Authors: Ziang Cao, Fangzhou Hong, Tong Wu, Liang Pan, Ziwei Liu
Abstract: Generating diverse and high-quality 3D assets automatically poses a fundamental yet challenging task in 3D computer vision. Despite extensive efforts in 3D generation, existing optimization-based approaches struggle to produce large-scale 3D assets efficiently. Meanwhile, feed-forward methods often focus on generating only a single category or a few categories, limiting their generalizability. Therefore, we introduce a diffusion-based feed-forward framework to address these challenges with a single model. To handle the large diversity and complexity in geometry and texture across categories efficiently, we 1) adopt improved triplane to guarantee efficiency; 2) introduce the 3D-aware transformer to aggregate the generalized 3D knowledge with specialized 3D features; and 3) devise the 3D-aware encoder/decoder to enhance the generalized 3D knowledge. Building upon our 3D-aware Diffusion model with TransFormer, DiffTF, we propose a stronger version for 3D generation, i.e., DiffTF++. It boils down to two parts: multi-view reconstruction loss and triplane refinement. Specifically, we utilize multi-view reconstruction loss to fine-tune the diffusion model and triplane decoder, thereby avoiding the negative influence caused by reconstruction errors and improving texture synthesis. By eliminating the mismatch between the two stages, the generative performance is enhanced, especially in texture. Additionally, a 3D-aware refinement process is introduced to filter out artifacts and refine triplanes, resulting in the generation of more intricate and reasonable details. Extensive experiments on ShapeNet and OmniObject3D convincingly demonstrate the effectiveness of our proposed modules and the state-of-the-art 3D object generation performance with large diversity, rich semantics, and high quality.
Authors: Chengde Lin, Xijun Lu, Guangxi Chen
Abstract: Synthesizing high-quality photorealistic images with textual descriptions as a condition is very challenging. Generative Adversarial Networks (GANs), the classical model for this task, frequently suffer from low consistency between image and text descriptions and insufficient richness in synthesized images. Recently, conditional affine transformations (CAT), such as conditional batch normalization and instance normalization, have been applied to different layers of GAN to control content synthesis in images. CAT is a multi-layer perceptron that independently predicts data based on batch statistics between neighboring layers, with global textual information unavailable to other layers. To address this issue, we first model CAT and a recurrent neural network (RAT) to ensure that different layers can access global information. We then introduce shuffle attention between RAT to mitigate the characteristic of information forgetting in recurrent neural networks. Moreover, both our generator and discriminator utilize the powerful pre-trained model, Clip, which has been extensively employed for establishing associations between text and images through the learning of multimodal representations in latent space. The discriminator utilizes CLIP's ability to comprehend complex scenes to accurately assess the quality of the generated images. Extensive experiments have been conducted on the CUB, Oxford, and CelebA-tiny datasets to demonstrate the superiority of the proposed model over current state-of-the-art models. The code is https://github.com/OxygenLu/RATLIP.
Authors: Jun Wang, Yu Mao, Yufei Cui, Nan Guan, Chun Jason Xue
Abstract: Immunohistochemistry (IHC) plays a crucial role in pathology as it detects the over-expression of protein in tissue samples. However, there are still fewer machine learning model studies on IHC's impact on accurate cancer grading. We discovered that IHC and H\&E possess distinct advantages and disadvantages while possessing certain complementary qualities. Building on this observation, we developed a two-stage multi-modal bilinear model with a feature pooling module. This model aims to maximize the potential of both IHC and HE's feature representation, resulting in improved performance compared to their individual use. Our experiments demonstrate that incorporating IHC data into machine learning models, alongside H\&E stained images, leads to superior predictive results for cancer grading. The proposed framework achieves an impressive ACC higher of 0.953 on the public dataset BCI.
Authors: Matthew Korban, Peter Youngs, Scott T. Acton
Abstract: This paper presents a novel spatiotemporal transformer network that introduces several original components to detect actions in untrimmed videos. First, the multi-feature selective semantic attention model calculates the correlations between spatial and motion features to model spatiotemporal interactions between different action semantics properly. Second, the motion-aware network encodes the locations of action semantics in video frames utilizing the motion-aware 2D positional encoding algorithm. Such a motion-aware mechanism memorizes the dynamic spatiotemporal variations in action frames that current methods cannot exploit. Third, the sequence-based temporal attention model captures the heterogeneous temporal dependencies in action frames. In contrast to standard temporal attention used in natural language processing, primarily aimed at finding similarities between linguistic words, the proposed sequence-based temporal attention is designed to determine both the differences and similarities between video frames that jointly define the meaning of actions. The proposed approach outperforms the state-of-the-art solutions on four spatiotemporal action datasets: AVA 2.2, AVA 2.1, UCF101-24, and EPIC-Kitchens.
Authors: Yifan Wang, Aleksander Holynski, Brian L. Curless, Steven M. Seitz
Abstract: We present Infinite Texture, a method for generating arbitrarily large texture images from a text prompt. Our approach fine-tunes a diffusion model on a single texture, and learns to embed that statistical distribution in the output domain of the model. We seed this fine-tuning process with a sample texture patch, which can be optionally generated from a text-to-image model like DALL-E 2. At generation time, our fine-tuned diffusion model is used through a score aggregation strategy to generate output texture images of arbitrary resolution on a single GPU. We compare synthesized textures from our method to existing work in patch-based and deep learning texture synthesis methods. We also showcase two applications of our generated textures in 3D rendering and texture transfer.
Authors: Xiameng Wei, Binbin Fan, Ying Wang, Yanxiang Feng, Laiyi Fu
Abstract: Ancient murals are valuable cultural heritage with great archaeological value. They provide insights into ancient religions, ceremonies, folklore, among other things through their content. However, due to long-term oxidation and inadequate protection, ancient murals have suffered continuous damage, including peeling and mold etc. Additionally, since ancient murals were typically painted indoors, the light intensity in images captured by digital devices is often low. The poor visibility hampers the further restoration of damaged areas. To address the escalating damage to ancient frescoes and facilitate batch restoration at archaeological sites, we propose a two-stage restoration model which called MER(Mural Enhancement and Restoration net) for ancient murals that are damaged and have been captured in low light. Our two-stage model not only enhances the visual quality of restored images but also achieves commendable results in relevant metric evaluations compared with other competitors. Furthermore, we have launched a website dedicated to the restoration of ancient mural paintings, utilizing the proposed model. Code is available at https://gitee.com/bbfan2024/MER.git.
Authors: Weili Nie, Sifei Liu, Morteza Mardani, Chao Liu, Benjamin Eckart, Arash Vahdat
Abstract: Existing text-to-image models struggle to follow complex text prompts, raising the need for extra grounding inputs for better controllability. In this work, we propose to decompose a scene into visual primitives - denoted as dense blob representations - that contain fine-grained details of the scene while being modular, human-interpretable, and easy-to-construct. Based on blob representations, we develop a blob-grounded text-to-image diffusion model, termed BlobGEN, for compositional generation. Particularly, we introduce a new masked cross-attention module to disentangle the fusion between blob representations and visual features. To leverage the compositionality of large language models (LLMs), we introduce a new in-context learning approach to generate blob representations from text prompts. Our extensive experiments show that BlobGEN achieves superior zero-shot generation quality and better layout-guided controllability on MS-COCO. When augmented by LLMs, our method exhibits superior numerical and spatial correctness on compositional image generation benchmarks. Project page: https://blobgen-2d.github.io.
Authors: Xin Wu, Zhanchao Huang, Li Wang, Jocelyn Chanussot, Jiaojiao Tian
Abstract: In large-scale disaster events, the planning of optimal rescue routes depends on the object detection ability at the disaster scene, with one of the main challenges being the presence of dense and occluded objects. Existing methods, which are typically based on the RGB modality, struggle to distinguish targets with similar colors and textures in crowded environments and are unable to identify obscured objects. To this end, we first construct two multimodal dense and occlusion vehicle detection datasets for large-scale events, utilizing RGB and height map modalities. Based on these datasets, we propose a multimodal collaboration network for dense and occluded vehicle detection, MuDet for short. MuDet hierarchically enhances the completeness of discriminable information within and across modalities and differentiates between simple and complex samples. MuDet includes three main modules: Unimodal Feature Hierarchical Enhancement (Uni-Enh), Multimodal Cross Learning (Mul-Lea), and Hard-easy Discriminative (He-Dis) Pattern. Uni-Enh and Mul-Lea enhance the features within each modality and facilitate the cross-integration of features from two heterogeneous modalities. He-Dis effectively separates densely occluded vehicle targets with significant intra-class differences and minimal inter-class differences by defining and thresholding confidence values, thereby suppressing the complex background. Experimental results on two re-labeled multimodal benchmark datasets, the 4K-SAI-LCS dataset, and the ISPRS Potsdam dataset, demonstrate the robustness and generalization of the MuDet. The codes of this work are available openly at \url{https://github.com/Shank2358/MuDet}.
Authors: Chenlei Lv, Dan Zhang
Abstract: As an important subtopic of image enhancement, color transfer aims to enhance the color scheme of a source image according to a reference one while preserving the semantic context. To implement color transfer, the palette-based color mapping framework was proposed. \textcolor{black}{It is a classical solution that does not depend on complex semantic analysis to generate a new color scheme. However, the framework usually requires manual settings, blackucing its practicality.} The quality of traditional palette generation depends on the degree of color separation. In this paper, we propose a new palette-based color transfer method that can automatically generate a new color scheme. With a redesigned palette-based clustering method, pixels can be classified into different segments according to color distribution with better applicability. {By combining deep learning-based image segmentation and a new color mapping strategy, color transfer can be implemented on foreground and background parts independently while maintaining semantic consistency.} The experimental results indicate that our method exhibits significant advantages over peer methods in terms of natural realism, color consistency, generality, and robustness.
Authors: Shishuai Hu, Zehui Liao, Zeyou Liu, Yong Xia
Abstract: Deep learning-based medical image segmentation models often face performance degradation when deployed across various medical centers, largely due to the discrepancies in data distribution. Test Time Adaptation (TTA) methods, which adapt pre-trained models to test data, have been employed to mitigate such discrepancies. However, existing TTA methods primarily focus on manipulating Batch Normalization (BN) layers or employing prompt and adversarial learning, which may not effectively rectify the inconsistencies arising from divergent data distributions. In this paper, we propose a novel Human-in-the-loop TTA (HiTTA) framework that stands out in two significant ways. First, it capitalizes on the largely overlooked potential of clinician-corrected predictions, integrating these corrections into the TTA process to steer the model towards predictions that coincide more closely with clinical annotation preferences. Second, our framework conceives a divergence loss, designed specifically to diminish the prediction divergence instigated by domain disparities, through the careful calibration of BN parameters. Our HiTTA is distinguished by its dual-faceted capability to acclimatize to the distribution of test data whilst ensuring the model's predictions align with clinical expectations, thereby enhancing its relevance in a medical context. Extensive experiments on a public dataset underscore the superiority of our HiTTA over existing TTA methods, emphasizing the advantages of integrating human feedback and our divergence loss in enhancing the model's performance and adaptability across diverse medical centers.
Authors: Zhen Chen, Xingjian Luo, Jinlin Wu, Danny T. M. Chan, Zhen Lei, Jinqiao Wang, Sebastien Ourselin, Hongbin Liu
Abstract: The surgical intervention is crucial to patient healthcare, and many studies have developed advanced algorithms to provide understanding and decision-making assistance for surgeons. Despite great progress, these algorithms are developed for a single specific task and scenario, and in practice require the manual combination of different functions, thus limiting the applicability. Thus, an intelligent and versatile surgical assistant is expected to accurately understand the surgeon's intentions and accordingly conduct the specific tasks to support the surgical process. In this work, by leveraging advanced multimodal large language models (MLLMs), we propose a Versatile Surgery Assistant (VS-Assistant) that can accurately understand the surgeon's intention and complete a series of surgical understanding tasks, e.g., surgical scene analysis, surgical instrument detection, and segmentation on demand. Specifically, to achieve superior surgical multimodal understanding, we devise a mixture of projectors (MOP) module to align the surgical MLLM in VS-Assistant to balance the natural and surgical knowledge. Moreover, we devise a surgical Function-Calling Tuning strategy to enable the VS-Assistant to understand surgical intentions, and thus make a series of surgical function calls on demand to meet the needs of the surgeons. Extensive experiments on neurosurgery data confirm that our VS-Assistant can understand the surgeon's intention more accurately than the existing MLLM, resulting in overwhelming performance in textual analysis and visual tasks. Source code and models will be made public.
Authors: Hongzhi You, Yijun Cao, Wei Yuan, Fanjun Wang, Ning Qiao, Yongjie Li
Abstract: From a perspective of feature matching, optical flow estimation for event cameras involves identifying event correspondences by comparing feature similarity across accompanying event frames. In this work, we introduces an effective and robust high-dimensional (HD) feature descriptor for event frames, utilizing Vector Symbolic Architectures (VSA). The topological similarity among neighboring variables within VSA contributes to the enhanced representation similarity of feature descriptors for flow-matching points, while its structured symbolic representation capacity facilitates feature fusion from both event polarities and multiple spatial scales. Based on this HD feature descriptor, we propose a novel feature matching framework for event-based optical flow, encompassing both model-based (VSA-Flow) and self-supervised learning (VSA-SM) methods. In VSA-Flow, accurate optical flow estimation validates the effectiveness of HD feature descriptors. In VSA-SM, a novel similarity maximization method based on the HD feature descriptor is proposed to learn optical flow in a self-supervised way from events alone, eliminating the need for auxiliary grayscale images. Evaluation results demonstrate that our VSA-based method achieves superior accuracy in comparison to both model-based and self-supervised learning methods on the DSEC benchmark, while remains competitive among both methods on the MVSEC benchmark. This contribution marks a significant advancement in event-based optical flow within the feature matching methodology.
Authors: Dasith de Silva Edirimuni, Xuequan Lu, Gang Li, Lei Wei, Antonio Robles-Kelly, Hongdong Li
Abstract: Point cloud filtering is a fundamental 3D vision task, which aims to remove noise while recovering the underlying clean surfaces. State-of-the-art methods remove noise by moving noisy points along stochastic trajectories to the clean surfaces. These methods often require regularization within the training objective and/or during post-processing, to ensure fidelity. In this paper, we introduce StraightPCF, a new deep learning based method for point cloud filtering. It works by moving noisy points along straight paths, thus reducing discretization errors while ensuring faster convergence to the clean surfaces. We model noisy patches as intermediate states between high noise patch variants and their clean counterparts, and design the VelocityModule to infer a constant flow velocity from the former to the latter. This constant flow leads to straight filtering trajectories. In addition, we introduce a DistanceModule that scales the straight trajectory using an estimated distance scalar to attain convergence near the clean surface. Our network is lightweight and only has $\sim530K$ parameters, being 17% of IterativePFN (a most recent point cloud filtering network). Extensive experiments on both synthetic and real-world data show our method achieves state-of-the-art results. Our method also demonstrates nice distributions of filtered points without the need for regularization. The implementation code can be found at: https://github.com/ddsediri/StraightPCF.
Authors: Cl\'ement Playout, Farida Cheriet
Abstract: Identifying lesions in fundus images is an important milestone toward an automated and interpretable diagnosis of retinal diseases. To support research in this direction, multiple datasets have been released, proposing groundtruth maps for different lesions. However, important discrepancies exist between the annotations and raise the question of generalization across datasets. This study characterizes several known datasets and compares different techniques that have been proposed to enhance the generalisation performance of a model, such as stochastic weight averaging, model soups and ensembles. Our results provide insights into how to combine coarsely labelled data with a finely-grained dataset in order to improve the lesions segmentation.
Authors: Benjamin Sinclair, Lucy Vivash, Jasmine Moses, Miranda Lynch, William Pham, Karina Dorfmann, Cassandra Marotta, Shaun Koh, Jacob Bunyamin, Ella Rowsthorn, Alex Jarema, Himashi Peiris, Zhaolin Chen, Sandy R Shultz, David K Wright, Dexiao Kong, Sharon L. Naismith, Terence J. O\'Brien, Meng Law
Abstract: Perivascular spaces(PVSs) form a central component of the brain\'s waste clearance system, the glymphatic system. These structures are visible on MRI images, and their morphology is associated with aging and neurological disease. Manual quantification of PVS is time consuming and subjective. Numerous deep learning methods for PVS segmentation have been developed, however the majority have been developed and evaluated on homogenous datasets and high resolution scans, perhaps limiting their applicability for the wide range of image qualities acquired in clinic and research. In this work we train a nnUNet, a top-performing biomedical image segmentation algorithm, on a heterogenous training sample of manually segmented MRI images of a range of different qualities and resolutions from 6 different datasets. These are compared to publicly available deep learning methods for 3D segmentation of PVS. The resulting model, PINGU (Perivascular space Identification Nnunet for Generalised Usage), achieved voxel and cluster level dice scores of 0.50(SD=0.15), 0.63(0.17) in the white matter(WM), and 0.54(0.11), 0.66(0.17) in the basal ganglia(BG). Performance on data from unseen sites was substantially lower for both PINGU(0.20-0.38(WM, voxel), 0.29-0.58(WM, cluster), 0.22-0.36(BG, voxel), 0.46-0.60(BG, cluster)) and the publicly available algorithms(0.18-0.30(WM, voxel), 0.29-0.38(WM cluster), 0.10-0.20(BG, voxel), 0.15-0.37(BG, cluster)), but PINGU strongly outperformed the publicly available algorithms, particularly in the BG. Finally, training PINGU on manual segmentations from a single site with homogenous scan properties gave marginally lower performances on internal cross-validation, but in some cases gave higher performance on external validation. PINGU stands out as broad-use PVS segmentation tool, with particular strength in the BG, an area of PVS related to vascular disease and pathology.
