even by fusing the two procedures into a model, the editing quality and stability cannot be ensured. To address this limitation, we propose \textbf{MaTe3D}: mask-guided text-based 3D-aware portrait editing. In this framework, first, we introduce a new SDF-based 3D generator which learns local and global representations with proposed SDF and density consistency losses. This enhances masked-based editing in local areas; second, we present a novel distillation strategy: Conditional Distillation on Geometry and Texture (CDGT). Compared to exiting distillation strategies, it mitigates visual ambiguity and avoids mismatch between texture and geometry, thereby producing stable texture and convincing geometry while editing. Additionally, we create the CatMask-HQ dataset, a large-scale high-resolution cat face annotation for exploration of model generalization and expansion. We perform expensive experiments on both the FFHQ and CatMask-HQ datasets to demonstrate the editing quality and stability of the proposed method. Our method faithfully generates a 3D-aware edited face image based on a modified mask and a text prompt. Our code and models will be publicly released.
Authors: Xijun Wang, Junbang Liang, Chun-Kai Wang, Kenan Deng, Yu Lou, Ming Lin, Shan Yang
Abstract: In this work, we propose an efficient Video-Language Alignment (ViLA) network. Our ViLA model addresses both efficient frame sampling and effective cross-modal alignment in a unified way. In our ViLA network, we design a new learnable text-guided Frame-Prompter together with a new cross-modal distillation (QFormer-Distiller) module. Pre-trained large image-language models have shown promising results on problems such as visual question answering (VQA). However, how to efficiently and effectively sample video frames when adapting pre-trained large image-language model to video-language alignment is still the major challenge. Compared with prior work, our ViLA model demonstrates the capability of selecting key frames with critical contents, thus improving the video-language alignment accuracy while reducing the inference latency +3.3% on NExT-QA Temporal with 3.0X speed up). Overall, our ViLA network outperforms the state-of-the-art methods on the video question-answering benchmarks: +4.6% on STAR Interaction, +2.2% on STAR average with 3.0X speed up, ours 2-frames out-perform SeViLA 4-frames on the VLEP dataset with 4.2X speed-up.
Authors: Zhicong Tang, Shuyang Gu, Chunyu Wang, Ting Zhang, Jianmin Bao, Dong Chen, Baining Guo
Abstract: This paper introduces a pioneering 3D volumetric encoder designed for text-to-3D generation. To scale up the training data for the diffusion model, a lightweight network is developed to efficiently acquire feature volumes from multi-view images. The 3D volumes are then trained on a diffusion model for text-to-3D generation using a 3D U-Net. This research further addresses the challenges of inaccurate object captions and high-dimensional feature volumes. The proposed model, trained on the public Objaverse dataset, demonstrates promising outcomes in producing diverse and recognizable samples from text prompts. Notably, it empowers finer control over object part characteristics through textual cues, fostering model creativity by seamlessly combining multiple concepts within a single object. This research significantly contributes to the progress of 3D generation by introducing an efficient, flexible, and scalable representation methodology. Code is available at https://github.com/checkcrab/VolumeDiffusion.
Authors: Guanqi Zhan, Chuanxia Zheng, Weidi Xie, Andrew Zisserman
Abstract: This paper studies amodal image segmentation: predicting entire object segmentation masks including both visible and invisible (occluded) parts. In previous work, the amodal segmentation ground truth on real images is usually predicted by manual annotaton and thus is subjective. In contrast, we use 3D data to establish an automatic pipeline to determine authentic ground truth amodal masks for partially occluded objects in real images. This pipeline is used to construct an amodal completion evaluation benchmark, MP3D-Amodal, consisting of a variety of object categories and labels. To better handle the amodal completion task in the wild, we explore two architecture variants: a two-stage model that first infers the occluder, followed by amodal mask completion; and a one-stage model that exploits the representation power of Stable Diffusion for amodal segmentation across many categories. Without bells and whistles, our method achieves a new state-of-the-art performance on Amodal segmentation datasets that cover a large variety of objects, including COCOA and our new MP3D-Amodal dataset. The dataset, model, and code are available at https://www.robots.ox.ac.uk/~vgg/research/amodal/.
Authors: Kaiyuan Yang, Fabio Musio, Yihui Ma, Norman Juchler, Johannes C. Paetzold, Rami Al-Maskari, Luciano H\"oher, Hongwei Bran Li, Ibrahim Ethem Hamamci, Anjany Sekuboyina, Suprosanna Shit, Houjing Huang, Chinmay Prabhakar, Ezequiel de la Rosa, Diana Waldmannstetter, Florian Kofler, Fernando Navarro, Martin Menten, Ivan Ezhov, Daniel Rueckert, Iris Vos, Ynte Ruigrok, Birgitta Velthuis, Hugo Kuijf, Julien H\"ammerli, Catherine Wurster, Philippe Bijlenga, Laura Westphal, Jeroen Bisschop, Elisa Colombo, Hakim Baazaoui, Andrew Makmur, James Hallinan, Bene Wiestler, Jan S. Kirschke, Roland Wiest, Emmanuel Montagnon, Laurent Letourneau-Guillon, Adrian Galdran, Francesco Galati, Daniele Falcetta, Maria A. Zuluaga, Chaolong Lin, Haoran Zhao, Zehan Zhang, Sinyoung Ra, Jongyun Hwang, Hyunjin Park, Junqiang Chen, Marek Wodzinski, Henning M\"uller, Pengcheng Shi, Wei Liu, Ting Ma, Cansu Yal\c{c}in, Rachika E. Hamadache, Joaquim Salvi, Xavier Llado, Uma Maria Lal-Trehan Estrada, Valeriia Abramova, Luca Giancardo, Arnau Oliver, Jialu Liu, Haibin Huang, Yue Cui, Zehang Lin, Yusheng Liu, Shunzhi Zhu, Tatsat R. Patel, Vincent M. Tutino, Maysam Orouskhani, Huayu Wang, Mahmud Mossa-Basha, Chengcheng Zhu, Maximilian R. Rokuss, Yannick Kirchhoff, Nico Disch, Julius Holzschuh, Fabian Isensee, Klaus Maier-Hein, Yuki Sato, Sven Hirsch, Susanne Wegener, Bjoern Menze
Abstract: The Circle of Willis (CoW) is an important network of arteries connecting major circulations of the brain. Its vascular architecture is believed to affect the risk, severity, and clinical outcome of serious neuro-vascular diseases. However, characterizing the highly variable CoW anatomy is still a manual and time-consuming expert task. The CoW is usually imaged by two angiographic imaging modalities, magnetic resonance angiography (MRA) and computed tomography angiography (CTA), but there exist limited public datasets with annotations on CoW anatomy, especially for CTA. Therefore we organized the TopCoW Challenge in 2023 with the release of an annotated CoW dataset. The TopCoW dataset was the first public dataset with voxel-level annotations for thirteen possible CoW vessel components, enabled by virtual-reality (VR) technology. It was also the first large dataset with paired MRA and CTA from the same patients. TopCoW challenge formalized the CoW characterization problem as a multiclass anatomical segmentation task with an emphasis on topological metrics. We invited submissions worldwide for the CoW segmentation task, which attracted over 140 registered participants from four continents. The top performing teams managed to segment many CoW components to Dice scores around 90%, but with lower scores for communicating arteries and rare variants. There were also topological mistakes for predictions with high Dice scores. Additional topological analysis revealed further areas for improvement in detecting certain CoW components and matching CoW variant topology accurately. TopCoW represented a first attempt at benchmarking the CoW anatomical segmentation task for MRA and CTA, both morphologically and topologically.
Authors: Zhilu Zhang, Shuohao Zhang, Renlong Wu, Zifei Yan, Wangmeng Zuo
Abstract: It is highly desired but challenging to acquire high-quality photos with clear content in low-light environments. Although multi-image processing methods (using burst, dual-exposure, or multi-exposure images) have made significant progress in addressing this issue, they typically focus on specific restoration or enhancement problems, being insufficient in exploiting multi-image. Motivated by that multi-exposure images are complementary in denoising, deblurring, high dynamic range imaging, and super-resolution, we propose to utilize exposure bracketing photography to unify restoration and enhancement tasks in this work. Due to the difficulty in collecting real-world pairs, we suggest a solution that first pre-trains the model with synthetic paired data and then adapts it to real-world unlabeled images. In particular, a temporally modulated recurrent network (TMRNet) and self-supervised adaptation method are proposed. Moreover, we construct a data simulation pipeline to synthesize pairs and collect real-world images from 200 nighttime scenarios. Experiments on both datasets show that our method performs favorably against the state-of-the-art multi-image processing ones. The dataset, code, and pre-trained models are available at https://github.com/cszhilu1998/BracketIRE.
Authors: Zikai Zhou, Yunhang Shen, Shitong Shao, Linrui Gong, Shaohui Lin
Abstract: Knowledge distillation has emerged as a highly effective method for bridging the representation discrepancy between large-scale models and lightweight models. Prevalent approaches involve leveraging appropriate metrics to minimize the divergence or distance between the knowledge extracted from the teacher model and the knowledge learned by the student model. Centered Kernel Alignment (CKA) is widely used to measure representation similarity and has been applied in several knowledge distillation methods. However, these methods are complex and fail to uncover the essence of CKA, thus not answering the question of how to use CKA to achieve simple and effective distillation properly. This paper first provides a theoretical perspective to illustrate the effectiveness of CKA, which decouples CKA to the upper bound of Maximum Mean Discrepancy~(MMD) and a constant term. Drawing from this, we propose a novel Relation-Centered Kernel Alignment~(RCKA) framework, which practically establishes a connection between CKA and MMD. Furthermore, we dynamically customize the application of CKA based on the characteristics of each task, with less computational source yet comparable performance than the previous methods. The extensive experiments on the CIFAR-100, ImageNet-1k, and MS-COCO demonstrate that our method achieves state-of-the-art performance on almost all teacher-student pairs for image classification and object detection, validating the effectiveness of our approaches. Our code is available in https://github.com/Klayand/PCKA
Authors: Zhenxing Ming, Julie Stephany Berrio, Mao Shan, Stewart Worrall
Abstract: This paper introduces InverseMatrixVT3D, an efficient method for transforming multi-view image features into 3D feature volumes for 3D semantic occupancy prediction. Existing methods for constructing 3D volumes often rely on depth estimation, device-specific operators, or transformer queries, which hinders the widespread adoption of 3D occupancy models. In contrast, our approach leverages two projection matrices to store the static mapping relationships and matrix multiplications to efficiently generate global Bird's Eye View (BEV) features and local 3D feature volumes. Specifically, we achieve this by performing matrix multiplications between multi-view image feature maps and two sparse projection matrices. We introduce a sparse matrix handling technique for the projection matrices to optimize GPU memory usage. Moreover, a global-local attention fusion module is proposed to integrate the global BEV features with the local 3D feature volumes to obtain the final 3D volume. We also employ a multi-scale supervision mechanism to enhance performance further. Extensive experiments performed on the nuScenes and SemanticKITTI datasets reveal that our approach not only stands out for its simplicity and effectiveness but also achieves the top performance in detecting vulnerable road users (VRU), crucial for autonomous driving and road safety. The code has been made available at: https://github.com/DanielMing123/InverseMatrixVT3D
Authors: Muhammad Haseeb Aslam, Muhammad Osama Zeeshan, Soufiane Belharbi, Marco Pedersoli, Alessandro Koerich, Simon Bacon, Eric Granger
Abstract: Deep learning models for multimodal expression recognition have reached remarkable performance in controlled laboratory environments because of their ability to learn complementary and redundant semantic information. However, these models struggle in the wild, mainly because of the unavailability and quality of modalities used for training. In practice, only a subset of the training-time modalities may be available at test time. Learning with privileged information enables models to exploit data from additional modalities that are only available during training. State-of-the-art knowledge distillation (KD) methods have been proposed to distill information from multiple teacher models (each trained on a modality) to a common student model. These privileged KD methods typically utilize point-to-point matching, yet have no explicit mechanism to capture the structural information in the teacher representation space formed by introducing the privileged modality. Experiments were performed on two challenging problems - pain estimation on the Biovid dataset (ordinal classification) and arousal-valance prediction on the Affwild2 dataset (regression). Results show that our proposed method can outperform state-of-the-art privileged KD methods on these problems. The diversity among modalities and fusion architectures indicates that PKDOT is modality- and model-agnostic.
