Authors: Sakhinana Sagar Srinivas, Geethan Sannidhi, Venkataramana Runkana
Abstract: We present a novel framework for analyzing and interpreting electron microscopy images in semiconductor manufacturing using vision-language instruction tuning. The framework employs a unique teacher-student approach, leveraging pre-trained multimodal large language models such as GPT-4 to generate instruction-following data for zero-shot visual question answering (VQA) and classification tasks, customizing smaller multimodal models (SMMs) for microscopy image analysis, resulting in an instruction-tuned language-and-vision assistant. Our framework merges knowledge engineering with machine learning to integrate domain-specific expertise from larger to smaller multimodal models within this specialized field, greatly reducing the need for extensive human labeling. Our study presents a secure, cost-effective, and customizable approach for analyzing microscopy images, addressing the challenges of adopting proprietary models in semiconductor manufacturing.
Authors: Yuheng Feng, Yangfan He, Yinghui Xia, Tianyu Shi, Jun Wang, Jinsong Yang
Abstract: Today's image generation systems are capable of producing realistic and high-quality images. However, user prompts often contain ambiguities, making it difficult for these systems to interpret users' potential intentions. Consequently, machines need to interact with users multiple rounds to better understand users' intents. The unpredictable costs of using or learning image generation models through multiple feedback interactions hinder their widespread adoption and full performance potential, especially for non-expert users. In this research, we aim to enhance the user-friendliness of our image generation system. To achieve this, we propose a reflective human-machine co-adaptation strategy, named RHM-CAS. Externally, the Agent engages in meaningful language interactions with users to reflect on and refine the generated images. Internally, the Agent tries to optimize the policy based on user preferences, ensuring that the final outcomes closely align with user preferences. Various experiments on different tasks demonstrate the effectiveness of the proposed method.
Authors: Rashmi BN (JSS Academy of Technical Education, Bengaluru), R. Guru (SJCE, Mysore), Anusuya M A (SJCE, Mysore)
Abstract: Advancements in object detection algorithms have opened new avenues for assistive technologies that cater to the needs of visually impaired individuals. This paper presents a novel approach for indoor assistance to the blind by addressing the challenge of small object detection. We propose a technique YOLO NAS Small architecture, a lightweight and efficient object detection model, optimized using the Super Gradients training framework. This combination enables real-time detection of small objects crucial for assisting the blind in navigating indoor environments, such as furniture, appliances, and household items. Proposed method emphasizes low latency and high accuracy, enabling timely and informative voice-based guidance to enhance the user's spatial awareness and interaction with their surroundings. The paper details the implementation, experimental results, and discusses the system's effectiveness in providing a practical solution for indoor assistance to the visually impaired.
Authors: Giorgos Savathrakis, Antonis Argyros
Abstract: Transformers demonstrate competitive performance in terms of precision on the problem of vision-based object detection. However, they require considerable computational resources due to the quadratic size of the attention weights. In this work, we propose to cluster the transformer input on the basis of its entropy. The reason for this is that the self-information of each pixel (whose sum is the entropy), is likely to be similar among pixels corresponding to the same objects. Clustering reduces the size of data given as input to the transformer and therefore reduces training time and GPU memory usage, while at the same time preserves meaningful information to be passed through the remaining parts of the network. The proposed process is organized in a module called ENACT, that can be plugged-in any transformer architecture that consists of a multi-head self-attention computation in its encoder. We ran extensive experiments using the COCO object detection dataset, and three detection transformers. The obtained results demonstrate that in all tested cases, there is consistent reduction in the required computational resources, while the precision of the detection task is only slightly reduced. The code of the ENACT module will become available at https://github.com/GSavathrakis/ENACT
Authors: Christian L\"owens, Thorben Funke, Andr\'e Wagner, Alexandru Paul Condurache
Abstract: Rigid point cloud registration is a fundamental problem and highly relevant in robotics and autonomous driving. Nowadays deep learning methods can be trained to match a pair of point clouds, given the transformation between them. However, this training is often not scalable due to the high cost of collecting ground truth poses. Therefore, we present a self-distillation approach to learn point cloud registration in an unsupervised fashion. Here, each sample is passed to a teacher network and an augmented view is passed to a student network. The teacher includes a trainable feature extractor and a learning-free robust solver such as RANSAC. The solver forces consistency among correspondences and optimizes for the unsupervised inlier ratio, eliminating the need for ground truth labels. Our approach simplifies the training procedure by removing the need for initial hand-crafted features or consecutive point cloud frames as seen in related methods. We show that our method not only surpasses them on the RGB-D benchmark 3DMatch but also generalizes well to automotive radar, where classical features adopted by others fail. The code is available at https://github.com/boschresearch/direg .
Authors: Gr\'egoire Petit, Nathan Palluau, Axel Bauer, Clemens Dlaska
Abstract: The application of machine learning to medical ultrasound videos of the heart, i.e., echocardiography, has recently gained traction with the availability of large public datasets. Traditional supervised tasks, such as ejection fraction regression, are now making way for approaches focusing more on the latent structure of data distributions, as well as generative methods. We propose a model trained exclusively by knowledge distillation, either on real or synthetical data, involving retrieving masks suggested by a teacher model. We achieve state-of-the-art (SOTA) values on the task of identifying end-diastolic and end-systolic frames. By training the model only on synthetic data, it reaches segmentation capabilities close to the performance when trained on real data with a significantly reduced number of weights. A comparison with the 5 main existing methods shows that our method outperforms the others in most cases. We also present a new evaluation method that does not require human annotation and instead relies on a large auxiliary model. We show that this method produces scores consistent with those obtained from human annotations. Relying on the integrated knowledge from a vast amount of records, this method overcomes certain inherent limitations of human annotator labeling. Code: https://github.com/GregoirePetit/EchoDFKD
Authors: Vincenzo Polizzi, Marco Cannici, Davide Scaramuzza, Jonathan Kelly
Abstract: Camera relocalization methods range from dense image alignment to direct camera pose regression from a query image. Among these, sparse feature matching stands out as an efficient, versatile, and generally lightweight approach with numerous applications. However, feature-based methods often struggle with significant viewpoint and appearance changes, leading to matching failures and inaccurate pose estimates. To overcome this limitation, we propose a novel approach that leverages a globally sparse yet locally dense 3D representation of 2D features. By tracking and triangulating landmarks over a sequence of frames, we construct a sparse voxel map optimized to render image patch descriptors observed during tracking. Given an initial pose estimate, we first synthesize descriptors from the voxels using volumetric rendering and then perform feature matching to estimate the camera pose. This methodology enables the generation of descriptors for unseen views, enhancing robustness to view changes. We extensively evaluate our method on the 7-Scenes and Cambridge Landmarks datasets. Our results show that our method significantly outperforms existing state-of-the-art feature representation techniques in indoor environments, achieving up to a 39% improvement in median translation error. Additionally, our approach yields comparable results to other methods for outdoor scenarios while maintaining lower memory and computational costs.
Authors: Alfonso Taboada Warmerdam, Mathilde Caron, Yuki M. Asano
Abstract: With the advent of billion-parameter foundation models, efficient fine-tuning has become increasingly important for the adaptation of models to downstream tasks. However, especially in computer vision, it can be hard to achieve good performance when access to quality labeled data is lacking. In this work, we propose a method adapting pretrained generalist models in a self-supervised manner by learning binary masks. These self-supervised masking networks (SMNs) are up to 79x more efficient to store and significantly improve performance on label-efficient downstream tasks. We validate the usefulness of learning binary masks as a fine-tuning method on 8 datasets and 3 model architectures, and we demonstrate the effectiveness of SMNs in 3 label-efficient settings.
Authors: Abdarahmane Traor\'e, Moulay A. Akhloufi
Abstract: Violence and abnormal behavior detection research have known an increase of interest in recent years, due mainly to a rise in crimes in large cities worldwide. In this work, we propose a deep learning architecture for violence detection which combines both recurrent neural networks (RNNs) and 2-dimensional convolutional neural networks (2D CNN). In addition to video frames, we use optical flow computed using the captured sequences. CNN extracts spatial characteristics in each frame, while RNN extracts temporal characteristics. The use of optical flow allows to encode the movements in the scenes. The proposed approaches reach the same level as the state-of-the-art techniques and sometime surpass them. It was validated on 3 databases achieving good results.
Authors: Tom Shaked, Yuval Goldman, Oran Shayer
Abstract: Foundational models, trained on vast and diverse datasets, have demonstrated remarkable capabilities in generalizing across different domains and distributions for various zero-shot tasks. Our work addresses the challenge of retaining these powerful generalization capabilities when adapting foundational models to specific downstream tasks through fine-tuning. To this end, we introduce a novel approach we call "similarity loss", which can be incorporated into the fine-tuning process of any task. By minimizing the distortion of fine-tuned embeddings from the pre-trained embeddings, our method strikes a balance between task-specific adaptation and preserving broad generalization abilities. We evaluate our approach on two diverse tasks: image classification on satellite imagery and face recognition, focusing on open-class and domain shift scenarios to assess out-of-distribution (OOD) performance. We demonstrate that this approach significantly improves OOD performance while maintaining strong in-distribution (ID) performance.
Authors: Abdarahmane Traor\'e, Moulay A. Akhloufi
Abstract: Abnormal behavior detection, action recognition, fight and violence detection in videos is an area that has attracted a lot of interest in recent years. In this work, we propose an architecture that combines a Bidirectional Gated Recurrent Unit (BiGRU) and a 2D Convolutional Neural Network (CNN) to detect violence in video sequences. A CNN is used to extract spatial characteristics from each frame, while the BiGRU extracts temporal and local motion characteristics using CNN extracted features from multiple frames. The proposed end-to-end deep learning network is tested in three public datasets with varying scene complexities. The proposed network achieves accuracies up to 98%. The obtained results are promising and show the performance of the proposed end-to-end approach.
Authors: Purvish Jajal, Nick John Eliopoulos, Benjamin Shiue-Hal Chou, George K. Thiravathukal, James C. Davis, Yung-Hsiang Lu
Abstract: We propose Vision Token Turing Machines (ViTTM), an efficient, low-latency, memory-augmented Vision Transformer (ViT). Our approach builds on Neural Turing Machines and Token Turing Machines, which were applied to NLP and sequential visual understanding tasks. ViTTMs are designed for non-sequential computer vision tasks such as image classification and segmentation. Our model creates two sets of tokens: process tokens and memory tokens; process tokens pass through encoder blocks and read-write from memory tokens at each encoder block in the network, allowing them to store and retrieve information from memory. By ensuring that there are fewer process tokens than memory tokens, we are able to reduce the inference time of the network while maintaining its accuracy. On ImageNet-1K, the state-of-the-art ViT-B has median latency of 529.5ms and 81.0% accuracy, while our ViTTM-B is 56% faster (234.1ms), with 2.4 times fewer FLOPs, with an accuracy of 82.9%. On ADE20K semantic segmentation, ViT-B achieves 45.65mIoU at 13.8 frame-per-second (FPS) whereas our ViTTM-B model acheives a 45.17 mIoU with 26.8 FPS (+94%).
Authors: Mohsen Azarmi, Mahdi Rezaei, He Wang, Ali Arabian
Abstract: Recent advancements in predicting pedestrian crossing intentions for Autonomous Vehicles using Computer Vision and Deep Neural Networks are promising. However, the black-box nature of DNNs poses challenges in understanding how the model works and how input features contribute to final predictions. This lack of interpretability delimits the trust in model performance and hinders informed decisions on feature selection, representation, and model optimisation; thereby affecting the efficacy of future research in the field. To address this, we introduce Context-aware Permutation Feature Importance (CAPFI), a novel approach tailored for pedestrian intention prediction. CAPFI enables more interpretability and reliable assessments of feature importance by leveraging subdivided scenario contexts, mitigating the randomness of feature values through targeted shuffling. This aims to reduce variance and prevent biased estimations in importance scores during permutations. We divide the Pedestrian Intention Estimation (PIE) dataset into 16 comparable context sets, measure the baseline performance of five distinct neural network architectures for intention prediction in each context, and assess input feature importance using CAPFI. We observed nuanced differences among models across various contextual characteristics. The research reveals the critical role of pedestrian bounding boxes and ego-vehicle speed in predicting pedestrian intentions, and potential prediction biases due to the speed feature through cross-context permutation evaluation. We propose an alternative feature representation by considering proximity change rate for rendering dynamic pedestrian-vehicle locomotion, thereby enhancing the contributions of input features to intention prediction. These findings underscore the importance of contextual features and their diversity to develop accurate and robust intent-predictive models.
Authors: Steven Hogue, Chenxu Zhang, Hamza Daruger, Yapeng Tian, Xiaohu Guo
Abstract: Audio-driven talking video generation has advanced significantly, but existing methods often depend on video-to-video translation techniques and traditional generative networks like GANs and they typically generate taking heads and co-speech gestures separately, leading to less coherent outputs. Furthermore, the gestures produced by these methods often appear overly smooth or subdued, lacking in diversity, and many gesture-centric approaches do not integrate talking head generation. To address these limitations, we introduce DiffTED, a new approach for one-shot audio-driven TED-style talking video generation from a single image. Specifically, we leverage a diffusion model to generate sequences of keypoints for a Thin-Plate Spline motion model, precisely controlling the avatar's animation while ensuring temporally coherent and diverse gestures. This innovative approach utilizes classifier-free guidance, empowering the gestures to flow naturally with the audio input without relying on pre-trained classifiers. Experiments demonstrate that DiffTED generates temporally coherent talking videos with diverse co-speech gestures.
Authors: Abhijay Ghildyal, Nabajeet Barman, Saman Zadtootaghaj
Abstract: For full-reference image quality assessment (FR-IQA) using deep-learning approaches, the perceptual similarity score between a distorted image and a reference image is typically computed as a distance measure between features extracted from a pretrained CNN or more recently, a Transformer network. Often, these intermediate features require further fine-tuning or processing with additional neural network layers to align the final similarity scores with human judgments. So far, most IQA models based on foundation models have primarily relied on the final layer or the embedding for the quality score estimation. In contrast, this work explores the potential of utilizing the intermediate features of these foundation models, which have largely been unexplored so far in the design of low-level perceptual similarity metrics. We demonstrate that the intermediate features are comparatively more effective. Moreover, without requiring any training, these metrics can outperform both traditional and state-of-the-art learned metrics by utilizing distance measures between the features.
Authors: Qinglong Cao, Yuntian Chen, Chao Ma, Xiaokang Yang
Abstract: Open-vocabulary image semantic segmentation (OVS) seeks to segment images into semantic regions across an open set of categories. Existing OVS methods commonly depend on foundational vision-language models and utilize similarity computation to tackle OVS tasks. However, these approaches are predominantly tailored to natural images and struggle with the unique characteristics of remote sensing images, such as rapidly changing orientations and significant scale variations. These challenges complicate OVS tasks in earth vision, requiring specialized approaches. To tackle this dilemma, we propose the first OVS framework specifically designed for remote sensing imagery, drawing inspiration from the distinct remote sensing traits. Particularly, to address the varying orientations, we introduce a rotation-aggregative similarity computation module that generates orientation-adaptive similarity maps as initial semantic maps. These maps are subsequently refined at both spatial and categorical levels to produce more accurate semantic maps. Additionally, to manage significant scale changes, we integrate multi-scale image features into the upsampling process, resulting in the final scale-aware semantic masks. To advance OVS in earth vision and encourage reproducible research, we establish the first open-sourced OVS benchmark for remote sensing imagery, including four public remote sensing datasets. Extensive experiments on this benchmark demonstrate our proposed method achieves state-of-the-art performance. All codes and datasets are available at https://github.com/caoql98/OVRS.
Authors: Xinlei Huang, Jialiang Tang, Xubin Zheng, Jinjia Zhou, Wenxin Yu, Ning Jiang
Abstract: Knowledge Distillation (KD) transfers knowledge from a large pre-trained teacher network to a compact and efficient student network, making it suitable for deployment on resource-limited media terminals. However, traditional KD methods require balanced data to ensure robust training, which is often unavailable in practical applications. In such scenarios, a few head categories occupy a substantial proportion of examples. This imbalance biases the trained teacher network towards the head categories, resulting in severe performance degradation on the less represented tail categories for both the teacher and student networks. In this paper, we propose a novel framework called Knowledge Rectification Distillation (KRDistill) to address the imbalanced knowledge inherited in the teacher network through the incorporation of the balanced category priors. Furthermore, we rectify the biased predictions produced by the teacher network, particularly focusing on the tail categories. Consequently, the teacher network can provide balanced and accurate knowledge to train a reliable student network. Intensive experiments conducted on various long-tailed datasets demonstrate that our KRDistill can effectively train reliable student networks in realistic scenarios of data imbalance.