Authors: Yingjie Zhai, Wenshuo Li, Yehui Tang, Xinghao Chen, Yunhe Wang
Abstract: Current architectures for video understanding mainly build upon 3D convolutional blocks or 2D convolutions with additional operations for temporal modeling. However, these methods all regard the temporal axis as a separate dimension of the video sequence, which requires large computation and memory budgets and thus limits their usage on mobile devices. In this paper, we propose to squeeze the time axis of a video sequence into the channel dimension and present a lightweight video recognition network, term as \textit{SqueezeTime}, for mobile video understanding. To enhance the temporal modeling capability of the proposed network, we design a Channel-Time Learning (CTL) Block to capture temporal dynamics of the sequence. This module has two complementary branches, in which one branch is for temporal importance learning and another branch with temporal position restoring capability is to enhance inter-temporal object modeling ability. The proposed SqueezeTime is much lightweight and fast with high accuracies for mobile video understanding. Extensive experiments on various video recognition and action detection benchmarks, i.e., Kinetics400, Kinetics600, HMDB51, AVA2.1 and THUMOS14, demonstrate the superiority of our model. For example, our SqueezeTime achieves $+1.2\%$ accuracy and $+80\%$ GPU throughput gain on Kinetics400 than prior methods. Codes are publicly available at https://github.com/xinghaochen/SqueezeTime and https://github.com/mindspore-lab/models/tree/master/research/huawei-noah/SqueezeTime.
URLs: https://github.com/xinghaochen/SqueezeTime, https://github.com/mindspore-lab/models/tree/master/research/huawei-noah/SqueezeTime.
Authors: Meisheng Guan, Haiyong Xu, Gangyi Jiang, Mei Yu, Yeyao Chen, Ting Luo, Yang Song
Abstract: Underwater imaging often suffers from low quality due to factors affecting light propagation and absorption in water. To improve image quality, some underwater image enhancement (UIE) methods based on convolutional neural networks (CNN) and Transformer have been proposed. However, CNN-based UIE methods are limited in modeling long-range dependencies, and Transformer-based methods involve a large number of parameters and complex self-attention mechanisms, posing efficiency challenges. Considering computational complexity and severe underwater image degradation, a state space model (SSM) with linear computational complexity for UIE, named WaterMamba, is proposed. We propose spatial-channel omnidirectional selective scan (SCOSS) blocks comprising spatial-channel coordinate omnidirectional selective scan (SCCOSS) modules and a multi-scale feedforward network (MSFFN). The SCOSS block models pixel and channel information flow, addressing dependencies. The MSFFN facilitates information flow adjustment and promotes synchronized operations within SCCOSS modules. Extensive experiments showcase WaterMamba's cutting-edge performance with reduced parameters and computational resources, outperforming state-of-the-art methods on various datasets, validating its effectiveness and generalizability. The code will be released on GitHub after acceptance.
Authors: Mart\'in Bay\'on-Guti\'errez, Mar\'ia Teresa Garc\'ia-Ord\'as, H\'ector Alaiz Moret\'on, Jose Aveleira-Mata, Sergio Rubio Mart\'in, Jos\'e Alberto Ben\'itez-Andrades
Abstract: Robust road surface estimation is required for autonomous ground vehicles to navigate safely. Despite it becoming one of the main targets for autonomous mobility researchers in recent years, it is still an open problem in which cameras and LiDAR sensors have demonstrated to be adequate to predict the position, size and shape of the road a vehicle is driving on in different environments. In this work, a novel Convolutional Neural Network model is proposed for the accurate estimation of the roadway surface. Furthermore, an ablation study has been conducted to investigate how different encoding strategies affect model performance, testing 6 slightly different neural network architectures. Our model is based on the use of a Twin Encoder-Decoder Neural Network (TEDNet) for independent camera and LiDAR feature extraction, and has been trained and evaluated on the Kitti-Road dataset. Bird's Eye View projections of the camera and LiDAR data are used in this model to perform semantic segmentation on whether each pixel belongs to the road surface. The proposed method performs among other state-of-the-art methods and operates at the same frame-rate as the LiDAR and cameras, so it is adequate for its use in real-time applications.
Authors: Liming Han, Zhaoxiang Liu, Shiguo Lian
Abstract: Image matching is still challenging in such scenes with large viewpoints or illumination changes or with low textures. In this paper, we propose a Transformer-based pseudo 3D image matching method. It upgrades the 2D features extracted from the source image to 3D features with the help of a reference image and matches to the 2D features extracted from the destination image by the coarse-to-fine 3D matching. Our key discovery is that by introducing the reference image, the source image's fine points are screened and furtherly their feature descriptors are enriched from 2D to 3D, which improves the match performance with the destination image. Experimental results on multiple datasets show that the proposed method achieves the state-of-the-art on the tasks of homography estimation, pose estimation and visual localization especially in challenging scenes.
Authors: Jin Wang, Bingfeng Zhang, Jian Pang, Honglong Chen, Weifeng Liu
Abstract: Few-shot segmentation remains challenging due to the limitations of its labeling information for unseen classes. Most previous approaches rely on extracting high-level feature maps from the frozen visual encoder to compute the pixel-wise similarity as a key prior guidance for the decoder. However, such a prior representation suffers from coarse granularity and poor generalization to new classes since these high-level feature maps have obvious category bias. In this work, we propose to replace the visual prior representation with the visual-text alignment capacity to capture more reliable guidance and enhance the model generalization. Specifically, we design two kinds of training-free prior information generation strategy that attempts to utilize the semantic alignment capability of the Contrastive Language-Image Pre-training model (CLIP) to locate the target class. Besides, to acquire more accurate prior guidance, we build a high-order relationship of attention maps and utilize it to refine the initial prior information. Experiments on both the PASCAL-5{i} and COCO-20{i} datasets show that our method obtains a clearly substantial improvement and reaches the new state-of-the-art performance.
Authors: Zhikan Wang, Zhongyao Cheng, Jiajie Xiong, Xun Xu, Tianrui Li, Bharadwaj Veeravalli, Xulei Yang
Abstract: In recent years, the rapid advancement of deepfake technology has revolutionized content creation, lowering forgery costs while elevating quality. However, this progress brings forth pressing concerns such as infringements on individual rights, national security threats, and risks to public safety. To counter these challenges, various detection methodologies have emerged, with Vision Transformer (ViT)-based approaches showcasing superior performance in generality and efficiency. This survey presents a timely overview of ViT-based deepfake detection models, categorized into standalone, sequential, and parallel architectures. Furthermore, it succinctly delineates the structure and characteristics of each model. By analyzing existing research and addressing future directions, this survey aims to equip researchers with a nuanced understanding of ViT's pivotal role in deepfake detection, serving as a valuable reference for both academic and practical pursuits in this domain.
Authors: Zong-Wei Hong, Yen-Yang Hung, Chu-Song Chen
Abstract: In this work, we introduce a novel method for calculating the 6DoF pose of an object using a single RGB-D image. Unlike existing methods that either directly predict objects' poses or rely on sparse keypoints for pose recovery, our approach addresses this challenging task using dense correspondence, i.e., we regress the object coordinates for each visible pixel. Our method leverages existing object detection methods. We incorporate a re-projection mechanism to adjust the camera's intrinsic matrix to accommodate cropping in RGB-D images. Moreover, we transform the 3D object coordinates into a residual representation, which can effectively reduce the output space and yield superior performance. We conducted extensive experiments to validate the efficacy of our approach for 6D pose estimation. Our approach outperforms most previous methods, especially in occlusion scenarios, and demonstrates notable improvements over the state-of-the-art methods. Our code is available on https://github.com/AI-Application-and-Integration-Lab/RDPN6D.
URLs: https://github.com/AI-Application-and-Integration-Lab/RDPN6D.
Authors: Mian Zou, Baosheng Yu, Yibing Zhan, Siwei Lyu, Kede Ma
Abstract: In recent years, deep learning has greatly streamlined the process of generating realistic fake face images. Aware of the dangers, researchers have developed various tools to spot these counterfeits. Yet none asked the fundamental question: What digital manipulations make a real photographic face image fake, while others do not? In this paper, we put face forgery in a semantic context and define that computational methods that alter semantic face attributes to exceed human discrimination thresholds are sources of face forgery. Guided by our new definition, we construct a large face forgery image dataset, where each image is associated with a set of labels organized in a hierarchical graph. Our dataset enables two new testing protocols to probe the generalization of face forgery detectors. Moreover, we propose a semantics-oriented face forgery detection method that captures label relations and prioritizes the primary task (\ie, real or fake face detection). We show that the proposed dataset successfully exposes the weaknesses of current detectors as the test set and consistently improves their generalizability as the training set. Additionally, we demonstrate the superiority of our semantics-oriented method over traditional binary and multi-class classification-based detectors.
Authors: Qinfeng Zhu, Yuan Fang, Yuanzhi Cai, Cheng Chen, Lei Fan
Abstract: Deep learning methods, especially Convolutional Neural Networks (CNN) and Vision Transformer (ViT), are frequently employed to perform semantic segmentation of high-resolution remotely sensed images. However, CNNs are constrained by their restricted receptive fields, while ViTs face challenges due to their quadratic complexity. Recently, the Mamba model, featuring linear complexity and a global receptive field, has gained extensive attention for vision tasks. In such tasks, images need to be serialized to form sequences compatible with the Mamba model. Numerous research efforts have explored scanning strategies to serialize images, aiming to enhance the Mamba model's understanding of images. However, the effectiveness of these scanning strategies remains uncertain. In this research, we conduct a comprehensive experimental investigation on the impact of mainstream scanning directions and their combinations on semantic segmentation of remotely sensed images. Through extensive experiments on the LoveDA, ISPRS Potsdam, and ISPRS Vaihingen datasets, we demonstrate that no single scanning strategy outperforms others, regardless of their complexity or the number of scanning directions involved. A simple, single scanning direction is deemed sufficient for semantic segmentation of high-resolution remotely sensed images. Relevant directions for future research are also recommended.
Authors: Sunyuan Qiang, Yanyan Liang, Jun Wan, Du Zhang
Abstract: Class-incremental learning (CIL) has emerged as a means to learn new classes incrementally without catastrophic forgetting of previous classes. Recently, CIL has undergone a paradigm shift towards dynamic architectures due to their superior performance. However, these models are still limited by the following aspects: (i) Data augmentation (DA), which are tightly coupled with CIL, remains under-explored in dynamic architecture scenarios. (ii) Feature representation. The discriminativeness of dynamic feature are sub-optimal and possess potential for refinement. (iii) Classifier. The misalignment between dynamic feature and classifier constrains the capabilities of the model. To tackle the aforementioned drawbacks, we propose the Dynamic Feature Learning and Matching (DFLM) model in this paper from above three perspectives. Specifically, we firstly introduce class weight information and non-stationary functions to extend the mix DA method for dynamically adjusting the focus on memory during training. Then, von Mises-Fisher (vMF) classifier is employed to effectively model the dynamic feature distribution and implicitly learn their discriminative properties. Finally, the matching loss is proposed to facilitate the alignment between the learned dynamic features and the classifier by minimizing the distribution distance. Extensive experiments on CIL benchmarks validate that our proposed model achieves significant performance improvements over existing methods.
Authors: Zhiwei Wang, Jun Huang, Longhua Ma, Chengyu Wu, Hongyu Ma
Abstract: In visual tasks, large teacher models capture essential features and deep information, enhancing performance. However, distilling this information into smaller student models often leads to performance loss due to structural differences and capacity limitations. To tackle this, we propose a distillation framework based on graph knowledge, including a multi-level feature alignment strategy and an attention-guided mechanism to provide a targeted learning trajectory for the student model. We emphasize spectral embedding (SE) as a key technique in our distillation process, which merges the student's feature space with the relational knowledge and structural complexities similar to the teacher network. This method captures the teacher's understanding in a graph-based representation, enabling the student model to more accurately mimic the complex structural dependencies present in the teacher model. Compared to methods that focus only on specific distillation areas, our strategy not only considers key features within the teacher model but also endeavors to capture the relationships and interactions among feature sets, encoding these complex pieces of information into a graph structure to understand and utilize the dynamic relationships among these pieces of information from a global perspective. Experiments show that our method outperforms previous feature distillation methods on the CIFAR-100, MS-COCO, and Pascal VOC datasets, proving its efficiency and applicability.
Authors: Wei Sun, Weixia Zhang, Yanwei Jiang, Haoning Wu, Zicheng Zhang, Jun Jia, Yingjie Zhou, Zhongpeng Ji, Xiongkuo Min, Weisi Lin, Guangtao Zhai
Abstract: Portrait images typically consist of a salient person against diverse backgrounds. With the development of mobile devices and image processing techniques, users can conveniently capture portrait images anytime and anywhere. However, the quality of these portraits may suffer from the degradation caused by unfavorable environmental conditions, subpar photography techniques, and inferior capturing devices. In this paper, we introduce a dual-branch network for portrait image quality assessment (PIQA), which can effectively address how the salient person and the background of a portrait image influence its visual quality. Specifically, we utilize two backbone networks (\textit{i.e.,} Swin Transformer-B) to extract the quality-aware features from the entire portrait image and the facial image cropped from it. To enhance the quality-aware feature representation of the backbones, we pre-train them on the large-scale video quality assessment dataset LSVQ and the large-scale facial image quality assessment dataset GFIQA. Additionally, we leverage LIQE, an image scene classification and quality assessment model, to capture the quality-aware and scene-specific features as the auxiliary features. Finally, we concatenate these features and regress them into quality scores via a multi-perception layer (MLP). We employ the fidelity loss to train the model via a learning-to-rank manner to mitigate inconsistencies in quality scores in the portrait image quality assessment dataset PIQ. Experimental results demonstrate that the proposed model achieves superior performance in the PIQ dataset, validating its effectiveness. The code is available at \url{https://github.com/sunwei925/DN-PIQA.git}.
Authors: Hao Li, Lipo Wang, Tianyun Zhao, Wei Zhao
Abstract: Image stitching aims to construct a wide field of view with high spatial resolution, which cannot be achieved in a single exposure. Typically, conventional image stitching techniques, other than deep learning, require complex computation and thus computational pricy, especially for stitching large raw images. In this study, inspired by the multiscale feature of fluid turbulence, we developed a fast feature point detection algorithm named local-peak scale-invariant feature transform (LP-SIFT), based on the multiscale local peaks and scale-invariant feature transform method. By combining LP-SIFT and RANSAC in image stitching, the stitching speed can be improved by orders, compared with the original SIFT method. Nine large images (over 2600*1600 pixels), arranged randomly without prior knowledge, can be stitched within 158.94 s. The algorithm is highly practical for applications requiring a wide field of view in diverse application scenes, e.g., terrain mapping, biological analysis, and even criminal investigation.
Authors: Yingnan Liu, Yingtian Zou, Rui Qiao, Fusheng Liu, Mong Li Lee, Wynne Hsu
Abstract: Domain generalization aims to develop models that are robust to distribution shifts. Existing methods focus on learning invariance across domains to enhance model robustness, and data augmentation has been widely used to learn invariant predictors, with most methods performing augmentation in the input space. However, augmentation in the input space has limited diversity whereas in the feature space is more versatile and has shown promising results. Nonetheless, feature semantics is seldom considered and existing feature augmentation methods suffer from a limited variety of augmented features. We decompose features into class-generic, class-specific, domain-generic, and domain-specific components. We propose a cross-domain feature augmentation method named XDomainMix that enables us to increase sample diversity while emphasizing the learning of invariant representations to achieve domain generalization. Experiments on widely used benchmark datasets demonstrate that our proposed method is able to achieve state-of-the-art performance. Quantitative analysis indicates that our feature augmentation approach facilitates the learning of effective models that are invariant across different domains.
Authors: Md Abulkalam Azad, Artem Chernyshov, John Nyberg, Ingrid Tveten, Lasse Lovstakken, H{\aa}vard Dalen, Bj{\o}rnar Grenne, Andreas {\O}stvik
Abstract: Tissue tracking in echocardiography is challenging due to the complex cardiac motion and the inherent nature of ultrasound acquisitions. Although optical flow methods are considered state-of-the-art (SOTA), they struggle with long-range tracking, noise occlusions, and drift throughout the cardiac cycle. Recently, novel learning-based point tracking techniques have been introduced to tackle some of these issues. In this paper, we build upon these techniques and introduce EchoTracker, a two-fold coarse-to-fine model that facilitates the tracking of queried points on a tissue surface across ultrasound image sequences. The architecture contains a preliminary coarse initialization of the trajectories, followed by reinforcement iterations based on fine-grained appearance changes. It is efficient, light, and can run on mid-range GPUs. Experiments demonstrate that the model outperforms SOTA methods, with an average position accuracy of 67% and a median trajectory error of 2.86 pixels. Furthermore, we show a relative improvement of 25% when using our model to calculate the global longitudinal strain (GLS) in a clinical test-retest dataset compared to other methods. This implies that learning-based point tracking can potentially improve performance and yield a higher diagnostic and prognostic value for clinical measurements than current techniques. Our source code is available at: https://github.com/riponazad/echotracker/.
Authors: Wei Lian, Zhesen Cui, Fei Ma, Hang Pan, Wangmeng Zuo
Abstract: In many applications, the demand arises for algorithms capable of aligning partially overlapping point sets while remaining invariant to the corresponding transformations. This research presents a method designed to meet such requirements through minimization of the objective function of the robust point matching (RPM) algorithm. First, we show that the RPM objective is a cubic polynomial. Then, through variable substitution, we transform the RPM objective to a quadratic function. Leveraging the convex envelope of bilinear monomials, we proceed to relax the resulting objective function, thus obtaining a lower bound problem that can be conveniently decomposed into distinct linear assignment and low-dimensional convex quadratic program components, both amenable to efficient optimization. Furthermore, a branch-and-bound (BnB) algorithm is devised, which solely branches over the transformation parameters, thereby boosting convergence rate. Empirical evaluations demonstrate better robustness of the proposed methodology against non-rigid deformation, positional noise, and outliers, particularly in scenarios where outliers remain distinct from inliers, when compared with prevailing state-of-the-art approaches.
Authors: Sunyuan Qiang, Xianfei Li, Yanyan Liang, Wenlong Liao, Tao He, Pai Peng
Abstract: The nature of diversity in real-world environments necessitates neural network models to expand from closed category settings to accommodate novel emerging categories. In this paper, we study the open-vocabulary object detection (OVD), which facilitates the detection of novel object classes under the supervision of only base annotations and open-vocabulary knowledge. However, we find that the inadequacy of neighboring relationships between regions during the alignment process inevitably constrains the performance on recent distillation-based OVD strategies. To this end, we propose Neighboring Region Attention Alignment (NRAA), which performs alignment within the attention mechanism of a set of neighboring regions to boost the open-vocabulary inference. Specifically, for a given proposal region, we randomly explore the neighboring boxes and conduct our proposed neighboring region attention (NRA) mechanism to extract relationship information. Then, this interaction information is seamlessly provided into the distillation procedure to assist the alignment between the detector and the pre-trained vision-language models (VLMs). Extensive experiments validate that our proposed model exhibits superior performance on open-vocabulary benchmarks.