Authors: Kai He, Kaixin Yao, Qixuan Zhang, Jingyi Yu, Lingjie Liu, Lan Xu
Abstract: Apparel's significant role in human appearance underscores the importance of garment digitalization for digital human creation. Recent advances in 3D content creation are pivotal for digital human creation. Nonetheless, garment generation from text guidance is still nascent. We introduce a text-driven 3D garment generation framework, DressCode, which aims to democratize design for novices and offer immense potential in fashion design, virtual try-on, and digital human creation. For our framework, we first introduce SewingGPT, a GPT-based architecture integrating cross-attention with text-conditioned embedding to generate sewing patterns with text guidance. We also tailored a pre-trained Stable Diffusion for high-quality, tile-based PBR texture generation. By leveraging a large language model, our framework generates CG-friendly garments through natural language interaction. Our method also facilitates pattern completion and texture editing, streamlining the design process through user-friendly interaction. This framework fosters innovation by allowing creators to freely experiment with designs and incorporate unique elements into their work, thereby igniting new ideas and artistic possibilities. With comprehensive evaluations and comparisons with other state-of-the-art methods, our method showcases the best quality and alignment with input prompts. User studies further validate our high-quality rendering results, highlighting its practical utility and potential in production settings. Our project page is https://IHe-KaiI.github.io/DressCode/.
Authors: Michal Shlapentokh-Rothman, Ansel Blume, Yao Xiao, Yuqun Wu, Sethuraman T V, Heyi Tao, Jae Yong Lee, Wilfredo Torres, Yu-Xiong Wang, Derek Hoiem
Abstract: We investigate whether region-based representations are effective for recognition. Regions were once a mainstay in recognition approaches, but pixel and patch-based features are now used almost exclusively. We show that recent class-agnostic segmenters like SAM can be effectively combined with strong unsupervised representations like DINOv2 and used for a wide variety of tasks, including semantic segmentation, object-based image retrieval, and multi-image analysis. Once the masks and features are extracted, these representations, even with linear decoders, enable competitive performance, making them well suited to applications that require custom queries. The compactness of the representation also makes it well-suited to video analysis and other problems requiring inference across many images.
Authors: Pranav Singh, Jacopo Cirrone
Abstract: Recent advancements in self-supervised learning have unlocked the potential to harness unlabeled data for auxiliary tasks, facilitating the learning of beneficial priors. This has been particularly advantageous in fields like medical image analysis, where labeled data are scarce. Although effective for classification tasks, this methodology has shown limitations in more complex applications, such as medical image segmentation. In this paper, we introduce Medical imaging Enhanced with Dynamic Self-Adaptive Semantic Segmentation (MedSASS), a dedicated self-supervised framework tailored for medical image segmentation. We evaluate MedSASS against existing state-of-the-art methods across four diverse medical datasets, showcasing its superiority. MedSASS outperforms existing CNN-based self-supervised methods by 3.83% and matches the performance of ViT-based methods. Furthermore, when MedSASS is trained end-to-end, covering both encoder and decoder, it demonstrates significant improvements of 14.4% for CNNs and 6% for ViT-based architectures compared to existing state-of-the-art self-supervised strategies.
Authors: Zihan Ma, Yongshang Li, Ronggui Ma, Chen Liang
Abstract: There are two challenges presented in parsing road scenes from UAV images: the complexity of processing high-resolution images and the dependency on extensive manual annotations required by traditional supervised deep learning methods to train robust and accurate models. In this paper, a novel unsupervised road parsing framework that leverages advancements in vision language models with fundamental computer vision techniques is introduced to address these critical challenges. Our approach initiates with a vision language model that efficiently processes ultra-high resolution images to rapidly identify road regions of interest. Subsequent application of the vision foundation model, SAM, generates masks for these regions without requiring category information. A self-supervised learning network then processes these masked regions to extract feature representations, which are clustered using an unsupervised algorithm that assigns unique IDs to each feature cluster. The masked regions are combined with the corresponding IDs to generate initial pseudo-labels, which initiate an iterative self-training process for regular semantic segmentation. Remarkably, the proposed method achieves a mean Intersection over Union (mIoU) of 89.96% on the development dataset without any manual annotation, demonstrating extraordinary flexibility by surpassing the limitations of human-defined categories, and autonomously acquiring knowledge of new categories from the dataset itself.
Authors: Changwoon Choi, Jaeah Lee, Jaesik Park, Young Min Kim
Abstract: While free-hand sketching has long served as an efficient representation to convey characteristics of an object, they are often subjective, deviating significantly from realistic representations. Moreover, sketches are not consistent for arbitrary viewpoints, making it hard to catch 3D shapes. We propose 3Dooole, generating descriptive and view-consistent sketch images given multi-view images of the target object. Our method is based on the idea that a set of 3D strokes can efficiently represent 3D structural information and render view-consistent 2D sketches. We express 2D sketches as a union of view-independent and view-dependent components. 3D cubic B ezier curves indicate view-independent 3D feature lines, while contours of superquadrics express a smooth outline of the volume of varying viewpoints. Our pipeline directly optimizes the parameters of 3D stroke primitives to minimize perceptual losses in a fully differentiable manner. The resulting sparse set of 3D strokes can be rendered as abstract sketches containing essential 3D characteristic shapes of various objects. We demonstrate that 3Doodle can faithfully express concepts of the original images compared with recent sketch generation approaches.
Authors: Antonio R\'ios-Vila, Jorge Calvo-Zaragoza, Thierry Paquet
Abstract: State-of-the-art end-to-end Optical Music Recognition (OMR) has, to date, primarily been carried out using monophonic transcription techniques to handle complex score layouts, such as polyphony, often by resorting to simplifications or specific adaptations. Despite their efficacy, these approaches imply challenges related to scalability and limitations. This paper presents the Sheet Music Transformer, the first end-to-end OMR model designed to transcribe complex musical scores without relying solely on monophonic strategies. Our model employs a Transformer-based image-to-sequence framework that predicts score transcriptions in a standard digital music encoding format from input images. Our model has been tested on two polyphonic music datasets and has proven capable of handling these intricate music structures effectively. The experimental outcomes not only indicate the competence of the model, but also show that it is better than the state-of-the-art methods, thus contributing to advancements in end-to-end OMR transcription.
Authors: Tim B\"uchner, Oliver Mothes, Orlando Guntinas-Lichius, Joachim Denzler
Abstract: Analyzing facial features and expressions is a complex task in computer vision. The human face is intricate, with significant shape, texture, and appearance variations. In medical contexts, facial structures and movements that differ from the norm are particularly important to study and require precise analysis to understand the underlying conditions. Given that solely the facial muscles, innervated by the facial nerve, are responsible for facial expressions, facial palsy can lead to severe impairments in facial movements. One affected area of interest is the subtle movements involved in blinking. It is an intricate spontaneous process that is not yet fully understood and needs high-resolution, time-specific analysis for detailed understanding. However, a significant challenge is that many computer vision techniques demand programming skills for automated extraction and analysis, making them less accessible to medical professionals who may not have these skills. The Jena Facial Palsy Toolbox (JeFaPaTo) has been developed to bridge this gap. It utilizes cutting-edge computer vision algorithms and offers a user-friendly interface for those without programming expertise. This toolbox makes advanced facial analysis more accessible to medical experts, simplifying integration into their workflow.
Authors: Ray Coden Mercurius, Ehsan Ahmadi, Soheil Mohamad Alizadeh Shabestary, Amir Rasouli
Abstract: Accurate prediction of pedestrians' future motions is critical for intelligent driving systems. Developing models for this task requires rich datasets containing diverse sets of samples. However, the existing naturalistic trajectory prediction datasets are generally imbalanced in favor of simpler samples and lack challenging scenarios. Such a long-tail effect causes prediction models to underperform on the tail portion of the data distribution containing safety-critical scenarios. Previous methods tackle the long-tail problem using methods such as contrastive learning and class-conditioned hypernetworks. These approaches, however, are not modular and cannot be applied to many machine learning architectures. In this work, we propose a modular model-agnostic framework for trajectory prediction that leverages a specialized mixture of experts. In our approach, each expert is trained with a specialized skill with respect to a particular part of the data. To produce predictions, we utilise a router network that selects the best expert by generating relative confidence scores. We conduct experimentation on common pedestrian trajectory prediction datasets and show that our method improves performance on long-tail scenarios. We further conduct ablation studies to highlight the contribution of different proposed components.
Authors: Kei Nakatsuru, Seiichi Uchida
Abstract: Kerning is the task of setting appropriate horizontal spaces for all possible letter pairs of a certain font. One of the difficulties of kerning is that the appropriate space differs for each letter pair. Therefore, for a total of 52 capital and small letters, we need to adjust $52 \times 52 = 2704$ different spaces. Another difficulty is that there is neither a general procedure nor criterion for automatic kerning; therefore, kerning is still done manually or with heuristics. In this paper, we tackle kerning by proposing two machine-learning models, called pairwise and set-wise models. The former is a simple deep neural network that estimates the letter space for two given letter images. In contrast, the latter is a transformer-based model that estimates the letter spaces for three or more given letter images. For example, the set-wise model simultaneously estimates 2704 spaces for 52 letter images for a certain font. Among the two models, the set-wise model is not only more efficient but also more accurate because its internal self-attention mechanism allows for more consistent kerning for all letters. Experimental results on about 2500 Google fonts and their quantitative and qualitative analyses show that the set-wise model has an average estimation error of only about 5.3 pixels when the average letter space of all fonts and letter pairs is about 115 pixels.
Authors: Lixian Zhang, Runmin Dong, Shuai Yuan, Jinxiao Zhang, Mengxuan Chen, Juepeng Zheng, Haohuan Fu
Abstract: Nighttime light (NTL) remote sensing observation serves as a unique proxy for quantitatively assessing progress toward meeting a series of Sustainable Development Goals (SDGs), such as poverty estimation, urban sustainable development, and carbon emission. However, existing NTL observations often suffer from pervasive degradation and inconsistency, limiting their utility for computing the indicators defined by the SDGs. In this study, we propose a novel approach to reconstruct high-resolution NTL images using multi-modal remote sensing data. To support this research endeavor, we introduce DeepLightMD, a comprehensive dataset comprising data from five heterogeneous sensors, offering fine spatial resolution and rich spectral information at a national scale. Additionally, we present DeepLightSR, a calibration-aware method for building bridges between spatially heterogeneous modality data in the multi-modality super-resolution. DeepLightSR integrates calibration-aware alignment, an auxiliary-to-main multi-modality fusion, and an auxiliary-embedded refinement to effectively address spatial heterogeneity, fuse diversely representative features, and enhance performance in $8\times$ super-resolution (SR) tasks. Extensive experiments demonstrate the superiority of DeepLightSR over 8 competing methods, as evidenced by improvements in PSNR (2.01 dB $ \sim $ 13.25 dB) and PIQE (0.49 $ \sim $ 9.32). Our findings underscore the practical significance of our proposed dataset and model in reconstructing high-resolution NTL data, supporting efficiently and quantitatively assessing the SDG progress.
Authors: Chi-Sheng Chen, Guan-Ying Chen, Dong Zhou, Di Jiang, Dai-Shi Chen
Abstract: Food classification is the foundation for developing food vision tasks and plays a key role in the burgeoning field of computational nutrition. Due to the complexity of food requiring fine-grained classification, recent academic research mainly modifies Convolutional Neural Networks (CNNs) and/or Vision Transformers (ViTs) to perform food category classification. However, to learn fine-grained features, the CNN backbone needs additional structural design, whereas ViT, containing the self-attention module, has increased computational complexity. In recent months, a new Sequence State Space (S4) model, through a Selection mechanism and computation with a Scan (S6), colloquially termed Mamba, has demonstrated superior performance and computation efficiency compared to the Transformer architecture. The VMamba model, which incorporates the Mamba mechanism into image tasks (such as classification), currently establishes the state-of-the-art (SOTA) on the ImageNet dataset. In this research, we introduce an academically underestimated food dataset CNFOOD-241, and pioneer the integration of a residual learning framework within the VMamba model to concurrently harness both global and local state features inherent in the original VMamba architectural design. The research results show that VMamba surpasses current SOTA models in fine-grained and food classification. The proposed Res-VMamba further improves the classification accuracy to 79.54\% without pretrained weight. Our findings elucidate that our proposed methodology establishes a new benchmark for SOTA performance in food recognition on the CNFOOD-241 dataset. The code can be obtained on GitHub: https://github.com/ChiShengChen/ResVMamba.