Authors: Yakun Niu, Lei Tan, Lei Zhang, Xianyu Zuo
Abstract: Image operation chain detection techniques have gained increasing attention recently in the field of multimedia forensics. However, existing detection methods suffer from the generalization problem. Moreover, the channel correlation of color images that provides additional forensic evidence is often ignored. To solve these issues, in this article, we propose a novel two-stream multi-channels fusion networks for color image operation chain detection in which the spatial artifact stream and the noise residual stream are explored in a complementary manner. Specifically, we first propose a novel deep residual architecture without pooling in the spatial artifact stream for learning the global features representation of multi-channel correlation. Then, a set of filters is designed to aggregate the correlation information of multi-channels while capturing the low-level features in the noise residual stream. Subsequently, the high-level features are extracted by the deep residual model. Finally, features from the two streams are fed into a fusion module, to effectively learn richer discriminative representations of the operation chain. Extensive experiments show that the proposed method achieves state-of-the-art generalization ability while maintaining robustness to JPEG compression. The source code used in these experiments will be released at https://github.com/LeiTan-98/TMFNet.
Authors: Yang Li, Quan Yuan, Guiyang Luo, Xiaoyuan Fu, Xuanhan Zhu, Yujia Yang, Rui Pan, Jinglin Li
Abstract: By sharing complementary perceptual information, multi-agent collaborative perception fosters a deeper understanding of the environment. Recent studies on collaborative perception mostly utilize CNNs or Transformers to learn feature representation and fusion in the spatial dimension, which struggle to handle long-range spatial-temporal features under limited computing and communication resources. Holistically modeling the dependencies over extensive spatial areas and extended temporal frames is crucial to enhancing feature quality. To this end, we propose a resource efficient cross-agent spatial-temporal collaborative state space model (SSM), named CollaMamba. Initially, we construct a foundational backbone network based on spatial SSM. This backbone adeptly captures positional causal dependencies from both single-agent and cross-agent views, yielding compact and comprehensive intermediate features while maintaining linear complexity. Furthermore, we devise a history-aware feature boosting module based on temporal SSM, extracting contextual cues from extended historical frames to refine vague features while preserving low overhead. Extensive experiments across several datasets demonstrate that CollaMamba outperforms state-of-the-art methods, achieving higher model accuracy while reducing computational and communication overhead by up to 71.9% and 1/64, respectively. This work pioneers the exploration of the Mamba's potential in collaborative perception. The source code will be made available.
Authors: Devansh Dhrafani, Yifei Liu, Andrew Jong, Ukcheol Shin, Yao He, Tyler Harp, Yaoyu Hu, Jean Oh, Sebastian Scherer
Abstract: Robust depth perception in visually-degraded environments is crucial for autonomous aerial systems. Thermal imaging cameras, which capture infrared radiation, are robust to visual degradation. However, due to lack of a large-scale dataset, the use of thermal cameras for unmanned aerial system (UAS) depth perception has remained largely unexplored. This paper presents a stereo thermal depth perception dataset for autonomous aerial perception applications. The dataset consists of stereo thermal images, LiDAR, IMU and ground truth depth maps captured in urban and forest settings under diverse conditions like day, night, rain, and smoke. We benchmark representative stereo depth estimation algorithms, offering insights into their performance in degraded conditions. Models trained on our dataset generalize well to unseen smoky conditions, highlighting the robustness of stereo thermal imaging for depth perception. We aim for this work to enhance robotic perception in disaster scenarios, allowing for exploration and operations in previously unreachable areas. The dataset and source code are available at https://firestereo.github.io.
Authors: Bojian Li, Bo Liu, Jinghua Yue, Fugen Zhou
Abstract: Depth estimation is a cornerstone of 3D reconstruction and plays a vital role in minimally invasive endoscopic surgeries. However, most current depth estimation networks rely on traditional convolutional neural networks, which are limited in their ability to capture global information. Foundation models offer a promising avenue for enhancing depth estimation, but those currently available are primarily trained on natural images, leading to suboptimal performance when applied to endoscopic images. In this work, we introduce a novel fine-tuning strategy for the Depth Anything Model and integrate it with an intrinsic-based unsupervised monocular depth estimation framework. Our approach includes a low-rank adaptation technique based on random vectors, which improves the model's adaptability to different scales. Additionally, we propose a residual block built on depthwise separable convolution to compensate for the transformer's limited ability to capture high-frequency details, such as edges and textures. Our experimental results on the SCARED dataset show that our method achieves state-of-the-art performance while minimizing the number of trainable parameters. Applying this method in minimally invasive endoscopic surgery could significantly enhance both the precision and safety of these procedures.
Authors: Aaryan Panda, Damodar Panigrahi, Shaswata Mitra, Sudip Mittal, Shahram Rahimi
Abstract: The field of Computer Vision (CV) has faced challenges. Initially, it relied on handcrafted features and rule-based algorithms, resulting in limited accuracy. The introduction of machine learning (ML) has brought progress, particularly Transfer Learning (TL), which addresses various CV problems by reusing pre-trained models. TL requires less data and computing while delivering nearly equal accuracy, making it a prominent technique in the CV landscape. Our research focuses on TL development and how CV applications use it to solve real-world problems. We discuss recent developments, limitations, and opportunities.
Authors: Qingqiao Hu, Daoan Zhang, Jiebo Luo, Zhenyu Gong, Benedikt Wiestler, Jianguo Zhang, Hongwei Bran Li
Abstract: Learning meaningful and interpretable representations from high-dimensional volumetric magnetic resonance (MR) images is essential for advancing personalized medicine. While Vision Transformers (ViTs) have shown promise in handling image data, their application to 3D multi-contrast MR images faces challenges due to computational complexity and interpretability. To address this, we propose a novel state-space-model (SSM)-based masked autoencoder which scales ViT-like models to handle high-resolution data effectively while also enhancing the interpretability of learned representations. We propose a latent-to-spatial mapping technique that enables direct visualization of how latent features correspond to specific regions in the input volumes in the context of SSM. We validate our method on two key neuro-oncology tasks: identification of isocitrate dehydrogenase mutation status and 1p/19q co-deletion classification, achieving state-of-the-art accuracy. Our results highlight the potential of SSM-based self-supervised learning to transform radiomics analysis by combining efficiency and interpretability.
Authors: Yanan Wang, Shuichiro Haruta, Donghuo Zeng, Julio Vizcarra, Mori Kurokawa
Abstract: Video question answering (VideoQA) is a task to predict the correct answer to questions posed about a given video. The system must comprehend spatial and temporal relationships among objects extracted from videos to perform causal and temporal reasoning. While prior works have focused on modeling individual object movements using transformer-based methods, they falter when capturing complex scenarios involving multiple objects (e.g., "a boy is throwing a ball in a hoop"). We propose a contrastive language event graph representation learning method called CLanG to address this limitation. Aiming to capture event representations associated with multiple objects, our method employs a multi-layer GNN-cluster module for adversarial graph representation learning, enabling contrastive learning between the question text and its relevant multi-object event graph. Our method outperforms a strong baseline, achieving up to 2.2% higher accuracy on two challenging VideoQA datasets, NExT-QA and TGIF-QA-R. In particular, it is 2.8% better than baselines in handling causal and temporal questions, highlighting its strength in reasoning multiple object-based events.
Authors: Yanan Wang, Shuichiro Haruta, Donghuo Zeng, Julio Vizcarra, Mori Kurokawa
Abstract: Capturing complex hierarchical human activities, from atomic actions (e.g., picking up one present, moving to the sofa, unwrapping the present) to contextual events (e.g., celebrating Christmas) is crucial for achieving high-performance video question answering (VideoQA). Recent works have expanded multimodal models (e.g., CLIP, LLaVA) to process continuous video sequences, enhancing the model's temporal reasoning capabilities. However, these approaches often fail to capture contextual events that can be decomposed into multiple atomic actions non-continuously distributed over relatively long-term sequences. In this paper, to leverage the spatial visual context representation capability of the CLIP model for obtaining non-continuous visual representations in terms of contextual events in videos, we convert long-term video sequences into a spatial image domain and finetune the multimodal model LLaVA for the VideoQA task. Our approach achieves competitive performance on the STAR task, in particular, with a 78.4% accuracy score, exceeding the current state-of-the-art score by 2.8 points on the NExTQA task.
Authors: Liang Feng, Ming Xu, Lihua Wen, Zhixuan Shen
Abstract: Pose estimation is a crucial task in computer vision, with wide applications in autonomous driving, human motion capture, and virtual reality. However, existing methods still face challenges in achieving high accuracy, particularly in complex scenes. This paper proposes a novel pose estimation method, GatedUniPose, which combines UniRepLKNet and Gated Convolution and introduces the GLACE module for embedding. Additionally, we enhance the feature map concatenation method in the head layer by using DySample upsampling. Compared to existing methods, GatedUniPose excels in handling complex scenes and occlusion challenges. Experimental results on the COCO, MPII, and CrowdPose datasets demonstrate that GatedUniPose achieves significant performance improvements with a relatively small number of parameters, yielding better or comparable results to models with similar or larger parameter sizes.
Authors: Zhenyuan Dong, Sai Qian Zhang
Abstract: Diffusion Transformers (DiTs) have recently attracted significant interest from both industry and academia due to their enhanced capabilities in visual generation, surpassing the performance of traditional diffusion models that employ U-Net. However, the improved performance of DiTs comes at the expense of higher parameter counts and implementation costs, which significantly limits their deployment on resource-constrained devices like mobile phones. We propose DiTAS, a data-free post-training quantization (PTQ) method for efficient DiT inference. DiTAS relies on the proposed temporal-aggregated smoothing techniques to mitigate the impact of the channel-wise outliers within the input activations, leading to much lower quantization error under extremely low bitwidth. To further enhance the performance of the quantized DiT, we adopt the layer-wise grid search strategy to optimize the smoothing factor. Experimental results demonstrate that our approach enables 4-bit weight, 8-bit activation (W4A8) quantization for DiTs while maintaining comparable performance as the full-precision model.
Authors: Yifei Yao, Hanrong Zhang
Abstract: In real-world clinical settings, data distributions evolve over time, with a continuous influx of new, limited disease cases. Therefore, class incremental learning is of great significance, i.e., deep learning models are required to learn new class knowledge while maintaining accurate recognition of previous diseases. However, traditional deep neural networks often suffer from severe forgetting of prior knowledge when adapting to new data unless trained from scratch, which undesirably costs much time and computational burden. Additionally, the sample sizes for different diseases can be highly imbalanced, with newly emerging diseases typically having much fewer instances, consequently causing the classification bias. To tackle these challenges, we are the first to propose a class-incremental learning method under limited samples in the biomedical field. First, we propose a novel cumulative entropy prediction module to measure the uncertainty of the samples, of which the most uncertain samples are stored in a memory bank as exemplars for the model's later review. Furthermore, we theoretically demonstrate its effectiveness in measuring uncertainty. Second, we developed a fine-grained semantic expansion module through various augmentations, leading to more compact distributions within the feature space and creating sufficient room for generalization to new classes. Besides, a cosine classifier is utilized to mitigate classification bias caused by imbalanced datasets. Across four imbalanced data distributions over two datasets, our method achieves optimal performance, surpassing state-of-the-art methods by as much as 53.54% in accuracy.
Authors: Shaode Yu, Ze Chen, Zhimu Yang, Jiacheng Gu, Bizu Feng
Abstract: Score prediction is crucial in realistic image sharpness assessment after informative features are collected. Recently, Kolmogorov-Arnold networks (KANs) have been developed and witnessed remarkable success in data fitting. This study presents Taylor series based KAN (TaylorKAN). Then, different KANs are explored on four realistic image databases (BID2011, CID2013, CLIVE, and KonIQ-10k) for score prediction by using 15 mid-level features and 2048 high-level features. When setting support vector regression as the baseline, experimental results indicate KANs are generally better or competitive, TaylorKAN is the best on three databases using mid-level feature input, while KANs are inferior on CLIVE when high-level features are used. This is the first study that explores KANs for image quality assessment. It sheds lights on how to select and improve KANs on related tasks.
Authors: Fuchen Zheng, Xinyi Chen, Xuhang Chen, Haolun Li, Xiaojiao Guo, Guoheng Huang, Chi-Man Pun, Shoujun Zhou
Abstract: Medical image segmentation, a crucial task in computer vision, facilitates the automated delineation of anatomical structures and pathologies, supporting clinicians in diagnosis, treatment planning, and disease monitoring. Notably, transformers employing shifted window-based self-attention have demonstrated exceptional performance. However, their reliance on local window attention limits the fusion of local and global contextual information, crucial for segmenting microtumors and miniature organs. To address this limitation, we propose the Adaptive Semantic Segmentation Network (ASSNet), a transformer architecture that effectively integrates local and global features for precise medical image segmentation. ASSNet comprises a transformer-based U-shaped encoder-decoder network. The encoder utilizes shifted window self-attention across five resolutions to extract multi-scale features, which are then propagated to the decoder through skip connections. We introduce an augmented multi-layer perceptron within the encoder to explicitly model long-range dependencies during feature extraction. Recognizing the constraints of conventional symmetrical encoder-decoder designs, we propose an Adaptive Feature Fusion (AFF) decoder to complement our encoder. This decoder incorporates three key components: the Long Range Dependencies (LRD) block, the Multi-Scale Feature Fusion (MFF) block, and the Adaptive Semantic Center (ASC) block. These components synergistically facilitate the effective fusion of multi-scale features extracted by the decoder while capturing long-range dependencies and refining object boundaries. Comprehensive experiments on diverse medical image segmentation tasks, including multi-organ, liver tumor, and bladder tumor segmentation, demonstrate that ASSNet achieves state-of-the-art results. Code and models are available at: \url{https://github.com/lzeeorno/ASSNet}.
Authors: Fuchen Zheng, Quanjun Li, Weixuan Li, Xuhang Chen, Yihang Dong, Guoheng Huang, Chi-Man Pun, Shoujun Zhou
Abstract: Medical image segmentation, a critical application of semantic segmentation in healthcare, has seen significant advancements through specialized computer vision techniques. While deep learning-based medical image segmentation is essential for assisting in medical diagnosis, the lack of diverse training data causes the long-tail problem. Moreover, most previous hybrid CNN-ViT architectures have limited ability to combine various attentions in different layers of the Convolutional Neural Network. To address these issues, we propose a Lagrange Duality Consistency (LDC) Loss, integrated with Boundary-Aware Contrastive Loss, as the overall training objective for semi-supervised learning to mitigate the long-tail problem. Additionally, we introduce CMAformer, a novel network that synergizes the strengths of ResUNet and Transformer. The cross-attention block in CMAformer effectively integrates spatial attention and channel attention for multi-scale feature fusion. Overall, our results indicate that CMAformer, combined with the feature fusion framework and the new consistency loss, demonstrates strong complementarity in semi-supervised learning ensembles. We achieve state-of-the-art results on multiple public medical image datasets. Example code are available at: \url{https://github.com/lzeeorno/Lagrange-Duality-and-CMAformer}.
URLs: https://github.com/lzeeorno/Lagrange-Duality-and-CMAformer
Authors: Mohammad Mehdi Rastikerdar, Jin Huang, Hui Guan, Deepak Ganesan
Abstract: Wildlife monitoring via camera traps has become an essential tool in ecology, but the deployment of machine learning models for on-device animal classification faces significant challenges due to domain shifts and resource constraints. This paper introduces WildFit, a novel approach that reconciles the conflicting goals of achieving high domain generalization performance and ensuring efficient inference for camera trap applications. WildFit leverages continuous background-aware model fine-tuning to deploy ML models tailored to the current location and time window, allowing it to maintain robust classification accuracy in the new environment without requiring significant computational resources. This is achieved by background-aware data synthesis, which generates training images representing the new domain by blending background images with animal images from the source domain. We further enhance fine-tuning effectiveness through background drift detection and class distribution drift detection, which optimize the quality of synthesized data and improve generalization performance. Our extensive evaluation across multiple camera trap datasets demonstrates that WildFit achieves significant improvements in classification accuracy and computational efficiency compared to traditional approaches.
Authors: Yu Guo, Guoqing Chen, Tieyong Zeng, Qiyu Jin, Michael Kwok-Po Ng
Abstract: Color image restoration methods typically represent images as vectors in Euclidean space or combinations of three monochrome channels. However, they often overlook the correlation between these channels, leading to color distortion and artifacts in the reconstructed image. To address this, we present Quaternion Nuclear Norm Minus Frobenius Norm Minimization (QNMF), a novel approach for color image reconstruction. QNMF utilizes quaternion algebra to capture the relationships among RGB channels comprehensively. By employing a regularization technique that involves nuclear norm minus Frobenius norm, QNMF approximates the underlying low-rank structure of quaternion-encoded color images. Theoretical proofs are provided to ensure the method's mathematical integrity. Demonstrating versatility and efficacy, the QNMF regularizer excels in various color low-level vision tasks, including denoising, deblurring, inpainting, and random impulse noise removal, achieving state-of-the-art results.
Authors: Liang Feng, Zhixuan Shen, Lihua Wen, Shiyao Li, Ming Xu
Abstract: This paper introduces GateAttentionPose, an innovative approach that enhances the UniRepLKNet architecture for pose estimation tasks. We present two key contributions: the Agent Attention module and the Gate-Enhanced Feedforward Block (GEFB). The Agent Attention module replaces large kernel convolutions, significantly improving computational efficiency while preserving global context modeling. The GEFB augments feature extraction and processing capabilities, particularly in complex scenes. Extensive evaluations on COCO and MPII datasets demonstrate that GateAttentionPose outperforms existing state-of-the-art methods, including the original UniRepLKNet, achieving superior or comparable results with improved efficiency. Our approach offers a robust solution for pose estimation across diverse applications, including autonomous driving, human motion capture, and virtual reality.