Authors: Jinwei Lin
Abstract: Neural Radiance Field(NeRF) is an novel implicit method to achieve the 3D reconstruction and representation with a high resolution. After the first research of NeRF is proposed, NeRF has gained a robust developing power and is booming in the 3D modeling, representation and reconstruction areas. However the first and most of the followed research projects based on NeRF is static, which are weak in the practical applications. Therefore, more researcher are interested and focused on the study of dynamic NeRF that is more feasible and useful in practical applications or situations. Compared with the static NeRF, implementing the Dynamic NeRF is more difficult and complex. But Dynamic is more potential in the future even is the basic of Editable NeRF. In this review, we made a detailed and abundant statement for the development and important implementation principles of Dynamci NeRF. The analysis of main principle and development of Dynamic NeRF is from 2021 to 2023, including the most of the Dynamic NeRF projects. What is more, with colorful and novel special designed figures and table, We also made a detailed comparison and analysis of different features of various of Dynamic. Besides, we analyzed and discussed the key methods to implement a Dynamic NeRF. The volume of the reference papers is large. The statements and comparisons are multidimensional. With a reading of this review, the whole development history and most of the main design method or principles of Dynamic NeRF can be easy understood and gained.
Authors: Qinglong Cao, Yuntian Chen, Lu Lu, Hao Sun, Zhenzhong Zeng, Xiaokang Yang, Dongxiao Zhang
Abstract: Large-scale Vision-Language Models (VLMs) have demonstrated exceptional performance in natural vision tasks, motivating researchers across domains to explore domain-specific VLMs. However, the construction of powerful domain-specific VLMs demands vast amounts of annotated data, substantial electrical energy, and computing resources, primarily accessible to industry, yet hindering VLM research in academia. To address this challenge and foster sustainable and equitable VLM research, we present the Generalized Domain Prompt Learning (GDPL) framework. GDPL facilitates the transfer of VLMs' robust recognition capabilities from natural vision to specialized domains, without the need for extensive data or resources. By leveraging small-scale domain-specific foundation models and minimal prompt samples, GDPL empowers the language branch with domain knowledge through quaternion networks, uncovering cross-modal relationships between domain-specific vision features and natural vision-based contextual embeddings. Simultaneously, GDPL guides the vision branch into specific domains through hierarchical propagation of generated vision prompt features, grounded in well-matched vision-language relations. Furthermore, to fully harness the domain adaptation potential of VLMs, we introduce a novel low-rank adaptation approach. Extensive experiments across diverse domains like remote sensing, medical imaging, geology, Synthetic Aperture Radar, and fluid dynamics, validate the efficacy of GDPL, demonstrating its ability to achieve state-of-the-art domain recognition performance in a prompt learning paradigm. Our framework paves the way for sustainable and inclusive VLM research, transcending the barriers between academia and industry.
Authors: Qingpeng Kong, Ching-Hao Chiu, Dewen Zeng, Yu-Jen Chen, Tsung-Yi Ho, Jingtong hu, Yiyu Shi
Abstract: Numerous studies have revealed that deep learning-based medical image classification models may exhibit bias towards specific demographic attributes, such as race, gender, and age. Existing bias mitigation methods often achieve high level of fairness at the cost of significant accuracy degradation. In response to this challenge, we propose an innovative and adaptable Soft Nearest Neighbor Loss-based channel pruning framework, which achieves fairness through channel pruning. Traditionally, channel pruning is utilized to accelerate neural network inference. However, our work demonstrates that pruning can also be a potent tool for achieving fairness. Our key insight is that different channels in a layer contribute differently to the accuracy of different groups. By selectively pruning critical channels that lead to the accuracy difference between the privileged and unprivileged groups, we can effectively improve fairness without sacrificing accuracy significantly. Experiments conducted on two skin lesion diagnosis datasets across multiple sensitive attributes validate the effectiveness of our method in achieving state-of-the-art trade-off between accuracy and fairness. Our code is available at https://github.com/Kqp1227/Sensitive-Channel-Pruning.
Authors: Carmela Calabrese, Stefano Berti, Giulia Pasquale, Lorenzo Natale
Abstract: Addressing multi-label action recognition in videos represents a significant challenge for robotic applications in dynamic environments, especially when the robot is required to cooperate with humans in tasks that involve objects. Existing methods still struggle to recognize unseen actions or require extensive training data. To overcome these problems, we propose Dual-VCLIP, a unified approach for zero-shot multi-label action recognition. Dual-VCLIP enhances VCLIP, a zero-shot action recognition method, with the DualCoOp method for multi-label image classification. The strength of our method is that at training time it only learns two prompts, and it is therefore much simpler than other methods. We validate our method on the Charades dataset that includes a majority of object-based actions, demonstrating that -- despite its simplicity -- our method performs favorably with respect to existing methods on the complete dataset, and promising performance when tested on unseen actions. Our contribution emphasizes the impact of verb-object class-splits during robots' training for new cooperative tasks, highlighting the influence on the performance and giving insights into mitigating biases.
Authors: Volodymyr Fedynyak, Yaroslav Romanus, Bohdan Hlovatskyi, Bohdan Sydor, Oles Dobosevych, Igor Babin, Roman Riazantsev
Abstract: The recent works on Video Object Segmentation achieved remarkable results by matching dense semantic and instance-level features between the current and previous frames for long-time propagation. Nevertheless, global feature matching ignores scene motion context, failing to satisfy temporal consistency. Even though some methods introduce local matching branch to achieve smooth propagation, they fail to model complex appearance changes due to the constraints of the local window. In this paper, we present DeVOS (Deformable VOS), an architecture for Video Object Segmentation that combines memory-based matching with motion-guided propagation resulting in stable long-term modeling and strong temporal consistency. For short-term local propagation, we propose a novel attention mechanism ADVA (Adaptive Deformable Video Attention), allowing the adaption of similarity search region to query-specific semantic features, which ensures robust tracking of complex shape and scale changes. DeVOS employs an optical flow to obtain scene motion features which are further injected to deformable attention as strong priors to learnable offsets. Our method achieves top-rank performance on DAVIS 2017 val and test-dev (88.1%, 83.0%), YouTube-VOS 2019 val (86.6%) while featuring consistent run-time speed and stable memory consumption
Authors: Aaryam Sharma, Chris Czarnecki, Yuhao Chen, Pengcheng Xi, Linlin Xu, Alexander Wong
Abstract: Monitoring dietary intake is a crucial aspect of promoting healthy living. In recent years, advances in computer vision technology have facilitated dietary intake monitoring through the use of images and depth cameras. However, the current state-of-the-art image-based food portion estimation algorithms assume that users take images of their meals one or two times, which can be inconvenient and fail to capture food items that are not visible from a top-down perspective, such as ingredients submerged in a stew. To address these limitations, we introduce an innovative solution that utilizes stationary user-facing cameras to track food items on utensils, not requiring any change of camera perspective after installation. The shallow depth of utensils provides a more favorable angle for capturing food items, and tracking them on the utensil's surface offers a significantly more accurate estimation of dietary intake without the need for post-meal image capture. The system is reliable for estimation of nutritional content of liquid-solid heterogeneous mixtures such as soups and stews. Through a series of experiments, we demonstrate the exceptional potential of our method as a non-invasive, user-friendly, and highly accurate dietary intake monitoring tool.
Authors: Andrew Shin, Yusuke Mori, Kunitake Kaneko
Abstract: Text-to-video generation task has witnessed a notable progress, with the generated outcomes reflecting the text prompts with high fidelity and impressive visual qualities. However, current text-to-video generation models are invariably focused on conveying the visual elements of a single scene, and have so far been indifferent to another important potential of the medium, namely a storytelling. In this paper, we examine text-to-video generation from a storytelling perspective, which has been hardly investigated, and make empirical remarks that spotlight the limitations of current text-to-video generation scheme. We also propose an evaluation framework for storytelling aspects of videos, and discuss the potential future directions.
Authors: Zhimin Li, Jianwei Zhang, Qin Lin, Jiangfeng Xiong, Yanxin Long, Xinchi Deng, Yingfang Zhang, Xingchao Liu, Minbin Huang, Zedong Xiao, Dayou Chen, Jiajun He, Jiahao Li, Wenyue Li, Chen Zhang, Rongwei Quan, Jianxiang Lu, Jiabin Huang, Xiaoyan Yuan, Xiaoxiao Zheng, Yixuan Li, Jihong Zhang, Chao Zhang, Meng Chen, Jie Liu, Zheng Fang, Weiyan Wang, Jinbao Xue, Yangyu Tao, Jianchen Zhu, Kai Liu, Sihuan Lin, Yifu Sun, Yun Li, Dongdong Wang, Mingtao Chen, Zhichao Hu, Xiao Xiao, Yan Chen, Yuhong Liu, Wei Liu, Di Wang, Yong Yang, Jie Jiang, Qinglin Lu
Abstract: We present Hunyuan-DiT, a text-to-image diffusion transformer with fine-grained understanding of both English and Chinese. To construct Hunyuan-DiT, we carefully design the transformer structure, text encoder, and positional encoding. We also build from scratch a whole data pipeline to update and evaluate data for iterative model optimization. For fine-grained language understanding, we train a Multimodal Large Language Model to refine the captions of the images. Finally, Hunyuan-DiT can perform multi-turn multimodal dialogue with users, generating and refining images according to the context. Through our holistic human evaluation protocol with more than 50 professional human evaluators, Hunyuan-DiT sets a new state-of-the-art in Chinese-to-image generation compared with other open-source models. Code and pretrained models are publicly available at github.com/Tencent/HunyuanDiT
Authors: Jie Zhang, Yuhan Li, Yude Wang, Stephen Lin, Shiguang Shan
Abstract: Few-shot segmentation (FSS) aims to train a model which can segment the object from novel classes with a few labeled samples. The insufficient generalization ability of models leads to unsatisfactory performance when the models lack enough labeled data from the novel classes. Considering that there are abundant unlabeled data available, it is promising to improve the generalization ability by exploiting these various data. For leveraging unlabeled data, we propose a novel method, named Image to Pseudo-Episode (IPE), to generate pseudo-episodes from unlabeled data. Specifically, our method contains two modules, i.e., the pseudo-label generation module and the episode generation module. The former module generates pseudo-labels from unlabeled images by the spectral clustering algorithm, and the latter module generates pseudo-episodes from pseudo-labeled images by data augmentation methods. Extensive experiments on PASCAL-$5^i$ and COCO-$20^i$ demonstrate that our method achieves the state-of-the-art performance for FSS.
Authors: Yulin Wang, Yang Yue, Rui Lu, Yizeng Han, Shiji Song, Gao Huang
Abstract: The superior performance of modern visual backbones usually comes with a costly training procedure. We contribute to this issue by generalizing the idea of curriculum learning beyond its original formulation, i.e., training models using easier-to-harder data. Specifically, we reformulate the training curriculum as a soft-selection function, which uncovers progressively more difficult patterns within each example during training, instead of performing easier-to-harder sample selection. Our work is inspired by an intriguing observation on the learning dynamics of visual backbones: during the earlier stages of training, the model predominantly learns to recognize some 'easier-to-learn' discriminative patterns in the data. These patterns, when observed through frequency and spatial domains, incorporate lower-frequency components, and the natural image contents without distortion or data augmentation. Motivated by these findings, we propose a curriculum where the model always leverages all the training data at every learning stage, yet the exposure to the 'easier-to-learn' patterns of each example is initiated first, with harder patterns gradually introduced as training progresses. To implement this idea in a computationally efficient way, we introduce a cropping operation in the Fourier spectrum of the inputs, enabling the model to learn from only the lower-frequency components. Then we show that exposing the contents of natural images can be readily achieved by modulating the intensity of data augmentation. Finally, we integrate these aspects and design curriculum schedules with tailored search algorithms. The resulting method, EfficientTrain++, is simple, general, yet surprisingly effective. It reduces the training time of a wide variety of popular models by 1.5-3.0x on ImageNet-1K/22K without sacrificing accuracy. It also demonstrates efficacy in self-supervised learning (e.g., MAE).
Authors: Nancy Hada, Aditya Singh, Kavita Vemuri
Abstract: Indian folk paintings have a rich mosaic of symbols, colors, textures, and stories making them an invaluable repository of cultural legacy. The paper presents a novel approach to classifying these paintings into distinct art forms and tagging them with their unique salient features. A custom dataset named FolkTalent, comprising 2279 digital images of paintings across 12 different forms, has been prepared using websites that are direct outlets of Indian folk paintings. Tags covering a wide range of attributes like color, theme, artistic style, and patterns are generated using GPT4, and verified by an expert for each painting. Classification is performed employing the RandomForest ensemble technique on fine-tuned Convolutional Neural Network (CNN) models to classify Indian folk paintings, achieving an accuracy of 91.83%. Tagging is accomplished via the prominent fine-tuned CNN-based backbones with a custom classifier attached to its top to perform multi-label image classification. The generated tags offer a deeper insight into the painting, enabling an enhanced search experience based on theme and visual attributes. The proposed hybrid model sets a new benchmark in folk painting classification and tagging, significantly contributing to cataloging India's folk-art heritage.
Authors: Gregory Holste, Mingquan Lin, Ruiwen Zhou, Fei Wang, Lei Liu, Qi Yan, Sarah H. Van Tassel, Kyle Kovacs, Emily Y. Chew, Zhiyong Lu, Zhangyang Wang, Yifan Peng
Abstract: Deep learning has enabled breakthroughs in automated diagnosis from medical imaging, with many successful applications in ophthalmology. However, standard medical image classification approaches only assess disease presence at the time of acquisition, neglecting the common clinical setting of longitudinal imaging. For slow, progressive eye diseases like age-related macular degeneration (AMD) and primary open-angle glaucoma (POAG), patients undergo repeated imaging over time to track disease progression and forecasting the future risk of developing disease is critical to properly plan treatment. Our proposed Longitudinal Transformer for Survival Analysis (LTSA) enables dynamic disease prognosis from longitudinal medical imaging, modeling the time to disease from sequences of fundus photography images captured over long, irregular time periods. Using longitudinal imaging data from the Age-Related Eye Disease Study (AREDS) and Ocular Hypertension Treatment Study (OHTS), LTSA significantly outperformed a single-image baseline in 19/20 head-to-head comparisons on late AMD prognosis and 18/20 comparisons on POAG prognosis. A temporal attention analysis also suggested that, while the most recent image is typically the most influential, prior imaging still provides additional prognostic value.
Authors: Tiantian Zhang, Manxi Lin, Hongda Guo, Xiaofan Zhang, Ka Fung Peter Chiu, Aasa Feragen, Qi Dou
Abstract: The Prostate Imaging Reporting and Data System (PI-RADS) is pivotal in the diagnosis of clinically significant prostate cancer through MRI imaging. Current deep learning-based PI-RADS scoring methods often lack the incorporation of essential PI-RADS clinical guidelines~(PICG) utilized by radiologists, potentially compromising scoring accuracy. This paper introduces a novel approach that adapts a multi-modal large language model (MLLM) to incorporate PICG into PI-RADS scoring without additional annotations and network parameters. We present a two-stage fine-tuning process aimed at adapting MLLMs originally trained on natural images to the MRI data domain while effectively integrating the PICG. In the first stage, we develop a domain adapter layer specifically tailored for processing 3D MRI image inputs and design the MLLM instructions to differentiate MRI modalities effectively. In the second stage, we translate PICG into guiding instructions for the model to generate PICG-guided image features. Through feature distillation, we align scoring network features with the PICG-guided image feature, enabling the scoring network to effectively incorporate the PICG information. We develop our model on a public dataset and evaluate it in a real-world challenging in-house dataset. Experimental results demonstrate that our approach improves the performance of current scoring networks.
Authors: Luisa Schwirten, Jannes Scholz, Daniel Kondermann, Janis Keuper
Abstract: Datasets labelled by human annotators are widely used in the training and testing of machine learning models. In recent years, researchers are increasingly paying attention to label quality. However, it is not always possible to objectively determine whether an assigned label is correct or not. The present work investigates this ambiguity in the annotation of autonomous driving datasets as an important dimension of data quality. Our experiments show that excluding highly ambiguous data from the training improves model performance of a state-of-the-art pedestrian detector in terms of LAMR, precision and F1 score, thereby saving training time and annotation costs. Furthermore, we demonstrate that, in order to safely remove ambiguous instances and ensure the retained representativeness of the training data, an understanding of the properties of the dataset and class under investigation is crucial.
Authors: Jonathan Roberts, Kai Han, Neil Houlsby, Samuel Albanie
Abstract: Large multimodal models (LMMs) have proven flexible and generalisable across many tasks and fields. Although they have strong potential to aid scientific research, their capabilities in this domain are not well characterised. A key aspect of scientific research is the ability to understand and interpret figures, which serve as a rich, compressed source of complex information. In this work, we present SciFIBench, a scientific figure interpretation benchmark. Our main benchmark consists of a 1000-question gold set of multiple-choice questions split between two tasks across 12 categories. The questions are curated from CS arXiv paper figures and captions, using adversarial filtering to find hard negatives and human verification for quality control. We evaluate 26 LMMs on SciFIBench, finding it to be a challenging benchmark. Finally, we investigate the alignment and reasoning faithfulness of the LMMs on augmented question sets from our benchmark. We release SciFIBench to encourage progress in this domain.
Authors: Ruchit Rawal, Khalid Saifullah, Ronen Basri, David Jacobs, Gowthami Somepalli, Tom Goldstein
Abstract: Current datasets for long-form video understanding often fall short of providing genuine long-form comprehension challenges, as many tasks derived from these datasets can be successfully tackled by analyzing just one or a few random frames from a video. To address this issue, we present a novel dataset and benchmark, CinePile, specifically designed for authentic long-form video understanding. This paper details our innovative approach for creating a question-answer dataset, utilizing advanced LLMs with human-in-the-loop and building upon human-generated raw data. Our comprehensive dataset comprises 305,000 multiple-choice questions (MCQs), covering various visual and multimodal aspects, including temporal comprehension, understanding human-object interactions, and reasoning about events or actions within a scene. Additionally, we evaluate recent video-centric LLMs, both open-source and proprietary, on the test split of our dataset. The findings reveal that even state-of-the-art video-centric LLMs significantly lag behind human performance in these tasks, highlighting the complexity and challenge inherent in video understanding. The dataset is available at https://hf.co/datasets/tomg-group-umd/cinepile
Authors: Zihao Wei, Zixuan Pan, Andrew Owens
Abstract: We propose a simple strategy for masking image patches during visual-language contrastive learning that improves the quality of the learned representations and the training speed. During each iteration of training, we randomly mask clusters of visually similar image patches, as measured by their raw pixel intensities. This provides an extra learning signal, beyond the contrastive training itself, since it forces a model to predict words for masked visual structures solely from context. It also speeds up training by reducing the amount of data used in each image. We evaluate the effectiveness of our model by pre-training on a number of benchmarks, finding that it outperforms other masking strategies, such as FLIP, on the quality of the learned representation.