Authors: Zhiying Leng, Tolga Birdal, Xiaohui Liang, Federico Tombari
Abstract: 3D shape generation from text is a fundamental task in 3D representation learning. The text-shape pairs exhibit a hierarchical structure, where a general text like ``chair" covers all 3D shapes of the chair, while more detailed prompts refer to more specific shapes. Furthermore, both text and 3D shapes are inherently hierarchical structures. However, existing Text2Shape methods, such as SDFusion, do not exploit that. In this work, we propose HyperSDFusion, a dual-branch diffusion model that generates 3D shapes from a given text. Since hyperbolic space is suitable for handling hierarchical data, we propose to learn the hierarchical representations of text and 3D shapes in hyperbolic space. First, we introduce a hyperbolic text-image encoder to learn the sequential and multi-modal hierarchical features of text in hyperbolic space. In addition, we design a hyperbolic text-graph convolution module to learn the hierarchical features of text in hyperbolic space. In order to fully utilize these text features, we introduce a dual-branch structure to embed text features in 3D feature space. At last, to endow the generated 3D shapes with a hierarchical structure, we devise a hyperbolic hierarchical loss. Our method is the first to explore the hyperbolic hierarchical representation for text-to-shape generation. Experimental results on the existing text-to-shape paired dataset, Text2Shape, achieved state-of-the-art results. We release our implementation under HyperSDFusion.github.io.
Authors: Sangmin Lee, Bolin Lai, Fiona Ryan, Bikram Boote, James M. Rehg
Abstract: Understanding social interactions involving both verbal and non-verbal cues is essential for effectively interpreting social situations. However, most prior works on multimodal social cues focus predominantly on single-person behaviors or rely on holistic visual representations that are not aligned to utterances in multi-party environments. Consequently, they are limited in modeling the intricate dynamics of multi-party interactions. In this paper, we introduce three new challenging tasks to model the fine-grained dynamics between multiple people: speaking target identification, pronoun coreference resolution, and mentioned player prediction. We contribute extensive data annotations to curate these new challenges in social deduction game settings. Furthermore, we propose a novel multimodal baseline that leverages densely aligned language-visual representations by synchronizing visual features with their corresponding utterances. This facilitates concurrently capturing verbal and non-verbal cues pertinent to social reasoning. Experiments demonstrate the effectiveness of the proposed approach with densely aligned multimodal representations in modeling fine-grained social interactions. Project website: https://sangmin-git.github.io/projects/MMSI.
Authors: Zhiqiang Pang, Hong Wang, Qi Xie, Deyu Meng, Zongben Xu
Abstract: Exploring and modeling rain generation mechanism is critical for augmenting paired data to ease training of rainy image processing models. Against this task, this study proposes a novel deep learning based rain generator, which fully takes the physical generation mechanism underlying rains into consideration and well encodes the learning of the fundamental rain factors (i.e., shape, orientation, length, width and sparsity) explicitly into the deep network. Its significance lies in that the generator not only elaborately design essential elements of the rain to simulate expected rains, like conventional artificial strategies, but also finely adapt to complicated and diverse practical rainy images, like deep learning methods. By rationally adopting filter parameterization technique, we first time achieve a deep network that is finely controllable with respect to rain factors and able to learn the distribution of these factors purely from data. Our unpaired generation experiments demonstrate that the rain generated by the proposed rain generator is not only of higher quality, but also more effective for deraining and downstream tasks compared to current state-of-the-art rain generation methods. Besides, the paired data augmentation experiments, including both in-distribution and out-of-distribution (OOD), further validate the diversity of samples generated by our model for in-distribution deraining and OOD generalization tasks.
Authors: Dimitrios Karageorgiou, Giorgos Kordopatis-Zilos, Symeon Papadopoulos
Abstract: In this work, we introduce OMG-Fuser, a fusion transformer-based network designed to extract information from various forensic signals to enable robust image forgery detection and localization. Our approach can operate with an arbitrary number of forensic signals and leverages object information for their analysis -- unlike previous methods that rely on fusion schemes with few signals and often disregard image semantics. To this end, we design a forensic signal stream composed of a transformer guided by an object attention mechanism, associating patches that depict the same objects. In that way, we incorporate object-level information from the image. Each forensic signal is processed by a different stream that adapts to its peculiarities. A token fusion transformer efficiently aggregates the outputs of an arbitrary number of network streams and generates a fused representation for each image patch. We assess two fusion variants on top of the proposed approach: (i) score-level fusion that fuses the outputs of multiple image forensics algorithms and (ii) feature-level fusion that fuses low-level forensic traces directly. Both variants exceed state-of-the-art performance on seven datasets for image forgery detection and localization, with a relative average improvement of 12.1% and 20.4% in terms of F1. Our model is robust against traditional and novel forgery attacks and can be expanded with new signals without training from scratch. Our code is publicly available at: https://github.com/mever-team/omgfuser
Authors: Jorgen Cani, Ioannis Mademlis, Adamantia Anna Rebolledo Chrysochoou, Georgios Th. Papadopoulos
Abstract: Illicit object detection is a critical task performed at various high-security locations, including airports, train stations, subways, and ports. The continuous and tedious work of examining thousands of X-ray images per hour can be mentally taxing. Thus, Deep Neural Networks (DNNs) can be used to automate the X-ray image analysis process, improve efficiency and alleviate the security officers' inspection burden. The neural architectures typically utilized in relevant literature are Convolutional Neural Networks (CNNs), with Vision Transformers (ViTs) rarely employed. In order to address this gap, this paper conducts a comprehensive evaluation of relevant ViT architectures on illicit item detection in X-ray images. This study utilizes both Transformer and hybrid backbones, such as SWIN and NextViT, and detectors, such as DINO and RT-DETR. The results demonstrate the remarkable accuracy of the DINO Transformer detector in the low-data regime, the impressive real-time performance of YOLOv8, and the effectiveness of the hybrid NextViT backbone.
Authors: Bo Wang, Jian Li, Yang Yu, Li Liu, Zhenping Sun, Dewen Hu
Abstract: Considering the complementarity of scene flow estimation in the spatial domain's focusing capability and 3D object tracking in the temporal domain's coherence, this study aims to address a comprehensive new task that can simultaneously capture fine-grained and long-term 3D motion in an online manner: long-term scene flow estimation (LSFE). We introduce SceneTracker, a novel learning-based LSFE network that adopts an iterative approach to approximate the optimal trajectory. Besides, it dynamically indexes and constructs appearance and depth correlation features simultaneously and employs the Transformer to explore and utilize long-range connections within and between trajectories. With detailed experiments, SceneTracker shows superior capabilities in handling 3D spatial occlusion and depth noise interference, highly tailored to the LSFE task's needs. The code for SceneTracker is available at https://github.com/wwsource/SceneTracker.
Authors: Xiaorui Huang, Gen Luo, Chaoyang Zhu, Bo Tong, Yiyi Zhou, Xiaoshuai Sun, Rongrong Ji
Abstract: Recently, Segment Anything Model (SAM) has become a research hotspot in the fields of multimedia and computer vision, which exhibits powerful yet versatile capabilities on various (un) conditional image segmentation tasks. Although SAM can support different types of segmentation prompts, we note that, compared to point- and box-guided segmentations, it performs much worse on text-instructed tasks, e.g., referring image segmentation (RIS). In this paper, we argue that deep text instruction tuning is key to mitigate such shortcoming caused by the shallow fusion scheme in its default light-weight mask decoder. To address this issue, we propose two simple yet effective deep instruction tuning (DIT) methods for SAM, one is end-to-end and the other is layer-wise. With minimal modifications, DITs can directly transform the image encoder of SAM as a stand-alone vision-language learner in contrast to building another deep fusion branch, maximizing the benefit of its superior segmentation capability. Extensive experiments on three highly competitive benchmark datasets of RIS show that a simple end-to-end DIT can improve SAM by a large margin, while the layer-wise DIT can further boost the performance to state-of-the-art with much less data and training expenditures. Our code is released at: https://github.com/wysnzzzz/DIT.
Authors: Quanwei Liu, Yanni Dong, Tao Huang, Lefei Zhang, Bo Du
Abstract: Hyperspectral image (HSI) classification techniques have been intensively studied and a variety of models have been developed. However, these HSI classification models are confined to pocket models and unrealistic ways of dataset partitioning. The former limits the generalization performance of the model and the latter is partitioned leading to inflated model evaluation metrics, which results in plummeting model performance in the real world. Therefore, we propose a universal knowledge embedded contrastive learning framework (KnowCL) for supervised, unsupervised, and semisupervised HSI classification, which largely closes the gap between HSI classification models between pocket models and standard vision backbones. We present a new HSI processing pipeline in conjunction with a range of data transformation and augmentation techniques that provide diverse data representations and realistic data partitioning. The proposed framework based on this pipeline is compatible with all kinds of backbones and can fully exploit labeled and unlabeled samples with the expected training time. Furthermore, we design a new loss function, which can adaptively fuse the supervised loss and unsupervised loss, enhancing the learning performance. This proposed new classification paradigm shows great potential in exploring for HSI classification technology. The code can be accessed at \url{https://github.com/quanweiliu/KnowCL}.
Authors: Maryam Ahmed, Tooba Bibi, Rizwan Ahmed Khan, Sidra Nasir
Abstract: The Deep learning (DL) models for diagnosing breast cancer from mammographic images often operate as "black boxes", making it difficult for healthcare professionals to trust and understand their decision-making processes. The study presents an integrated framework combining Convolutional Neural Networks (CNNs) and Explainable Artificial Intelligence (XAI) for the enhanced diagnosis of breast cancer using the CBIS-DDSM dataset. The methodology encompasses an elaborate data preprocessing pipeline and advanced data augmentation techniques to counteract dataset limitations and transfer learning using pre-trained networks such as VGG-16, Inception-V3 and ResNet was employed. A focal point of our study is the evaluation of XAI's effectiveness in interpreting model predictions, highlighted by utilizing the Hausdorff measure to assess the alignment between AI-generated explanations and expert annotations quantitatively. This approach is critical for XAI in promoting trustworthiness and ethical fairness in AI-assisted diagnostics. The findings from our research illustrate the effective collaboration between CNNs and XAI in advancing diagnostic methods for breast cancer, thereby facilitating a more seamless integration of advanced AI technologies within clinical settings. By enhancing the interpretability of AI driven decisions, this work lays the groundwork for improved collaboration between AI systems and medical practitioners, ultimately enriching patient care. Furthermore, the implications of our research extended well beyond the current methodologies. It encourages further research into how to combine multimodal data and improve AI explanations to meet the needs of clinical practice.
Authors: Zijin Yang, Kai Zeng, Kejiang Chen, Han Fang, Weiming Zhang, Nenghai Yu
Abstract: Ethical concerns surrounding copyright protection and inappropriate content generation pose challenges for the practical implementation of diffusion models. One effective solution involves watermarking the generated images. However, existing methods often compromise the model performance or require additional training, which is undesirable for operators and users. To address this issue, we propose Gaussian Shading, a diffusion model watermarking technique that is both performance-lossless and training-free, while serving the dual purpose of copyright protection and tracing of offending content. Our watermark embedding is free of model parameter modifications and thus is plug-and-play. We map the watermark to latent representations following a standard Gaussian distribution, which is indistinguishable from latent representations obtained from the non-watermarked diffusion model. Therefore we can achieve watermark embedding with lossless performance, for which we also provide theoretical proof. Furthermore, since the watermark is intricately linked with image semantics, it exhibits resilience to lossy processing and erasure attempts. The watermark can be extracted by Denoising Diffusion Implicit Models (DDIM) inversion and inverse sampling. We evaluate Gaussian Shading on multiple versions of Stable Diffusion, and the results demonstrate that Gaussian Shading not only is performance-lossless but also outperforms existing methods in terms of robustness.