Authors: \c{C}a\u{g}han K\"oksal, Ghazal Ghazaei, Nassir Navab
Abstract: Surgical scenes convey crucial information about the quality of surgery. Pixel-wise localization of tools and anatomical structures is the first task towards deeper surgical analysis for microscopic or endoscopic surgical views. This is typically done via fully-supervised methods which are annotation greedy and in several cases, demanding medical expertise. Considering the profusion of surgical videos obtained through standardized surgical workflows, we propose an annotation-efficient framework for the semantic segmentation of surgical scenes. We employ image-based self-supervised object discovery to identify the most salient tools and anatomical structures in surgical videos. These proposals are further refined within a minimally supervised fine-tuning step. Our unsupervised setup reinforced with only 36 annotation labels indicates comparable localization performance with fully-supervised segmentation models. Further, leveraging surgical phase labels as weak labels can better guide model attention towards surgical tools, leading to $\sim 2\%$ improvement in tool localization. Extensive ablation studies on the CaDIS dataset validate the effectiveness of our proposed solution in discovering relevant surgical objects with minimal or no supervision.
Authors: Muhammad Yaseen
Abstract: This study provides a comprehensive analysis of the YOLOv9 object detection model, focusing on its architectural innovations, training methodologies, and performance improvements over its predecessors. Key advancements, such as the Generalized Efficient Layer Aggregation Network GELAN and Programmable Gradient Information PGI, significantly enhance feature extraction and gradient flow, leading to improved accuracy and efficiency. By incorporating Depthwise Convolutions and the lightweight C3Ghost architecture, YOLOv9 reduces computational complexity while maintaining high precision. Benchmark tests on Microsoft COCO demonstrate its superior mean Average Precision mAP and faster inference times, outperforming YOLOv8 across multiple metrics. The model versatility is highlighted by its seamless deployment across various hardware platforms, from edge devices to high performance GPUs, with built in support for PyTorch and TensorRT integration. This paper provides the first in depth exploration of YOLOv9s internal features and their real world applicability, establishing it as a state of the art solution for real time object detection across industries, from IoT devices to large scale industrial applications.
Authors: Renjie Wu, Hu Wang, Hsiang-Ting Chen
Abstract: During multimodal model training and reasoning, data samples may miss certain modalities and lead to compromised model performance due to sensor limitations, cost constraints, privacy concerns, data loss, and temporal and spatial factors. This survey provides an overview of recent progress in Multimodal Learning with Missing Modality (MLMM), focusing on deep learning techniques. It is the first comprehensive survey that covers the historical background and the distinction between MLMM and standard multimodal learning setups, followed by a detailed analysis of current MLMM methods, applications, and datasets, concluding with a discussion about challenges and potential future directions in the field.
Authors: Oliver Grainge, Michael Milford, Indu Bodala, Sarvapali D. Ramchurn, Shoaib Ehsan
Abstract: Visual Place Recognition (VPR) is fundamental for the global re-localization of robots and devices, enabling them to recognize previously visited locations based on visual inputs. This capability is crucial for maintaining accurate mapping and localization over large areas. Given that VPR methods need to operate in real-time on embedded systems, it is critical to optimize these systems for minimal resource consumption. While the most efficient VPR approaches employ standard convolutional backbones with fixed descriptor dimensions, these often lead to redundancy in the embedding space as well as in the network architecture. Our work introduces a novel structured pruning method, to not only streamline common VPR architectures but also to strategically remove redundancies within the feature embedding space. This dual focus significantly enhances the efficiency of the system, reducing both map and model memory requirements and decreasing feature extraction and retrieval latencies. Our approach has reduced memory usage and latency by 21% and 16%, respectively, across models, while minimally impacting recall@1 accuracy by less than 1%. This significant improvement enhances real-time applications on edge devices with negligible accuracy loss.
Authors: Ming Li, Xiong Yang, Chaofan Wu, Jiaheng Li, Pinzhi Wang, Xuejiao Hu, Sidan Du, Yang Li
Abstract: Omnidirectional Depth Estimation has broad application prospects in fields such as robotic navigation and autonomous driving. In this paper, we propose a robotic prototype system and corresponding algorithm designed to validate omnidirectional depth estimation for navigation and obstacle avoidance in real-world scenarios for both robots and vehicles. The proposed HexaMODE system captures 360$^\circ$ depth maps using six surrounding arranged fisheye cameras. We introduce a combined spherical sweeping method and optimize the model architecture for proposed RtHexa-OmniMVS algorithm to achieve real-time omnidirectional depth estimation. To ensure high accuracy, robustness, and generalization in real-world environments, we employ a teacher-student self-training strategy, utilizing large-scale unlabeled real-world data for model training. The proposed algorithm demonstrates high accuracy in various complex real-world scenarios, both indoors and outdoors, achieving an inference speed of 15 fps on edge computing platforms.
Authors: Corentin Sautier, Gilles Puy, Alexandre Boulch, Renaud Marlet, Vincent Lepetit
Abstract: Online object segmentation and tracking in Lidar point clouds enables autonomous agents to understand their surroundings and make safe decisions. Unfortunately, manual annotations for these tasks are prohibitively costly. We tackle this problem with the task of class-agnostic unsupervised online instance segmentation and tracking. To that end, we leverage an instance segmentation backbone and propose a new training recipe that enables the online tracking of objects. Our network is trained on pseudo-labels, eliminating the need for manual annotations. We conduct an evaluation using metrics adapted for temporal instance segmentation. Computing these metrics requires temporally-consistent instance labels. When unavailable, we construct these labels using the available 3D bounding boxes and semantic labels in the dataset. We compare our method against strong baselines and demonstrate its superiority across two different outdoor Lidar datasets.
Authors: Shun Zou, Zhuo Zhang, Yi Zou, Guangwei Gao
Abstract: In the field of medical microscopic image classification (MIC), CNN-based and Transformer-based models have been extensively studied. However, CNNs struggle with modeling long-range dependencies, limiting their ability to fully utilize semantic information in images. Conversely, Transformers are hampered by the complexity of quadratic computations. To address these challenges, we propose a model based on the Mamba architecture: Microscopic-Mamba. Specifically, we designed the Partially Selected Feed-Forward Network (PSFFN) to replace the last linear layer of the Visual State Space Module (VSSM), enhancing Mamba's local feature extraction capabilities. Additionally, we introduced the Modulation Interaction Feature Aggregation (MIFA) module to effectively modulate and dynamically aggregate global and local features. We also incorporated a parallel VSSM mechanism to improve inter-channel information interaction while reducing the number of parameters. Extensive experiments have demonstrated that our method achieves state-of-the-art performance on five public datasets. Code is available at https://github.com/zs1314/Microscopic-Mamba
Authors: Rongzihan Song, Zhenyu Weng, Huiping Zhuang, Jinchang Ren, Yongming Chen, Zhiping Lin
Abstract: Multiple object tracking (MOT) involves identifying multiple targets and assigning them corresponding IDs within a video sequence, where occlusions are often encountered. Recent methods address occlusions using appearance cues through online learning techniques to improve adaptivity or offline learning techniques to utilize temporal information from videos. However, most existing online learning-based MOT methods are unable to learn from all past tracking information to improve adaptivity on long-term occlusions while maintaining real-time tracking speed. On the other hand, temporal information-based offline learning methods maintain a long-term memory to store past tracking information, but this approach restricts them to use only local past information during tracking. To address these challenges, we propose a new MOT framework called the Feature Adaptive Continual-learning Tracker (FACT), which enables real-time tracking and feature learning for targets by utilizing all past tracking information. We demonstrate that the framework can be integrated with various state-of-the-art feature-based trackers, thereby improving their tracking ability. Specifically, we develop the feature adaptive continual-learning (FAC) module, a neural network that can be trained online to learn features adaptively using all past tracking information during tracking. Moreover, we also introduce a two-stage association module specifically designed for the proposed continual learning-based tracking. Extensive experiment results demonstrate that the proposed method achieves state-of-the-art online tracking performance on MOT17 and MOT20 benchmarks. The code will be released upon acceptance.
Authors: Longfei Liu, Wen Guo, Shihua Huang, Cheng Li, Xi Shen
Abstract: Reducing false positives is essential for enhancing object detector performance, as reflected in the mean Average Precision (mAP) metric. Although object detectors have achieved notable improvements and high mAP scores on the COCO dataset, analysis reveals limited progress in addressing false positives caused by non-target visual clutter-background objects not included in the annotated categories. This issue is particularly critical in real-world applications, such as fire and smoke detection, where minimizing false alarms is crucial. In this study, we introduce COCO-FP, a new evaluation dataset derived from the ImageNet-1K dataset, designed to address this issue. By extending the original COCO validation dataset, COCO-FP specifically assesses object detectors' performance in mitigating background false positives. Our evaluation of both standard and advanced object detectors shows a significant number of false positives in both closed-set and open-set scenarios. For example, the AP50 metric for YOLOv9-E decreases from 72.8 to 65.7 when shifting from COCO to COCO-FP. The dataset is available at https://github.com/COCO-FP/COCO-FP.
Authors: Inzamamul Alam, Muhammad Shahid Muneer, Simon S. Woo
Abstract: In the wake of a fabricated explosion image at the Pentagon, an ability to discern real images from fake counterparts has never been more critical. Our study introduces a novel multi-modal approach to detect AI-generated images amidst the proliferation of new generation methods such as Diffusion models. Our method, UGAD, encompasses three key detection steps: First, we transform the RGB images into YCbCr channels and apply an Integral Radial Operation to emphasize salient radial features. Secondly, the Spatial Fourier Extraction operation is used for a spatial shift, utilizing a pre-trained deep learning network for optimal feature extraction. Finally, the deep neural network classification stage processes the data through dense layers using softmax for classification. Our approach significantly enhances the accuracy of differentiating between real and AI-generated images, as evidenced by a 12.64% increase in accuracy and 28.43% increase in AUC compared to existing state-of-the-art methods.
Authors: Xiaohuan Lu, Lian Zhao, Wai Keung Wong, Jie Wen, Jiang Long, Wulin Xie
Abstract: In real-world scenarios, multi-view multi-label learning often encounters the challenge of incomplete training data due to limitations in data collection and unreliable annotation processes. The absence of multi-view features impairs the comprehensive understanding of samples, omitting crucial details essential for classification. To address this issue, we present a task-augmented cross-view imputation network (TACVI-Net) for the purpose of handling partial multi-view incomplete multi-label classification. Specifically, we employ a two-stage network to derive highly task-relevant features to recover the missing views. In the first stage, we leverage the information bottleneck theory to obtain a discriminative representation of each view by extracting task-relevant information through a view-specific encoder-classifier architecture. In the second stage, an autoencoder based multi-view reconstruction network is utilized to extract high-level semantic representation of the augmented features and recover the missing data, thereby aiding the final classification task. Extensive experiments on five datasets demonstrate that our TACVI-Net outperforms other state-of-the-art methods.
Authors: Roy Friedman, Rhea Chowers
Abstract: We propose a new method for generating realistic datasets with distribution shifts using any decoder-based generative model. Our approach systematically creates datasets with varying intensities of distribution shifts, facilitating a comprehensive analysis of model performance degradation. We then use these generated datasets to evaluate the performance of various commonly used networks and observe a consistent decline in performance with increasing shift intensity, even when the effect is almost perceptually unnoticeable to the human eye. We see this degradation even when using data augmentations. We also find that enlarging the training dataset beyond a certain point has no effect on the robustness and that stronger inductive biases increase robustness.
Authors: Kerem Cekmeceli, Meva Himmetoglu, Guney I. Tombak, Anna Susmelj, Ertunc Erdil, Ender Konukoglu
Abstract: Neural networks achieve state-of-the-art performance in many supervised learning tasks when the training data distribution matches the test data distribution. However, their performance drops significantly under domain (covariate) shift, a prevalent issue in medical image segmentation due to varying acquisition settings across different scanner models and protocols. Recently, foundational models (FMs) trained on large datasets have gained attention for their ability to be adapted for downstream tasks and achieve state-of-the-art performance with excellent generalization capabilities on natural images. However, their effectiveness in medical image segmentation remains underexplored. In this paper, we investigate the domain generalization performance of various FMs, including DinoV2, SAM, MedSAM, and MAE, when fine-tuned using various parameter-efficient fine-tuning (PEFT) techniques such as Ladder and Rein (+LoRA) and decoder heads. We introduce a novel decode head architecture, HQHSAM, which simply integrates elements from two state-of-the-art decoder heads, HSAM and HQSAM, to enhance segmentation performance. Our extensive experiments on multiple datasets, encompassing various anatomies and modalities, reveal that FMs, particularly with the HQHSAM decode head, improve domain generalization for medical image segmentation. Moreover, we found that the effectiveness of PEFT techniques varies across different FMs. These findings underscore the potential of FMs to enhance the domain generalization performance of neural networks in medical image segmentation across diverse clinical settings, providing a solid foundation for future research. Code and models are available for research purposes at \url{https://github.com/kerem-cekmeceli/Foundation-Models-for-Medical-Imagery}.
URLs: https://github.com/kerem-cekmeceli/Foundation-Models-for-Medical-Imagery
Authors: Zhangyue Ling, Pritthijit Nath, C\'esar Quilodr\'an-Casas
Abstract: This study explores the application of diffusion models in the field of typhoons, predicting multiple ERA5 meteorological variables simultaneously from Digital Typhoon satellite images. The focus of this study is taken to be Taiwan, an area very vulnerable to typhoons. By comparing the performance of Conditional Denoising Diffusion Probability Model (CDDPM) with Convolutional Neural Networks (CNN) and Squeeze-and-Excitation Networks (SENet), results suggest that the CDDPM performs best in generating accurate and realistic meteorological data. Specifically, CDDPM achieved a PSNR of 32.807, which is approximately 7.9% higher than CNN and 5.5% higher than SENet. Furthermore, CDDPM recorded an RMSE of 0.032, showing a 11.1% improvement over CNN and 8.6% improvement over SENet. A key application of this research can be for imputation purposes in missing meteorological datasets and generate additional high-quality meteorological data using satellite images. It is hoped that the results of this analysis will enable more robust and detailed forecasting, reducing the impact of severe weather events on vulnerable regions. Code accessible at https://github.com/TammyLing/Typhoon-forecasting.
Authors: Sichun Wu, Kazi Injamamul Haque, Zerrin Yumak
Abstract: Audio-driven 3D facial animation synthesis has been an active field of research with attention from both academia and industry. While there are promising results in this area, recent approaches largely focus on lip-sync and identity control, neglecting the role of emotions and emotion control in the generative process. That is mainly due to the lack of emotionally rich facial animation data and algorithms that can synthesize speech animations with emotional expressions at the same time. In addition, majority of the models are deterministic, meaning given the same audio input, they produce the same output motion. We argue that emotions and non-determinism are crucial to generate diverse and emotionally-rich facial animations. In this paper, we propose ProbTalk3D a non-deterministic neural network approach for emotion controllable speech-driven 3D facial animation synthesis using a two-stage VQ-VAE model and an emotionally rich facial animation dataset 3DMEAD. We provide an extensive comparative analysis of our model against the recent 3D facial animation synthesis approaches, by evaluating the results objectively, qualitatively, and with a perceptual user study. We highlight several objective metrics that are more suitable for evaluating stochastic outputs and use both in-the-wild and ground truth data for subjective evaluation. To our knowledge, that is the first non-deterministic 3D facial animation synthesis method incorporating a rich emotion dataset and emotion control with emotion labels and intensity levels. Our evaluation demonstrates that the proposed model achieves superior performance compared to state-of-the-art emotion-controlled, deterministic and non-deterministic models. We recommend watching the supplementary video for quality judgement. The entire codebase is publicly available (https://github.com/uuembodiedsocialai/ProbTalk3D/).
Authors: Ling Xing, Hongyu Qu, Rui Yan, Xiangbo Shu, Jinhui Tang
Abstract: Dense-localization Audio-Visual Events (DAVE) aims to identify time boundaries and corresponding categories for events that can be heard and seen concurrently in an untrimmed video. Existing methods typically encode audio and visual representation separately without any explicit cross-modal alignment constraint. Then they adopt dense cross-modal attention to integrate multimodal information for DAVE. Thus these methods inevitably aggregate irrelevant noise and events, especially in complex and long videos, leading to imprecise detection. In this paper, we present LOCO, a Locality-aware cross-modal Correspondence learning framework for DAVE. The core idea is to explore local temporal continuity nature of audio-visual events, which serves as informative yet free supervision signals to guide the filtering of irrelevant information and inspire the extraction of complementary multimodal information during both unimodal and cross-modal learning stages. i) Specifically, LOCO applies Locality-aware Correspondence Correction (LCC) to uni-modal features via leveraging cross-modal local-correlated properties without any extra annotations. This enforces uni-modal encoders to highlight similar semantics shared by audio and visual features. ii) To better aggregate such audio and visual features, we further customize Cross-modal Dynamic Perception layer (CDP) in cross-modal feature pyramid to understand local temporal patterns of audio-visual events by imposing local consistency within multimodal features in a data-driven manner. By incorporating LCC and CDP, LOCO provides solid performance gains and outperforms existing methods for DAVE. The source code will be released.