Authors: Lingdong Kong, Shaoyuan Xie, Hanjiang Hu, Yaru Niu, Wei Tsang Ooi, Benoit R. Cottereau, Lai Xing Ng, Yuexin Ma, Wenwei Zhang, Liang Pan, Kai Chen, Ziwei Liu, Weichao Qiu, Wei Zhang, Xu Cao, Hao Lu, Ying-Cong Chen, Caixin Kang, Xinning Zhou, Chengyang Ying, Wentao Shang, Xingxing Wei, Yinpeng Dong, Bo Yang, Shengyin Jiang, Zeliang Ma, Dengyi Ji, Haiwen Li, Xingliang Huang, Yu Tian, Genghua Kou, Fan Jia, Yingfei Liu, Tiancai Wang, Ying Li, Xiaoshuai Hao, Yifan Yang, Hui Zhang, Mengchuan Wei, Yi Zhou, Haimei Zhao, Jing Zhang, Jinke Li, Xiao He, Xiaoqiang Cheng, Bingyang Zhang, Lirong Zhao, Dianlei Ding, Fangsheng Liu, Yixiang Yan, Hongming Wang, Nanfei Ye, Lun Luo, Yubo Tian, Yiwei Zuo, Zhe Cao, Yi Ren, Yunfan Li, Wenjie Liu, Xun Wu, Yifan Mao, Ming Li, Jian Liu, Jiayang Liu, Zihan Qin, Cunxi Chu, Jialei Xu, Wenbo Zhao, Junjun Jiang, Xianming Liu, Ziyan Wang, Chiwei Li, Shilong Li, Chendong Yuan, Songyue Yang, Wentao Liu, Peng Chen, Bin Zhou, Yubo Wang, Chi Zhang, Jianhang Sun, Hai Chen, Xiao Yang, Lizhong Wang, Dongyi Fu, Yongchun Lin, Huitong Yang, Haoang Li, Yadan Luo, Xianjing Cheng, Yong Xu
Abstract: In the realm of autonomous driving, robust perception under out-of-distribution conditions is paramount for the safe deployment of vehicles. Challenges such as adverse weather, sensor malfunctions, and environmental unpredictability can severely impact the performance of autonomous systems. The 2024 RoboDrive Challenge was crafted to propel the development of driving perception technologies that can withstand and adapt to these real-world variabilities. Focusing on four pivotal tasks -- BEV detection, map segmentation, semantic occupancy prediction, and multi-view depth estimation -- the competition laid down a gauntlet to innovate and enhance system resilience against typical and atypical disturbances. This year's challenge consisted of five distinct tracks and attracted 140 registered teams from 93 institutes across 11 countries, resulting in nearly one thousand submissions evaluated through our servers. The competition culminated in 15 top-performing solutions, which introduced a range of innovative approaches including advanced data augmentation, multi-sensor fusion, self-supervised learning for error correction, and new algorithmic strategies to enhance sensor robustness. These contributions significantly advanced the state of the art, particularly in handling sensor inconsistencies and environmental variability. Participants, through collaborative efforts, pushed the boundaries of current technologies, showcasing their potential in real-world scenarios. Extensive evaluations and analyses provided insights into the effectiveness of these solutions, highlighting key trends and successful strategies for improving the resilience of driving perception systems. This challenge has set a new benchmark in the field, providing a rich repository of techniques expected to guide future research in this field.
Authors: Christy Dunlap, Changgen Li, Hari Pandey, Ngan Le, Han Hu
Abstract: This paper presents BubbleID, a sophisticated deep learning architecture designed to comprehensively identify both static and dynamic attributes of bubbles within sequences of boiling images. By amalgamating segmentation powered by Mask R-CNN with SORT-based tracking techniques, the framework is capable of analyzing each bubble's location, dimensions, interface shape, and velocity over its lifetime, and capturing dynamic events such as bubble departure. BubbleID is trained and tested on boiling images across diverse heater surfaces and operational settings. This paper also offers a comparative analysis of bubble interface dynamics prior to and post-critical heat flux (CHF) conditions.
Authors: Po-Hsun Chu, Ching-Han Chen
Abstract: Binary convolutional neural networks (BCNNs) provide a potential solution to reduce the memory requirements and computational costs associated with deep neural networks (DNNs). However, achieving a trade-off between performance and computational resources remains a significant challenge. Furthermore, the fully connected layer of BCNNs has evolved into a significant computational bottleneck. This is mainly due to the conventional practice of excluding the input layer and fully connected layer from binarization to prevent a substantial loss in accuracy. In this paper, we propose a hybrid model named ReActXGB, where we replace the fully convolutional layer of ReActNet-A with XGBoost. This modification targets to narrow the performance gap between BCNNs and real-valued networks while maintaining lower computational costs. Experimental results on the FashionMNIST benchmark demonstrate that ReActXGB outperforms ReActNet-A by 1.47% in top-1 accuracy, along with a reduction of 7.14% in floating-point operations (FLOPs) and 1.02% in model size.
Authors: Quentin Ferdinand (ENSTA Bretagne, Lab-STICC\_MATRIX), Gilles Le Chenadec (ENSTA Bretagne, Lab-STICC\_MATRIX), Benoit Clement (CROSSING, ENSTA Bretagne, Lab-STICC\_MATRIX), Panagiotis Papadakis (Lab-STICC\_RAMBO, IMT Atlantique - INFO), Quentin Oliveau
Abstract: Class incremental learning consists in training discriminative models to classify an increasing number of classes over time. However, doing so using only the newly added class data leads to the known problem of catastrophic forgetting of the previous classes. Recently, dynamic deep learning architectures have been shown to exhibit a better stability-plasticity trade-off by dynamically adding new feature extractors to the model in order to learn new classes followed by a compression step to scale the model back to its original size, thus avoiding a growing number of parameters. In this context, we propose a new algorithm that enhances the compression of previous class knowledge by cutting and mixing patches of previous class samples with the new images during compression using our Rehearsal-CutMix method. We show that this new data augmentation reduces catastrophic forgetting by specifically targeting past class information and improving its compression. Extensive experiments performed on the CIFAR and ImageNet datasets under diverse incremental learning evaluation protocols demonstrate that our approach consistently outperforms the state-of-the-art . The code will be made available upon publication of our work.
Authors: Jonathan Windle, Iain Matthews, Sarah Taylor
Abstract: Co-speech gesturing is an important modality in conversation, providing context and social cues. In character animation, appropriate and synchronised gestures add realism, and can make interactive agents more engaging. Historically, methods for automatically generating gestures were predominantly audio-driven, exploiting the prosodic and speech-related content that is encoded in the audio signal. In this paper we instead experiment with using LLM features for gesture generation that are extracted from text using LLAMA2. We compare against audio features, and explore combining the two modalities in both objective tests and a user study. Surprisingly, our results show that LLAMA2 features on their own perform significantly better than audio features and that including both modalities yields no significant difference to using LLAMA2 features in isolation. We demonstrate that the LLAMA2 based model can generate both beat and semantic gestures without any audio input, suggesting LLMs can provide rich encodings that are well suited for gesture generation.
Authors: Chi-en Amy Tai, Alexander Wong
Abstract: Breast cancer is a significant cause of death from cancer in women globally, highlighting the need for improved diagnostic imaging to enhance patient outcomes. Accurate tumour identification is essential for diagnosis, treatment, and monitoring, emphasizing the importance of advanced imaging technologies that provide detailed views of tumour characteristics and disease. Synthetic correlated diffusion imaging (CDI$^s$) is a recent method that has shown promise for prostate cancer delineation compared to current MRI images. In this paper, we explore tuning the coefficients in the computation of CDI$^s$ for breast cancer tumour delineation by maximizing the area under the receiver operating characteristic curve (AUC) using a Nelder-Mead simplex optimization strategy. We show that the best AUC is achieved by the CDI$^s$ - Optimized modality, outperforming the best gold-standard modality by 0.0044. Notably, the optimized CDI$^s$ modality also achieves AUC values over 0.02 higher than the Unoptimized CDI$^s$ value, demonstrating the importance of optimizing the CDI$^s$ exponents for the specific cancer application.
Authors: Wenqi Dong, Bangbang Yang, Lin Ma, Xiao Liu, Liyuan Cui, Hujun Bao, Yuewen Ma, Zhaopeng Cui
Abstract: As humans, we aspire to create media content that is both freely willed and readily controlled. Thanks to the prominent development of generative techniques, we now can easily utilize 2D diffusion methods to synthesize images controlled by raw sketch or designated human poses, and even progressively edit/regenerate local regions with masked inpainting. However, similar workflows in 3D modeling tasks are still unavailable due to the lack of controllability and efficiency in 3D generation. In this paper, we present a novel controllable and interactive 3D assets modeling framework, named Coin3D. Coin3D allows users to control the 3D generation using a coarse geometry proxy assembled from basic shapes, and introduces an interactive generation workflow to support seamless local part editing while delivering responsive 3D object previewing within a few seconds. To this end, we develop several techniques, including the 3D adapter that applies volumetric coarse shape control to the diffusion model, proxy-bounded editing strategy for precise part editing, progressive volume cache to support responsive preview, and volume-SDS to ensure consistent mesh reconstruction. Extensive experiments of interactive generation and editing on diverse shape proxies demonstrate that our method achieves superior controllability and flexibility in the 3D assets generation task.
Authors: Simegnew Yihunie Alaba
Abstract: Global Positioning System (GPS) navigation provides accurate positioning with global coverage, making it a reliable option in open areas with unobstructed sky views. However, signal degradation may occur in indoor spaces and urban canyons. In contrast, Inertial Measurement Units (IMUs) consist of gyroscopes and accelerometers that offer relative motion information such as acceleration and rotational changes. Unlike GPS, IMUs do not rely on external signals, making them useful in GPS-denied environments. Nonetheless, IMUs suffer from drift over time due to the accumulation of errors while integrating acceleration to determine velocity and position. Therefore, fusing the GPS and IMU is crucial for enhancing the reliability and precision of navigation systems in autonomous vehicles, especially in environments where GPS signals are compromised. To ensure smooth navigation and overcome the limitations of each sensor, the proposed method fuses GPS and IMU data. This sensor fusion uses the Unscented Kalman Filter (UKF) Bayesian filtering technique. The proposed navigation system is designed to be robust, delivering continuous and accurate positioning critical for the safe operation of autonomous vehicles, particularly in GPS-denied environments. This project uses KITTI GNSS and IMU datasets for experimental validation, showing that the GNSS-IMU fusion technique reduces GNSS-only data's RMSE. The RMSE decreased from 13.214, 13.284, and 13.363 to 4.271, 5.275, and 0.224 for the x-axis, y-axis, and z-axis, respectively. The experimental result using UKF shows promising direction in improving autonomous vehicle navigation using GPS and IMU sensor fusion using the best of two sensors in GPS-denied environments.
Authors: Talat Zehra, Joseph Marino, Wendy Wang, Grigoriy Frantsuzov, Saad Nadeem
Abstract: Histology slide digitization is becoming essential for telepathology (remote consultation), knowledge sharing (education), and using the state-of-the-art artificial intelligence algorithms (augmented/automated end-to-end clinical workflows). However, the cumulative costs of digital multi-slide high-speed brightfield scanners, cloud/on-premises storage, and personnel (IT and technicians) make the current slide digitization workflows out-of-reach for limited-resource settings, further widening the health equity gap; even single-slide manual scanning commercial solutions are costly due to hardware requirements (high-resolution cameras, high-spec PC/workstation, and support for only high-end microscopes). In this work, we present a new cloud slide digitization workflow for creating scanner-quality whole-slide images (WSIs) from uploaded low-quality videos, acquired from cheap and inexpensive microscopes with built-in cameras. Specifically, we present a pipeline to create stitched WSIs while automatically deblurring out-of-focus regions, upsampling input 10X images to 40X resolution, and reducing brightness/contrast and light-source illumination variations. We demonstrate the WSI creation efficacy from our workflow on World Health Organization-declared neglected tropical disease, Cutaneous Leishmaniasis (prevalent only in the poorest regions of the world and only diagnosed by sub-specialist dermatopathologists, rare in poor countries), as well as other common pathologies on core biopsies of breast, liver, duodenum, stomach and lymph node. The code and pretrained models will be accessible via our GitHub (https://github.com/nadeemlab/DeepLIIF), and the cloud platform will be available at https://deepliif.org for uploading microscope videos and downloading/viewing WSIs with shareable links (no sign-in required) for telepathology and knowledge sharing.
URLs: https://github.com/nadeemlab/DeepLIIF),, https://deepliif.org
Authors: Rachel Hong, William Agnew, Tadayoshi Kohno, Jamie Morgenstern
Abstract: As training datasets become increasingly drawn from unstructured, uncontrolled environments such as the web, researchers and industry practitioners have increasingly relied upon data filtering techniques to "filter out the noise" of web-scraped data. While datasets have been widely shown to reflect the biases and values of their creators, in this paper we contribute to an emerging body of research that assesses the filters used to create these datasets. We show that image-text data filtering also has biases and is value-laden, encoding specific notions of what is counted as "high-quality" data. In our work, we audit a standard approach of image-text CLIP-filtering on the academic benchmark DataComp's CommonPool by analyzing discrepancies of filtering through various annotation techniques across multiple modalities of image, text, and website source. We find that data relating to several imputed demographic groups -- such as LGBTQ+ people, older women, and younger men -- are associated with higher rates of exclusion. Moreover, we demonstrate cases of exclusion amplification: not only are certain marginalized groups already underrepresented in the unfiltered data, but CLIP-filtering excludes data from these groups at higher rates. The data-filtering step in the machine learning pipeline can therefore exacerbate representation disparities already present in the data-gathering step, especially when existing filters are designed to optimize a specifically-chosen downstream performance metric like zero-shot image classification accuracy. Finally, we show that the NSFW filter fails to remove sexually-explicit content from CommonPool, and that CLIP-filtering includes several categories of copyrighted content at high rates. Our conclusions point to a need for fundamental changes in dataset creation and filtering practices.
Authors: Katherine Henneberger, Jing Qin
Abstract: Tensors serve as a crucial tool in the representation and analysis of complex, multi-dimensional data. As data volumes continue to expand, there is an increasing demand for developing optimization algorithms that can directly operate on tensors to deliver fast and effective computations. Many problems in real-world applications can be formulated as the task of recovering high-order tensors characterized by sparse and/or low-rank structures. In this work, we propose novel Kaczmarz algorithms with a power of the $\ell_1$-norm regularization for reconstructing high-order tensors by exploiting sparsity and/or low-rankness of tensor data. In addition, we develop both a block and an accelerated variant, along with a thorough convergence analysis of these algorithms. A variety of numerical experiments on both synthetic and real-world datasets demonstrate the effectiveness and significant potential of the proposed methods in image and video processing tasks, such as image sequence destriping and video deconvolution.
Authors: Lucas Aronson (Department of Radiology, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA), Ruben Ngnitewe Massaa (Department of Radiology, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA), Syed Jamal Safdar Gardezi (Department of Radiology, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA), Andrew L. Wentland (Department of Radiology, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA, Department of Medical Physics, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA, Department of Biomedical Engineering, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA)
Abstract: Objective: Automated segmentation tools are useful for calculating kidney volumes rapidly and accurately. Furthermore, these tools have the power to facilitate large-scale image-based artificial intelligence projects by generating input labels, such as for image registration algorithms. Prior automated segmentation models have largely ignored non-contrast computed tomography (CT) imaging. This work aims to implement and train a deep learning (DL) model to segment the kidneys and cystic renal lesions (CRLs) from non-contrast CT scans. Methods: Manual segmentation of the kidneys and CRLs was performed on 150 non-contrast abdominal CT scans. The data were divided into an 80/20 train/test split and a deep learning (DL) model was trained to segment the kidneys and CRLs. Various scoring metrics were used to assess model performance, including the Dice Similarity Coefficient (DSC), Jaccard Index (JI), and absolute and percent error kidney volume and lesion volume. Bland-Altman (B-A) analysis was performed to compare manual versus DL-based kidney volumes. Results: The DL model achieved a median kidney DSC of 0.934, median CRL DSC of 0.711, and total median study DSC of 0.823. Average volume errors were 0.9% for renal parenchyma, 37.0% for CRLs, and 2.2% overall. B-A analysis demonstrated that DL-based volumes tended to be greater than manual volumes, with a mean bias of +3.0 ml (+/- 2 SD of +/- 50.2 ml). Conclusion: A deep learning model trained to segment kidneys and cystic renal lesions on non-contrast CT examinations was able to provide highly accurate segmentations, with a median kidney Dice Similarity Coefficient of 0.934. Keywords: deep learning; kidney segmentation; artificial intelligence; convolutional neural networks.
Authors: Yacine Izza, Xuanxiang Huang, Antonio Morgado, Jordi Planes, Alexey Ignatiev, Joao Marques-Silva
Abstract: The uses of machine learning (ML) have snowballed in recent years. In many cases, ML models are highly complex, and their operation is beyond the understanding of human decision-makers. Nevertheless, some uses of ML models involve high-stakes and safety-critical applications. Explainable artificial intelligence (XAI) aims to help human decision-makers in understanding the operation of such complex ML models, thus eliciting trust in their operation. Unfortunately, the majority of past XAI work is based on informal approaches, that offer no guarantees of rigor. Unsurprisingly, there exists comprehensive experimental and theoretical evidence confirming that informal methods of XAI can provide human-decision makers with erroneous information. Logic-based XAI represents a rigorous approach to explainability; it is model-based and offers the strongest guarantees of rigor of computed explanations. However, a well-known drawback of logic-based XAI is the complexity of logic reasoning, especially for highly complex ML models. Recent work proposed distance-restricted explanations, i.e. explanations that are rigorous provided the distance to a given input is small enough. Distance-restricted explainability is tightly related with adversarial robustness, and it has been shown to scale for moderately complex ML models, but the number of inputs still represents a key limiting factor. This paper investigates novel algorithms for scaling up the performance of logic-based explainers when computing and enumerating ML model explanations with a large number of inputs.