Authors: Junbo Qiao, Wei Li, Haizhen Xie, Hanting Chen, Yunshuai Zhou, Zhijun Tu, Jie Hu, Shaohui Lin
Abstract: Transformer is leading a trend in the field of image processing. Despite the great success that existing lightweight image processing transformers have achieved, they are tailored to FLOPs or parameters reduction, rather than practical inference acceleration. In this paper, we present a latency-aware image processing transformer, termed LIPT. We devise the low-latency proportion LIPT block that substitutes memory-intensive operators with the combination of self-attention and convolutions to achieve practical speedup. Specifically, we propose a novel non-volatile sparse masking self-attention (NVSM-SA) that utilizes a pre-computing sparse mask to capture contextual information from a larger window with no extra computation overload. Besides, a high-frequency reparameterization module (HRM) is proposed to make LIPT block reparameterization friendly, which improves the model's detail reconstruction capability. Extensive experiments on multiple image processing tasks (e.g., image super-resolution (SR), JPEG artifact reduction, and image denoising) demonstrate the superiority of LIPT on both latency and PSNR. LIPT achieves real-time GPU inference with state-of-the-art performance on multiple image SR benchmarks.
Authors: Yijia Chen, Pinghua Chen, Xiangxin Zhou, Yingtie Lei, Ziyang Zhou, Mingxian Li
Abstract: In the field of computer vision, visible light images often exhibit low contrast in low-light conditions, presenting a significant challenge. While infrared imagery provides a potential solution, its utilization entails high costs and practical limitations. Recent advancements in deep learning, particularly the deployment of Generative Adversarial Networks (GANs), have facilitated the transformation of visible light images to infrared images. However, these methods often experience unstable training phases and may produce suboptimal outputs. To address these issues, we propose a novel end-to-end Transformer-based model that efficiently converts visible light images into high-fidelity infrared images. Initially, the Texture Mapping Module and Color Perception Adapter collaborate to extract texture and color features from the visible light image. The Dynamic Fusion Aggregation Module subsequently integrates these features. Finally, the transformation into an infrared image is refined through the synergistic action of the Color Perception Adapter and the Enhanced Perception Attention mechanism. Comprehensive benchmarking experiments confirm that our model outperforms existing methods, producing infrared images of markedly superior quality, both qualitatively and quantitatively. Furthermore, the proposed model enables more effective downstream applications for infrared images than other methods.
Authors: Bin Wang, Fei Deng, Peifan Jiang, Shuang Wang, Xiao Han, Zhixuan Zhang
Abstract: Low-dose computed tomography (LDCT) has become the technology of choice for diagnostic medical imaging, given its lower radiation dose compared to standard CT, despite increasing image noise and potentially affecting diagnostic accuracy. To address this, advanced deep learning-based LDCT denoising algorithms have been developed, primarily using Convolutional Neural Networks (CNNs) or Transformer Networks with the Unet architecture. This architecture enhances image detail by integrating feature maps from the encoder and decoder via skip connections. However, current methods often overlook enhancements to the Unet architecture itself, focusing instead on optimizing encoder and decoder structures. This approach can be problematic due to the significant differences in feature map characteristics between the encoder and decoder, where simple fusion strategies may not effectively reconstruct images.In this paper, we introduce WiTUnet, a novel LDCT image denoising method that utilizes nested, dense skip pathways instead of traditional skip connections to improve feature integration. WiTUnet also incorporates a windowed Transformer structure to process images in smaller, non-overlapping segments, reducing computational load. Additionally, the integration of a Local Image Perception Enhancement (LiPe) module in both the encoder and decoder replaces the standard multi-layer perceptron (MLP) in Transformers, enhancing local feature capture and representation. Through extensive experimental comparisons, WiTUnet has demonstrated superior performance over existing methods in key metrics such as Peak Signal-to-Noise Ratio (PSNR), Structural Similarity (SSIM), and Root Mean Square Error (RMSE), significantly improving noise removal and image quality.
Authors: Song Xia, Yu Yi, Xudong Jiang, Henghui Ding
Abstract: Randomized Smoothing (RS) has been proven a promising method for endowing an arbitrary image classifier with certified robustness. However, the substantial uncertainty inherent in the high-dimensional isotropic Gaussian noise imposes the curse of dimensionality on RS. Specifically, the upper bound of ${\ell_2}$ certified robustness radius provided by RS exhibits a diminishing trend with the expansion of the input dimension $d$, proportionally decreasing at a rate of $1/\sqrt{d}$. This paper explores the feasibility of providing ${\ell_2}$ certified robustness for high-dimensional input through the utilization of dual smoothing in the lower-dimensional space. The proposed Dual Randomized Smoothing (DRS) down-samples the input image into two sub-images and smooths the two sub-images in lower dimensions. Theoretically, we prove that DRS guarantees a tight ${\ell_2}$ certified robustness radius for the original input and reveal that DRS attains a superior upper bound on the ${\ell_2}$ robustness radius, which decreases proportionally at a rate of $(1/\sqrt m + 1/\sqrt n )$ with $m+n=d$. Extensive experiments demonstrate the generalizability and effectiveness of DRS, which exhibits a notable capability to integrate with established methodologies, yielding substantial improvements in both accuracy and ${\ell_2}$ certified robustness baselines of RS on the CIFAR-10 and ImageNet datasets. Code is available at https://github.com/xiasong0501/DRS.
Authors: Rasel Ahmed Bhuiyan, Adam Czajka
Abstract: Post-mortem iris recognition is an emerging application of iris-based human identification in a forensic setup. One factor that may be useful in conditioning iris recognition methods is the tissue decomposition level, which is correlated with the post-mortem interval (PMI), i.g., the number of hours that have elapsed since death. PMI, however, is not always available, and its precise estimation remains one of the core challenges in forensic examination. This paper presents the first known to us method of PMI estimation directly from forensic iris images. To assess the feasibility of the iris-based PMI estimation, convolutional neural networks-based models (VGG19, DenseNet121, ResNet152, and Inception_v3) were trained to predict the PMI from (a) near-infrared (NIR), (b) visible (RGB), and (c) multispectral forensic iris images. Models were evaluated following a 10-fold cross-validation in (S1) sample-disjoint, (S2) subject-disjoint, and (S3) cross-dataset scenarios. We found that using the multispectral data offers a spectacularly low mean absolute error (MAE) of approximately 3.5 hours in scenario (S1), a bit worse MAE of approximately 17.5 hours in scenario (S2), and an MAE of approximately 69.0 hours of in the scenario (S3). This suggests that if the environmental conditions are favorable (e.g., bodies are kept in low temperatures), forensic iris images provide features that are indicative of the PMI and can be automatically estimated. The source codes and model weights are made available with the paper.
Authors: Zhanjie Zhang, Quanwei Zhang, Huaizhong Lin, Wei Xing, Juncheng Mo, Shuaicheng Huang, Jinheng Xie, Guangyuan Li, Junsheng Luan, Lei Zhao, Dalong Zhang, Lixia Chen
Abstract: Artistic style transfer aims to transfer the learned artistic style onto an arbitrary content image, generating artistic stylized images. Existing generative adversarial network-based methods fail to generate highly realistic stylized images and always introduce obvious artifacts and disharmonious patterns. Recently, large-scale pre-trained diffusion models opened up a new way for generating highly realistic artistic stylized images. However, diffusion model-based methods generally fail to preserve the content structure of input content images well, introducing some undesired content structure and style patterns. To address the above problems, we propose a novel pre-trained diffusion-based artistic style transfer method, called LSAST, which can generate highly realistic artistic stylized images while preserving the content structure of input content images well, without bringing obvious artifacts and disharmonious style patterns. Specifically, we introduce a Step-aware and Layer-aware Prompt Space, a set of learnable prompts, which can learn the style information from the collection of artworks and dynamically adjusts the input images' content structure and style pattern. To train our prompt space, we propose a novel inversion method, called Step-ware and Layer-aware Prompt Inversion, which allows the prompt space to learn the style information of the artworks collection. In addition, we inject a pre-trained conditional branch of ControlNet into our LSAST, which further improved our framework's ability to maintain content structure. Extensive experiments demonstrate that our proposed method can generate more highly realistic artistic stylized images than the state-of-the-art artistic style transfer methods.
Authors: Longfei Huang, Shupeng Zhong, Xiangyu Wu, Ruoxuan Li
Abstract: This report introduces a solution to the Topic 1 Zero-shot Image Captioning of 2024 NICE : New frontiers for zero-shot Image Captioning Evaluation. In contrast to NICE 2023 datasets, this challenge involves new annotations by humans with significant differences in caption style and content. Therefore, we enhance image captions effectively through retrieval augmentation and caption grading methods. At the data level, we utilize high-quality captions generated by image caption models as training data to address the gap in text styles. At the model level, we employ OFA (a large-scale visual-language pre-training model based on handcrafted templates) to perform the image captioning task. Subsequently, we propose caption-level strategy for the high-quality caption data generated by the image caption models and integrate them with retrieval augmentation strategy into the template to compel the model to generate higher quality, more matching, and semantically enriched captions based on the retrieval augmentation prompts. Our approach achieves a CIDEr score of 234.11.
Authors: Ganesh Sistu, Senthil Yogamani
Abstract: Object detection is a mature problem in autonomous driving with pedestrian detection being one of the first deployed algorithms. It has been comprehensively studied in the literature. However, object detection is relatively less explored for fisheye cameras used for surround-view near field sensing. The standard bounding box representation fails in fisheye cameras due to heavy radial distortion, particularly in the periphery. To mitigate this, we explore extending the standard object detection output representation of bounding box. We design rotated bounding boxes, ellipse, generic polygon as polar arc/angle representations and define an instance segmentation mIOU metric to analyze these representations. The proposed model FisheyeDetNet with polygon outperforms others and achieves a mAP score of 49.5 % on Valeo fisheye surround-view dataset for automated driving applications. This dataset has 60K images captured from 4 surround-view cameras across Europe, North America and Asia. To the best of our knowledge, this is the first detailed study on object detection on fisheye cameras for autonomous driving scenarios.
Authors: Bowen Qu, Xiaoyu Liang, Shangkun Sun, Wei Gao
Abstract: The recent advancements in Text-to-Video Artificial Intelligence Generated Content (AIGC) have been remarkable. Compared with traditional videos, the assessment of AIGC videos encounters various challenges: visual inconsistency that defy common sense, discrepancies between content and the textual prompt, and distribution gap between various generative models, etc. Target at these challenges, in this work, we categorize the assessment of AIGC video quality into three dimensions: visual harmony, video-text consistency, and domain distribution gap. For each dimension, we design specific modules to provide a comprehensive quality assessment of AIGC videos. Furthermore, our research identifies significant variations in visual quality, fluidity, and style among videos generated by different text-to-video models. Predicting the source generative model can make the AIGC video features more discriminative, which enhances the quality assessment performance. The proposed method was used in the third-place winner of the NTIRE 2024 Quality Assessment for AI-Generated Content - Track 2 Video, demonstrating its effectiveness. Code will be available at https://github.com/Coobiw/TriVQA.
Authors: Haniyeh Ehsani Oskouie, Mohammad-Shahram Moin, Shohreh Kasaei
Abstract: Deep neural networks have made significant advancements in accurately estimating scene flow using point clouds, which is vital for many applications like video analysis, action recognition, and navigation. Robustness of these techniques, however, remains a concern, particularly in the face of adversarial attacks that have been proven to deceive state-of-the-art deep neural networks in many domains. Surprisingly, the robustness of scene flow networks against such attacks has not been thoroughly investigated. To address this problem, the proposed approach aims to bridge this gap by introducing adversarial white-box attacks specifically tailored for scene flow networks. Experimental results show that the generated adversarial examples obtain up to 33.7 relative degradation in average end-point error on the KITTI and FlyingThings3D datasets. The study also reveals the significant impact that attacks targeting point clouds in only one dimension or color channel have on average end-point error. Analyzing the success and failure of these attacks on the scene flow networks and their 2D optical flow network variants show a higher vulnerability for the optical flow networks.