Authors: Yuan Wu, Zhiqiang Yan, Zhengxue Wang, Xiang Li, Le Hui, Jian Yang
Abstract: The task of vision-based 3D occupancy prediction aims to reconstruct 3D geometry and estimate its semantic classes from 2D color images, where the 2D-to-3D view transformation is an indispensable step. Most previous methods conduct forward projection, such as BEVPooling and VoxelPooling, both of which map the 2D image features into 3D grids. However, the current grid representing features within a certain height range usually introduces many confusing features that belong to other height ranges. To address this challenge, we present Deep Height Decoupling (DHD), a novel framework that incorporates explicit height prior to filter out the confusing features. Specifically, DHD first predicts height maps via explicit supervision. Based on the height distribution statistics, DHD designs Mask Guided Height Sampling (MGHS) to adaptively decoupled the height map into multiple binary masks. MGHS projects the 2D image features into multiple subspaces, where each grid contains features within reasonable height ranges. Finally, a Synergistic Feature Aggregation (SFA) module is deployed to enhance the feature representation through channel and spatial affinities, enabling further occupancy refinement. On the popular Occ3D-nuScenes benchmark, our method achieves state-of-the-art performance even with minimal input frames. Code is available at https://github.com/yanzq95/DHD.
Authors: Kamirul Kamirul, Odysseas Pappas, Alin Achim
Abstract: We present Sparse R-CNN OBB, a novel framework for the detection of oriented objects in SAR images leveraging sparse learnable proposals. The Sparse R-CNN OBB has streamlined architecture and ease of training as it utilizes a sparse set of 300 proposals instead of training a proposals generator on hundreds of thousands of anchors. To the best of our knowledge, Sparse R-CNN OBB is the first to adopt the concept of sparse learnable proposals for the detection of oriented objects, as well as for the detection of ships in Synthetic Aperture Radar (SAR) images. The detection head of the baseline model, Sparse R-CNN, is re-designed to enable the model to capture object orientation. We also fine-tune the model on RSDD-SAR dataset and provide a performance comparison to state-of-the-art models. Experimental results shows that Sparse R-CNN OBB achieves outstanding performance, surpassing other models on both inshore and offshore scenarios. The code is available at: www.github.com/ka-mirul/Sparse-R-CNN-OBB.
Authors: Kelian Baert, Shrisha Bharadwaj, Fabien Castan, Benoit Maujean, Marc Christie, Victoria Abrevaya, Adnane Boukhayma
Abstract: Feedforward monocular face capture methods seek to reconstruct posed faces from a single image of a person. Current state of the art approaches have the ability to regress parametric 3D face models in real-time across a wide range of identities, lighting conditions and poses by leveraging large image datasets of human faces. These methods however suffer from clear limitations in that the underlying parametric face model only provides a coarse estimation of the face shape, thereby limiting their practical applicability in tasks that require precise 3D reconstruction (aging, face swapping, digital make-up, ...). In this paper, we propose a method for high-precision 3D face capture taking advantage of a collection of unconstrained videos of a subject as prior information. Our proposal builds on a two stage approach. We start with the reconstruction of a detailed 3D face avatar of the person, capturing both precise geometry and appearance from a collection of videos. We then use the encoder from a pre-trained monocular face reconstruction method, substituting its decoder with our personalized model, and proceed with transfer learning on the video collection. Using our pre-estimated image formation model, we obtain a more precise self-supervision objective, enabling improved expression and pose alignment. This results in a trained encoder capable of efficiently regressing pose and expression parameters in real-time from previously unseen images, which combined with our personalized geometry model yields more accurate and high fidelity mesh inference. Through extensive qualitative and quantitative evaluation, we showcase the superiority of our final model as compared to state-of-the-art baselines, and demonstrate its generalization ability to unseen pose, expression and lighting.
Authors: Fatemeh Askari, Amirreza Fateh, Mohammad Reza Mohammadi
Abstract: In the context of few-shot classification, the goal is to train a classifier using a limited number of samples while maintaining satisfactory performance. However, traditional metric-based methods exhibit certain limitations in achieving this objective. These methods typically rely on a single distance value between the query feature and support feature, thereby overlooking the contribution of shallow features. To overcome this challenge, we propose a novel approach in this paper. Our approach involves utilizing multi-output embedding network that maps samples into distinct feature spaces. The proposed method extract feature vectors at different stages, enabling the model to capture both global and abstract features. By utilizing these diverse feature spaces, our model enhances its performance. Moreover, employing a self-attention mechanism improves the refinement of features at each stage, leading to even more robust representations and improved overall performance. Furthermore, assigning learnable weights to each stage significantly improved performance and results. We conducted comprehensive evaluations on the MiniImageNet and FC100 datasets, specifically in the 5-way 1-shot and 5-way 5-shot scenarios. Additionally, we performed a cross-domain task from MiniImageNet to the CUB dataset, achieving high accuracy in the testing domain. These evaluations demonstrate the efficacy of our proposed method in comparison to state-of-the-art approaches. https://github.com/FatemehAskari/MSENet
Authors: Siyu Chen, Ting Han, Changshe Zhang, Weiquan Liu, Jinhe Su, Zongyue Wang, Guorong Cai
Abstract: RGB-D has gradually become a crucial data source for understanding complex scenes in assisted driving. However, existing studies have paid insufficient attention to the intrinsic spatial properties of depth maps. This oversight significantly impacts the attention representation, leading to prediction errors caused by attention shift issues. To this end, we propose a novel learnable Depth interaction Pyramid Transformer (DiPFormer) to explore the effectiveness of depth. Firstly, we introduce Depth Spatial-Aware Optimization (Depth SAO) as offset to represent real-world spatial relationships. Secondly, the similarity in the feature space of RGB-D is learned by Depth Linear Cross-Attention (Depth LCA) to clarify spatial differences at the pixel level. Finally, an MLP Decoder is utilized to effectively fuse multi-scale features for meeting real-time requirements. Comprehensive experiments demonstrate that the proposed DiPFormer significantly addresses the issue of attention misalignment in both road detection (+7.5%) and semantic segmentation (+4.9% / +1.5%) tasks. DiPFormer achieves state-of-the-art performance on the KITTI (97.57% F-score on KITTI road and 68.74% mIoU on KITTI-360) and Cityscapes (83.4% mIoU) datasets.
Authors: Seonho Lee, Jiho Choi, Seohyun Lim, Jiwook Kim, Hyunjung Shim
Abstract: Recent advancements in text-to-image diffusion models have demonstrated remarkable success, yet they often struggle to fully capture the user's intent. Existing approaches using textual inputs combined with bounding boxes or region masks fall short in providing precise spatial guidance, often leading to misaligned or unintended object orientation. To address these limitations, we propose Scribble-Guided Diffusion (ScribbleDiff), a training-free approach that utilizes simple user-provided scribbles as visual prompts to guide image generation. However, incorporating scribbles into diffusion models presents challenges due to their sparse and thin nature, making it difficult to ensure accurate orientation alignment. To overcome these challenges, we introduce moment alignment and scribble propagation, which allow for more effective and flexible alignment between generated images and scribble inputs. Experimental results on the PASCAL-Scribble dataset demonstrate significant improvements in spatial control and consistency, showcasing the effectiveness of scribble-based guidance in diffusion models. Our code is available at https://github.com/kaist-cvml-lab/scribble-diffusion.
Authors: Simon de Moreau, Yasser Almehio, Andrei Bursuc, Hafid El-Idrissi, Bogdan Stanciulescu, Fabien Moutarde
Abstract: Nighttime camera-based depth estimation is a highly challenging task, especially for autonomous driving applications, where accurate depth perception is essential for ensuring safe navigation. We aim to improve the reliability of perception systems at night time, where models trained on daytime data often fail in the absence of precise but costly LiDAR sensors. In this work, we introduce Light Enhanced Depth (LED), a novel cost-effective approach that significantly improves depth estimation in low-light environments by harnessing a pattern projected by high definition headlights available in modern vehicles. LED leads to significant performance boosts across multiple depth-estimation architectures (encoder-decoder, Adabins, DepthFormer) both on synthetic and real datasets. Furthermore, increased performances beyond illuminated areas reveal a holistic enhancement in scene understanding. Finally, we release the Nighttime Synthetic Drive Dataset, a new synthetic and photo-realistic nighttime dataset, which comprises 49,990 comprehensively annotated images.
Authors: Qian Chen, Shihao Shu, Xiangzhi Bai
Abstract: Novel-view synthesis based on visible light has been extensively studied. In comparison to visible light imaging, thermal infrared imaging offers the advantage of all-weather imaging and strong penetration, providing increased possibilities for reconstruction in nighttime and adverse weather scenarios. However, thermal infrared imaging is influenced by physical characteristics such as atmospheric transmission effects and thermal conduction, hindering the precise reconstruction of intricate details in thermal infrared scenes, manifesting as issues of floaters and indistinct edge features in synthesized images. To address these limitations, this paper introduces a physics-induced 3D Gaussian splatting method named Thermal3D-GS. Thermal3D-GS begins by modeling atmospheric transmission effects and thermal conduction in three-dimensional media using neural networks. Additionally, a temperature consistency constraint is incorporated into the optimization objective to enhance the reconstruction accuracy of thermal infrared images. Furthermore, to validate the effectiveness of our method, the first large-scale benchmark dataset for this field named Thermal Infrared Novel-view Synthesis Dataset (TI-NSD) is created. This dataset comprises 20 authentic thermal infrared video scenes, covering indoor, outdoor, and UAV(Unmanned Aerial Vehicle) scenarios, totaling 6,664 frames of thermal infrared image data. Based on this dataset, this paper experimentally verifies the effectiveness of Thermal3D-GS. The results indicate that our method outperforms the baseline method with a 3.03 dB improvement in PSNR and significantly addresses the issues of floaters and indistinct edge features present in the baseline method. Our dataset and codebase will be released in \href{https://github.com/mzzcdf/Thermal3DGS}{\textcolor{red}{Thermal3DGS}}.
Authors: Weixiang Zhang, Shuzhao Xie, Shijia Ge, Wei Yao, Chen Tang, Zhi Wang
Abstract: Neural Radiance Fields have achieved success in creating powerful 3D media representations with their exceptional reconstruction capabilities. However, the computational demands of volume rendering pose significant challenges during model training. Existing acceleration techniques often involve redesigning the model architecture, leading to limitations in compatibility across different frameworks. Furthermore, these methods tend to overlook the substantial memory costs incurred. In response to these challenges, we introduce an expansive supervision mechanism that efficiently balances computational load, rendering quality and flexibility for neural radiance field training. This mechanism operates by selectively rendering a small but crucial subset of pixels and expanding their values to estimate the error across the entire area for each iteration. Compare to conventional supervision, our method effectively bypasses redundant rendering processes, resulting in notable reductions in both time and memory consumption. Experimental results demonstrate that integrating expansive supervision within existing state-of-the-art acceleration frameworks can achieve 69% memory savings and 42% time savings, with negligible compromise in visual quality.
Authors: Junsung Lee, Minsoo Kang, Bohyung Han
Abstract: We propose a simple but effective training-free approach tailored to diffusion-based image-to-image translation. Our approach revises the original noise prediction network of a pretrained diffusion model by introducing a noise correction term. We formulate the noise correction term as the difference between two noise predictions; one is computed from the denoising network with a progressive interpolation of the source and target prompt embeddings, while the other is the noise prediction with the source prompt embedding. The final noise prediction network is given by a linear combination of the standard denoising term and the noise correction term, where the former is designed to reconstruct must-be-preserved regions while the latter aims to effectively edit regions of interest relevant to the target prompt. Our approach can be easily incorporated into existing image-to-image translation methods based on diffusion models. Extensive experiments verify that the proposed technique achieves outstanding performance with low latency and consistently improves existing frameworks when combined with them.
Authors: Chenyang Lei, Liyi Chen, Jun Cen, Xiao Chen, Zhen Lei, Felix Heide, Ziwei Liu, Qifeng Chen, Zhaoxiang Zhang
Abstract: Foundation models like ChatGPT and Sora that are trained on a huge scale of data have made a revolutionary social impact. However, it is extremely challenging for sensors in many different fields to collect similar scales of natural images to train strong foundation models. To this end, this work presents a simple and effective framework SimMAT to study an open problem: the transferability from vision foundation models trained on natural RGB images to other image modalities of different physical properties (e.g., polarization). SimMAT consists of a modality-agnostic transfer layer (MAT) and a pretrained foundation model. We apply SimMAT to a representative vision foundation model Segment Anything Model (SAM) to support any evaluated new image modality. Given the absence of relevant benchmarks, we construct a new benchmark to evaluate the transfer learning performance. Our experiments confirm the intriguing potential of transferring vision foundation models in enhancing other sensors' performance. Specifically, SimMAT can improve the segmentation performance (mIoU) from 22.15% to 53.88% on average for evaluated modalities and consistently outperforms other baselines. We hope that SimMAT can raise awareness of cross-modal transfer learning and benefit various fields for better results with vision foundation models.
Authors: Zicheng Duan, Yuxuan Ding, Chenhui Gou, Ziqin Zhou, Ethan Smith, Lingqiao Liu
Abstract: Zero-shot subject-driven image generation aims to produce images that incorporate a subject from a given example image. The challenge lies in preserving the subject's identity while aligning with the text prompt, which often requires modifying certain aspects of the subject's appearance. Despite advancements in diffusion model based methods, existing approaches still struggle to balance identity preservation with text prompt alignment. In this study, we conducted an in-depth investigation into this issue and uncovered key insights for achieving effective identity preservation while maintaining a strong balance. Our key findings include: (1) the design of the subject image encoder significantly impacts identity preservation quality, and (2) generating an initial layout is crucial for both text alignment and identity preservation. Building on these insights, we introduce a new approach called EZIGen, which employs two main strategies: a carefully crafted subject image Encoder based on the UNet architecture of the pretrained Stable Diffusion model to ensure high-quality identity transfer, following a process that decouples the guidance stages and iteratively refines the initial image layout. Through these strategies, EZIGen achieves state-of-the-art results on multiple subject-driven benchmarks with a unified model and 100 times less training data.
Authors: Ozan Unal, Christos Sakaridis, Luc Van Gool
Abstract: 3D segmentation is a core problem in computer vision and, similarly to many other dense prediction tasks, it requires large amounts of annotated data for adequate training. However, densely labeling 3D point clouds to employ fully-supervised training remains too labor intensive and expensive. Semi-supervised training provides a more practical alternative, where only a small set of labeled data is given, accompanied by a larger unlabeled set. This area thus studies the effective use of unlabeled data to reduce the performance gap that arises due to the lack of annotations. In this work, inspired by Bayesian deep learning, we first propose a Bayesian self-training framework for semi-supervised 3D semantic segmentation. Employing stochastic inference, we generate an initial set of pseudo-labels and then filter these based on estimated point-wise uncertainty. By constructing a heuristic $n$-partite matching algorithm, we extend the method to semi-supervised 3D instance segmentation, and finally, with the same building blocks, to dense 3D visual grounding. We demonstrate state-of-the-art results for our semi-supervised method on SemanticKITTI and ScribbleKITTI for 3D semantic segmentation and on ScanNet and S3DIS for 3D instance segmentation. We further achieve substantial improvements in dense 3D visual grounding over supervised-only baselines on ScanRefer. Our project page is available at ouenal.github.io/bst/.
Authors: Zhaoli Deng, Kaibin Zhou, Fanyi Wang, Zhenpeng Mi
Abstract: The development of diffusion models has significantly advanced the research on image stylization, particularly in the area of stylizing a content image based on a given style image, which has attracted many scholars. The main challenge in this reference image stylization task lies in how to maintain the details of the content image while incorporating the color and texture features of the style image. This challenge becomes even more pronounced when the content image is a portrait which has complex textural details. To address this challenge, we propose a diffusion model-based reference image stylization method specifically for portraits, called MagicStyle. MagicStyle consists of two phases: Content and Style DDIM Inversion (CSDI) and Feature Fusion Forward (FFF). The CSDI phase involves a reverse denoising process, where DDIM Inversion is performed separately on the content image and the style image, storing the self-attention query, key and value features of both images during the inversion process. The FFF phase executes forward denoising, harmoniously integrating the texture and color information from the pre-stored feature queries, keys and values into the diffusion generation process based on our Well-designed Feature Fusion Attention (FFA). We conducted comprehensive comparative and ablation experiments to validate the effectiveness of our proposed MagicStyle and FFA.