Authors: Yuchen Wang, Xingyu Zhu, Guanhui Ye, Shiyao Zhang, Xuetao Wei
Abstract: DNN-based watermarking methods are rapidly developing and delivering impressive performances. Recent advances achieve resolution-agnostic image watermarking by reducing the variant resolution watermarking problem to a fixed resolution watermarking problem. However, such a reduction process can potentially introduce artifacts and low robustness. To address this issue, we propose the first, to the best of our knowledge, Resolution-Agnostic Image WaterMarking (RAIMark) framework by watermarking the implicit neural representation (INR) of image. Unlike previous methods, our method does not rely on the previous reduction process by directly watermarking the continuous signal instead of image pixels, thus achieving resolution-agnostic watermarking. Precisely, given an arbitrary-resolution image, we fit an INR for the target image. As a continuous signal, such an INR can be sampled to obtain images with variant resolutions. Then, we quickly fine-tune the fitted INR to get a watermarked INR conditioned on a binary secret message. A pre-trained watermark decoder extracts the hidden message from any sampled images with arbitrary resolutions. By directly watermarking INR, we achieve resolution-agnostic watermarking with increased robustness. Extensive experiments show that our method outperforms previous methods with significant improvements: averagely improved bit accuracy by 7%$\sim$29%. Notably, we observe that previous methods are vulnerable to at least one watermarking attack (e.g. JPEG, crop, resize), while ours are robust against all watermarking attacks.
Authors: Andre Kassis, Urs Hengartner
Abstract: Reports regarding the misuse of $\textit{Generative AI}$ ($\textit{GenAI}$) to create harmful deepfakes are emerging daily. Recently, defensive watermarking, which enables $\textit{GenAI}$ providers to hide fingerprints in their images to later use for deepfake detection, has been on the rise. Yet, its potential has not been fully explored. We present $\textit{UnMarker}$ -- the first practical $\textit{universal}$ attack on defensive watermarking. Unlike existing attacks, $\textit{UnMarker}$ requires no detector feedback, no unrealistic knowledge of the scheme or similar models, and no advanced denoising pipelines that may not be available. Instead, being the product of an in-depth analysis of the watermarking paradigm revealing that robust schemes must construct their watermarks in the spectral amplitudes, $\textit{UnMarker}$ employs two novel adversarial optimizations to disrupt the spectra of watermarked images, erasing the watermarks. Evaluations against the $\textit{SOTA}$ prove its effectiveness, not only defeating traditional schemes while retaining superior quality compared to existing attacks but also breaking $\textit{semantic}$ watermarks that alter the image's structure, reducing the best detection rate to $43\%$ and rendering them useless. To our knowledge, $\textit{UnMarker}$ is the first practical attack on $\textit{semantic}$ watermarks, which have been deemed the future of robust watermarking. $\textit{UnMarker}$ casts doubts on the very penitential of this countermeasure and exposes its paradoxical nature as designing schemes for robustness inevitably compromises other robustness aspects.
Authors: Yihong Chen, Zhen Fan, Shuai Dong, Zhiwei Chen, Wenjie Li, Minghui Qin, Min Zeng, Xubing Lu, Guofu Zhou, Xingsen Gao, Jun-Ming Liu
Abstract: Stereo image super-resolution (SR) refers to the reconstruction of a high-resolution (HR) image from a pair of low-resolution (LR) images as typically captured by a dual-camera device. To enhance the quality of SR images, most previous studies focused on increasing the number and size of feature maps and introducing complex and computationally intensive structures, resulting in models with high computational complexity. Here, we propose a simple yet efficient stereo image SR model called NAFRSSR, which is modified from the previous state-of-the-art model NAFSSR by introducing recursive connections and lightweighting the constituent modules. Our NAFRSSR model is composed of nonlinear activation free and group convolution-based blocks (NAFGCBlocks) and depth-separated stereo cross attention modules (DSSCAMs). The NAFGCBlock improves feature extraction and reduces number of parameters by removing the simple channel attention mechanism from NAFBlock and using group convolution. The DSSCAM enhances feature fusion and reduces number of parameters by replacing 1x1 pointwise convolution in SCAM with weight-shared 3x3 depthwise convolution. Besides, we propose to incorporate trainable edge detection operator into NAFRSSR to further improve the model performance. Four variants of NAFRSSR with different sizes, namely, NAFRSSR-Mobile (NAFRSSR-M), NAFRSSR-Tiny (NAFRSSR-T), NAFRSSR-Super (NAFRSSR-S) and NAFRSSR-Base (NAFRSSR-B) are designed, and they all exhibit fewer parameters, higher PSNR/SSIM, and faster speed than the previous state-of-the-art models. In particular, to the best of our knowledge, NAFRSSR-M is the lightest (0.28M parameters) and fastest (50 ms inference time) model achieving an average PSNR/SSIM as high as 24.657 dB/0.7622 on the benchmark datasets. Codes and models will be released at https://github.com/JNUChenYiHong/NAFRSSR.
Authors: Melanie Dohmen (Bayer AG, Berlin, Germany), Mark Klemens (Bayer AG, Berlin, Germany), Ivo Baltruschat (Bayer AG, Berlin, Germany), Tuan Truong (Bayer AG, Berlin, Germany), Matthias Lenga (Bayer AG, Berlin, Germany)
Abstract: Image-to-image translation can create large impact in medical imaging, i.e. if images of a patient can be translated to another modality, type or sequence for better diagnosis. However, these methods must be validated by human reader studies, which are costly and restricted to small samples. Automatic evaluation of large samples to pre-evaluate and continuously improve methods before human validation is needed. In this study, we give an overview of reference and non-reference metrics for image synthesis assessment and investigate the ability of nine metrics, that need a reference (SSIM, MS-SSIM, PSNR, MSE, NMSE, MAE, LPIPS, NMI and PCC) and three non-reference metrics (BLUR, MSN, MNG) to detect 11 kinds of distortions in MR images from the BraSyn dataset. In addition we test a downstream segmentation metric and the effect of three normalization methods (Minmax, cMinMax and Zscore). Although PSNR and SSIM are frequently used to evaluate generative models for image-to-image-translation tasks in the medical domain, they show very specific shortcomings. SSIM ignores blurring but is very sensitive to intensity shifts in unnormalized MR images. PSNR is even more sensitive to different normalization methods and hardly measures the degree of distortions. Further metrics, such as LPIPS, NMI and DICE can be very useful to evaluate other similarity aspects. If the images to be compared are misaligned, most metrics are flawed. By carefully selecting and reasonably combining image similarity metrics, the training and selection of generative models for MR image synthesis can be improved. Many aspects of their output can be validated before final and costly evaluation by trained radiologists is conducted.
Authors: Rezkellah Noureddine Khiati, Pierre-Yves Brillet, Aur\'elien Justet, Radu Ispa, Catalin Fetita
Abstract: This paper addresses the problem of pathological lung segmentation, a significant challenge in medical image analysis, particularly pronounced in cases of peripheral opacities (severe fibrosis and consolidation) because of the textural similarity between lung tissue and surrounding areas. To overcome these challenges, this paper emphasizes the use of CycleGAN for unpaired image-to-image translation, in order to provide an augmentation method able to generate fake pathological images matching an existing ground truth. Although previous studies have employed CycleGAN, they often neglect the challenge of shape deformation, which is crucial for accurate medical image segmentation. Our work introduces an innovative strategy that incorporates additional loss functions. Specifically, it proposes an L1 loss based on the lung surrounding which shape is constrained to remain unchanged at the transition from the healthy to pathological domains. The lung surrounding is derived based on ground truth lung masks available in the healthy domain. Furthermore, preprocessing steps, such as cropping based on ribs/vertebra locations, are applied to refine the input for the CycleGAN, ensuring that the network focus on the lung region. This is essential to avoid extraneous biases, such as the zoom effect bias, which can divert attention from the main task. The method is applied to enhance in semi-supervised manner the lung segmentation process by employing a U-Net model trained with on-the-fly data augmentation incorporating synthetic pathological tissues generated by the CycleGAN model. Preliminary results from this research demonstrate significant qualitative and quantitative improvements, setting a new benchmark in the field of pathological lung segmentation. Our code is available at https://github.com/noureddinekhiati/Semi-supervised-lung-segmentation
URLs: https://github.com/noureddinekhiati/Semi-supervised-lung-segmentation
Authors: Jared Mejia, Victoria Dean, Tess Hellebrekers, Abhinav Gupta
Abstract: Although pre-training on a large amount of data is beneficial for robot learning, current paradigms only perform large-scale pretraining for visual representations, whereas representations for other modalities are trained from scratch. In contrast to the abundance of visual data, it is unclear what relevant internet-scale data may be used for pretraining other modalities such as tactile sensing. Such pretraining becomes increasingly crucial in the low-data regimes common in robotics applications. In this paper, we address this gap by using contact microphones as an alternative tactile sensor. Our key insight is that contact microphones capture inherently audio-based information, allowing us to leverage large-scale audio-visual pretraining to obtain representations that boost the performance of robotic manipulation. To the best of our knowledge, our method is the first approach leveraging large-scale multisensory pre-training for robotic manipulation. For supplementary information including videos of real robot experiments, please see https://sites.google.com/view/hearing-touch.
Authors: Tianhao Peng, Chen Feng, Duolikun Danier, Fan Zhang, David Bull
Abstract: With recent advances in deep learning, numerous algorithms have been developed to enhance video quality, reduce visual artefacts and improve perceptual quality. However, little research has been reported on the quality assessment of enhanced content - the evaluation of enhancement methods is often based on quality metrics that were designed for compression applications. In this paper, we propose a novel blind deep video quality assessment (VQA) method specifically for enhanced video content. It employs a new Recurrent Memory Transformer (RMT) based network architecture to obtain video quality representations, which is optimised through a novel content-quality-aware contrastive learning strategy based on a new database containing 13K training patches with enhanced content. The extracted quality representations are then combined through linear regression to generate video-level quality indices. The proposed method, RMT-BVQA, has been evaluated on the VDPVE (VQA Dataset for Perceptual Video Enhancement) database through a five-fold cross validation. The results show its superior correlation performance when compared to ten existing no-reference quality metrics.
Authors: Khoi Tran Dang, Kevin Delmas, J\'er\'emie Guiochet, Joris Gu\'erin
Abstract: With the increasing use of neural networks in critical systems, runtime monitoring becomes essential to reject unsafe predictions during inference. Various techniques have emerged to establish rejection scores that maximize the separability between the distributions of safe and unsafe predictions. The efficacy of these approaches is mostly evaluated using threshold-agnostic metrics, such as the area under the receiver operating characteristic curve. However, in real-world applications, an effective monitor also requires identifying a good threshold to transform these scores into meaningful binary decisions. Despite the pivotal importance of threshold optimization, this problem has received little attention. A few studies touch upon this question, but they typically assume that the runtime data distribution mirrors the training distribution, which is a strong assumption as monitors are supposed to safeguard a system against potentially unforeseen threats. In this work, we present rigorous experiments on various image datasets to investigate: 1. The effectiveness of monitors in handling unforeseen threats, which are not available during threshold adjustments. 2. Whether integrating generic threats into the threshold optimization scheme can enhance the robustness of monitors.
Authors: Jue Jiang, Aneesh Rangnekar, Harini Veeraraghavan
Abstract: Self-supervised learning (SSL) is an approach to extract useful feature representations from unlabeled data, and enable fine-tuning on downstream tasks with limited labeled examples. Self-pretraining is a SSL approach that uses the curated task dataset for both pretraining the networks and fine-tuning them. Availability of large, diverse, and uncurated public medical image sets provides the opportunity to apply SSL in the "wild" and potentially extract features robust to imaging variations. However, the benefit of wild- vs self-pretraining has not been studied for medical image analysis. In this paper, we compare robustness of wild versus self-pretrained transformer (vision transformer [ViT] and hierarchical shifted window [Swin]) models to computed tomography (CT) imaging differences for non-small cell lung cancer (NSCLC) segmentation. Wild-pretrained Swin models outperformed self-pretrained Swin for the various imaging acquisitions. ViT resulted in similar accuracy for both wild- and self-pretrained models. Masked image prediction pretext task that forces networks to learn the local structure resulted in higher accuracy compared to contrastive task that models global image information. Wild-pretrained models resulted in higher feature reuse at the lower level layers and feature differentiation close to output layer after fine-tuning. Hence, we conclude: Wild-pretrained networks were more robust to analyzed CT imaging differences for lung tumor segmentation than self-pretrained methods. Swin architecture benefited from such pretraining more than ViT.
Authors: Mateusz Cedro, Marcin Chlebus
Abstract: The increasing complexity of Artificial Intelligence models poses challenges to interpretability, particularly in the healthcare sector. This study investigates the impact of deep learning model complexity and Explainable AI (XAI) efficacy, utilizing four ResNet architectures (ResNet-18, 34, 50, 101). Through methodical experimentation on 4,369 lung X-ray images of COVID-19-infected and healthy patients, the research evaluates models' classification performance and the relevance of corresponding XAI explanations with respect to the ground-truth disease masks. Results indicate that the increase in model complexity is associated with a decrease in classification accuracy and AUC-ROC scores (ResNet-18: 98.4%, 0.997; ResNet-101: 95.9%, 0.988). Notably, in eleven out of twelve statistical tests performed, no statistically significant differences occurred between XAI quantitative metrics - Relevance Rank Accuracy and the proposed Positive Attribution Ratio - across trained models. These results suggest that increased model complexity does not consistently lead to higher performance or relevance of explanations for models' decision-making processes.
Authors: Beilei Cui, Mobarakol Islam, Long Bai, An Wang, Hongliang Ren
Abstract: Depth estimation plays a crucial role in various tasks within endoscopic surgery, including navigation, surface reconstruction, and augmented reality visualization. Despite the significant achievements of foundation models in vision tasks, including depth estimation, their direct application to the medical domain often results in suboptimal performance. This highlights the need for efficient adaptation methods to adapt these models to endoscopic depth estimation. We propose Endoscopic Depth Any Camera (EndoDAC) which is an efficient self-supervised depth estimation framework that adapts foundation models to endoscopic scenes. Specifically, we develop the Dynamic Vector-Based Low-Rank Adaptation (DV-LoRA) and employ Convolutional Neck blocks to tailor the foundational model to the surgical domain, utilizing remarkably few trainable parameters. Given that camera information is not always accessible, we also introduce a self-supervised adaptation strategy that estimates camera intrinsics using the pose encoder. Our framework is capable of being trained solely on monocular surgical videos from any camera, ensuring minimal training costs. Experiments demonstrate that our approach obtains superior performance even with fewer training epochs and unaware of the ground truth camera intrinsics. Code is available at https://github.com/BeileiCui/EndoDAC.
Authors: Zichen Wang, Xi Deng, Ziyi Zhang, Wenzel Jakob, Steve Marschner
Abstract: We present a simple algorithm for differentiable rendering of surfaces represented by Signed Distance Fields (SDF), which makes it easy to integrate rendering into gradient-based optimization pipelines. To tackle visibility-related derivatives that make rendering non-differentiable, existing physically based differentiable rendering methods often rely on elaborate guiding data structures or reparameterization with a global impact on variance. In this article, we investigate an alternative that embraces nonzero bias in exchange for low variance and architectural simplicity. Our method expands the lower-dimensional boundary integral into a thin band that is easy to sample when the underlying surface is represented by an SDF. We demonstrate the performance and robustness of our formulation in end-to-end inverse rendering tasks, where it obtains results that are competitive with or superior to existing work.
Authors: Wei Sun, Haoning Wu, Zicheng Zhang, Jun Jia, Zhichao Zhang, Linhan Cao, Qiubo Chen, Xiongkuo Min, Weisi Lin, Guangtao Zhai
Abstract: In this paper, we present a simple but effective method to enhance blind video quality assessment (BVQA) models for social media videos. Motivated by previous researches that leverage pre-trained features extracted from various computer vision models as the feature representation for BVQA, we further explore rich quality-aware features from pre-trained blind image quality assessment (BIQA) and BVQA models as auxiliary features to help the BVQA model to handle complex distortions and diverse content of social media videos. Specifically, we use SimpleVQA, a BVQA model that consists of a trainable Swin Transformer-B and a fixed SlowFast, as our base model. The Swin Transformer-B and SlowFast components are responsible for extracting spatial and motion features, respectively. Then, we extract three kinds of features from Q-Align, LIQE, and FAST-VQA to capture frame-level quality-aware features, frame-level quality-aware along with scene-specific features, and spatiotemporal quality-aware features, respectively. Through concatenating these features, we employ a multi-layer perceptron (MLP) network to regress them into quality scores. Experimental results demonstrate that the proposed model achieves the best performance on three public social media VQA datasets. Moreover, the proposed model won first place in the CVPR NTIRE 2024 Short-form UGC Video Quality Assessment Challenge. The code is available at \url{https://github.com/sunwei925/RQ-VQA.git}.
Authors: Claus Hofmann, Simon Schmid, Bernhard Lehner, Daniel Klotz, Sepp Hochreiter
Abstract: Out-of-distribution (OOD) detection is critical when deploying machine learning models in the real world. Outlier exposure methods, which incorporate auxiliary outlier data in the training process, can drastically improve OOD detection performance compared to approaches without advanced training strategies. We introduce Hopfield Boosting, a boosting approach, which leverages modern Hopfield energy (MHE) to sharpen the decision boundary between the in-distribution and OOD data. Hopfield Boosting encourages the model to concentrate on hard-to-distinguish auxiliary outlier examples that lie close to the decision boundary between in-distribution and auxiliary outlier data. Our method achieves a new state-of-the-art in OOD detection with outlier exposure, improving the FPR95 metric from 2.28 to 0.92 on CIFAR-10 and from 11.76 to 7.94 on CIFAR-100.