Authors: Wenhao Wang, Yifan Sun, Zhentao Tan, Yi Yang
Abstract: This paper explores in-context learning for image copy detection (ICD), i.e., prompting an ICD model to identify replicated images with new tampering patterns without the need for additional training. The prompts (or the contexts) are from a small set of image-replica pairs that reflect the new patterns and are used at inference time. Such in-context ICD has good realistic value, because it requires no fine-tuning and thus facilitates fast reaction against the emergence of unseen patterns. To accommodate the "seen $\rightarrow$ unseen" generalization scenario, we construct the first large-scale pattern dataset named AnyPattern, which has the largest number of tamper patterns ($90$ for training and $10$ for testing) among all the existing ones. We benchmark AnyPattern with popular ICD methods and reveal that existing methods barely generalize to novel patterns. We further propose a simple in-context ICD method named ImageStacker. ImageStacker learns to select the most representative image-replica pairs and employs them as the pattern prompts in a stacking manner (rather than the popular concatenation manner). Experimental results show (1) training with our large-scale dataset substantially benefits pattern generalization ($+26.66 \%$ $\mu AP$), (2) the proposed ImageStacker facilitates effective in-context ICD (another round of $+16.75 \%$ $\mu AP$), and (3) AnyPattern enables in-context ICD, i.e., without such a large-scale dataset, in-context learning does not emerge even with our ImageStacker. Beyond the ICD task, we also demonstrate how AnyPattern can benefit artists, i.e., the pattern retrieval method trained on AnyPattern can be generalized to identify style mimicry by text-to-image models. The project is publicly available at https://anypattern.github.io.
Authors: Yonghao Dang, Jianqin Yin, Liyuan Liu, Pengxiang Ding, Yuan Sun, Yanzhu Hu
Abstract: Multi-person pose estimation (MPPE) presents a formidable yet crucial challenge in computer vision. Most existing methods predominantly concentrate on isolated interaction either between instances or joints, which is inadequate for scenarios demanding concurrent localization of both instances and joints. This paper introduces a novel CNN-based single-stage method, named Dual-path Hierarchical Relation Network (DHRNet), to extract instance-to-joint and joint-to-instance interactions concurrently. Specifically, we design a dual-path interaction modeling module (DIM) that strategically organizes cross-instance and cross-joint interaction modeling modules in two complementary orders, enriching interaction information by integrating merits from different correlation modeling branches. Notably, DHRNet excels in joint localization by leveraging information from other instances and joints. Extensive evaluations on challenging datasets, including COCO, CrowdPose, and OCHuman datasets, showcase DHRNet's state-of-the-art performance. The code will be released at https://github.com/YHDang/dhrnet-multi-pose-estimation.
URLs: https://github.com/YHDang/dhrnet-multi-pose-estimation.
Authors: Hongyun Yu, Zhan Qu, Qihang Yu, Jianchuan Chen, Zhonghua Jiang, Zhiwen Chen, Shengyu Zhang, Jimin Xu, Fei Wu, Chengfei Lv, Gang Yu
Abstract: Recent works on audio-driven talking head synthesis using Neural Radiance Fields (NeRF) have achieved impressive results. However, due to inadequate pose and expression control caused by NeRF implicit representation, these methods still have some limitations, such as unsynchronized or unnatural lip movements, and visual jitter and artifacts. In this paper, we propose GaussianTalker, a novel method for audio-driven talking head synthesis based on 3D Gaussian Splatting. With the explicit representation property of 3D Gaussians, intuitive control of the facial motion is achieved by binding Gaussians to 3D facial models. GaussianTalker consists of two modules, Speaker-specific Motion Translator and Dynamic Gaussian Renderer. Speaker-specific Motion Translator achieves accurate lip movements specific to the target speaker through universalized audio feature extraction and customized lip motion generation. Dynamic Gaussian Renderer introduces Speaker-specific BlendShapes to enhance facial detail representation via a latent pose, delivering stable and realistic rendered videos. Extensive experimental results suggest that GaussianTalker outperforms existing state-of-the-art methods in talking head synthesis, delivering precise lip synchronization and exceptional visual quality. Our method achieves rendering speeds of 130 FPS on NVIDIA RTX4090 GPU, significantly exceeding the threshold for real-time rendering performance, and can potentially be deployed on other hardware platforms.
Authors: Yaofeng Xie, Lingwei Kong, Kai Chen, Ziqiang Zheng, Xiao Yu, Zhibin Yu, Bing Zheng
Abstract: Learning-based underwater image enhancement (UIE) methods have made great progress. However, the lack of large-scale and high-quality paired training samples has become the main bottleneck hindering the development of UIE. The inter-frame information in underwater videos can accelerate or optimize the UIE process. Thus, we constructed the first large-scale high-resolution underwater video enhancement benchmark (UVEB) to promote the development of underwater vision.It contains 1,308 pairs of video sequences and more than 453,000 high-resolution with 38\% Ultra-High-Definition (UHD) 4K frame pairs. UVEB comes from multiple countries, containing various scenes and video degradation types to adapt to diverse and complex underwater environments. We also propose the first supervised underwater video enhancement method, UVE-Net. UVE-Net converts the current frame information into convolutional kernels and passes them to adjacent frames for efficient inter-frame information exchange. By fully utilizing the redundant degraded information of underwater videos, UVE-Net completes video enhancement better. Experiments show the effective network design and good performance of UVE-Net.
Authors: Anahita Fathi Kazerooni, Nastaran Khalili, Deep Gandhi, Xinyang Liu, Zhifan Jiang, Syed Muhammed Anwar, Jake Albrecht, Maruf Adewole, Udunna Anazodo, Hannah Anderson, Sina Bagheri, Ujjwal Baid, Timothy Bergquist, Austin J. Borja, Evan Calabrese, Verena Chung, Gian-Marco Conte, Farouk Dako, James Eddy, Ivan Ezhov, Ariana Familiar, Keyvan Farahani, Anurag Gottipati, Debanjan Haldar, Shuvanjan Haldar, Juan Eugenio Iglesias, Anastasia Janas, Elaine Johansen, Blaise V Jones, Neda Khalili, Florian Kofler, Dominic LaBella, Hollie Anne Lai, Koen Van Leemput, Hongwei Bran Li, Nazanin Maleki, Aaron S McAllister, Zeke Meier, Bjoern Menze, Ahmed W Moawad, Khanak K Nandolia, Julija Pavaine, Marie Piraud, Tina Poussaint, Sanjay P Prabhu, Zachary Reitman, Andres Rodriguez, Jeffrey D Rudie, Mariana Sanchez-Montano, Ibraheem Salman Shaikh, Lubdha M. Shah, Nakul Sheth, Russel Taki Shinohara, Wenxin Tu, Karthik Viswanathan, Chunhao Wang, Jeffrey B Ware, Benedikt Wiestler, Walter Wiggins, Anna Zapaishchykova, Mariam Aboian, Miriam Bornhorst, Peter de Blank, Michelle Deutsch, Maryam Fouladi, Lindsey Hoffman, Benjamin Kann, Margot Lazow, Leonie Mikael, Ali Nabavizadeh, Roger Packer, Spyridon Bakas, Adam Resnick, Brian Rood, Arastoo Vossough, Marius George Linguraru
Abstract: Pediatric tumors of the central nervous system are the most common cause of cancer-related death in children. The five-year survival rate for high-grade gliomas in children is less than 20%. Due to their rarity, the diagnosis of these entities is often delayed, their treatment is mainly based on historic treatment concepts, and clinical trials require multi-institutional collaborations. Here we present the CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs challenge, focused on pediatric brain tumors with data acquired across multiple international consortia dedicated to pediatric neuro-oncology and clinical trials. The CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs challenge brings together clinicians and AI/imaging scientists to lead to faster development of automated segmentation techniques that could benefit clinical trials, and ultimately the care of children with brain tumors.
Authors: Jingyang Lin, Yingda Xia, Jianpeng Zhang, Ke Yan, Le Lu, Jiebo Luo, Ling Zhang
Abstract: Medical Vision-Language Pretraining (Med-VLP) establishes a connection between visual content from medical images and the relevant textual descriptions. Existing Med-VLP methods primarily focus on 2D images depicting a single body part, notably chest X-rays. In this paper, we extend the scope of Med-VLP to encompass 3D images, specifically targeting full-body scenarios, by using a multimodal dataset of CT images and reports. Compared with the 2D counterpart, 3D VLP is required to effectively capture essential semantics from significantly sparser representation in 3D imaging. In this paper, we introduce CT-GLIP (Grounded Language-Image Pretraining with CT scans), a novel method that constructs organ-level image-text pairs to enhance multimodal contrastive learning, aligning grounded visual features with precise diagnostic text. Additionally, we developed an abnormality dictionary to augment contrastive learning with diverse contrastive pairs. Our method, trained on a multimodal CT dataset comprising 44,011 organ-level vision-text pairs from 17,702 patients across 104 organs, demonstrates it can identify organs and abnormalities in a zero-shot manner using natural languages. The performance of CT-GLIP is validated on a separate test set of 1,130 patients, focusing on the 16 most frequent abnormalities across 7 organs. The experimental results show our model's superior performance over the standard CLIP framework across zero-shot and fine-tuning scenarios, using both CNN and ViT architectures.
Authors: Qinghe Wang, Baolu Li, Xiaomin Li, Bing Cao, Liqian Ma, Huchuan Lu, Xu Jia
Abstract: Recent advances in text-to-image models have opened new frontiers in human-centric generation. However, these models cannot be directly employed to generate images with consistent newly coined identities. In this work, we propose CharacterFactory, a framework that allows sampling new characters with consistent identities in the latent space of GANs for diffusion models. More specifically, we consider the word embeddings of celeb names as ground truths for the identity-consistent generation task and train a GAN model to learn the mapping from a latent space to the celeb embedding space. In addition, we design a context-consistent loss to ensure that the generated identity embeddings can produce identity-consistent images in various contexts. Remarkably, the whole model only takes 10 minutes for training, and can sample infinite characters end-to-end during inference. Extensive experiments demonstrate excellent performance of the proposed CharacterFactory on character creation in terms of identity consistency and editability. Furthermore, the generated characters can be seamlessly combined with the off-the-shelf image/video/3D diffusion models. We believe that the proposed CharacterFactory is an important step for identity-consistent character generation. Project page is available at: https://qinghew.github.io/CharacterFactory/.
Authors: Melih Yazgan, Thomas Graf, Min Liu, Tobias Fleck, J. Marius Zoellner
Abstract: This survey analyzes intermediate fusion methods in collaborative perception for autonomous driving, categorized by real-world challenges. We examine various methods, detailing their features and the evaluation metrics they employ. The focus is on addressing challenges like transmission efficiency, localization errors, communication disruptions, and heterogeneity. Moreover, we explore strategies to counter adversarial attacks and defenses, as well as approaches to adapt to domain shifts. The objective is to present an overview of how intermediate fusion methods effectively meet these diverse challenges, highlighting their role in advancing the field of collaborative perception in autonomous driving.
Authors: Yifan Zhao, Zhenyu Liang, Zhichao Lu, Ran Cheng
Abstract: As one of the emerging challenges in Automated Machine Learning, the Hardware-aware Neural Architecture Search (HW-NAS) tasks can be treated as black-box multi-objective optimization problems (MOPs). An important application of HW-NAS is real-time semantic segmentation, which plays a pivotal role in autonomous driving scenarios. The HW-NAS for real-time semantic segmentation inherently needs to balance multiple optimization objectives, including model accuracy, inference speed, and hardware-specific considerations. Despite its importance, benchmarks have yet to be developed to frame such a challenging task as multi-objective optimization. To bridge the gap, we introduce a tailored streamline to transform the task of HW-NAS for real-time semantic segmentation into standard MOPs. Building upon the streamline, we present a benchmark test suite, CitySeg/MOP, comprising fifteen MOPs derived from the Cityscapes dataset. The CitySeg/MOP test suite is integrated into the EvoXBench platform to provide seamless interfaces with various programming languages (e.g., Python and MATLAB) for instant fitness evaluations. We comprehensively assessed the CitySeg/MOP test suite on various multi-objective evolutionary algorithms, showcasing its versatility and practicality. Source codes are available at https://github.com/EMI-Group/evoxbench.
Authors: Zhijie Rao, Jingcai Guo, Xiaocheng Lu, Jingming Liang, Jie Zhang, Haozhao Wang, Kang Wei, Xiaofeng Cao
Abstract: Zero-shot learning has consistently yielded remarkable progress via modeling nuanced one-to-one visual-attribute correlation. Existing studies resort to refining a uniform mapping function to align and correlate the sample regions and subattributes, ignoring two crucial issues: 1) the inherent asymmetry of attributes; and 2) the unutilized channel information. This paper addresses these issues by introducing a simple yet effective approach, dubbed Dual Expert Distillation Network (DEDN), where two experts are dedicated to coarse- and fine-grained visual-attribute modeling, respectively. Concretely, one coarse expert, namely cExp, has a complete perceptual scope to coordinate visual-attribute similarity metrics across dimensions, and moreover, another fine expert, namely fExp, consists of multiple specialized subnetworks, each corresponds to an exclusive set of attributes. Two experts cooperatively distill from each other to reach a mutual agreement during training. Meanwhile, we further equip DEDN with a newly designed backbone network, i.e., Dual Attention Network (DAN), which incorporates both region and channel attention information to fully exploit and leverage visual semantic knowledge. Experiments on various benchmark datasets indicate a new state-of-the-art.