Authors: Jian Qian, Miao Sun, Ashley Lee, Jie Li, Shenglong Zhuo, Patrick Yin Chiang
Abstract: Depth completion aims to predict dense depth maps with sparse depth measurements from a depth sensor. Currently, Convolutional Neural Network (CNN) based models are the most popular methods applied to depth completion tasks. However, despite the excellent high-end performance, they suffer from a limited representation area. To overcome the drawbacks of CNNs, a more effective and powerful method has been presented: the Transformer, which is an adaptive self-attention setting sequence-to-sequence model. While the standard Transformer quadratically increases the computational cost from the key-query dot-product of input resolution which improperly employs depth completion tasks. In this work, we propose a different window-based Transformer architecture for depth completion tasks named Sparse-to-Dense Transformer (SDformer). The network consists of an input module for the depth map and RGB image features extraction and concatenation, a U-shaped encoder-decoder Transformer for extracting deep features, and a refinement module. Specifically, we first concatenate the depth map features with the RGB image features through the input model. Then, instead of calculating self-attention with the whole feature maps, we apply different window sizes to extract the long-range depth dependencies. Finally, we refine the predicted features from the input module and the U-shaped encoder-decoder Transformer module to get the enriching depth features and employ a convolution layer to obtain the dense depth map. In practice, the SDformer obtains state-of-the-art results against the CNN-based depth completion models with lower computing loads and parameters on the NYU Depth V2 and KITTI DC datasets.
Authors: Lipisha Chaudhary, Fei Xu, Ifeoma Nwogu
Abstract: Both manual (relating to the use of hands) and non-manual markers (NMM), such as facial expressions or mouthing cues, are important for providing the complete meaning of phrases in American Sign Language (ASL). Efforts have been made in advancing sign language to spoken/written language understanding, but most of these have primarily focused on manual features only. In this work, using advanced neural machine translation methods, we examine and report on the extent to which facial expressions contribute to understanding sign language phrases. We present a sign language translation architecture consisting of two-stream encoders, with one encoder handling the face and the other handling the upper body (with hands). We propose a new parallel cross-attention decoding mechanism that is useful for quantifying the influence of each input modality on the output. The two streams from the encoder are directed simultaneously to different attention stacks in the decoder. Examining the properties of the parallel cross-attention weights allows us to analyze the importance of facial markers compared to body and hand features during a translating task.
Authors: Takuto Onikubo, Yusuke Matsui
Abstract: Recently, text-to-image generative models have been misused to create unauthorized malicious images of individuals, posing a growing social problem. Previous solutions, such as Anti-DreamBooth, add adversarial noise to images to protect them from being used as training data for malicious generation. However, we found that the adversarial noise can be removed by adversarial purification methods such as DiffPure. Therefore, we propose a new adversarial attack method that adds strong perturbation on the high-frequency areas of images to make it more robust to adversarial purification. Our experiment showed that the adversarial images retained noise even after adversarial purification, hindering malicious image generation.
Authors: Hassan Rasheed, Reuben Dorent, Maximilian Fehrentz, Tina Kapur, William M. Wells III, Alexandra Golby, Sarah Frisken, Julia A. Schnabel, Nazim Haouchine
Abstract: We propose in this paper a texture-invariant 2D keypoints descriptor specifically designed for matching preoperative Magnetic Resonance (MR) images with intraoperative Ultrasound (US) images. We introduce a matching-by-synthesis strategy, where intraoperative US images are synthesized from MR images accounting for multiple MR modalities and intraoperative US variability. We build our training set by enforcing keypoints localization over all images then train a patient-specific descriptor network that learns texture-invariant discriminant features in a supervised contrastive manner, leading to robust keypoints descriptors. Our experiments on real cases with ground truth show the effectiveness of the proposed approach, outperforming the state-of-the-art methods and achieving 80.35% matching precision on average.
Authors: M. J. Allen, D. Moreno-Fern\'andez, P. Ruiz-Benito, S. W. D. Grieve, E. R. Lines
Abstract: The global increase in observed forest dieback, characterised by the death of tree foliage, heralds widespread decline in forest ecosystems. This degradation causes significant changes to ecosystem services and functions, including habitat provision and carbon sequestration, which can be difficult to detect using traditional monitoring techniques, highlighting the need for large-scale and high-frequency monitoring. Contemporary developments in the instruments and methods to gather and process data at large-scales mean this monitoring is now possible. In particular, the advancement of low-cost drone technology and deep learning on consumer-level hardware provide new opportunities. Here, we use an approach based on deep learning and vegetation indices to assess crown dieback from RGB aerial data without the need for expensive instrumentation such as LiDAR. We use an iterative approach to match crown footprints predicted by deep learning with field-based inventory data from a Mediterranean ecosystem exhibiting drought-induced dieback, and compare expert field-based crown dieback estimation with vegetation index-based estimates. We obtain high overall segmentation accuracy (mAP: 0.519) without the need for additional technical development of the underlying Mask R-CNN model, underscoring the potential of these approaches for non-expert use and proving their applicability to real-world conservation. We also find colour-coordinate based estimates of dieback correlate well with expert field-based estimation. Substituting ground truth for Mask R-CNN model predictions showed negligible impact on dieback estimates, indicating robustness. Our findings demonstrate the potential of automated data collection and processing, including the application of deep learning, to improve the coverage, speed and cost of forest dieback monitoring.
Authors: Martin Thi{\ss}en, Thi Ngoc Diep Tran, Ben Joel Sch\"onbein, Ute Trapp, Barbara Esteve Ratsch, Beate Egner, Romana Piat, Elke Hergenr\"other
Abstract: The examination of the musculoskeletal system in dogs is a challenging task in veterinary practice. In this work, a novel method has been developed that enables efficient documentation of a dog's condition through a visual representation. However, since the visual documentation is new, there is no existing training data. The objective of this work is therefore to mitigate the impact of data scarcity in order to develop an AI-based diagnostic support system. To this end, the potential of synthetic data that mimics realistic visual documentations of diseases for pre-training AI models is investigated. We propose a method for generating synthetic image data that mimics realistic visual documentations. Initially, a basic dataset containing three distinct classes is generated, followed by the creation of a more sophisticated dataset containing 36 different classes. Both datasets are used for the pre-training of an AI model. Subsequently, an evaluation dataset is created, consisting of 250 manually created visual documentations for five different diseases. This dataset, along with a subset containing 25 examples. The obtained results on the evaluation dataset containing 25 examples demonstrate a significant enhancement of approximately 10% in diagnosis accuracy when utilizing generated synthetic images that mimic real-world visual documentations. However, these results do not hold true for the larger evaluation dataset containing 250 examples, indicating that the advantages of using synthetic data for pre-training an AI model emerge primarily when dealing with few examples of visual documentations for a given disease. Overall, this work provides valuable insights into mitigating the limitations imposed by limited training data through the strategic use of generated synthetic data, presenting an approach applicable beyond the canine musculoskeletal assessment domain.
Authors: Boxiang Rong, Artur Grigorev, Wenbo Wang, Michael J. Black, Bernhard Thomaszewski, Christina Tsalicoglou, Otmar Hilliges
Abstract: We introduce Gaussian Garments, a novel approach for reconstructing realistic simulation-ready garment assets from multi-view videos. Our method represents garments with a combination of a 3D mesh and a Gaussian texture that encodes both the color and high-frequency surface details. This representation enables accurate registration of garment geometries to multi-view videos and helps disentangle albedo textures from lighting effects. Furthermore, we demonstrate how a pre-trained graph neural network (GNN) can be fine-tuned to replicate the real behavior of each garment. The reconstructed Gaussian Garments can be automatically combined into multi-garment outfits and animated with the fine-tuned GNN.
Authors: Joy Hsu, Jiayuan Mao, Joshua B. Tenenbaum, Noah D. Goodman, Jiajun Wu
Abstract: A unique aspect of human visual understanding is the ability to flexibly interpret abstract concepts: acquiring lifted rules explaining what they symbolize, grounding them across familiar and unfamiliar contexts, and making predictions or reasoning about them. While off-the-shelf vision-language models excel at making literal interpretations of images (e.g., recognizing object categories such as tree branches), they still struggle to make sense of such visual abstractions (e.g., how an arrangement of tree branches may form the walls of a maze). To address this challenge, we introduce Deep Schema Grounding (DSG), a framework that leverages explicit structured representations of visual abstractions for grounding and reasoning. At the core of DSG are schemas--dependency graph descriptions of abstract concepts that decompose them into more primitive-level symbols. DSG uses large language models to extract schemas, then hierarchically grounds concrete to abstract components of the schema onto images with vision-language models. The grounded schema is used to augment visual abstraction understanding. We systematically evaluate DSG and different methods in reasoning on our new Visual Abstractions Dataset, which consists of diverse, real-world images of abstract concepts and corresponding question-answer pairs labeled by humans. We show that DSG significantly improves the abstract visual reasoning performance of vision-language models, and is a step toward human-aligned understanding of visual abstractions.
Authors: Ali Abdollah, Amirmohammad Izadi, Armin Saghafian, Reza Vahidimajd, Mohammad Mozafari, Amirreza Mirzaei, Mohammadmahdi Samiei, Mahdieh Soleymani Baghshah
Abstract: Vision-language models (VLMs) like CLIP have showcased a remarkable ability to extract transferable features for downstream tasks. Nonetheless, the training process of these models is usually based on a coarse-grained contrastive loss between the global embedding of images and texts which may lose the compositional structure of these modalities. Many recent studies have shown VLMs lack compositional understandings like attribute binding and identifying object relationships. Although some recent methods have tried to achieve finer-level alignments, they either are not based on extracting meaningful components of proper granularity or don't properly utilize the modalities' correspondence (especially in image-text pairs with more ingredients). Addressing these limitations, we introduce Compositional Alignment (ComAlign), a fine-grained approach to discover more exact correspondence of text and image components using only the weak supervision in the form of image-text pairs. Our methodology emphasizes that the compositional structure (including entities and relations) extracted from the text modality must also be retained in the image modality. To enforce correspondence of fine-grained concepts in image and text modalities, we train a lightweight network lying on top of existing visual and language encoders using a small dataset. The network is trained to align nodes and edges of the structure across the modalities. Experimental results on various VLMs and datasets demonstrate significant improvements in retrieval and compositional benchmarks, affirming the effectiveness of our plugin model.
Authors: Hao Chen, Jiafu Wu, Ying Jin, Jinlong Peng, Xiaofeng Mao, Mingmin Chi, Mufeng Yao, Bo Peng, Jian Li, Yun Cao
Abstract: Recently, methods like Zero-1-2-3 have focused on single-view based 3D reconstruction and have achieved remarkable success. However, their predictions for unseen areas heavily rely on the inductive bias of large-scale pretrained diffusion models. Although subsequent work, such as DreamComposer, attempts to make predictions more controllable by incorporating additional views, the results remain unrealistic due to feature entanglement in the vanilla latent space, including factors such as lighting, material, and structure. To address these issues, we introduce the Visual Isotropy 3D Reconstruction Model (VI3DRM), a diffusion-based sparse views 3D reconstruction model that operates within an ID consistent and perspective-disentangled 3D latent space. By facilitating the disentanglement of semantic information, color, material properties and lighting, VI3DRM is capable of generating highly realistic images that are indistinguishable from real photographs. By leveraging both real and synthesized images, our approach enables the accurate construction of pointmaps, ultimately producing finely textured meshes or point clouds. On the NVS task, tested on the GSO dataset, VI3DRM significantly outperforms state-of-the-art method DreamComposer, achieving a PSNR of 38.61, an SSIM of 0.929, and an LPIPS of 0.027. Code will be made available upon publication.
Authors: Quan Meng, Lei Li, Matthias Nie{\ss}ner, Angela Dai
Abstract: We present LT3SD, a novel latent diffusion model for large-scale 3D scene generation. Recent advances in diffusion models have shown impressive results in 3D object generation, but are limited in spatial extent and quality when extended to 3D scenes. To generate complex and diverse 3D scene structures, we introduce a latent tree representation to effectively encode both lower-frequency geometry and higher-frequency detail in a coarse-to-fine hierarchy. We can then learn a generative diffusion process in this latent 3D scene space, modeling the latent components of a scene at each resolution level. To synthesize large-scale scenes with varying sizes, we train our diffusion model on scene patches and synthesize arbitrary-sized output 3D scenes through shared diffusion generation across multiple scene patches. Through extensive experiments, we demonstrate the efficacy and benefits of LT3SD for large-scale, high-quality unconditional 3D scene generation and for probabilistic completion for partial scene observations.
Authors: Yinwei Wu, Xianpan Zhou, Bing Ma, Xuefeng Su, Kai Ma, Xinchao Wang
Abstract: While Text-to-Image (T2I) diffusion models excel at generating visually appealing images of individual instances, they struggle to accurately position and control the features generation of multiple instances. The Layout-to-Image (L2I) task was introduced to address the positioning challenges by incorporating bounding boxes as spatial control signals, but it still falls short in generating precise instance features. In response, we propose the Instance Feature Generation (IFG) task, which aims to ensure both positional accuracy and feature fidelity in generated instances. To address the IFG task, we introduce the Instance Feature Adapter (IFAdapter). The IFAdapter enhances feature depiction by incorporating additional appearance tokens and utilizing an Instance Semantic Map to align instance-level features with spatial locations. The IFAdapter guides the diffusion process as a plug-and-play module, making it adaptable to various community models. For evaluation, we contribute an IFG benchmark and develop a verification pipeline to objectively compare models' abilities to generate instances with accurate positioning and features. Experimental results demonstrate that IFAdapter outperforms other models in both quantitative and qualitative evaluations.
Authors: Abhishek Dangeti, Pavan Gajula, Vivek Srivastava, Vikram Jamwal
Abstract: Clustering artworks based on style has many potential real-world applications like art recommendations, style-based search and retrieval, and the study of artistic style evolution in an artwork corpus. However, clustering artworks based on style is largely an unaddressed problem. A few present methods for clustering artworks principally rely on generic image feature representations derived from deep neural networks and do not specifically deal with the artistic style. In this paper, we introduce and deliberate over the notion of style-based clustering of visual artworks. Our main objective is to explore neural feature representations and architectures that can be used for style-based clustering and observe their impact and effectiveness. We develop different methods and assess their relative efficacy for style-based clustering through qualitative and quantitative analysis by applying them to four artwork corpora and four curated synthetically styled datasets. Our analysis provides some key novel insights on architectures, feature representations, and evaluation methods suitable for style-based clustering.
Authors: NaHyeon Park, Kunhee Kim, Hyunjung Shim
Abstract: Recent breakthroughs in text-to-image models have opened up promising research avenues in personalized image generation, enabling users to create diverse images of a specific subject using natural language prompts. However, existing methods often suffer from performance degradation when given only a single reference image. They tend to overfit the input, producing highly similar outputs regardless of the text prompt. This paper addresses the challenge of one-shot personalization by mitigating overfitting, enabling the creation of controllable images through text prompts. Specifically, we propose a selective fine-tuning strategy that focuses on the text encoder. Furthermore, we introduce three key techniques to enhance personalization performance: (1) augmentation tokens to encourage feature disentanglement and alleviate overfitting, (2) a knowledge-preservation loss to reduce language drift and promote generalizability across diverse prompts, and (3) SNR-weighted sampling for efficient training. Extensive experiments demonstrate that our approach efficiently generates high-quality, diverse images using only a single reference image while significantly reducing memory and storage requirements.
Authors: Hongyu Li, Tianrui Hui, Zihan Ding, Jing Zhang, Bin Ma, Xiaoming Wei, Jizhong Han, Si Liu
Abstract: Panoptic narrative grounding (PNG), whose core target is fine-grained image-text alignment, requires a panoptic segmentation of referred objects given a narrative caption. Previous discriminative methods achieve only weak or coarse-grained alignment by panoptic segmentation pretraining or CLIP model adaptation. Given the recent progress of text-to-image Diffusion models, several works have shown their capability to achieve fine-grained image-text alignment through cross-attention maps and improved general segmentation performance. However, the direct use of phrase features as static prompts to apply frozen Diffusion models to the PNG task still suffers from a large task gap and insufficient vision-language interaction, yielding inferior performance. Therefore, we propose an Extractive-Injective Phrase Adapter (EIPA) bypass within the Diffusion UNet to dynamically update phrase prompts with image features and inject the multimodal cues back, which leverages the fine-grained image-text alignment capability of Diffusion models more sufficiently. In addition, we also design a Multi-Level Mutual Aggregation (MLMA) module to reciprocally fuse multi-level image and phrase features for segmentation refinement. Extensive experiments on the PNG benchmark show that our method achieves new state-of-the-art performance.
Authors: Siqi Wan, Yehao Li, Jingwen Chen, Yingwei Pan, Ting Yao, Yang Cao, Tao Mei
Abstract: Diffusion models have led to the revolutionizing of generative modeling in numerous image synthesis tasks. Nevertheless, it is not trivial to directly apply diffusion models for synthesizing an image of a target person wearing a given in-shop garment, i.e., image-based virtual try-on (VTON) task. The difficulty originates from the aspect that the diffusion process should not only produce holistically high-fidelity photorealistic image of the target person, but also locally preserve every appearance and texture detail of the given garment. To address this, we shape a new Diffusion model, namely GarDiff, which triggers the garment-focused diffusion process with amplified guidance of both basic visual appearance and detailed textures (i.e., high-frequency details) derived from the given garment. GarDiff first remoulds a pre-trained latent diffusion model with additional appearance priors derived from the CLIP and VAE encodings of the reference garment. Meanwhile, a novel garment-focused adapter is integrated into the UNet of diffusion model, pursuing local fine-grained alignment with the visual appearance of reference garment and human pose. We specifically design an appearance loss over the synthesized garment to enhance the crucial, high-frequency details. Extensive experiments on VITON-HD and DressCode datasets demonstrate the superiority of our GarDiff when compared to state-of-the-art VTON approaches. Code is publicly available at: \href{https://github.com/siqi0905/GarDiff/tree/master}{https://github.com/siqi0905/GarDiff/tree/master}.