Authors: Xingzhe Su, Wenwen Qiang, Jie Hu, Fengge Wu, Changwen Zheng, Fuchun Sun
Abstract: Generative adversarial networks (GANs) have achieved remarkable progress in the natural image field. However, when applying GANs in the remote sensing (RS) image generation task, an extraordinary phenomenon is observed: the GAN model is more sensitive to the size of training data for RS image generation than for natural image generation. In other words, the generation quality of RS images will change significantly with the number of training categories or samples per category. In this paper, we first analyze this phenomenon from two kinds of toy experiments and conclude that the amount of feature information contained in the GAN model decreases with reduced training data. Then we establish a structural causal model (SCM) of the data generation process and interpret the generated data as the counterfactuals. Based on this SCM, we theoretically prove that the quality of generated images is positively correlated with the amount of feature information. This provides insights for enriching the feature information learned by the GAN model during training. Consequently, we propose two innovative adjustment schemes, namely Uniformity Regularization (UR) and Entropy Regularization (ER), to increase the information learned by the GAN model at the distributional and sample levels, respectively. We theoretically and empirically demonstrate the effectiveness and versatility of our methods. Extensive experiments on three RS datasets and two natural datasets show that our methods outperform the well-established models on RS image generation tasks. The source code is available at https://github.com/rootSue/Causal-RSGAN.
Authors: Tarun Kalluri, Weiyao Wang, Heng Wang, Manmohan Chandraker, Lorenzo Torresani, Du Tran
Abstract: Many top-down architectures for instance segmentation achieve significant success when trained and tested on pre-defined closed-world taxonomy. However, when deployed in the open world, they exhibit notable bias towards seen classes and suffer from significant performance drop. In this work, we propose a novel approach for open world instance segmentation called bottom-Up and top-Down Open-world Segmentation (UDOS) that combines classical bottom-up segmentation algorithms within a top-down learning framework. UDOS first predicts parts of objects using a top-down network trained with weak supervision from bottom-up segmentations. The bottom-up segmentations are class-agnostic and do not overfit to specific taxonomies. The part-masks are then fed into affinity-based grouping and refinement modules to predict robust instance-level segmentations. UDOS enjoys both the speed and efficiency from the top-down architectures and the generalization ability to unseen categories from bottom-up supervision. We validate the strengths of UDOS on multiple cross-category as well as cross-dataset transfer tasks from 5 challenging datasets including MS-COCO, LVIS, ADE20k, UVO and OpenImages, achieving significant improvements over state-of-the-art across the board. Our code and models are available on our project page.
Authors: Keumgang Cha, Junghoon Seo, Taekyung Lee
Abstract: As the potential of foundation models in visual tasks has garnered significant attention, pretraining these models before downstream tasks has become a crucial step. The three key factors in pretraining foundation models are the pretraining method, the size of the pretraining dataset, and the number of model parameters. Recently, research in the remote sensing field has focused primarily on the pretraining method and the size of the dataset, with limited emphasis on the number of model parameters. This paper addresses this gap by examining the effect of increasing the number of model parameters on the performance of foundation models in downstream tasks such as rotated object detection and semantic segmentation. We pretrained foundation models with varying numbers of parameters, including 86M, 605.26M, 1.3B, and 2.4B, to determine whether performance in downstream tasks improved with an increase in parameters. To the best of our knowledge, this is the first billion-scale foundation model in the remote sensing field. Furthermore, we propose an effective method for scaling up and fine-tuning a vision transformer in the remote sensing field. To evaluate general performance in downstream tasks, we employed the DOTA v2.0 and DIOR-R benchmark datasets for rotated object detection, and the Potsdam and LoveDA datasets for semantic segmentation. Experimental results demonstrated that, across all benchmark datasets and downstream tasks, the performance of the foundation models and data efficiency improved as the number of parameters increased. Moreover, our models achieve the state-of-the-art performance on several datasets including DIOR-R, Postdam, and LoveDA.
Authors: Tomas Jakab, Ruining Li, Shangzhe Wu, Christian Rupprecht, Andrea Vedaldi
Abstract: We present Farm3D, a method for learning category-specific 3D reconstructors for articulated objects, relying solely on "free" virtual supervision from a pre-trained 2D diffusion-based image generator. Recent approaches can learn a monocular network that predicts the 3D shape, albedo, illumination, and viewpoint of any object occurrence, given a collection of single-view images of an object category. However, these approaches heavily rely on manually curated clean training data, which are expensive to obtain. We propose a framework that uses an image generator, such as Stable Diffusion, to generate synthetic training data that are sufficiently clean and do not require further manual curation, enabling the learning of such a reconstruction network from scratch. Additionally, we incorporate the diffusion model as a score to enhance the learning process. The idea involves randomizing certain aspects of the reconstruction, such as viewpoint and illumination, generating virtual views of the reconstructed 3D object, and allowing the 2D network to assess the quality of the resulting image, thus providing feedback to the reconstructor. Unlike work based on distillation, which produces a single 3D asset for each textual prompt, our approach yields a monocular reconstruction network capable of outputting a controllable 3D asset from any given image, whether real or generated, in a single forward pass in a matter of seconds. Our network can be used for analysis, including monocular reconstruction, or for synthesis, generating articulated assets for real-time applications such as video games.
Authors: Sai Sathiesh Rajan, Ezekiel Soremekun, Yves Le Traon, Sudipta Chattopadhyay
Abstract: Ensuring that all classes of objects are detected with equal accuracy is essential in AI systems. For instance, being unable to identify any one class of objects could have fatal consequences in autonomous driving systems. Hence, ensuring the reliability of image recognition systems is crucial. This work addresses how to validate group fairness in image recognition software. We propose a distribution-aware fairness testing approach (called DistroFair) that systematically exposes class-level fairness violations in image classifiers via a synergistic combination of out-of-distribution (OOD) testing and semantic-preserving image mutation. DistroFair automatically learns the distribution (e.g., number/orientation) of objects in a set of images. Then it systematically mutates objects in the images to become OOD using three semantic-preserving image mutations - object deletion, object insertion and object rotation. We evaluate DistroFair using two well-known datasets (CityScapes and MS-COCO) and three major, commercial image recognition software (namely, Amazon Rekognition, Google Cloud Vision and Azure Computer Vision). Results show that about 21% of images generated by DistroFair reveal class-level fairness violations using either ground truth or metamorphic oracles. DistroFair is up to 2.3x more effective than two main baselines, i.e., (a) an approach which focuses on generating images only within the distribution (ID) and (b) fairness analysis using only the original image dataset. We further observed that DistroFair is efficient, it generates 460 images per hour, on average. Finally, we evaluate the semantic validity of our approach via a user study with 81 participants, using 30 real images and 30 corresponding mutated images generated by DistroFair. We found that images generated by DistroFair are 80% as realistic as real-world images.
Authors: Yao Liu, Gangfeng Cui, Jiahui Luo, Xiaojun Chang, Lina Yao
Abstract: As a fundamental aspect of human life, two-person interactions contain meaningful information about people's activities, relationships, and social settings. Human action recognition serves as the foundation for many smart applications, with a strong focus on personal privacy. However, recognizing two-person interactions poses more challenges due to increased body occlusion and overlap compared to single-person actions. In this paper, we propose a point cloud-based network named Two-stream Multi-level Dynamic Point Transformer for two-person interaction recognition. Our model addresses the challenge of recognizing two-person interactions by incorporating local-region spatial information, appearance information, and motion information. To achieve this, we introduce a designed frame selection method named Interval Frame Sampling (IFS), which efficiently samples frames from videos, capturing more discriminative information in a relatively short processing time. Subsequently, a frame features learning module and a two-stream multi-level feature aggregation module extract global and partial features from the sampled frames, effectively representing the local-region spatial information, appearance information, and motion information related to the interactions. Finally, we apply a transformer to perform self-attention on the learned features for the final classification. Extensive experiments are conducted on two large-scale datasets, the interaction subsets of NTU RGB+D 60 and NTU RGB+D 120. The results show that our network outperforms state-of-the-art approaches in most standard evaluation settings.
Authors: Dominik Engel, Leon Sick, Timo Ropinski
Abstract: In volume rendering, transfer functions are used to classify structures of interest, and to assign optical properties such as color and opacity. They are commonly defined as 1D or 2D functions that map simple features to these optical properties. As the process of designing a transfer function is typically tedious and unintuitive, several approaches have been proposed for their interactive specification. In this paper, we present a novel method to define transfer functions for volume rendering by leveraging the feature extraction capabilities of self-supervised pre-trained vision transformers. To design a transfer function, users simply select the structures of interest in a slice viewer, and our method automatically selects similar structures based on the high-level features extracted by the neural network. Contrary to previous learning-based transfer function approaches, our method does not require training of models and allows for quick inference, enabling an interactive exploration of the volume data. Our approach reduces the amount of necessary annotations by interactively informing the user about the current classification, so they can focus on annotating the structures of interest that still require annotation. In practice, this allows users to design transfer functions within seconds, instead of minutes. We compare our method to existing learning-based approaches in terms of annotation and compute time, as well as with respect to segmentation accuracy. Our accompanying video showcases the interactivity and effectiveness of our method.
Authors: Alhasan Abdellatif, Ahmed H. Elsheikh, Hannah Menke
Abstract: Texture models based on Generative Adversarial Networks (GANs) use zero-padding to implicitly encode positional information of the image features. However, when extending the spatial input to generate images at large sizes, zero-padding can often lead to degradation of quality due to the incorrect positional information at the center of the image and limit the diversity within the generated images. In this paper, we propose a novel approach for generating stochastic texture images at large arbitrary sizes using GANs model that is based on patch-by-patch generation. Instead of zero-padding, the model uses \textit{local padding} in the generator that shares border features between the generated patches; providing positional context and ensuring consistency at the boundaries. The proposed models are trainable on a single texture image and have a constant GPU scalability with respect to the output image size, and hence can generate images of infinite sizes. We show in the experiments that our method has a significant advancement beyond existing texture models in terms of the quality and diversity of the generated textures. Furthermore, the implementation of local padding in the state-of-the-art super-resolution models effectively eliminates tiling artifacts enabling large-scale super-resolution. Our code is available at \url{https://github.com/ai4netzero/Infinite_Texture_GANs
Authors: Luming Tang, Nataniel Ruiz, Qinghao Chu, Yuanzhen Li, Aleksander Holynski, David E. Jacobs, Bharath Hariharan, Yael Pritch, Neal Wadhwa, Kfir Aberman, Michael Rubinstein
Abstract: Recent advances in generative imagery have brought forth outpainting and inpainting models that can produce high-quality, plausible image content in unknown regions. However, the content these models hallucinate is necessarily inauthentic, since they are unaware of the true scene. In this work, we propose RealFill, a novel generative approach for image completion that fills in missing regions of an image with the content that should have been there. RealFill is a generative inpainting model that is personalized using only a few reference images of a scene. These reference images do not have to be aligned with the target image, and can be taken with drastically varying viewpoints, lighting conditions, camera apertures, or image styles. Once personalized, RealFill is able to complete a target image with visually compelling contents that are faithful to the original scene. We evaluate RealFill on a new image completion benchmark that covers a set of diverse and challenging scenarios, and find that it outperforms existing approaches by a large margin. Project page: https://realfill.github.io
Authors: Zhiyao Sun, Tian Lv, Sheng Ye, Matthieu Lin, Jenny Sheng, Yu-Hui Wen, Minjing Yu, Yong-Jin Liu
Abstract: The generation of stylistic 3D facial animations driven by speech presents a significant challenge as it requires learning a many-to-many mapping between speech, style, and the corresponding natural facial motion. However, existing methods either employ a deterministic model for speech-to-motion mapping or encode the style using a one-hot encoding scheme. Notably, the one-hot encoding approach fails to capture the complexity of the style and thus limits generalization ability. In this paper, we propose DiffPoseTalk, a generative framework based on the diffusion model combined with a style encoder that extracts style embeddings from short reference videos. During inference, we employ classifier-free guidance to guide the generation process based on the speech and style. In particular, our style includes the generation of head poses, thereby enhancing user perception. Additionally, we address the shortage of scanned 3D talking face data by training our model on reconstructed 3DMM parameters from a high-quality, in-the-wild audio-visual dataset. Extensive experiments and user study demonstrate that our approach outperforms state-of-the-art methods. The code and dataset are at https://diffposetalk.github.io .
Authors: Weifeng Lin, Ziheng Wu, Wentao Yang, Mingxin Huang, Lianwen Jin
Abstract: Fine-tuning pre-trained Vision Transformers (ViTs) has showcased significant promise in enhancing visual recognition tasks. Yet, the demand for individualized and comprehensive fine-tuning processes for each task entails substantial computational and memory costs, posing a considerable challenge. Recent advancements in Parameter-Efficient Transfer Learning (PETL) have shown potential for achieving high performance with fewer parameter updates compared to full fine-tuning. However, their effectiveness is primarily observed in simple tasks like image classification, while they encounter challenges with more complex vision tasks like dense prediction. To address this gap, this study aims to identify an effective tuning method that caters to a wider range of visual tasks. In this paper, we introduce Hierarchical Side-Tuning (HST), an innovative PETL method facilitating the transfer of ViT models to diverse downstream tasks. Diverging from existing methods that focus solely on fine-tuning parameters within specific input spaces or modules, HST employs a lightweight Hierarchical Side Network (HSN). This network leverages intermediate activations from the ViT backbone to model multi-scale features, enhancing prediction capabilities. To evaluate HST, we conducted comprehensive experiments across a range of visual tasks, including classification, object detection, instance segmentation, and semantic segmentation. Remarkably, HST achieved state-of-the-art performance in 13 out of the 19 tasks on the VTAB-1K benchmark, with the highest average Top-1 accuracy of 76.1%, while fine-tuning a mere 0.78M parameters. When applied to object detection and semantic segmentation tasks on the COCO and ADE20K testdev benchmarks, HST outperformed existing PETL methods and even surpassed full fine-tuning.
Authors: Amit Bracha, Thomas Dag\`es, Ron Kimmel
Abstract: While dealing with matching shapes to their parts, we often apply a tool known as functional maps. The idea is to translate the shape matching problem into ``convenient'' spaces by which matching is performed algebraically by solving a least squares problem. Here, we argue that such formulations, though popular in this field, introduce errors in the estimated match when partiality is invoked. Such errors are unavoidable even for advanced feature extraction networks, and they can be shown to escalate with increasing degrees of shape partiality, adversely affecting the learning capability of such systems. To circumvent these limitations, we propose a novel approach for partial shape matching. Our study of functional maps led us to a novel method that establishes direct correspondence between partial and full shapes through feature matching bypassing the need for functional map intermediate spaces. The Gromov distance between metric spaces leads to the construction of the first part of our loss functions. For regularization we use two options: a term based on the area preserving property of the mapping, and a relaxed version that avoids the need to resort to functional maps. The proposed approach shows superior performance on the SHREC'16 dataset, outperforming existing unsupervised methods for partial shape matching. Notably, it achieves state-of-the-art results on the SHREC'16 HOLES benchmark, superior also compared to supervised methods. We demonstrate the benefits of the proposed unsupervised method when applied to a new dataset PFAUST for part-to-full shape correspondence
Authors: Samiran Gode, Akshay Hinduja, Michael Kaess
Abstract: In this paper, we address the challenging problem of data association for underwater SLAM through a novel method for sonar image correspondence using learned features. We introduce SONIC (SONar Image Correspondence), a pose-supervised network designed to yield robust feature correspondence capable of withstanding viewpoint variations. The inherent complexity of the underwater environment stems from the dynamic and frequently limited visibility conditions, restricting vision to a few meters of often featureless expanses. This makes camera-based systems suboptimal in most open water application scenarios. Consequently, multibeam imaging sonars emerge as the preferred choice for perception sensors. However, they too are not without their limitations. While imaging sonars offer superior long-range visibility compared to cameras, their measurements can appear different from varying viewpoints. This inherent variability presents formidable challenges in data association, particularly for feature-based methods. Our method demonstrates significantly better performance in generating correspondences for sonar images which will pave the way for more accurate loop closure constraints and sonar-based place recognition. Code as well as simulated and real-world datasets will be made public to facilitate further development in the field.
Authors: Yueqian Lin, Jingyang Zhang, Yiran Chen, Hai Li
Abstract: Natural Adversarial Examples (NAEs), images arising naturally from the environment and capable of deceiving classifiers, are instrumental in robustly evaluating and identifying vulnerabilities in trained models. In this work, unlike prior works that passively collect NAEs from real images, we propose to actively synthesize NAEs using the state-of-the-art Stable Diffusion. Specifically, our method formulates a controlled optimization process, where we perturb the token embedding that corresponds to a specified class to generate NAEs. This generation process is guided by the gradient of loss from the target classifier, ensuring that the created image closely mimics the ground-truth class yet fools the classifier. Named SD-NAE (Stable Diffusion for Natural Adversarial Examples), our innovative method is effective in producing valid and useful NAEs, which is demonstrated through a meticulously designed experiment. Code is available at https://github.com/linyueqian/SD-NAE.
Authors: Zeqing Wang, Wentao Wan, Qiqing Lao, Runmeng Chen, Minjie Lang, Keze Wang, Liang Lin
Abstract: Recently, several methods have been proposed to augment large Vision Language Models (VLMs) for Visual Question Answering (VQA) simplicity by incorporating external knowledge from knowledge bases or visual clues derived from question decomposition. Although having achieved promising results, these methods still suffer from the challenge that VLMs cannot inherently understand the incorporated knowledge and might fail to generate the optimal answers. Contrarily, human cognition engages visual questions through a top-down reasoning process, systematically exploring relevant issues to derive a comprehensive answer. This not only facilitates an accurate answer but also provides a transparent rationale for the decision-making pathway. Motivated by this cognitive mechanism, we introduce a novel, explainable multi-agent collaboration framework designed to imitate human-like top-down reasoning by leveraging the expansive knowledge of Large Language Models (LLMs). Our framework comprises three agents, i.e., Responder, Seeker, and Integrator, each contributing uniquely to the top-down reasoning process. The VLM-based Responder generates the answer candidates for the question and gives responses to other issues. The Seeker, primarily based on LLM, identifies relevant issues related to the question to inform the Responder and constructs a Multi-View Knowledge Base (MVKB) for the given visual scene by leveraging the understanding capabilities of LLM. The Integrator agent combines information from the Seeker and the Responder to produce the final VQA answer. Through this collaboration mechanism, our framework explicitly constructs an MVKB for a specific visual scene and reasons answers in a top-down reasoning process. Extensive and comprehensive evaluations on diverse VQA datasets and VLMs demonstrate the superior applicability and interpretability of our framework over the existing compared methods.