Authors: Moritz Sturm, Lorenzo Cerrone, Fred A. Hamprecht
Abstract: Cell tracking remains a pivotal yet challenging task in biomedical research. The full potential of deep learning for this purpose is often untapped due to the limited availability of comprehensive and varied training data sets. In this paper, we present SynCellFactory, a generative cell video augmentation. At the heart of SynCellFactory lies the ControlNet architecture, which has been fine-tuned to synthesize cell imagery with photorealistic accuracy in style and motion patterns. This technique enables the creation of synthetic yet realistic cell videos that mirror the complexity of authentic microscopy time-lapses. Our experiments demonstrate that SynCellFactory boosts the performance of well-established deep learning models for cell tracking, particularly when original training data is sparse.
Authors: Parul Gupta, Munawar Hayat, Abhinav Dhall, Thanh-Toan Do
Abstract: Few-shot image synthesis entails generating diverse and realistic images of novel categories using only a few example images. While multiple recent efforts in this direction have achieved impressive results, the existing approaches are dependent only upon the few novel samples available at test time in order to generate new images, which restricts the diversity of the generated images. To overcome this limitation, we propose Conditional Distribution Modelling (CDM) -- a framework which effectively utilizes Diffusion models for few-shot image generation. By modelling the distribution of the latent space used to condition a Diffusion process, CDM leverages the learnt statistics of the training data to get a better approximation of the unseen class distribution, thereby removing the bias arising due to limited number of few shot samples. Simultaneously, we devise a novel inversion based optimization strategy that further improves the approximated unseen class distribution, and ensures the fidelity of the generated samples to the unseen class. The experimental results on four benchmark datasets demonstrate the effectiveness of our proposed CDM for few-shot generation.
Authors: Chenxi Liu, Gan Sun, Wenqi Liang, Jiahua Dong, Can Qin, Yang Cong
Abstract: Pre-trained large text-to-image (T2I) models with an appropriate text prompt has attracted growing interests in customized images generation field. However, catastrophic forgetting issue make it hard to continually synthesize new user-provided styles while retaining the satisfying results amongst learned styles. In this paper, we propose MuseumMaker, a method that enables the synthesis of images by following a set of customized styles in a never-end manner, and gradually accumulate these creative artistic works as a Museum. When facing with a new customization style, we develop a style distillation loss module to extract and learn the styles of the training data for new image generation. It can minimize the learning biases caused by content of new training images, and address the catastrophic overfitting issue induced by few-shot images. To deal with catastrophic forgetting amongst past learned styles, we devise a dual regularization for shared-LoRA module to optimize the direction of model update, which could regularize the diffusion model from both weight and feature aspects, respectively. Meanwhile, to further preserve historical knowledge from past styles and address the limited representability of LoRA, we consider a task-wise token learning module where a unique token embedding is learned to denote a new style. As any new user-provided style come, our MuseumMaker can capture the nuances of the new styles while maintaining the details of learned styles. Experimental results on diverse style datasets validate the effectiveness of our proposed MuseumMaker method, showcasing its robustness and versatility across various scenarios.
Authors: Jean-Eric Campagne
Abstract: This paper aims to explore the evolution of image denoising in a pedagological way. We briefly review classical methods such as Fourier analysis and wavelet bases, highlighting the challenges they faced until the emergence of neural networks, notably the U-Net, in the 2010s. The remarkable performance of these networks has been demonstrated in studies such as Kadkhodaie et al. (2024). They exhibit adaptability to various image types, including those with fixed regularity, facial images, and bedroom scenes, achieving optimal results and biased towards geometry-adaptive harmonic basis. The introduction of score diffusion has played a crucial role in image generation. In this context, denoising becomes essential as it facilitates the estimation of probability density scores. We discuss the prerequisites for genuine learning of probability densities, offering insights that extend from mathematical research to the implications of universal structures.
Authors: Junfeng Ni, Yixin Chen, Bohan Jing, Nan Jiang, Bin Wang, Bo Dai, Yixin Zhu, Song-Chun Zhu, Siyuan Huang
Abstract: While neural implicit representations have gained popularity in multi-view 3D reconstruction, previous work struggles to yield physically plausible results, thereby limiting their applications in physics-demanding domains like embodied AI and robotics. The lack of plausibility originates from both the absence of physics modeling in the existing pipeline and their inability to recover intricate geometrical structures. In this paper, we introduce PhyRecon, which stands as the first approach to harness both differentiable rendering and differentiable physics simulation to learn implicit surface representations. Our framework proposes a novel differentiable particle-based physical simulator seamlessly integrated with the neural implicit representation. At its core is an efficient transformation between SDF-based implicit representation and explicit surface points by our proposed algorithm, Surface Points Marching Cubes (SP-MC), enabling differentiable learning with both rendering and physical losses. Moreover, we model both rendering and physical uncertainty to identify and compensate for the inconsistent and inaccurate monocular geometric priors. The physical uncertainty additionally enables a physics-guided pixel sampling to enhance the learning of slender structures. By amalgamating these techniques, our model facilitates efficient joint modeling with appearance, geometry, and physics. Extensive experiments demonstrate that PhyRecon significantly outperforms all state-of-the-art methods in terms of reconstruction quality. Our reconstruction results also yield superior physical stability, verified by Isaac Gym, with at least a 40% improvement across all datasets, opening broader avenues for future physics-based applications.
Authors: Ye Fang, Zeyi Sun, Tong Wu, Jiaqi Wang, Ziwei Liu, Gordon Wetzstein, Dahua Lin
Abstract: Physically realistic materials are pivotal in augmenting the realism of 3D assets across various applications and lighting conditions. However, existing 3D assets and generative models often lack authentic material properties. Manual assignment of materials using graphic software is a tedious and time-consuming task. In this paper, we exploit advancements in Multimodal Large Language Models (MLLMs), particularly GPT-4V, to present a novel approach, Make-it-Real: 1) We demonstrate that GPT-4V can effectively recognize and describe materials, allowing the construction of a detailed material library. 2) Utilizing a combination of visual cues and hierarchical text prompts, GPT-4V precisely identifies and aligns materials with the corresponding components of 3D objects. 3) The correctly matched materials are then meticulously applied as reference for the new SVBRDF material generation according to the original diffuse map, significantly enhancing their visual authenticity. Make-it-Real offers a streamlined integration into the 3D content creation workflow, showcasing its utility as an essential tool for developers of 3D assets.
Authors: Jaime Spencer, Fabio Tosi, Matteo Poggi, Ripudaman Singh Arora, Chris Russell, Simon Hadfield, Richard Bowden, GuangYuan Zhou, ZhengXin Li, Qiang Rao, YiPing Bao, Xiao Liu, Dohyeong Kim, Jinseong Kim, Myunghyun Kim, Mykola Lavreniuk, Rui Li, Qing Mao, Jiang Wu, Yu Zhu, Jinqiu Sun, Yanning Zhang, Suraj Patni, Aradhye Agarwal, Chetan Arora, Pihai Sun, Kui Jiang, Gang Wu, Jian Liu, Xianming Liu, Junjun Jiang, Xidan Zhang, Jianing Wei, Fangjun Wang, Zhiming Tan, Jiabao Wang, Albert Luginov, Muhammad Shahzad, Seyed Hosseini, Aleksander Trajcevski, James H. Elder
Abstract: This paper discusses the results of the third edition of the Monocular Depth Estimation Challenge (MDEC). The challenge focuses on zero-shot generalization to the challenging SYNS-Patches dataset, featuring complex scenes in natural and indoor settings. As with the previous edition, methods can use any form of supervision, i.e. supervised or self-supervised. The challenge received a total of 19 submissions outperforming the baseline on the test set: 10 among them submitted a report describing their approach, highlighting a diffused use of foundational models such as Depth Anything at the core of their method. The challenge winners drastically improved 3D F-Score performance, from 17.51% to 23.72%.
Authors: Lin Xu, Yilin Zhao, Daquan Zhou, Zhijie Lin, See Kiong Ng, Jiashi Feng
Abstract: Vision-language pre-training has significantly elevated performance across a wide range of image-language applications. Yet, the pre-training process for video-related tasks demands exceptionally large computational and data resources, which hinders the progress of video-language models. This paper investigates a straight-forward, highly efficient, and resource-light approach to adapting an existing image-language pre-trained model for dense video understanding. Our preliminary experiments reveal that directly fine-tuning pre-trained image-language models with multiple frames as inputs on video datasets leads to performance saturation or even a drop. Our further investigation reveals that it is largely attributed to the bias of learned high-norm visual features. Motivated by this finding, we propose a simple but effective pooling strategy to smooth the feature distribution along the temporal dimension and thus reduce the dominant impacts from the extreme features. The new model is termed Pooling LLaVA, or PLLaVA in short. PLLaVA achieves new state-of-the-art performance on modern benchmark datasets for both video question-answer and captioning tasks. Notably, on the recent popular VideoChatGPT benchmark, PLLaVA achieves a score of 3.48 out of 5 on average of five evaluated dimensions, exceeding the previous SOTA results from GPT4V (IG-VLM) by 9%. On the latest multi-choice benchmark MVBench, PLLaVA achieves 58.1% accuracy on average across 20 sub-tasks, 14.5% higher than GPT4V (IG-VLM). Code is available at https://pllava.github.io/
Authors: Xinpeng Li, Teng Wang, Jian Zhao, Shuyi Mao, Jinbao Wang, Feng Zheng, Xiaojiang Peng, Xuelong Li
Abstract: Emotion recognition aims to discern the emotional state of subjects within an image, relying on subject-centric and contextual visual cues. Current approaches typically follow a two-stage pipeline: first localize subjects by off-the-shelf detectors, then perform emotion classification through the late fusion of subject and context features. However, the complicated paradigm suffers from disjoint training stages and limited interaction between fine-grained subject-context elements. To address the challenge, we present a single-stage emotion recognition approach, employing a Decoupled Subject-Context Transformer (DSCT), for simultaneous subject localization and emotion classification. Rather than compartmentalizing training stages, we jointly leverage box and emotion signals as supervision to enrich subject-centric feature learning. Furthermore, we introduce DSCT to facilitate interactions between fine-grained subject-context cues in a decouple-then-fuse manner. The decoupled query token--subject queries and context queries--gradually intertwine across layers within DSCT, during which spatial and semantic relations are exploited and aggregated. We evaluate our single-stage framework on two widely used context-aware emotion recognition datasets, CAER-S and EMOTIC. Our approach surpasses two-stage alternatives with fewer parameter numbers, achieving a 3.39% accuracy improvement and a 6.46% average precision gain on CAER-S and EMOTIC datasets, respectively.
Authors: Georgia Baltsou, Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos
Abstract: AI systems rely on extensive training on large datasets to address various tasks. However, image-based systems, particularly those used for demographic attribute prediction, face significant challenges. Many current face image datasets primarily focus on demographic factors such as age, gender, and skin tone, overlooking other crucial facial attributes like hairstyle and accessories. This narrow focus limits the diversity of the data and consequently the robustness of AI systems trained on them. This work aims to address this limitation by proposing a methodology for generating synthetic face image datasets that capture a broader spectrum of facial diversity. Specifically, our approach integrates a systematic prompt formulation strategy, encompassing not only demographics and biometrics but also non-permanent traits like make-up, hairstyle, and accessories. These prompts guide a state-of-the-art text-to-image model in generating a comprehensive dataset of high-quality realistic images and can be used as an evaluation set in face analysis systems. Compared to existing datasets, our proposed dataset proves equally or more challenging in image classification tasks while being much smaller in size.