URLs: https://github.com/siqi0905/GarDiff/tree/master, https://github.com/siqi0905/GarDiff/tree/master
Authors: Yifu Chen, Jingwen Chen, Yingwei Pan, Yehao Li, Ting Yao, Zhineng Chen, Tao Mei
Abstract: Recent years have witnessed the success of large text-to-image diffusion models and their remarkable potential to generate high-quality images. The further pursuit of enhancing the editability of images has sparked significant interest in the downstream task of inpainting a novel object described by a text prompt within a designated region in the image. Nevertheless, the problem is not trivial from two aspects: 1) Solely relying on one single U-Net to align text prompt and visual object across all the denoising timesteps is insufficient to generate desired objects; 2) The controllability of object generation is not guaranteed in the intricate sampling space of diffusion model. In this paper, we propose to decompose the typical single-stage object inpainting into two cascaded processes: 1) semantic pre-inpainting that infers the semantic features of desired objects in a multi-modal feature space; 2) high-fieldity object generation in diffusion latent space that pivots on such inpainted semantic features. To achieve this, we cascade a Transformer-based semantic inpainter and an object inpainting diffusion model, leading to a novel CAscaded Transformer-Diffusion (CAT-Diffusion) framework for text-guided object inpainting. Technically, the semantic inpainter is trained to predict the semantic features of the target object conditioning on unmasked context and text prompt. The outputs of the semantic inpainter then act as the informative visual prompts to guide high-fieldity object generation through a reference adapter layer, leading to controllable object inpainting. Extensive evaluations on OpenImages-V6 and MSCOCO validate the superiority of CAT-Diffusion against the state-of-the-art methods. Code is available at \url{https://github.com/Nnn-s/CATdiffusion}.
Authors: Qiuhong Shen, Xingyi Yang, Xinchao Wang
Abstract: This study addresses the challenge of accurately segmenting 3D Gaussian Splatting from 2D masks. Conventional methods often rely on iterative gradient descent to assign each Gaussian a unique label, leading to lengthy optimization and sub-optimal solutions. Instead, we propose a straightforward yet globally optimal solver for 3D-GS segmentation. The core insight of our method is that, with a reconstructed 3D-GS scene, the rendering of the 2D masks is essentially a linear function with respect to the labels of each Gaussian. As such, the optimal label assignment can be solved via linear programming in closed form. This solution capitalizes on the alpha blending characteristic of the splatting process for single step optimization. By incorporating the background bias in our objective function, our method shows superior robustness in 3D segmentation against noises. Remarkably, our optimization completes within 30 seconds, about 50$\times$ faster than the best existing methods. Extensive experiments demonstrate the efficiency and robustness of our method in segmenting various scenes, and its superior performance in downstream tasks such as object removal and inpainting. Demos and code will be available at https://github.com/florinshen/FlashSplat.
Authors: Runjia Li, Junlin Han, Luke Melas-Kyriazi, Chunyi Sun, Zhaochong An, Zhongrui Gui, Shuyang Sun, Philip Torr, Tomas Jakab
Abstract: We present DreamBeast, a novel method based on score distillation sampling (SDS) for generating fantastical 3D animal assets composed of distinct parts. Existing SDS methods often struggle with this generation task due to a limited understanding of part-level semantics in text-to-image diffusion models. While recent diffusion models, such as Stable Diffusion 3, demonstrate a better part-level understanding, they are prohibitively slow and exhibit other common problems associated with single-view diffusion models. DreamBeast overcomes this limitation through a novel part-aware knowledge transfer mechanism. For each generated asset, we efficiently extract part-level knowledge from the Stable Diffusion 3 model into a 3D Part-Affinity implicit representation. This enables us to instantly generate Part-Affinity maps from arbitrary camera views, which we then use to modulate the guidance of a multi-view diffusion model during SDS to create 3D assets of fantastical animals. DreamBeast significantly enhances the quality of generated 3D creatures with user-specified part compositions while reducing computational overhead, as demonstrated by extensive quantitative and qualitative evaluations.
Authors: Omer Regev, Omri Avrahami, Dani Lischinski
Abstract: Recent advancements in generative models have revolutionized image generation and editing, making these tasks accessible to non-experts. This paper focuses on local image editing, particularly the task of adding new content to a loosely specified area. Existing methods often require a precise mask or a detailed description of the location, which can be cumbersome and prone to errors. We propose Click2Mask, a novel approach that simplifies the local editing process by requiring only a single point of reference (in addition to the content description). A mask is dynamically grown around this point during a Blended Latent Diffusion (BLD) process, guided by a masked CLIP-based semantic loss. Click2Mask surpasses the limitations of segmentation-based and fine-tuning dependent methods, offering a more user-friendly and contextually accurate solution. Our experiments demonstrate that Click2Mask not only minimizes user effort but also delivers competitive or superior local image manipulation results compared to SoTA methods, according to both human judgement and automatic metrics. Key contributions include the simplification of user input, the ability to freely add objects unconstrained by existing segments, and the integration potential of our dynamic mask approach within other editing methods.
Authors: Andrea Conti, Matteo Poggi, Valerio Cambareri, Stefano Mattoccia
Abstract: High frame rate and accurate depth estimation plays an important role in several tasks crucial to robotics and automotive perception. To date, this can be achieved through ToF and LiDAR devices for indoor and outdoor applications, respectively. However, their applicability is limited by low frame rate, energy consumption, and spatial sparsity. Depth on Demand (DoD) allows for accurate temporal and spatial depth densification achieved by exploiting a high frame rate RGB sensor coupled with a potentially lower frame rate and sparse active depth sensor. Our proposal jointly enables lower energy consumption and denser shape reconstruction, by significantly reducing the streaming requirements on the depth sensor thanks to its three core stages: i) multi-modal encoding, ii) iterative multi-modal integration, and iii) depth decoding. We present extended evidence assessing the effectiveness of DoD on indoor and outdoor video datasets, covering both environment scanning and automotive perception use cases.
Authors: Thomas Hanwen Zhu, Ruining Li, Tomas Jakab
Abstract: We present DreamHOI, a novel method for zero-shot synthesis of human-object interactions (HOIs), enabling a 3D human model to realistically interact with any given object based on a textual description. This task is complicated by the varying categories and geometries of real-world objects and the scarcity of datasets encompassing diverse HOIs. To circumvent the need for extensive data, we leverage text-to-image diffusion models trained on billions of image-caption pairs. We optimize the articulation of a skinned human mesh using Score Distillation Sampling (SDS) gradients obtained from these models, which predict image-space edits. However, directly backpropagating image-space gradients into complex articulation parameters is ineffective due to the local nature of such gradients. To overcome this, we introduce a dual implicit-explicit representation of a skinned mesh, combining (implicit) neural radiance fields (NeRFs) with (explicit) skeleton-driven mesh articulation. During optimization, we transition between implicit and explicit forms, grounding the NeRF generation while refining the mesh articulation. We validate our approach through extensive experiments, demonstrating its effectiveness in generating realistic HOIs.
Authors: Hemant Kumar Aggarwal, Sudhanya Chatterjee, Dattesh Shanbhag, Uday Patil, K. V. S. Hari
Abstract: Single-shot magnetic resonance (MR) imaging acquires the entire k-space data in a single shot and it has various applications in whole-body imaging. However, the long acquisition time for the entire k-space in single-shot fast spin echo (SSFSE) MR imaging poses a challenge, as it introduces T2-blur in the acquired images. This study aims to enhance the reconstruction quality of SSFSE MR images by (a) optimizing the trajectory for measuring the k-space, (b) acquiring fewer samples to speed up the acquisition process, and (c) reducing the impact of T2-blur. The proposed method adheres to physics constraints due to maximum gradient strength and slew-rate available while optimizing the trajectory within an end-to-end learning framework. Experiments were conducted on publicly available fastMRI multichannel dataset with 8-fold and 16-fold acceleration factors. An experienced radiologist's evaluation on a five-point Likert scale indicates improvements in the reconstruction quality as the ACL fibers are sharper than comparative methods.
Authors: Xuebin Wang, Chunxiuzi Liu, Meng Zhao, Ke Zhang, Zengru Di, He Liu
Abstract: This study introduces an artificial neural network (ANN) for image classification task, inspired by the aversive olfactory learning circuits of the nematode Caenorhabditis elegans (C. elegans). Despite the remarkable performance of ANNs in a variety of tasks, they face challenges such as excessive parameterization, high training costs and limited generalization capabilities. C. elegans, with its simple nervous system comprising only 302 neurons, serves as a paradigm in neurobiological research and is capable of complex behaviors including learning. This research identifies key neural circuits associated with aversive olfactory learning in C. elegans through behavioral experiments and high-throughput gene sequencing, translating them into an image classification ANN architecture. Additionally, two other image classification ANNs with distinct architectures were constructed for comparative performance analysis to highlight the advantages of bio-inspired design. The results indicate that the ANN inspired by the aversive olfactory learning circuits of C. elegans achieves higher accuracy, better consistency and faster convergence rates in image classification task, especially when tackling more complex classification challenges. This study not only showcases the potential of bio-inspired design in enhancing ANN capabilities but also provides a novel perspective and methodology for future ANN design.
Authors: Javad Hassannataj Joloudari, Mohammad Maftoun, Bahareh Nakisa, Roohallah Alizadehsani, Meisam Yadollahzadeh-Tabari
Abstract: The Complex Emotion Recognition System (CERS) deciphers complex emotional states by examining combinations of basic emotions expressed, their interconnections, and the dynamic variations. Through the utilization of advanced algorithms, CERS provides profound insights into emotional dynamics, facilitating a nuanced understanding and customized responses. The attainment of such a level of emotional recognition in machines necessitates the knowledge distillation and the comprehension of novel concepts akin to human cognition. The development of AI systems for discerning complex emotions poses a substantial challenge with significant implications for affective computing. Furthermore, obtaining a sizable dataset for CERS proves to be a daunting task due to the intricacies involved in capturing subtle emotions, necessitating specialized methods for data collection and processing. Incorporating physiological signals such as Electrocardiogram (ECG) and Electroencephalogram (EEG) can notably enhance CERS by furnishing valuable insights into the user's emotional state, enhancing the quality of datasets, and fortifying system dependability. A comprehensive literature review was conducted in this study to assess the efficacy of machine learning, deep learning, and meta-learning approaches in both basic and complex emotion recognition utilizing EEG, ECG signals, and facial expression datasets. The chosen research papers offer perspectives on potential applications, clinical implications, and results of CERSs, with the objective of promoting their acceptance and integration into clinical decision-making processes. This study highlights research gaps and challenges in understanding CERSs, encouraging further investigation by relevant studies and organizations. Lastly, the significance of meta-learning approaches in improving CERS performance and guiding future research endeavors is underscored.
Authors: Michal K. Grzeszczyk, Przemys{\l}aw Korzeniowski, Samer Alabed, Andrew J. Swift, Tomasz Trzci\'nski, Arkadiusz Sitek
Abstract: Right Heart Catheterization is a gold standard procedure for diagnosing Pulmonary Hypertension by measuring mean Pulmonary Artery Pressure (mPAP). It is invasive, costly, time-consuming and carries risks. In this paper, for the first time, we explore the estimation of mPAP from videos of noninvasive Cardiac Magnetic Resonance Imaging. To enhance the predictive capabilities of Deep Learning models used for this task, we introduce an additional modality in the form of demographic features and clinical measurements. Inspired by all-Multilayer Perceptron architectures, we present TabMixer, a novel module enabling the integration of imaging and tabular data through spatial, temporal and channel mixing. Specifically, we present the first approach that utilizes Multilayer Perceptrons to interchange tabular information with imaging features in vision models. We test TabMixer for mPAP estimation and show that it enhances the performance of Convolutional Neural Networks, 3D-MLP and Vision Transformers while being competitive with previous modules for imaging and tabular data. Our approach has the potential to improve clinical processes involving both modalities, particularly in noninvasive mPAP estimation, thus, significantly enhancing the quality of life for individuals affected by Pulmonary Hypertension. We provide a source code for using TabMixer at https://github.com/SanoScience/TabMixer.
Authors: Ke Chen, Yifeng Wang, Yufei Zhou, Haohan Wang
Abstract: In the field of Alzheimer's disease diagnosis, segmentation and classification tasks are inherently interconnected. Sharing knowledge between models for these tasks can significantly improve training efficiency, particularly when training data is scarce. However, traditional knowledge distillation techniques often struggle to bridge the gap between segmentation and classification due to the distinct nature of tasks and different model architectures. To address this challenge, we propose a dual-stream pipeline that facilitates cross-task and cross-architecture knowledge sharing. Our approach introduces a dual-stream embedding module that unifies feature representations from segmentation and classification models, enabling dimensional integration of these features to guide the classification model. We validated our method on multiple 3D datasets for Alzheimer's disease diagnosis, demonstrating significant improvements in classification performance, especially on small datasets. Furthermore, we extended our pipeline with a residual temporal attention mechanism for early diagnosis, utilizing images taken before the atrophy of patients' brain mass. This advancement shows promise in enabling diagnosis approximately six months earlier in mild and asymptomatic stages, offering critical time for intervention.
Authors: Charles Meyers, Mohammad Reza Saleh Sedghpour, Tommy L\"ofstedt, Erik Elmroth
Abstract: Considering the growing prominence of production-level AI and the threat of adversarial attacks that can evade a model at run-time, evaluating the robustness of models to these evasion attacks is of critical importance. Additionally, testing model changes likely means deploying the models to (e.g. a car or a medical imaging device), or a drone to see how it affects performance, making un-tested changes a public problem that reduces development speed, increases cost of development, and makes it difficult (if not impossible) to parse cause from effect. In this work, we used survival analysis as a cloud-native, time-efficient and precise method for predicting model performance in the presence of adversarial noise. For neural networks in particular, the relationships between the learning rate, batch size, training time, convergence time, and deployment cost are highly complex, so researchers generally rely on benchmark datasets to assess the ability of a model to generalize beyond the training data. To address this, we propose using accelerated failure time models to measure the effect of hardware choice, batch size, number of epochs, and test-set accuracy by using adversarial attacks to induce failures on a reference model architecture before deploying the model to the real world. We evaluate several GPU types and use the Tree Parzen Estimator to maximize model robustness and minimize model run-time simultaneously. This provides a way to evaluate the model and optimise it in a single step, while simultaneously allowing us to model the effect of model parameters on training time, prediction time, and accuracy. Using this technique, we demonstrate that newer, more-powerful hardware does decrease the training time, but with a monetary and power cost that far outpaces the marginal gains in accuracy.
Authors: Layth Hamad, Muhammad Asif Khan, Amr Mohamed
Abstract: Autonomous robots use simultaneous localization and mapping (SLAM) for efficient and safe navigation in various environments. LiDAR sensors are integral in these systems for object identification and localization. However, LiDAR systems though effective in detecting solid objects (e.g., trash bin, bottle, etc.), encounter limitations in identifying semitransparent or non-tangible objects (e.g., fire, smoke, steam, etc.) due to poor reflecting characteristics. Additionally, LiDAR also fails to detect features such as navigation signs and often struggles to detect certain hazardous materials that lack a distinct surface for effective laser reflection. In this paper, we propose a highly accurate stereo-vision approach to complement LiDAR in autonomous robots. The system employs advanced stereo vision-based object detection to detect both tangible and non-tangible objects and then uses simple machine learning to precisely estimate the depth and size of the object. The depth and size information is then integrated into the SLAM process to enhance the robot's navigation capabilities in complex environments. Our evaluation, conducted on an autonomous robot equipped with LiDAR and stereo-vision systems demonstrates high accuracy in the estimation of an object's depth and size. A video illustration of the proposed scheme is available at: \url{https://www.youtube.com/watch?v=nusI6tA9eSk}.
Authors: Bangya Liu, Suman Banerjee
Abstract: Recent advances in 3D Gaussian Splatting (3DGS) have garnered significant attention in computer vision and computer graphics due to its high rendering speed and remarkable quality. While extant research has endeavored to extend the application of 3DGS from static to dynamic scenes, such efforts have been consistently impeded by excessive model sizes, constraints on video duration, and content deviation. These limitations significantly compromise the streamability of dynamic 3D Gaussian models, thereby restricting their utility in downstream applications, including volumetric video, autonomous vehicle, and immersive technologies such as virtual, augmented, and mixed reality. This paper introduces SwinGS, a novel framework for training, delivering, and rendering volumetric video in a real-time streaming fashion. To address the aforementioned challenges and enhance streamability, SwinGS integrates spacetime Gaussian with Markov Chain Monte Carlo (MCMC) to adapt the model to fit various 3D scenes across frames, in the meantime employing a sliding window captures Gaussian snapshots for each frame in an accumulative way. We implement a prototype of SwinGS and demonstrate its streamability across various datasets and scenes. Additionally, we develop an interactive WebGL viewer enabling real-time volumetric video playback on most devices with modern browsers, including smartphones and tablets. Experimental results show that SwinGS reduces transmission costs by 83.6% compared to previous work with ignorable compromise in PSNR. Moreover, SwinGS easily scales to long video sequences without compromising quality.