Authors: Xun Guo, Mingwu Zheng, Liang Hou, Yuan Gao, Yufan Deng, Pengfei Wan, Di Zhang, Yufan Liu, Weiming Hu, Zhengjun Zha, Haibin Huang, Chongyang Ma
Abstract: Text-guided image-to-video (I2V) generation aims to generate a coherent video that preserves the identity of the input image and semantically aligns with the input prompt. Existing methods typically augment pretrained text-to-video (T2V) models by either concatenating the image with noised video frames channel-wise before being fed into the model or injecting the image embedding produced by pretrained image encoders in cross-attention modules. However, the former approach often necessitates altering the fundamental weights of pretrained T2V models, thus restricting the model's compatibility within the open-source communities and disrupting the model's prior knowledge. Meanwhile, the latter typically fails to preserve the identity of the input image. We present I2V-Adapter to overcome such limitations. I2V-Adapter adeptly propagates the unnoised input image to subsequent noised frames through a cross-frame attention mechanism, maintaining the identity of the input image without any changes to the pretrained T2V model. Notably, I2V-Adapter only introduces a few trainable parameters, significantly alleviating the training cost and also ensures compatibility with existing community-driven personalized models and control tools. Moreover, we propose a novel Frame Similarity Prior to balance the motion amplitude and the stability of generated videos through two adjustable control coefficients. Our experimental results demonstrate that I2V-Adapter is capable of producing high-quality videos. This performance, coupled with its agility and adaptability, represents a substantial advancement in the field of I2V, particularly for personalized and controllable applications.
Authors: Soufiane Belharbi, Marco Pedersoli, Alessandro Lameiras Koerich, Simon Bacon, Eric Granger
Abstract: Although state-of-the-art classifiers for facial expression recognition (FER) can achieve a high level of accuracy, they lack interpretability, an important feature for end-users. Experts typically associate spatial action units (\aus) from a codebook to facial regions for the visual interpretation of expressions. In this paper, the same expert steps are followed. A new learning strategy is proposed to explicitly incorporate \au cues into classifier training, allowing to train deep interpretable models. During training, this \au codebook is used, along with the input image expression label, and facial landmarks, to construct a \au heatmap that indicates the most discriminative image regions of interest w.r.t the facial expression. This valuable spatial cue is leveraged to train a deep interpretable classifier for FER. This is achieved by constraining the spatial layer features of a classifier to be correlated with \au heatmaps. Using a composite loss, the classifier is trained to correctly classify an image while yielding interpretable visual layer-wise attention correlated with \au maps, simulating the expert decision process. Our strategy only relies on image class expression for supervision, without additional manual annotations. Our new strategy is generic, and can be applied to any deep CNN- or transformer-based classifier without requiring any architectural change or significant additional training time. Our extensive evaluation on two public benchmarks \rafdb, and \affectnet datasets shows that our proposed strategy can improve layer-wise interpretability without degrading classification performance. In addition, we explore a common type of interpretable classifiers that rely on class activation mapping (CAM) methods, and show that our approach can also improve CAM interpretability.
Authors: Jacob Fein-Ashley, Tian Ye, Sachini Wickramasinghe, Bingyi Zhang, Rajgopal Kannan, Viktor Prasanna
Abstract: Image classifiers often rely on convolutional neural networks (CNN) for their tasks, which are inherently more heavyweight than multilayer perceptrons (MLPs), which can be problematic in real-time applications. Additionally, many image classification models work on both RGB and grayscale datasets. Classifiers that operate solely on grayscale images are much less common. Grayscale image classification has diverse applications, including but not limited to medical image classification and synthetic aperture radar (SAR) automatic target recognition (ATR). Thus, we present a novel grayscale (single channel) image classification approach using a vectorized view of images. We exploit the lightweightness of MLPs by viewing images as a vector and reducing our problem setting to the grayscale image classification setting. We find that using a single graph convolutional layer batch-wise increases accuracy and reduces variance in the performance of our model. Moreover, we develop a customized accelerator on FPGA for the proposed model with several optimizations to improve its performance. Our experimental results on benchmark grayscale image datasets demonstrate the effectiveness of the proposed model, achieving vastly lower latency (up to 16$\times$ less) and competitive or leading performance compared to other state-of-the-art image classification models on various domain-specific grayscale image classification datasets.
Authors: Jeong Hun Yeo, Seunghee Han, Minsu Kim, Yong Man Ro
Abstract: In visual speech processing, context modeling capability is one of the most important requirements due to the ambiguous nature of lip movements. For example, homophenes, words that share identical lip movements but produce different sounds, can be distinguished by considering the context. In this paper, we propose a novel framework, namely Visual Speech Processing incorporated with LLMs (VSP-LLM), to maximize the context modeling ability by bringing the overwhelming power of LLMs. Specifically, VSP-LLM is designed to perform multi-tasks of visual speech recognition and translation, where the given instructions control the type of task. The input video is mapped to the input latent space of an LLM by employing a self-supervised visual speech model. Focused on the fact that there is redundant information in input frames, we propose a novel deduplication method that reduces the embedded visual features by employing visual speech units. Through the proposed deduplication and Low Rank Adaptation (LoRA), VSP-LLM can be trained in a computationally efficient manner. In the translation dataset, the MuAViC benchmark, we demonstrate that VSP-LLM trained on just 30 hours of labeled data can more effectively translate lip movements compared to the recent model trained with 433 hours of data.
Authors: Tarun Kalluri, Bodhisattwa Prasad Majumder, Manmohan Chandraker
Abstract: We introduce LaGTran, a novel framework that utilizes readily available or easily acquired text descriptions to guide robust transfer of discriminative knowledge from labeled source to unlabeled target data with domain shifts. While unsupervised adaptation methods have been established to address this problem, they show limitations in handling challenging domain shifts due to their exclusive operation within the pixel-space. Motivated by our observation that semantically richer text modality has more favorable transfer properties, we devise a transfer mechanism to use a source-trained text-classifier to generate predictions on the target text descriptions, and utilize these predictions as supervision for the corresponding images. Our approach driven by language guidance is surprisingly easy and simple, yet significantly outperforms all prior approaches on challenging datasets like GeoNet and DomainNet, validating its extreme effectiveness. To further extend the scope of our study beyond images, we introduce a new benchmark to study ego-exo transfer in videos and find that our language-aided LaGTran yields significant gains in this highly challenging and non-trivial transfer setting. Code, models, and proposed datasets are publicly available at https://tarun005.github.io/lagtran/.
Authors: Wenhao Wang, Yi Yang
Abstract: The arrival of Sora marks a new era for text-to-video diffusion models, bringing significant advancements in video generation and potential applications. However, Sora, along with other text-to-video diffusion models, is highly reliant on prompts, and there is no publicly available dataset that features a study of text-to-video prompts. In this paper, we introduce VidProM, the first large-scale dataset comprising 1.67 Million unique text-to-Video Prompts from real users. Additionally, this dataset includes 6.69 million videos generated by four state-of-the-art diffusion models, alongside some related data. We initially discuss the curation of this large-scale dataset, a process that is both time-consuming and costly. Subsequently, we underscore the need for a new prompt dataset specifically designed for text-to-video generation by illustrating how VidProM differs from DiffusionDB, a large-scale prompt-gallery dataset for image generation. Our extensive and diverse dataset also opens up many exciting new research areas. For instance, we suggest exploring text-to-video prompt engineering, efficient video generation, and video copy detection for diffusion models to develop better, more efficient, and safer models. The project (including the collected dataset VidProM and related code) is publicly available at https://vidprom.github.io under the CC-BY-NC 4.0 License.
Authors: Deyi Ji, Siqi Gao, Lanyun Zhu, Qi Zhu, Yiru Zhao, Peng Xu, Hongtao Lu, Feng Zhao, Jieping Ye
Abstract: In this paper, we address the challenge of multi-object tracking (MOT) in moving Unmanned Aerial Vehicle (UAV) scenarios, where irregular flight trajectories, such as hovering, turning left/right, and moving up/down, lead to significantly greater complexity compared to fixed-camera MOT. Specifically, changes in the scene background not only render traditional frame-to-frame object IOU association methods ineffective but also introduce significant view shifts in the objects, which complicates tracking. To overcome these issues, we propose a novel universal HomView-MOT framework, which for the first time, harnesses the view Homography inherent in changing scenes to solve MOT challenges in moving environments, incorporating Homographic Matching and View-Centric concepts. We introduce a Fast Homography Estimation (FHE) algorithm for rapid computation of Homography matrices between video frames, enabling object View-Centric ID Learning (VCIL) and leveraging multi-view Homography to learn cross-view ID features. Concurrently, our Homographic Matching Filter (HMF) maps object bounding boxes from different frames onto a common view plane for a more realistic physical IOU association. Extensive experiments have proven that these innovations allow HomView-MOT to achieve state-of-the-art performance on prominent UAV MOT datasets VisDrone and UAVDT.
Authors: Chaolei Tan, Jianhuang Lai, Wei-Shi Zheng, Jian-Fang Hu
Abstract: Video Paragraph Grounding (VPG) is an emerging task in video-language understanding, which aims at localizing multiple sentences with semantic relations and temporal order from an untrimmed video. However, existing VPG approaches are heavily reliant on a considerable number of temporal labels that are laborious and time-consuming to acquire. In this work, we introduce and explore Weakly-Supervised Video Paragraph Grounding (WSVPG) to eliminate the need of temporal annotations. Different from previous weakly-supervised grounding frameworks based on multiple instance learning or reconstruction learning for two-stage candidate ranking, we propose a novel siamese learning framework that jointly learns the cross-modal feature alignment and temporal coordinate regression without timestamp labels to achieve concise one-stage localization for WSVPG. Specifically, we devise a Siamese Grounding TRansformer (SiamGTR) consisting of two weight-sharing branches for learning complementary supervision. An Augmentation Branch is utilized for directly regressing the temporal boundaries of a complete paragraph within a pseudo video, and an Inference Branch is designed to capture the order-guided feature correspondence for localizing multiple sentences in a normal video. We demonstrate by extensive experiments that our paradigm has superior practicability and flexibility to achieve efficient weakly-supervised or semi-supervised learning, outperforming state-of-the-art methods trained with the same or stronger supervision.
Authors: Quankai Gao, Qiangeng Xu, Zhe Cao, Ben Mildenhall, Wenchao Ma, Le Chen, Danhang Tang, Ulrich Neumann
Abstract: Creating 4D fields of Gaussian Splatting from images or videos is a challenging task due to its under-constrained nature. While the optimization can draw photometric reference from the input videos or be regulated by generative models, directly supervising Gaussian motions remains underexplored. In this paper, we introduce a novel concept, Gaussian flow, which connects the dynamics of 3D Gaussians and pixel velocities between consecutive frames. The Gaussian flow can be efficiently obtained by splatting Gaussian dynamics into the image space. This differentiable process enables direct dynamic supervision from optical flow. Our method significantly benefits 4D dynamic content generation and 4D novel view synthesis with Gaussian Splatting, especially for contents with rich motions that are hard to be handled by existing methods. The common color drifting issue that happens in 4D generation is also resolved with improved Guassian dynamics. Superior visual quality on extensive experiments demonstrates our method's effectiveness. Quantitative and qualitative evaluations show that our method achieves state-of-the-art results on both tasks of 4D generation and 4D novel view synthesis. Project page: https://zerg-overmind.github.io/GaussianFlow.github.io/
URLs: https://zerg-overmind.github.io/GaussianFlow.github.io/
Authors: Alexander Vedernikov, Zhaodong Sun, Virpi-Liisa Kykyri, Mikko Pohjola, Miriam Nokia, Xiaobai Li
Abstract: Engagement measurement finds application in healthcare, education, services. The use of physiological and behavioral features is viable, but the impracticality of traditional physiological measurement arises due to the need for contact sensors. We demonstrate the feasibility of unsupervised remote photoplethysmography (rPPG) as an alternative for contact sensors in deriving heart rate variability (HRV) features, then fusing these with behavioral features to measure engagement in online group meetings. Firstly, a unique Engagement Dataset of online interactions among social workers is collected with granular engagement labels, offering insight into virtual meeting dynamics. Secondly, a pre-trained rPPG model is customized to reconstruct rPPG signals from video meetings in an unsupervised manner, enabling the calculation of HRV features. Thirdly, the feasibility of estimating engagement from HRV features using short observation windows, with a notable enhancement when using longer observation windows of two to four minutes, is demonstrated. Fourthly, the effectiveness of behavioral cues is evaluated when fused with physiological data, which further enhances engagement estimation performance. An accuracy of 94% is achieved when only HRV features are used, eliminating the need for contact sensors or ground truth signals; use of behavioral cues raises the accuracy to 96%. Facial analysis offers precise engagement measurement, beneficial for future applications.
Authors: Lifan Jiang, Zhihui Wang, Changmiao Wang, Ming Li, Jiaxu Leng, Xindong Wu
Abstract: Object detection, a quintessential task in the realm of perceptual computing, can be tackled using a generative methodology. In the present study, we introduce a novel framework designed to articulate object detection as a denoising diffusion process, which operates on the perturbed bounding boxes of annotated entities. This framework, termed ConsistencyDet, leverages an innovative denoising concept known as the Consistency Model. The hallmark of this model is its self-consistency feature, which empowers the model to map distorted information from any temporal stage back to its pristine state, thereby realizing a "one-step denoising" mechanism. Such an attribute markedly elevates the operational efficiency of the model, setting it apart from the conventional Diffusion Model. Throughout the training phase, ConsistencyDet initiates the diffusion sequence with noise-infused boxes derived from the ground-truth annotations and conditions the model to perform the denoising task. Subsequently, in the inference stage, the model employs a denoising sampling strategy that commences with bounding boxes randomly sampled from a normal distribution. Through iterative refinement, the model transforms an assortment of arbitrarily generated boxes into definitive detections. Comprehensive evaluations employing standard benchmarks, such as MS-COCO and LVIS, corroborate that ConsistencyDet surpasses other leading-edge detectors in performance metrics. Our code is available at https://github.com/Tankowa/ConsistencyDet.
Authors: Alexander Vedernikov, Puneet Kumar, Haoyu Chen, Tapio Seppanen, Xiaobai Li
Abstract: Engagement analysis finds various applications in healthcare, education, advertisement, services. Deep Neural Networks, used for analysis, possess complex architecture and need large amounts of input data, computational power, inference time. These constraints challenge embedding systems into devices for real-time use. To address these limitations, we present a novel two-stream feature fusion "Tensor-Convolution and Convolution-Transformer Network" (TCCT-Net) architecture. To better learn the meaningful patterns in the temporal-spatial domain, we design a "CT" stream that integrates a hybrid convolutional-transformer. In parallel, to efficiently extract rich patterns from the temporal-frequency domain and boost processing speed, we introduce a "TC" stream that uses Continuous Wavelet Transform (CWT) to represent information in a 2D tensor form. Evaluated on the EngageNet dataset, the proposed method outperforms existing baselines, utilizing only two behavioral features (head pose rotations) compared to the 98 used in baseline models. Furthermore, comparative analysis shows TCCT-Net's architecture offers an order-of-magnitude improvement in inference speed compared to state-of-the-art image-based Recurrent Neural Network (RNN) methods. The code will be released at https://github.com/vedernikovphoto/TCCT_Net.
Authors: Charles Gaydon, Floryne Roche
Abstract: Knowledge of tree species distribution is fundamental to managing forests. New deep learning approaches promise significant accuracy gains for forest mapping, and are becoming a critical tool for mapping multiple tree species at scale. To advance the field, deep learning researchers need large benchmark datasets with high-quality annotations. To this end, we present the PureForest dataset: a large-scale, open, multimodal dataset designed for tree species classification from both Aerial Lidar Scanning (ALS) point clouds and Very High Resolution (VHR) aerial images. Most current public Lidar datasets for tree species classification have low diversity as they only span a small area of a few dozen annotated hectares at most. In contrast, PureForest has 18 tree species grouped into 13 semantic classes, and spans 339 km$^2$ across 449 distinct monospecific forests, and is to date the largest and most comprehensive Lidar dataset for the identification of tree species. By making PureForest publicly available, we hope to provide a challenging benchmark dataset to support the development of deep learning approaches for tree species identification from Lidar and/or aerial imagery. In this data paper, we describe the annotation workflow, the dataset, the recommended evaluation methodology, and establish a baseline performance from both 3D and 2D modalities.
Authors: Xuanhua He, Quande Liu, Shengju Qian, Xin Wang, Tao Hu, Ke Cao, Keyu Yan, Jie Zhang
Abstract: Generating high fidelity human video with specified identities has attracted significant attention in the content generation community. However, existing techniques struggle to strike a balance between training efficiency and identity preservation, either requiring tedious case-by-case finetuning or usually missing the identity details in video generation process. In this study, we present ID-Animator, a zero-shot human-video generation approach that can perform personalized video generation given single reference facial image without further training. ID-Animator inherits existing diffusion-based video generation backbones with a face adapter to encode the ID-relevant embeddings from learnable facial latent queries. To facilitate the extraction of identity information in video generation, we introduce an ID-oriented dataset construction pipeline, which incorporates decoupled human attribute and action captioning technique from a constructed facial image pool. Based on this pipeline, a random face reference training method is further devised to precisely capture the ID-relevant embeddings from reference images, thus improving the fidelity and generalization capacity of our model for ID-specific video generation. Extensive experiments demonstrate the superiority of ID-Animator to generate personalized human videos over previous models. Moreover, our method is highly compatible with popular pre-trained T2V models like animatediff and various community backbone models, showing high extendability in real-world applications for video generation where identity preservation is highly desired. Our codes and checkpoints will be released at https://github.com/ID-Animator/ID-Animator.
Authors: Yuliang Liu, Mingxin Huang, Hao Yan, Linger Deng, Weijia Wu, Hao Lu, Chunhua Shen, Lianwen Jin, Xiang Bai
Abstract: Text spotting, a task involving the extraction of textual information from image or video sequences, faces challenges in cross-domain adaption, such as image-to-image and image-to-video generalization. In this paper, we introduce a new method, termed VimTS, which enhances the generalization ability of the model by achieving better synergy among different tasks. Typically, we propose a Prompt Queries Generation Module and a Tasks-aware Adapter to effectively convert the original single-task model into a multi-task model suitable for both image and video scenarios with minimal additional parameters. The Prompt Queries Generation Module facilitates explicit interaction between different tasks, while the Tasks-aware Adapter helps the model dynamically learn suitable features for each task. Additionally, to further enable the model to learn temporal information at a lower cost, we propose a synthetic video text dataset (VTD-368k) by leveraging the Content Deformation Fields (CoDeF) algorithm. Notably, our method outperforms the state-of-the-art method by an average of 2.6% in six cross-domain benchmarks such as TT-to-IC15, CTW1500-to-TT, and TT-to-CTW1500. For video-level cross-domain adaption, our method even surpasses the previous end-to-end video spotting method in ICDAR2015 video and DSText v2 by an average of 5.5% on the MOTA metric, using only image-level data. We further demonstrate that existing Large Multimodal Models exhibit limitations in generating cross-domain scene text spotting, in contrast to our VimTS model which requires significantly fewer parameters and data. The code and datasets will be made available at the https://VimTextSpotter.github.io.