Authors: Haoyu Wang, Zhilu Zhang, Donglin Di, Shiliang Zhang, Wangmeng Zuo
Abstract: The goal of image-based virtual try-on is to generate an image of the target person naturally wearing the given clothing. However, most existing methods solely focus on the frontal try-on using the frontal clothing. When the views of the clothing and person are significantly inconsistent, particularly when the person's view is non-frontal, the results are unsatisfactory. To address this challenge, we introduce Multi-View Virtual Try-ON (MV-VTON), which aims to reconstruct the dressing results of a person from multiple views using the given clothes. On the one hand, given that single-view clothes provide insufficient information for MV-VTON, we instead employ two images, i.e., the frontal and back views of the clothing, to encompass the complete view as much as possible. On the other hand, the diffusion models that have demonstrated superior abilities are adopted to perform our MV-VTON. In particular, we propose a view-adaptive selection method where hard-selection and soft-selection are applied to the global and local clothing feature extraction, respectively. This ensures that the clothing features are roughly fit to the person's view. Subsequently, we suggest a joint attention block to align and fuse clothing features with person features. Additionally, we collect a MV-VTON dataset, i.e., Multi-View Garment (MVG), in which each person has multiple photos with diverse views and poses. Experiments show that the proposed method not only achieves state-of-the-art results on MV-VTON task using our MVG dataset, but also has superiority on frontal-view virtual try-on task using VITON-HD and DressCode datasets. Codes and datasets will be publicly released at https://github.com/hywang2002/MV-VTON .
Authors: Ethan Tseng, Grace Kuo, Seung-Hwan Baek, Nathan Matsuda, Andrew Maimone, Florian Schiffers, Praneeth Chakravarthula, Qiang Fu, Wolfgang Heidrich, Douglas Lanman, Felix Heide
Abstract: Holographic displays can generate light fields by dynamically modulating the wavefront of a coherent beam of light using a spatial light modulator, promising rich virtual and augmented reality applications. However, the limited spatial resolution of existing dynamic spatial light modulators imposes a tight bound on the diffraction angle. As a result, modern holographic displays possess low \'{e}tendue, which is the product of the display area and the maximum solid angle of diffracted light. The low \'{e}tendue forces a sacrifice of either the field-of-view (FOV) or the display size. In this work, we lift this limitation by presenting neural \'{e}tendue expanders. This new breed of optical elements, which is learned from a natural image dataset, enables higher diffraction angles for ultra-wide FOV while maintaining both a compact form factor and the fidelity of displayed contents to human viewers. With neural \'{e}tendue expanders, we experimentally achieve 64$\times$ \'{e}tendue expansion of natural images in full color, expanding the FOV by an order of magnitude horizontally and vertically, with high-fidelity reconstruction quality (measured in PSNR) over 29 dB on retinal-resolution images.
Authors: Quan Quan, Qingsong Yao, Jun Li, S. Kevin Zhou
Abstract: The success of deep learning methods relies on the availability of well-labeled large-scale datasets. However, for medical images, annotating such abundant training data often requires experienced radiologists and consumes their limited time. Few-shot learning is developed to alleviate this burden, which achieves competitive performances with only several labeled data. However, a crucial yet previously overlooked problem in few-shot learning is about the selection of template images for annotation before learning, which affects the final performance. We herein propose a novel Sample Choosing Policy (SCP) to select "the most worthy" images for annotation, in the context of few-shot medical landmark detection. SCP consists of three parts: 1) Self-supervised training for building a pre-trained deep model to extract features from radiological images, 2) Key Point Proposal for localizing informative patches, and 3) Representative Score Estimation for searching the most representative samples or templates. The advantage of SCP is demonstrated by various experiments on three widely-used public datasets. For one-shot medical landmark detection, its use reduces the mean radial errors on Cephalometric and HandXray datasets by 14.2% (from 3.595mm to 3.083mm) and 35.5% (4.114mm to 2.653mm), respectively.
Authors: Qing Li, Yixin Zhu, Yitao Liang, Ying Nian Wu, Song-Chun Zhu, Siyuan Huang
Abstract: Current learning models often struggle with human-like systematic generalization, particularly in learning compositional rules from limited data and extrapolating them to novel combinations. We introduce the Neural-Symbolic Recursive Machine (NSR), whose core is a Grounded Symbol System (GSS), allowing for the emergence of combinatorial syntax and semantics directly from training data. The NSR employs a modular design that integrates neural perception, syntactic parsing, and semantic reasoning. These components are synergistically trained through a novel deduction-abduction algorithm. Our findings demonstrate that NSR's design, imbued with the inductive biases of equivariance and compositionality, grants it the expressiveness to adeptly handle diverse sequence-to-sequence tasks and achieve unparalleled systematic generalization. We evaluate NSR's efficacy across four challenging benchmarks designed to probe systematic generalization capabilities: SCAN for semantic parsing, PCFG for string manipulation, HINT for arithmetic reasoning, and a compositional machine translation task. The results affirm NSR's superiority over contemporary neural and hybrid models in terms of generalization and transferability.
Authors: Louisa Conwill, Sam English Anthony, Walter J. Scheirer
Abstract: Augmented reality and other photo editing filters are popular methods used to modify faces online. Considering the important role of facial perception in communication, how do we perceive this increasing number of modified faces? In this paper we present the results of six surveys that measure familiarity with different styles of facial filters, perceived strangeness of faces edited with different filters, and ability to discern whether images are filtered. Our results demonstrate that faces modified with more traditional face filters are perceived similarly to unmodified faces, and faces filtered with augmented reality filters are perceived differently from unmodified faces. We discuss possible explanations for these results, including a societal adjustment to traditional photo editing techniques or the inherent differences in the different types of filters. We conclude with a discussion of how to build online spaces more responsibly based on our results.
Authors: Riccardo Fogliato, Pratik Patil, Pietro Perona
Abstract: Matching algorithms are commonly used to predict matches between items in a collection. For example, in 1:1 face verification, a matching algorithm predicts whether two face images depict the same person. Accurately assessing the uncertainty of the error rates of such algorithms can be challenging when data are dependent and error rates are low, two aspects that have been often overlooked in the literature. In this work, we review methods for constructing confidence intervals for error rates in 1:1 matching tasks. We derive and examine the statistical properties of these methods, demonstrating how coverage and interval width vary with sample size, error rates, and degree of data dependence on both analysis and experiments with synthetic and real-world datasets. Based on our findings, we provide recommendations for best practices for constructing confidence intervals for error rates in 1:1 matching tasks.
Authors: Hailong Hu, Jun Pang
Abstract: Diffusion models have been remarkably successful in data synthesis. However, when these models are applied to sensitive datasets, such as banking and human face data, they might bring up severe privacy concerns. This work systematically presents the first privacy study about property inference attacks against diffusion models, where adversaries aim to extract sensitive global properties of its training set from a diffusion model. Specifically, we focus on the most practical attack scenario: adversaries are restricted to accessing only synthetic data. Under this realistic scenario, we conduct a comprehensive evaluation of property inference attacks on various diffusion models trained on diverse data types, including tabular and image datasets. A broad range of evaluations reveals that diffusion models and their samplers are universally vulnerable to property inference attacks. In response, we propose a new model-agnostic plug-in method PriSampler to mitigate the risks of the property inference of diffusion models. PriSampler can be directly applied to well-trained diffusion models and support both stochastic and deterministic sampling. Extensive experiments illustrate the effectiveness of our defense, and it can lead adversaries to infer the proportion of properties as close as predefined values that model owners wish. Notably, PriSampler also shows its significantly superior performance to diffusion models trained with differential privacy on both model utility and defense performance. This work will elevate the awareness of preventing property inference attacks and encourage privacy-preserving synthetic data release.
Authors: Jinan Bao, Hanshi Sun, Hanqiu Deng, Yinsheng He, Zhaoxiang Zhang, Xingyu Li
Abstract: Anomaly detection (AD) is a fundamental research problem in machine learning and computer vision, with practical applications in industrial inspection, video surveillance, and medical diagnosis. In medical imaging, AD is especially vital for detecting and diagnosing anomalies that may indicate rare diseases or conditions. However, there is a lack of a universal and fair benchmark for evaluating AD methods on medical images, which hinders the development of more generalized and robust AD methods in this specific domain. To bridge this gap, we introduce a comprehensive evaluation benchmark for assessing anomaly detection methods on medical images. This benchmark encompasses six reorganized datasets from five medical domains (i.e. brain MRI, liver CT, retinal OCT, chest X-ray, and digital histopathology) and three key evaluation metrics, and includes a total of fourteen state-of-the-art AD algorithms. This standardized and well-curated medical benchmark with the well-structured codebase enables comprehensive comparisons among recently proposed anomaly detection methods. It will facilitate the community to conduct a fair comparison and advance the field of AD on medical imaging. More information on BMAD is available in our GitHub repository: https://github.com/DorisBao/BMAD
Authors: Muhammad Muneeb Saad, Mubashir Husain Rehmani, Ruairi O'Reilly
Abstract: Biomedical image datasets can be imbalanced due to the rarity of targeted diseases. Generative Adversarial Networks play a key role in addressing this imbalance by enabling the generation of synthetic images to augment datasets. It is important to generate synthetic images that incorporate a diverse range of features to accurately represent the distribution of features present in the training imagery. Furthermore, the absence of diverse features in synthetic images can degrade the performance of machine learning classifiers. The mode collapse problem impacts Generative Adversarial Networks' capacity to generate diversified images. Mode collapse comes in two varieties: intra-class and inter-class. In this paper, both varieties of the mode collapse problem are investigated, and their subsequent impact on the diversity of synthetic X-ray images is evaluated. This work contributes an empirical demonstration of the benefits of integrating the adaptive input-image normalization with the Deep Convolutional GAN and Auxiliary Classifier GAN to alleviate the mode collapse problems. Synthetically generated images are utilized for data augmentation and training a Vision Transformer model. The classification performance of the model is evaluated using accuracy, recall, and precision scores. Results demonstrate that the DCGAN and the ACGAN with adaptive input-image normalization outperform the DCGAN and ACGAN with un-normalized X-ray images as evidenced by the superior diversity scores and classification scores.
Authors: Weiyang Liu, Zeju Qiu, Yao Feng, Yuliang Xiu, Yuxuan Xue, Longhui Yu, Haiwen Feng, Zhen Liu, Juyeon Heo, Songyou Peng, Yandong Wen, Michael J. Black, Adrian Weller, Bernhard Sch\"olkopf
Abstract: Large foundation models are becoming ubiquitous, but training them from scratch is prohibitively expensive. Thus, efficiently adapting these powerful models to downstream tasks is increasingly important. In this paper, we study a principled finetuning paradigm -- Orthogonal Finetuning (OFT) -- for downstream task adaptation. Despite demonstrating good generalizability, OFT still uses a fairly large number of trainable parameters due to the high dimensionality of orthogonal matrices. To address this, we start by examining OFT from an information transmission perspective, and then identify a few key desiderata that enable better parameter-efficiency. Inspired by how the Cooley-Tukey fast Fourier transform algorithm enables efficient information transmission, we propose an efficient orthogonal parameterization using butterfly structures. We apply this parameterization to OFT, creating a novel parameter-efficient finetuning method, called Orthogonal Butterfly (BOFT). By subsuming OFT as a special case, BOFT introduces a generalized orthogonal finetuning framework. Finally, we conduct an extensive empirical study of adapting large vision transformers, large language models, and text-to-image diffusion models to various downstream tasks in vision and language.
Authors: Mirsaeed Abdollahi, Ali Jafarizadeh, Amirhosein Ghafouri Asbagh, Navid Sobhi, Keysan Pourmoghtader, Siamak Pedrammehr, Houshyar Asadi, Roohallah Alizadehsani, Ru-San Tan, U. Rajendra Acharya
Abstract: Background: Cardiovascular diseases (CVDs) are the leading cause of death globally. The use of artificial intelligence (AI) methods - in particular, deep learning (DL) - has been on the rise lately for the analysis of different CVD-related topics. The use of fundus images and optical coherence tomography angiography (OCTA) in the diagnosis of retinal diseases has also been extensively studied. To better understand heart function and anticipate changes based on microvascular characteristics and function, researchers are currently exploring the integration of AI with non-invasive retinal scanning. There is great potential to reduce the number of cardiovascular events and the financial strain on healthcare systems by utilizing AI-assisted early detection and prediction of cardiovascular diseases on a large scale. Method: A comprehensive search was conducted across various databases, including PubMed, Medline, Google Scholar, Scopus, Web of Sciences, IEEE Xplore, and ACM Digital Library, using specific keywords related to cardiovascular diseases and artificial intelligence. Results: The study included 87 English-language publications selected for relevance, and additional references were considered. This paper provides an overview of the recent developments and difficulties in using artificial intelligence and retinal imaging to diagnose cardiovascular diseases. It provides insights for further exploration in this field. Conclusion: Researchers are trying to develop precise disease prognosis patterns in response to the aging population and the growing global burden of CVD. AI and deep learning are revolutionizing healthcare by potentially diagnosing multiple CVDs from a single retinal image. However, swifter adoption of these technologies in healthcare systems is required.