Authors: Tanisha Hisariya, Huan Zhang, Jinhua Liang
Abstract: Rapid advancements in artificial intelligence have significantly enhanced generative tasks involving music and images, employing both unimodal and multimodal approaches. This research develops a model capable of generating music that resonates with the emotions depicted in visual arts, integrating emotion labeling, image captioning, and language models to transform visual inputs into musical compositions. Addressing the scarcity of aligned art and music data, we curated the Emotion Painting Music Dataset, pairing paintings with corresponding music for effective training and evaluation. Our dual-stage framework converts images to text descriptions of emotional content and then transforms these descriptions into music, facilitating efficient learning with minimal data. Performance is evaluated using metrics such as Fr\'echet Audio Distance (FAD), Total Harmonic Distortion (THD), Inception Score (IS), and KL divergence, with audio-emotion text similarity confirmed by the pre-trained CLAP model to demonstrate high alignment between generated music and text. This synthesis tool bridges visual art and music, enhancing accessibility for the visually impaired and opening avenues in educational and therapeutic applications by providing enriched multi-sensory experiences.
Authors: Yuan Yin, Pegah Khayatan, \'Eloi Zablocki, Alexandre Boulch, Matthieu Cord
Abstract: Machine learning based autonomous driving systems often face challenges with safety-critical scenarios that are rare in real-world data, hindering their large-scale deployment. While increasing real-world training data coverage could address this issue, it is costly and dangerous. This work explores generating safety-critical driving scenarios by modifying complex real-world regular scenarios through trajectory optimization. We propose ReGentS, which stabilizes generated trajectories and introduces heuristics to avoid obvious collisions and optimization problems. Our approach addresses unrealistic diverging trajectories and unavoidable collision scenarios that are not useful for training robust planner. We also extend the scenario generation framework to handle real-world data with up to 32 agents. Additionally, by using a differentiable simulator, our approach simplifies gradient descent-based optimization involving a simulator, paving the way for future advancements. The code is available at https://github.com/valeoai/ReGentS.
Authors: Vamsi Krishna Vasa, Peijie Qiu, Wenhui Zhu, Yujian Xiong, Oana Dumitrascu, Yalin Wang
Abstract: Retinal fundus photography offers a non-invasive way to diagnose and monitor a variety of retinal diseases, but is prone to inherent quality glitches arising from systemic imperfections or operator/patient-related factors. However, high-quality retinal images are crucial for carrying out accurate diagnoses and automated analyses. The fundus image enhancement is typically formulated as a distribution alignment problem, by finding a one-to-one mapping between a low-quality image and its high-quality counterpart. This paper proposes a context-informed optimal transport (OT) learning framework for tackling unpaired fundus image enhancement. In contrast to standard generative image enhancement methods, which struggle with handling contextual information (e.g., over-tampered local structures and unwanted artifacts), the proposed context-aware OT learning paradigm better preserves local structures and minimizes unwanted artifacts. Leveraging deep contextual features, we derive the proposed context-aware OT using the earth mover's distance and show that the proposed context-OT has a solid theoretical guarantee. Experimental results on a large-scale dataset demonstrate the superiority of the proposed method over several state-of-the-art supervised and unsupervised methods in terms of signal-to-noise ratio, structural similarity index, as well as two downstream tasks. The code is available at \url{https://github.com/Retinal-Research/Contextual-OT}.
Authors: Andrew Lee, Ian Chuang, Ling-Yuan Chen, Iman Soltani
Abstract: We present InterACT: Inter-dependency aware Action Chunking with Hierarchical Attention Transformers, a novel imitation learning framework for bimanual manipulation that integrates hierarchical attention to capture inter-dependencies between dual-arm joint states and visual inputs. InterACT consists of a Hierarchical Attention Encoder and a Multi-arm Decoder, both designed to enhance information aggregation and coordination. The encoder processes multi-modal inputs through segment-wise and cross-segment attention mechanisms, while the decoder leverages synchronization blocks to refine individual action predictions, providing the counterpart's prediction as context. Our experiments on a variety of simulated and real-world bimanual manipulation tasks demonstrate that InterACT significantly outperforms existing methods. Detailed ablation studies validate the contributions of key components of our work, including the impact of CLS tokens, cross-segment encoders, and synchronization blocks.
Authors: Shun Zou, Zhuo Zhang, Guangwei Gao
Abstract: Optical Coherence Tomography Angiography (OCTA) is a crucial imaging technique for visualizing retinal vasculature and diagnosing eye diseases such as diabetic retinopathy and glaucoma. However, precise segmentation of OCTA vasculature remains challenging due to the multi-scale vessel structures and noise from poor image quality and eye lesions. In this study, we proposed OCTAMamba, a novel U-shaped network based on the Mamba architecture, designed to segment vasculature in OCTA accurately. OCTAMamba integrates a Quad Stream Efficient Mining Embedding Module for local feature extraction, a Multi-Scale Dilated Asymmetric Convolution Module to capture multi-scale vasculature, and a Focused Feature Recalibration Module to filter noise and highlight target areas. Our method achieves efficient global modeling and local feature extraction while maintaining linear complexity, making it suitable for low-computation medical applications. Extensive experiments on the OCTA 3M, OCTA 6M, and ROSSA datasets demonstrated that OCTAMamba outperforms state-of-the-art methods, providing a new reference for efficient OCTA segmentation. Code is available at https://github.com/zs1314/OCTAMamba
Authors: Lap Yan Lennon Chan, Chenxin Li, Yixuan Yuan
Abstract: Accurate lesion segmentation in whole-body PET/CT scans is crucial for cancer diagnosis and treatment planning, but limited datasets often hinder the performance of automated segmentation models. In this paper, we explore the potential of leveraging the deep prior from a generative model to serve as a data augmenter for automated lesion segmentation in PET/CT scans. We adapt the DiffTumor method, originally designed for CT images, to generate synthetic PET-CT images with lesions. Our approach trains the generative model on the AutoPET dataset and uses it to expand the training data. We then compare the performance of segmentation models trained on the original and augmented datasets. Our findings show that the model trained on the augmented dataset achieves a higher Dice score, demonstrating the potential of our data augmentation approach. In a nutshell, this work presents a promising direction for improving lesion segmentation in whole-body PET/CT scans with limited datasets, potentially enhancing the accuracy and reliability of cancer diagnostics.
Authors: Hanqiu Wang, Zihao Zhan, Haoqi Shan, Siqi Dai, Max Panoff, Shuo Wang
Abstract: The advent and growing popularity of Virtual Reality (VR) and Mixed Reality (MR) solutions have revolutionized the way we interact with digital platforms. The cutting-edge gaze-controlled typing methods, now prevalent in high-end models of these devices, e.g., Apple Vision Pro, have not only improved user experience but also mitigated traditional keystroke inference attacks that relied on hand gestures, head movements and acoustic side-channels. However, this advancement has paradoxically given birth to a new, potentially more insidious cyber threat, GAZEploit. In this paper, we unveil GAZEploit, a novel eye-tracking based attack specifically designed to exploit these eye-tracking information by leveraging the common use of virtual appearances in VR applications. This widespread usage significantly enhances the practicality and feasibility of our attack compared to existing methods. GAZEploit takes advantage of this vulnerability to remotely extract gaze estimations and steal sensitive keystroke information across various typing scenarios-including messages, passwords, URLs, emails, and passcodes. Our research, involving 30 participants, achieved over 80% accuracy in keystroke inference. Alarmingly, our study also identified over 15 top-rated apps in the Apple Store as vulnerable to the GAZEploit attack, emphasizing the urgent need for bolstered security measures for this state-of-the-art VR/MR text entry method.
Authors: Andr\'e F. R. Guarda (Instituto de Telecomunica\c{c}\~oes, Lisbon, Portugal), Nuno M. M. Rodrigues (Instituto de Telecomunica\c{c}\~oes, Lisbon, Portugal, ESTG, Polit\'ecnico de Leiria, Leiria, Portugal), Fernando Pereira (Instituto de Telecomunica\c{c}\~oes, Lisbon, Portugal, Instituto Superior T\'ecnico - Universidade de Lisboa, Lisbon, Portugal)
Abstract: Efficient point cloud coding has become increasingly critical for multiple applications such as virtual reality, autonomous driving, and digital twin systems, where rich and interactive 3D data representations may functionally make the difference. Deep learning has emerged as a powerful tool in this domain, offering advanced techniques for compressing point clouds more efficiently than conventional coding methods while also allowing effective computer vision tasks performed in the compressed domain thus, for the first time, making available a common compressed visual representation effective for both man and machine. Taking advantage of this potential, JPEG has recently finalized the JPEG Pleno Learning-based Point Cloud Coding (PCC) standard offering efficient lossy coding of static point clouds, targeting both human visualization and machine processing by leveraging deep learning models for geometry and color coding. The geometry is processed directly in its original 3D form using sparse convolutional neural networks, while the color data is projected onto 2D images and encoded using the also learning-based JPEG AI standard. The goal of this paper is to provide a complete technical description of the JPEG PCC standard, along with a thorough benchmarking of its performance against the state-of-the-art, while highlighting its main strengths and weaknesses. In terms of compression performance, JPEG PCC outperforms the conventional MPEG PCC standards, especially in geometry coding, achieving significant rate reductions. Color compression performance is less competitive but this is overcome by the power of a full learning-based coding framework for both geometry and color and the associated effective compressed domain processing.
Authors: Heejong Kim, Leo Milecki, Mina C Moghadam, Fengbei Liu, Minh Nguyen, Eric Qiu, Abhishek Thanki, Mert R Sabuncu
Abstract: Segmentation is a crucial task in the medical imaging field and is often an important primary step or even a prerequisite to the analysis of medical volumes. Yet treatments such as surgery complicate the accurate delineation of regions of interest. The BraTS Post-Treatment 2024 Challenge published the first public dataset for post-surgery glioma segmentation and addresses the aforementioned issue by fostering the development of automated segmentation tools for glioma in MRI data. In this effort, we propose two straightforward approaches to enhance the segmentation performances of deep learning-based methodologies. First, we incorporate an additional input based on a simple linear combination of the available MRI sequences input, which highlights enhancing tumors. Second, we employ various ensembling methods to weigh the contribution of a battery of models. Our results demonstrate that these approaches significantly improve segmentation performance compared to baseline models, underscoring the effectiveness of these simple approaches in improving medical image segmentation tasks.
Authors: Aaron Rock Menezes, Bharath Ramsundar
Abstract: Automated cell segmentation is crucial for various biological and medical applications, facilitating tasks like cell counting, morphology analysis, and drug discovery. However, manual segmentation is time-consuming and prone to subjectivity, necessitating robust automated methods. This paper presents open-source infrastructure, utilizing the UNet model, a deep-learning architecture noted for its effectiveness in image segmentation tasks. This implementation is integrated into the open-source DeepChem package, enhancing accessibility and usability for researchers and practitioners. The resulting tool offers a convenient and user-friendly interface, reducing the barrier to entry for cell segmentation while maintaining high accuracy. Additionally, we benchmark this model against various datasets, demonstrating its robustness and versatility across different imaging conditions and cell types.
Authors: Santanu Roy, Archit Gupta, Shubhi Tiwari, Palak Sahu
Abstract: Alzheimer's Disease (AD) is a non-curable progressive neurodegenerative disorder that affects the human brain, leading to a decline in memory, cognitive abilities, and eventually, the ability to carry out daily tasks. Manual diagnosis of Alzheimer's disease from MRI images is fraught with less sensitivity and it is a very tedious process for neurologists. Therefore, there is a need for an automatic Computer Assisted Diagnosis (CAD) system, which can detect AD at early stages with higher accuracy. In this research, we have proposed a novel AD-Lite Net model (trained from scratch), that could alleviate the aforementioned problem. The novelties we bring here in this research are, (I) We have proposed a very lightweight CNN model by incorporating Depth Wise Separable Convolutional (DWSC) layers and Global Average Pooling (GAP) layers. (II) We have leveraged a ``parallel concatenation block'' (pcb), in the proposed AD-Lite Net model. This pcb consists of a Transformation layer (Tx-layer), followed by two convolutional layers, which are thereby concatenated with the original base model. This Tx-layer converts the features into very distinct kind of features, which are imperative for the Alzheimer's disease. As a consequence, the proposed AD-Lite Net model with ``parallel concatenation'' converges faster and automatically mitigates the class imbalance problem from the MRI datasets in a very generalized way. For the validity of our proposed model, we have implemented it on three different MRI datasets. Furthermore, we have combined the ADNI and AD datasets and subsequently performed a 10-fold cross-validation experiment to verify the model's generalization ability. Extensive experimental results showed that our proposed model has outperformed all the existing CNN models, and one recent trend Vision Transformer (ViT) model by a significant margin.
Authors: Daniel Capell\'an-Mart\'in, Zhifan Jiang, Abhijeet Parida, Xinyang Liu, Van Lam, Hareem Nisar, Austin Tapp, Sarah Elsharkawi, Maria J. Ledesma-Carbayo, Syed Muhammad Anwar, Marius George Linguraru
Abstract: Segmenting brain tumors in multi-parametric magnetic resonance imaging enables performing quantitative analysis in support of clinical trials and personalized patient care. This analysis provides the potential to impact clinical decision-making processes, including diagnosis and prognosis. In 2023, the well-established Brain Tumor Segmentation (BraTS) challenge presented a substantial expansion with eight tasks and 4,500 brain tumor cases. In this paper, we present a deep learning-based ensemble strategy that is evaluated for newly included tumor cases in three tasks: pediatric brain tumors (PED), intracranial meningioma (MEN), and brain metastases (MET). In particular, we ensemble outputs from state-of-the-art nnU-Net and Swin UNETR models on a region-wise basis. Furthermore, we implemented a targeted post-processing strategy based on a cross-validated threshold search to improve the segmentation results for tumor sub-regions. The evaluation of our proposed method on unseen test cases for the three tasks resulted in lesion-wise Dice scores for PED: 0.653, 0.809, 0.826; MEN: 0.876, 0.867, 0.849; and MET: 0.555, 0.6, 0.58; for the enhancing tumor, tumor core, and whole tumor, respectively. Our method was ranked first for PED, third for MEN, and fourth for MET, respectively.
Authors: Himanshu Gaurav Singh, Antonio Loquercio, Carmelo Sferrazza, Jane Wu, Haozhi Qi, Pieter Abbeel, Jitendra Malik
Abstract: We present an approach to learn general robot manipulation priors from 3D hand-object interaction trajectories. We build a framework to use in-the-wild videos to generate sensorimotor robot trajectories. We do so by lifting both the human hand and the manipulated object in a shared 3D space and retargeting human motions to robot actions. Generative modeling on this data gives us a task-agnostic base policy. This policy captures a general yet flexible manipulation prior. We empirically demonstrate that finetuning this policy, with both reinforcement learning (RL) and behavior cloning (BC), enables sample-efficient adaptation to downstream tasks and simultaneously improves robustness and generalizability compared to prior approaches. Qualitative experiments are available at: \url{https://hgaurav2k.github.io/hop/}.
Authors: Daniel N. Nissani (Nissensohn)
Abstract: In response to an object presentation, supervised learning schemes generally respond with a parsimonious label. Upon a similar presentation we humans respond again with a label, but are flooded, in addition, by a myriad of associations. A significant portion of these consist of the presented object attributes. Contrastive learning is a semi-supervised learning scheme based on the application of identity preserving transformations on the object input representations. It is conjectured in this work that these same applied transformations preserve, in addition to the identity of the presented object, also the identity of its semantically meaningful attributes. The corollary of this is that the output representations of such a contrastive learning scheme contain valuable information not only for the classification of the presented object, but also for the presence or absence decision of any attribute of interest. Simulation results which demonstrate this idea and the feasibility of this conjecture are presented.
Authors: Hadar Hezi, Daniel Shats, Daniel Gurevich, Yosef E. Maruvka, Moti Freiman
Abstract: Molecular subtypes of colorectal cancer (CRC) significantly influence treatment decisions. While convolutional neural networks (CNNs) have recently been introduced for automated CRC subtype identification using H&E stained histopathological images, the correlation between CRC subtype genomic variants and their corresponding cellular morphology expressed by their imaging phenotypes is yet to be fully explored. The goal of this study was to determine such correlations by incorporating genomic variants in CNN models for CRC subtype classification from H&E images. We utilized the publicly available TCGA-CRC-DX dataset, which comprises whole slide images from 360 CRC-diagnosed patients (260 for training and 100 for testing). This dataset also provides information on CRC subtype classifications and genomic variations. We trained CNN models for CRC subtype classification that account for potential correlation between genomic variations within CRC subtypes and their corresponding cellular morphology patterns. We assessed the interplay between CRC subtypes' genomic variations and cellular morphology patterns by evaluating the CRC subtype classification accuracy of the different models in a stratified 5-fold cross-validation experimental setup using the area under the ROC curve (AUROC) and average precision (AP) as the performance metrics. Combining the CNN models account for variations in CIMP and SNP further improved classification accuracy (AUROC: 0.847$\pm$0.01 vs. 0.787$\pm$0.03, p$=$0.01, AP: 0.68$\pm$0.02 vs. 0.64$\pm$0.05).