Authors: Zhihao Guo, Peng Wang
Abstract: Neural Radiance Fields have achieved impressive results in 3D reconstruction and novel view generation. A significant challenge within NeRF involves editing reconstructed 3D scenes, such as object removal, which demands consistency across multiple views and the synthesis of high-quality perspectives. Previous studies have integrated depth priors, typically sourced from LiDAR or sparse depth estimates from COLMAP, to enhance NeRF's performance in object removal. However, these methods are either expensive or time-consuming. This paper proposes a new pipeline that leverages SpinNeRF and monocular depth estimation models like ZoeDepth to enhance NeRF's performance in complex object removal with improved efficiency. A thorough evaluation of COLMAP's dense depth reconstruction on the KITTI dataset is conducted to demonstrate that COLMAP can be viewed as a cost-effective and scalable alternative for acquiring depth ground truth compared to traditional methods like LiDAR. This serves as the basis for evaluating the performance of monocular depth estimation models to determine the best one for generating depth priors for SpinNeRF. The new pipeline is tested in various scenarios involving 3D reconstruction and object removal, and the results indicate that our pipeline significantly reduces the time required for depth prior acquisition for object removal and enhances the fidelity of the synthesized views, suggesting substantial potential for building high-fidelity digital twin systems with increased efficiency in the future.
Authors: Samuel Lavoie, Polina Kirichenko, Mark Ibrahim, Mahmoud Assran, Andrew Gordon Wilson, Aaron Courville, Nicolas Ballas
Abstract: There are a thousand ways to caption an image. Contrastive Language Pretraining (CLIP) on the other hand, works by mapping an image and its caption to a single vector -- limiting how well CLIP-like models can represent the diverse ways to describe an image. In this work, we introduce Llip, Latent Language Image Pretraining, which models the diversity of captions that could match an image. Llip's vision encoder outputs a set of visual features that are mixed into a final representation by conditioning on information derived from the text. We show that Llip outperforms non-contextualized baselines like CLIP and SigLIP on a variety of tasks even with large-scale encoders. Llip improves zero-shot classification by an average of 2.9% zero-shot classification benchmarks with a ViT-G/14 encoder. Specifically, Llip attains a zero-shot top-1 accuracy of 83.5% on ImageNet outperforming a similarly sized CLIP by 1.4%. We also demonstrate improvement on zero-shot retrieval on MS-COCO by 6.0%. We provide a comprehensive analysis of the components introduced by the method and demonstrate that Llip leads to richer visual representations.
Authors: Zixun Jiao, Xihan Wang, Zhaoqiang Xia, Lianhe Shao, Quanli Gao
Abstract: Reconstructing the hand mesh from one single RGB image is a challenging task because hands are often occluded by other objects. Most previous works attempt to explore more additional information and adopt attention mechanisms for improving 3D reconstruction performance, while it would increase computational complexity simultaneously. To achieve a performance-reserving architecture with high computational efficiency, in this work, we propose a simple but effective 3D hand mesh reconstruction network (i.e., HandS3C), which is the first time to incorporate state space model into the task of hand mesh reconstruction. In the network, we design a novel state-space spatial-channel attention module that extends the effective receptive field, extracts hand features in the spatial dimension, and enhances regional features of hands in the channel dimension. This helps to reconstruct a complete and detailed hand mesh. Extensive experiments conducted on well-known datasets facing heavy occlusions (such as FREIHAND, DEXYCB, and HO3D) demonstrate that our proposed HandS3C achieves state-of-the-art performance while maintaining a minimal parameters.
Authors: Xunchu Zhou, Xiaohong Liu, Yunlong Dong, Tengchuan Kou, Yixuan Gao, Zicheng Zhang, Chunyi Li, Haoning Wu, Guangtao Zhai
Abstract: Recently, User-Generated Content (UGC) videos have gained popularity in our daily lives. However, UGC videos often suffer from poor exposure due to the limitations of photographic equipment and techniques. Therefore, Video Exposure Correction (VEC) algorithms have been proposed, Low-Light Video Enhancement (LLVE) and Over-Exposed Video Recovery (OEVR) included. Equally important to the VEC is the Video Quality Assessment (VQA). Unfortunately, almost all existing VQA models are built generally, measuring the quality of a video from a comprehensive perspective. As a result, Light-VQA, trained on LLVE-QA, is proposed for assessing LLVE. We extend the work of Light-VQA by expanding the LLVE-QA dataset into Video Exposure Correction Quality Assessment (VEC-QA) dataset with over-exposed videos and their corresponding corrected versions. In addition, we propose Light-VQA+, a VQA model specialized in assessing VEC. Light-VQA+ differs from Light-VQA mainly from the usage of the CLIP model and the vision-language guidance during the feature extraction, followed by a new module referring to the Human Visual System (HVS) for more accurate assessment. Extensive experimental results show that our model achieves the best performance against the current State-Of-The-Art (SOTA) VQA models on the VEC-QA dataset and other public datasets.
Authors: Chao He, Hongxi Wei
Abstract: Deep image hashing aims to map input images into simple binary hash codes via deep neural networks and thus enable effective large-scale image retrieval. Recently, hybrid networks that combine convolution and Transformer have achieved superior performance on various computer tasks and have attracted extensive attention from researchers. Nevertheless, the potential benefits of such hybrid networks in image retrieval still need to be verified. To this end, we propose a hybrid convolutional and self-attention deep hashing method known as HybridHash. Specifically, we propose a backbone network with stage-wise architecture in which the block aggregation function is introduced to achieve the effect of local self-attention and reduce the computational complexity. The interaction module has been elaborately designed to promote the communication of information between image blocks and to enhance the visual representations. We have conducted comprehensive experiments on three widely used datasets: CIFAR-10, NUS-WIDE and IMAGENET. The experimental results demonstrate that the method proposed in this paper has superior performance with respect to state-of-the-art deep hashing methods. Source code is available https://github.com/shuaichaochao/HybridHash.
Authors: Weihao Yu, Xinchao Wang
Abstract: Mamba, an architecture with RNN-like token mixer of state space model (SSM), was recently introduced to address the quadratic complexity of the attention mechanism and subsequently applied to vision tasks. Nevertheless, the performance of Mamba for vision is often underwhelming when compared with convolutional and attention-based models. In this paper, we delve into the essence of Mamba, and conceptually conclude that Mamba is ideally suited for tasks with long-sequence and autoregressive characteristics. For vision tasks, as image classification does not align with either characteristic, we hypothesize that Mamba is not necessary for this task; Detection and segmentation tasks are also not autoregressive, yet they adhere to the long-sequence characteristic, so we believe it is still worthwhile to explore Mamba's potential for these tasks. To empirically verify our hypotheses, we construct a series of models named MambaOut through stacking Mamba blocks while removing their core token mixer, SSM. Experimental results strongly support our hypotheses. Specifically, our MambaOut model surpasses all visual Mamba models on ImageNet image classification, indicating that Mamba is indeed unnecessary for this task. As for detection and segmentation, MambaOut cannot match the performance of state-of-the-art visual Mamba models, demonstrating the potential of Mamba for long-sequence visual tasks. The code is available at https://github.com/yuweihao/MambaOut
Authors: Nicol\'as Gaggion, Candelaria Mosquera, Lucas Mansilla, Julia Mariel Saidman, Martina Aineseder, Diego H. Milone, Enzo Ferrante
Abstract: The development of successful artificial intelligence models for chest X-ray analysis relies on large, diverse datasets with high-quality annotations. While several databases of chest X-ray images have been released, most include disease diagnosis labels but lack detailed pixel-level anatomical segmentation labels. To address this gap, we introduce an extensive chest X-ray multi-center segmentation dataset with uniform and fine-grain anatomical annotations for images coming from five well-known publicly available databases: ChestX-ray8, Chexpert, MIMIC-CXR-JPG, Padchest, and VinDr-CXR, resulting in 657,566 segmentation masks. Our methodology utilizes the HybridGNet model to ensure consistent and high-quality segmentations across all datasets. Rigorous validation, including expert physician evaluation and automatic quality control, was conducted to validate the resulting masks. Additionally, we provide individualized quality indices per mask and an overall quality estimation per dataset. This dataset serves as a valuable resource for the broader scientific community, streamlining the development and assessment of innovative methodologies in chest X-ray analysis. The CheXmask dataset is publicly available at: https://physionet.org/content/chexmask-cxr-segmentation-data/
URLs: https://physionet.org/content/chexmask-cxr-segmentation-data/
Authors: Shihong Liu, Zhiqiu Lin, Samuel Yu, Ryan Lee, Tiffany Ling, Deepak Pathak, Deva Ramanan
Abstract: Vision-language models (VLMs) pre-trained on web-scale datasets have demonstrated remarkable capabilities on downstream tasks when fine-tuned with minimal data. However, many VLMs rely on proprietary data and are not open-source, which restricts the use of white-box approaches for fine-tuning. As such, we aim to develop a black-box approach to optimize VLMs through natural language prompts, thereby avoiding the need to access model parameters, feature embeddings, or even output logits. We propose employing chat-based LLMs to search for the best text prompt for VLMs. Specifically, we adopt an automatic hill-climbing procedure that converges to an effective prompt by evaluating the performance of current prompts and asking LLMs to refine them based on textual feedback, all within a conversational process without human-in-the-loop. In a challenging 1-shot image classification setup, our simple approach surpasses the white-box continuous prompting method (CoOp) by an average of 1.5% across 11 datasets including ImageNet. Our approach also outperforms both human-engineered and LLM-generated prompts. We highlight the advantage of conversational feedback that incorporates both positive and negative prompts, suggesting that LLMs can utilize the implicit gradient direction in textual feedback for a more efficient search. In addition, we find that the text prompts generated through our strategy are not only more interpretable but also transfer well across different VLM architectures in a black-box manner. Lastly, we apply our framework to optimize the state-of-the-art black-box VLM (DALL-E 3) for text-to-image generation, prompt inversion, and personalization.
Authors: Jessica Quaye, Alicia Parrish, Oana Inel, Charvi Rastogi, Hannah Rose Kirk, Minsuk Kahng, Erin van Liemt, Max Bartolo, Jess Tsang, Justin White, Nathan Clement, Rafael Mosquera, Juan Ciro, Vijay Janapa Reddi, Lora Aroyo
Abstract: With the rise of text-to-image (T2I) generative AI models reaching wide audiences, it is critical to evaluate model robustness against non-obvious attacks to mitigate the generation of offensive images. By focusing on ``implicitly adversarial'' prompts (those that trigger T2I models to generate unsafe images for non-obvious reasons), we isolate a set of difficult safety issues that human creativity is well-suited to uncover. To this end, we built the Adversarial Nibbler Challenge, a red-teaming methodology for crowdsourcing a diverse set of implicitly adversarial prompts. We have assembled a suite of state-of-the-art T2I models, employed a simple user interface to identify and annotate harms, and engaged diverse populations to capture long-tail safety issues that may be overlooked in standard testing. The challenge is run in consecutive rounds to enable a sustained discovery and analysis of safety pitfalls in T2I models. In this paper, we present an in-depth account of our methodology, a systematic study of novel attack strategies and discussion of safety failures revealed by challenge participants. We also release a companion visualization tool for easy exploration and derivation of insights from the dataset. The first challenge round resulted in over 10k prompt-image pairs with machine annotations for safety. A subset of 1.5k samples contains rich human annotations of harm types and attack styles. We find that 14% of images that humans consider harmful are mislabeled as ``safe'' by machines. We have identified new attack strategies that highlight the complexity of ensuring T2I model robustness. Our findings emphasize the necessity of continual auditing and adaptation as new vulnerabilities emerge. We are confident that this work will enable proactive, iterative safety assessments and promote responsible development of T2I models.
Authors: Yiliang Zhou, Hanley Ong, Patrick Kennedy, Carol Wu, Jacob Kazam, Keith Hentel, Adam Flanders, George Shih, Yifan Peng
Abstract: The study examines the application of GPT-4V, a multi-modal large language model equipped with visual recognition, in detecting radiological findings from a set of 100 chest radiographs and suggests that GPT-4V is currently not ready for real-world diagnostic usage in interpreting chest radiographs.
Authors: Minghuan Liu, Zixuan Chen, Xuxin Cheng, Yandong Ji, Ri-Zhao Qiu, Ruihan Yang, Xiaolong Wang
Abstract: We study the problem of mobile manipulation using legged robots equipped with an arm, namely legged loco-manipulation. The robot legs, while usually utilized for mobility, offer an opportunity to amplify the manipulation capabilities by conducting whole-body control. That is, the robot can control the legs and the arm at the same time to extend its workspace. We propose a framework that can conduct the whole-body control autonomously with visual observations. Our approach, namely Visual Whole-Body Control(VBC), is composed of a low-level policy using all degrees of freedom to track the body velocities along with the end-effector position, and a high-level policy proposing the velocities and end-effector position based on visual inputs. We train both levels of policies in simulation and perform Sim2Real transfer for real robot deployment. We perform extensive experiments and show significant improvements over baselines in picking up diverse objects in different configurations (heights, locations, orientations) and environments.
Authors: Siang Chen, Wei Tang, Pengwei Xie, Wenming Yang, Guijin Wang
Abstract: Fast and robust object grasping in clutter is a crucial component of robotics. Most current works resort to the whole observed point cloud for 6-Dof grasp generation, ignoring the guidance information excavated from global semantics, thus limiting high-quality grasp generation and real-time performance. In this work, we show that the widely used heatmaps are underestimated in the efficiency of 6-Dof grasp generation. Therefore, we propose an effective local grasp generator combined with grasp heatmaps as guidance, which infers in a global-to-local semantic-to-point way. Specifically, Gaussian encoding and the grid-based strategy are applied to predict grasp heatmaps as guidance to aggregate local points into graspable regions and provide global semantic information. Further, a novel non-uniform anchor sampling mechanism is designed to improve grasp accuracy and diversity. Benefiting from the high-efficiency encoding in the image space and focusing on points in local graspable regions, our framework can perform high-quality grasp detection in real-time and achieve state-of-the-art results. In addition, real robot experiments demonstrate the effectiveness of our method with a success rate of 94% and a clutter completion rate of 100%. Our code is available at https://github.com/THU-VCLab/HGGD.
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: Weijian Sun, Yanbo Jia, Qi Zeng, Zihao Liu, Jiang Liao, Yue Li, Xianfeng Li
Abstract: Deep-learning-based techniques have been widely adopted for autonomous driving software stacks for mass production in recent years, focusing primarily on perception modules, with some work extending this method to prediction modules. However, the downstream planning and control modules are still designed with hefty handcrafted rules, dominated by optimization-based methods such as quadratic programming or model predictive control. This results in a performance bottleneck for autonomous driving systems in that corner cases simply cannot be solved by enumerating hand-crafted rules. We present a deep-learning-based approach that brings prediction, decision, and planning modules together with the attempt to overcome the rule-based methods' deficiency in real-world applications of autonomous driving, especially for urban scenes. The DNN model we proposed is solely trained with 10 hours of human driver data, and it supports all mass-production ADAS features available on the market to date. This method is deployed onto a Jiyue test car with no modification to its factory-ready sensor set and compute platform. the feasibility, usability, and commercial potential are demonstrated in this article.
Authors: Ola Shorinwa, Johnathan Tucker, Aliyah Smith, Aiden Swann, Timothy Chen, Roya Firoozi, Monroe Kennedy III, Mac Schwager
Abstract: We present Splat-MOVER, a modular robotics stack for open-vocabulary robotic manipulation, which leverages the editability of Gaussian Splatting (GSplat) scene representations to enable multi-stage manipulation tasks. Splat-MOVER consists of: (i) ASK-Splat, a GSplat representation that distills latent codes for language semantics and grasp affordance into the 3D scene. ASK-Splat enables geometric, semantic, and affordance understanding of 3D scenes, which is critical for many robotics tasks; (ii) SEE-Splat, a real-time scene-editing module using 3D semantic masking and infilling to visualize the motions of objects that result from robot interactions in the real-world. SEE-Splat creates a "digital twin" of the evolving environment throughout the manipulation task; and (iii) Grasp-Splat, a grasp generation module that uses ASK-Splat and SEE-Splat to propose candidate grasps for open-world objects. ASK-Splat is trained in real-time from RGB images in a brief scanning phase prior to operation, while SEE-Splat and Grasp-Splat run in real-time during operation. We demonstrate the superior performance of Splat-MOVER in hardware experiments on a Kinova robot compared to two recent baselines in four single-stage, open-vocabulary manipulation tasks, as well as in four multi-stage manipulation tasks using the edited scene to reflect scene changes due to prior manipulation stages, which is not possible with the existing baselines. Code for this project and a link to the project page will be made available soon.
Authors: Mukaffi Bin Moin, Fatema Tuj Johora Faria, Swarnajit Saha, Busra Kamal Rafa, Mohammad Shafiul Alam
Abstract: Lung and colon cancer are serious worldwide health challenges that require early and precise identification to reduce mortality risks. However, diagnosis, which is mostly dependent on histopathologists' competence, presents difficulties and hazards when expertise is insufficient. While diagnostic methods like imaging and blood markers contribute to early detection, histopathology remains the gold standard, although time-consuming and vulnerable to inter-observer mistakes. Limited access to high-end technology further limits patients' ability to receive immediate medical care and diagnosis. Recent advances in deep learning have generated interest in its application to medical imaging analysis, specifically the use of histopathological images to diagnose lung and colon cancer. The goal of this investigation is to use and adapt existing pre-trained CNN-based models, such as Xception, DenseNet201, ResNet101, InceptionV3, DenseNet121, DenseNet169, ResNet152, and InceptionResNetV2, to enhance classification through better augmentation strategies. The results show tremendous progress, with all eight models reaching impressive accuracy ranging from 97% to 99%. Furthermore, attention visualization techniques such as GradCAM, GradCAM++, ScoreCAM, Faster Score-CAM, and LayerCAM, as well as Vanilla Saliency and SmoothGrad, are used to provide insights into the models' classification decisions, thereby improving interpretability and understanding of malignant and benign image classification.