Authors: Emerson Sie, Xinyu Wu, Heyu Guo, Deepak Vasisht
Abstract: Millimeter-wave (mmWave) radar is increasingly being considered as an alternative to optical sensors for robotic primitives like simultaneous localization and mapping (SLAM). While mmWave radar overcomes some limitations of optical sensors, such as occlusions, poor lighting conditions, and privacy concerns, it also faces unique challenges, such as missed obstacles due to specular reflections or fake objects due to multipath. To address these challenges, we propose Radarize, a self-contained SLAM pipeline that uses only a commodity single-chip mmWave radar. Our radar-native approach uses techniques such as Doppler shift-based odometry and multipath artifact suppression to improve performance. We evaluate our method on a large dataset of 146 trajectories spanning 4 buildings and mounted on 3 different platforms, totaling approximately 4.7 Km of travel distance. Our results show that our method outperforms state-of-the-art radar and radar-inertial approaches by approximately 5x in terms of odometry and 8x in terms of end-to-end SLAM, as measured by absolute trajectory error (ATE), without the need for additional sensors such as IMUs or wheel encoders.
Authors: Akshay K. Burusa, Eldert J. van Henten, Gert Kootstra
Abstract: Robots are increasingly used in tomato greenhouses to automate labour-intensive tasks such as selective harvesting and de-leafing. To perform these tasks, robots must be able to accurately and efficiently perceive the plant nodes that need to be cut, despite the high levels of occlusion from other plant parts. We formulate this problem as a local next-best-view (NBV) planning task where the robot has to plan an efficient set of camera viewpoints to overcome occlusion and improve the quality of perception. Our formulation focuses on quickly improving the perception accuracy of a single target node to maximise its chances of being cut. Previous methods of NBV planning mostly focused on global view planning and used random sampling of candidate viewpoints for exploration, which could suffer from high computational costs, ineffective view selection due to poor candidates, or non-smooth trajectories due to inefficient sampling. We propose a gradient-based NBV planner using differential ray sampling, which directly estimates the local gradient direction for viewpoint planning to overcome occlusion and improve perception. Through simulation experiments, we showed that our planner can handle occlusions and improve the 3D reconstruction and position estimation of nodes equally well as a sampling-based NBV planner, while taking ten times less computation and generating 28% more efficient trajectories.
Authors: Zhikai Li, Murong Yi, Ali Uneri, Sihan Niu, Craig Jones
Abstract: Polyp segmentation is a key aspect of colorectal cancer prevention, enabling early detection and guiding subsequent treatments. Intelligent diagnostic tools, including deep learning solutions, are widely explored to streamline and potentially automate this process. However, even with many powerful network architectures, there still comes the problem of producing accurate edge segmentation. In this paper, we introduce a novel network, namely RTA-Former, that employs a transformer model as the encoder backbone and innovatively adapts Reverse Attention (RA) with a transformer stage in the decoder for enhanced edge segmentation. The results of the experiments illustrate that RTA-Former achieves state-of-the-art (SOTA) performance in five polyp segmentation datasets. The strong capability of RTA-Former holds promise in improving the accuracy of Transformer-based polyp segmentation, potentially leading to better clinical decisions and patient outcomes. Our code is publicly available on GitHub.
Authors: Shih-Yang Liu, Chien-Yi Wang, Hongxu Yin, Pavlo Molchanov, Yu-Chiang Frank Wang, Kwang-Ting Cheng, Min-Hung Chen
Abstract: Among the widely used parameter-efficient finetuning (PEFT) methods, LoRA and its variants have gained considerable popularity because of avoiding additional inference costs. However, there still often exists an accuracy gap between these methods and full fine-tuning (FT). In this work, we first introduce a novel weight decomposition analysis to investigate the inherent differences between FT and LoRA. Aiming to resemble the learning capacity of FT from the findings, we propose Weight-Decomposed LowRank Adaptation (DoRA). DoRA decomposes the pre-trained weight into two components, magnitude and direction, for fine-tuning, specifically employing LoRA for directional updates to efficiently minimize the number of trainable parameters. By employing DoRA, we enhance both the learning capacity and training stability of LoRA while avoiding any additional inference overhead. DoRA consistently outperforms LoRA on fine-tuning LLaMA, LLaVA, and VL-BART on various downstream tasks, such as commonsense reasoning, visual instruction tuning, and image/video-text understanding. Code available at https://github.com/NVlabs/DoRA.
Authors: Aruna Mohan, Danne Elbers, Or Zilbershot, Fatemeh Afghah, David Vorchheimer
Abstract: Remote patient monitoring based on wearable single-lead electrocardiogram (ECG) devices has significant potential for enabling the early detection of heart disease, especially in combination with artificial intelligence (AI) approaches for automated heart disease detection. There have been prior studies applying AI approaches based on deep learning for heart disease detection. However, these models are yet to be widely accepted as a reliable aid for clinical diagnostics, in part due to the current black-box perception surrounding many AI algorithms. In particular, there is a need to identify the key features of the ECG signal that contribute toward making an accurate diagnosis, thereby enhancing the interpretability of the model. In the present study, we develop a vision transformer approach to identify atrial fibrillation based on single-lead ECG data. A residual network (ResNet) approach is also developed for comparison with the vision transformer approach. These models are applied to the Chapman-Shaoxing dataset to classify atrial fibrillation, as well as another common arrhythmia, sinus bradycardia, and normal sinus rhythm heartbeats. The models enable the identification of the key regions of the heartbeat that determine the resulting classification, and highlight the importance of P-waves and T-waves, as well as heartbeat duration and signal amplitude, in distinguishing normal sinus rhythm from atrial fibrillation and sinus bradycardia.
Authors: Ningyu Zhang, Bozhong Tian, Siyuan Cheng, Xiaozhuan Liang, Yi Hu, Kouying Xue, Yanjie Gou, Xi Chen, Huajun Chen
Abstract: Knowledge editing for large language models can offer an efficient solution to alter a model's behavior without negatively impacting the overall performance. However, the current approaches encounter issues with limited generalizability across tasks, necessitating one distinct editor for each task, significantly hindering the broader applications. To address this, we take the first step to analyze the multi-task generalization issue in knowledge editing. Specifically, we develop an instruction-based editing technique, termed InstructEdit, which facilitates the editor's adaptation to various task performances simultaneously using simple instructions. With only one unified editor for each LLM, we empirically demonstrate that InstructEdit can improve the editor's control, leading to an average 14.86% increase in Reliability in multi-task editing setting. Furthermore, experiments involving holdout unseen task illustrate that InstructEdit consistently surpass previous strong baselines. To further investigate the underlying mechanisms of instruction-based knowledge editing, we analyze the principal components of the editing gradient directions, which unveils that instructions can help control optimization direction with stronger OOD generalization. Code and datasets are available in https://github.com/zjunlp/EasyEdit.
Authors: Xinwei Ou, Ce Zhu, Xiaolin Huang, Yipeng Liu
Abstract: Second-order optimization techniques have the potential to achieve faster convergence rates compared to first-order methods through the incorporation of second-order derivatives or statistics. However, their utilization in deep learning is limited due to their computational inefficiency. Various approaches have been proposed to address this issue, primarily centered on minimizing the size of the matrix to be inverted. Nevertheless, the necessity of performing the inverse operation iteratively persists. In this work, we present a fast natural gradient descent (FNGD) method that only requires inversion during the first epoch. Specifically, it is revealed that natural gradient descent (NGD) is essentially a weighted sum of per-sample gradients. Our novel approach further proposes to share these weighted coefficients across epochs without affecting empirical performance. Consequently, FNGD exhibits similarities to the average sum in first-order methods, leading to the computational complexity of FNGD being comparable to that of first-order methods. Extensive experiments on image classification and machine translation tasks demonstrate the efficiency of the proposed FNGD. For training ResNet-18 on CIFAR-100, FNGD can achieve a speedup of 2.07$\times$ compared with KFAC. For training Transformer on Multi30K, FNGD outperforms AdamW by 24 BLEU score while requiring almost the same training time.
Authors: Samuel Sze, Lars Kunze
Abstract: In autonomous vehicles, understanding the surrounding 3D environment of the ego vehicle in real-time is essential. A compact way to represent scenes while encoding geometric distances and semantic object information is via 3D semantic occupancy maps. State of the art 3D mapping methods leverage transformers with cross-attention mechanisms to elevate 2D vision-centric camera features into the 3D domain. However, these methods encounter significant challenges in real-time applications due to their high computational demands during inference. This limitation is particularly problematic in autonomous vehicles, where GPU resources must be shared with other tasks such as localization and planning. In this paper, we introduce an approach that extracts features from front-view 2D camera images and LiDAR scans, then employs a sparse convolution network (Minkowski Engine), for 3D semantic occupancy prediction. Given that outdoor scenes in autonomous driving scenarios are inherently sparse, the utilization of sparse convolution is particularly apt. By jointly solving the problems of 3D scene completion of sparse scenes and 3D semantic segmentation, we provide a more efficient learning framework suitable for real-time applications in autonomous vehicles. We also demonstrate competitive accuracy on the nuScenes dataset.
Authors: Ye Wang, Yaxiong Wang, Yujiao Wu, Bingchen Zhao, Xueming Qian
Abstract: Generalized Class Discovery (GCD) aims to dynamically assign labels to unlabelled data partially based on knowledge learned from labelled data, where the unlabelled data may come from known or novel classes. The prevailing approach generally involves clustering across all data and learning conceptions by prototypical contrastive learning. However, existing methods largely hinge on the performance of clustering algorithms and are thus subject to their inherent limitations. Firstly, the estimated cluster number is often smaller than the ground truth, making the existing methods suffer from the lack of prototypes for comprehensive conception learning. To address this issue, we propose an adaptive probing mechanism that introduces learnable potential prototypes to expand cluster prototypes (centers). As there is no ground truth for the potential prototype, we develop a self-supervised prototype learning framework to optimize the potential prototype in an end-to-end fashion. Secondly, clustering is computationally intensive, and the conventional strategy of clustering both labelled and unlabelled instances exacerbates this issue. To counteract this inefficiency, we opt to cluster only the unlabelled instances and subsequently expand the cluster prototypes with our introduced potential prototypes to fast explore novel classes. Despite the simplicity of our proposed method, extensive empirical analysis on a wide range of datasets confirms that our method consistently delivers state-of-the-art results. Specifically, our method surpasses the nearest competitor by a significant margin of \textbf{9.7}$\%$ within the Stanford Cars dataset and \textbf{12$\times$} clustering efficiency within the Herbarium 19 dataset. We will make the code and checkpoints publicly available at \url{https://github.com/xjtuYW/PNP.git}.
Authors: Aojun Lu, Tao Feng, Hangjie Yuan, Xiaotian Song, Yanan Sun
Abstract: Efforts to overcome catastrophic forgetting have primarily centered around developing more effective Continual Learning (CL) methods. In contrast, less attention was devoted to analyzing the role of network architecture design (e.g., network depth, width, and components) in contributing to CL. This paper seeks to bridge this gap between network architecture design and CL, and to present a holistic study on the impact of network architectures on CL. This work considers architecture design at the network scaling level, i.e., width and depth, and also at the network components, i.e., skip connections, global pooling layers, and down-sampling. In both cases, we first derive insights through systematically exploring how architectural designs affect CL. Then, grounded in these insights, we craft a specialized search space for CL and further propose a simple yet effective ArchCraft method to steer a CL-friendly architecture, namely, this method recrafts AlexNet/ResNet into AlexAC/ResAC. Experimental validation across various CL settings and scenarios demonstrates that improved architectures are parameter-efficient, achieving state-of-the-art performance of CL while being 86%, 61%, and 97% more compact in terms of parameters than the naive CL architecture in Task IL and Class IL. Code is available at https://github.com/byyx666/ArchCraft.