Authors: Florentin Bieder, Julia Wolleb, Alicia Durrer, Robin Sandk\"uhler, Philippe C. Cattin
Abstract: Denoising diffusion models have recently achieved state-of-the-art performance in many image-generation tasks. They do, however, require a large amount of computational resources. This limits their application to medical tasks, where we often deal with large 3D volumes, like high-resolution three-dimensional data. In this work, we present a number of different ways to reduce the resource consumption for 3D diffusion models and apply them to a dataset of 3D images. The main contribution of this paper is the memory-efficient patch-based diffusion model \textit{PatchDDM}, which can be applied to the total volume during inference while the training is performed only on patches. While the proposed diffusion model can be applied to any image generation tasks, we evaluate the method on the tumor segmentation task of the BraTS2020 dataset and demonstrate that we can generate meaningful three-dimensional segmentations.
Authors: Abhishek Tyagi, Abhay Tyagi, Manpreet Kaur, Richa Aggarwal, Kapil D. Soni, Jayanthi Sivaswamy, Anjan Trikha
Abstract: Visual servoing for the development of autonomous robotic systems capable of administering UltraSound (US) guided regional anesthesia requires real-time segmentation of nerves, needle tip localization and needle trajectory extrapolation. First, we recruited 227 patients to build a large dataset of 41,000 anesthesiologist annotated images from US videos of brachial plexus nerves and developed models to localize nerves in the US images. Generalizability of the best suited model was tested on the datasets constructed from separate US scanners. Using these nerve segmentation predictions, we define automated anesthesia needle targets by fitting an ellipse to the nerve contours. Next, we developed an image analysis tool to guide the needle toward their targets. For the segmentation of the needle, a natural RGB pre-trained neural network was first fine-tuned on a large US dataset for domain transfer and then adapted for the needle using a small dataset. The segmented needle trajectory angle is calculated using Radon transformation and the trajectory is extrapolated from the needle tip. The intersection of the extrapolated trajectory with the needle target guides the needle navigation for drug delivery. The needle trajectory average error was within acceptable range of 5 mm as per experienced anesthesiologists. The entire dataset has been released publicly for further study by the research community at https://github.com/Regional-US/
Authors: Johannes K\"unzel, Anna Hilsmann, Peter Eisert
Abstract: We introduce BTSeg (Barlow Twins regularized Segmentation), an innovative, semi-supervised training approach enhancing semantic segmentation models in order to effectively tackle adverse weather conditions without requiring additional labeled training data. Images captured at similar locations but under varying adverse conditions are regarded as manifold representation of the same scene, thereby enabling the model to conceptualize its understanding of the environment. BTSeg shows cutting-edge performance for the new challenging ACG benchmark and sets a new state-of-the-art for weakly-supervised domain adaptation for the ACDC dataset. To support further research, we have made our code publicly available at https://github.com/fraunhoferhhi/BTSeg .
Authors: Hongkuan Zhou, Wei Cao, Aifen Sui, Zhenshan Bing
Abstract: End-to-end autonomous driving, where the entire driving pipeline is replaced with a single neural network, has recently gained research attention because of its simpler structure and faster inference time. Despite this appealing approach largely reducing the complexity in the driving pipeline, it also leads to safety issues because the trained policy is not always compliant with the traffic rules. In this paper, we proposed P-CSG, a penalty-based imitation learning approach with contrastive-based cross semantics generation sensor fusion technologies to increase the overall performance of end-to-end autonomous driving. In this method, we introduce three penalties - red light, stop sign, and curvature speed penalty to make the agent more sensitive to traffic rules. The proposed cross semantics generation helps to align the shared information of different input modalities. We assessed our model's performance using the CARLA Leaderboard - Town 05 Long Benchmark and Longest6 Benchmark, achieving 8.5% and 2.0% driving score improvement compared to the baselines. Furthermore, we conducted robustness evaluations against adversarial attacks like FGSM and Dot attacks, revealing a substantial increase in robustness compared to other baseline models. More detailed information can be found at https://hk-zh.github.io/p-csg-plus.
Authors: Shuhao Kang, Youqi Liao, Jianping Li, Fuxun Liang, Yuhao Li, Xianghong Zou, Fangning Li, Xieyuanli Chen, Zhen Dong, Bisheng Yang
Abstract: Image-to-point cloud (I2P) registration is a fundamental task for robots and autonomous vehicles to achieve cross-modality data fusion and localization. Current I2P registration methods primarily focus on estimating correspondences at the point or pixel level, often neglecting global alignment. As a result, I2P matching can easily converge to a local optimum if it lacks high-level guidance from global constraints. To improve the success rate and general robustness, this paper introduces CoFiI2P, a novel I2P registration network that extracts correspondences in a coarse-to-fine manner. First, the image and point cloud data are processed through a two-stream encoder-decoder network for hierarchical feature extraction. Second, a coarse-to-fine matching module is designed to leverage these features and establish robust feature correspondences. Specifically, In the coarse matching phase, a novel I2P transformer module is employed to capture both homogeneous and heterogeneous global information from the image and point cloud data. This enables the estimation of coarse super-point/super-pixel matching pairs with discriminative descriptors. In the fine matching module, point/pixel pairs are established with the guidance of super-point/super-pixel correspondences. Finally, based on matching pairs, the transform matrix is estimated with the EPnP-RANSAC algorithm. Experiments conducted on the KITTI Odometry dataset demonstrate that CoFiI2P achieves impressive results, with a relative rotation error (RRE) of 1.14 degrees and a relative translation error (RTE) of 0.29 meters, while maintaining real-time speed.Additional experiments on the Nuscenes datasets confirm our method's generalizability. The project page is available at \url{https://whu-usi3dv.github.io/CoFiI2P}.
Authors: Zhe Zhang, Gaochang Wu, Jing Zhang, Xiatian Zhu, Dacheng Tao, Tianyou Chai
Abstract: Unsupervised Domain Adaptive Semantic Segmentation (UDA-SS) aims to transfer the supervision from a labeled source domain to an unlabeled target domain. The majority of existing UDA-SS works typically consider images whilst recent attempts have extended further to tackle videos by modeling the temporal dimension. Although the two lines of research share the major challenges -- overcoming the underlying domain distribution shift, their studies are largely independent, resulting in fragmented insights, a lack of holistic understanding, and missed opportunities for cross-pollination of ideas. This fragmentation prevents the unification of methods, leading to redundant efforts and suboptimal knowledge transfer across image and video domains. Under this observation, we advocate unifying the study of UDA-SS across video and image scenarios, enabling a more comprehensive understanding, synergistic advancements, and efficient knowledge sharing. To that end, we explore the unified UDA-SS from a general data augmentation perspective, serving as a unifying conceptual framework, enabling improved generalization, and potential for cross-pollination of ideas, ultimately contributing to the overall progress and practical impact of this field of research. Specifically, we propose a Quad-directional Mixup (QuadMix) method, characterized by tackling distinct point attributes and feature inconsistencies through four-directional paths for intra- and inter-domain mixing in a feature space. To deal with temporal shifts with videos, we incorporate optical flow-guided feature aggregation across spatial and temporal dimensions for fine-grained domain alignment. Extensive experiments show that our method outperforms the state-of-the-art works by large margins on four challenging UDA-SS benchmarks. Our source code and models will be released at \url{https://github.com/ZHE-SAPI/UDASS}.
Authors: Gongye Liu, Menghan Xia, Yong Zhang, Haoxin Chen, Jinbo Xing, Yibo Wang, Xintao Wang, Yujiu Yang, Ying Shan
Abstract: Text-to-video (T2V) models have shown remarkable capabilities in generating diverse videos. However, they struggle to produce user-desired stylized videos due to (i) text's inherent clumsiness in expressing specific styles and (ii) the generally degraded style fidelity. To address these challenges, we introduce StyleCrafter, a generic method that enhances pre-trained T2V models with a style control adapter, enabling video generation in any style by providing a reference image. Considering the scarcity of stylized video datasets, we propose to first train a style control adapter using style-rich image datasets, then transfer the learned stylization ability to video generation through a tailor-made finetuning paradigm. To promote content-style disentanglement, we remove style descriptions from the text prompt and extract style information solely from the reference image using a decoupling learning strategy. Additionally, we design a scale-adaptive fusion module to balance the influences of text-based content features and image-based style features, which helps generalization across various text and style combinations. StyleCrafter efficiently generates high-quality stylized videos that align with the content of the texts and resemble the style of the reference images. Experiments demonstrate that our approach is more flexible and efficient than existing competitors.
Authors: Wei Feng, Xin Wang, Hong Chen, Zeyang Zhang, Houlun Chen, Zihan Song, Yuwei Zhou, Yuekui Yang, Haiyang Wu, Wenwu Zhu
Abstract: Recently, researchers have attempted to investigate the capability of LLMs in handling videos and proposed several video LLM models. However, the ability of LLMs to handle video grounding (VG), which is an important time-related video task requiring the model to precisely locate the start and end timestamps of temporal moments in videos that match the given textual queries, still remains unclear and unexplored in literature. To fill the gap, in this paper, we propose the LLM4VG benchmark, which systematically evaluates the performance of different LLMs on video grounding tasks. Based on our proposed LLM4VG, we design extensive experiments to examine two groups of video LLM models on video grounding: (i) the video LLMs trained on the text-video pairs (denoted as VidLLM), and (ii) the LLMs combined with pretrained visual description models such as the video/image captioning model. We propose prompt methods to integrate the instruction of VG and description from different kinds of generators, including caption-based generators for direct visual description and VQA-based generators for information enhancement. We also provide comprehensive comparisons of various VidLLMs and explore the influence of different choices of visual models, LLMs, prompt designs, etc, as well. Our experimental evaluations lead to two conclusions: (i) the existing VidLLMs are still far away from achieving satisfactory video grounding performance, and more time-related video tasks should be included to further fine-tune these models, and (ii) the combination of LLMs and visual models shows preliminary abilities for video grounding with considerable potential for improvement by resorting to more reliable models and further guidance of prompt instructions.
Authors: Haoxiang Yang, Chengguo Yuan, Yabin Zhu, Lan Chen, Xiao Wang, Futian Wang
Abstract: The mainstream human activity recognition (HAR) algorithms are developed based on RGB cameras, which are easily influenced by low-quality images (e.g., low illumination, motion blur). Meanwhile, the privacy protection issue caused by ultra-high definition (HD) RGB cameras aroused more and more people's attention. Inspired by the success of event cameras which perform better on high dynamic range, no motion blur, and low energy consumption, we propose to recognize human actions based on the event stream. We propose a lightweight uncertainty-aware information propagation based Mobile-Former network for efficient pattern recognition, which aggregates the MobileNet and Transformer network effectively. Specifically, we first embed the event images using a stem network into feature representations, then, feed them into uncertainty-aware Mobile-Former blocks for local and global feature learning and fusion. Finally, the features from MobileNet and Transformer branches are concatenated for pattern recognition. Extensive experiments on multiple event-based recognition datasets fully validated the effectiveness of our model. The source code of this work will be released at https://github.com/Event-AHU/Uncertainty_aware_MobileFormer.
URLs: https://github.com/Event-AHU/Uncertainty_aware_MobileFormer.
Authors: Ruibo Ming, Zhewei Huang, Zhuoxuan Ju, Jianming Hu, Lihui Peng, Shuchang Zhou
Abstract: Future Frame Synthesis (FFS) aims to enable models to generate sequences of future frames based on existing content. This task has garnered widespread application across various domains. In this paper, we comprehensively survey both historical and contemporary works in this field, encompassing widely used datasets and algorithms. Our survey scrutinizes the challenges and the evolving landscape of FFS within the realm of computer vision. We propose a novel taxonomy centered on the stochastic nature of related algorithms. This taxonomy emphasizes the gradual transition from deterministic to generative synthesis methodologies, highlighting significant advancements and shifts in approach.
Authors: Yaning Zhang, Zitong Yu, Xiaobin Huang, Linlin Shen, Jianfeng Ren
Abstract: The rapid advancement of photorealistic generators has reached a critical juncture where the discrepancy between authentic and manipulated images is increasingly indistinguishable. Thus, benchmarking and advancing techniques detecting digital manipulation become an urgent issue. Although there have been a number of publicly available face forgery datasets, the forgery faces are mostly generated using GAN-based synthesis technology, which does not involve the most recent technologies like diffusion. The diversity and quality of images generated by diffusion models have been significantly improved and thus a much more challenging face forgery dataset shall be used to evaluate SOTA forgery detection literature. In this paper, we propose a large-scale, diverse, and fine-grained high-fidelity dataset, namely GenFace, to facilitate the advancement of deepfake detection, which contains a large number of forgery faces generated by advanced generators such as the diffusion-based model and more detailed labels about the manipulation approaches and adopted generators. In addition to evaluating SOTA approaches on our benchmark, we design an innovative cross appearance-edge learning (CAEL) detector to capture multi-grained appearance and edge global representations, and detect discriminative and general forgery traces. Moreover, we devise an appearance-edge cross-attention (AECA) module to explore the various integrations across two domains. Extensive experiment results and visualizations show that our detection model outperforms the state of the arts on different settings like cross-generator, cross-forgery, and cross-dataset evaluations. Code and datasets will be available at \url{https://github.com/Jenine-321/GenFace
Authors: Xuesong Li, Zeeshan Hayder, Ali Zia, Connor Cassidy, Shiming Liu, Warwick Stiller, Eric Stone, Warren Conaty, Lars Petersson, Vivien Rolland
Abstract: Crop biomass, a critical indicator of plant growth, health, and productivity, is invaluable for crop breeding programs and agronomic research. However, the accurate and scalable quantification of crop biomass remains inaccessible due to limitations in existing measurement methods. One of the obstacles impeding the advancement of current crop biomass prediction methodologies is the scarcity of publicly available datasets. Addressing this gap, we introduce a new dataset in this domain, i.e. Multi-modality dataset for crop biomass estimation (MMCBE). Comprising 216 sets of multi-view drone images, coupled with LiDAR point clouds, and hand-labelled ground truth, MMCBE represents the first multi-modality one in the field. This dataset aims to establish benchmark methods for crop biomass quantification and foster the development of vision-based approaches. We have rigorously evaluated state-of-the-art crop biomass estimation methods using MMCBE and ventured into additional potential applications, such as 3D crop reconstruction from drone imagery and novel-view rendering. With this publication, we are making our comprehensive dataset available to the broader community.
Authors: Simon Damm, Mike Laszkiewicz, Johannes Lederer, Asja Fischer
Abstract: Recent advances in multimodal foundation models have set new standards in few-shot anomaly detection. This paper explores whether high-quality visual features alone are sufficient to rival existing state-of-the-art vision-language models. We affirm this by adapting DINOv2 for one-shot and few-shot anomaly detection, with a focus on industrial applications. We show that this approach does not only rival existing techniques but can even outmatch them in many settings. Our proposed vision-only approach, AnomalyDINO, is based on patch similarities and enables both image-level anomaly prediction and pixel-level anomaly segmentation. The approach is methodologically simple and training-free and, thus, does not require any additional data for fine-tuning or meta-learning. Despite its simplicity, AnomalyDINO achieves state-of-the-art results in one- and few-shot anomaly detection (e.g., pushing the one-shot performance on MVTec-AD from an AUROC of 93.1% to 96.6%). The reduced overhead, coupled with its outstanding few-shot performance, makes AnomalyDINO a strong candidate for fast deployment, e.g., in industrial contexts.
Authors: Hyungjin Chung, Jeongsol Kim, Geon Yeong Park, Hyelin Nam, Jong Chul Ye
Abstract: Classifier-free guidance (CFG) is a fundamental tool in modern diffusion models for text-guided generation. Although effective, CFG has notable drawbacks. For instance, DDIM with CFG lacks invertibility, complicating image editing; furthermore, high guidance scales, essential for high-quality outputs, frequently result in issues like mode collapse. Contrary to the widespread belief that these are inherent limitations of diffusion models, this paper reveals that the problems actually stem from the off-manifold phenomenon associated with CFG, rather than the diffusion models themselves. More specifically, inspired by the recent advancements of diffusion model-based inverse problem solvers (DIS), we reformulate text-guidance as an inverse problem with a text-conditioned score matching loss and develop CFG++, a novel approach that tackles the off-manifold challenges inherent in traditional CFG. CFG++ features a surprisingly simple fix to CFG, yet it offers significant improvements, including better sample quality for text-to-image generation, invertibility, smaller guidance scales, reduced mode collapse, etc. Furthermore, CFG++ enables seamless interpolation between unconditional and conditional sampling at lower guidance scales, consistently outperforming traditional CFG at all scales. Moreover, CFG++ can be easily integrated into high-order diffusion solvers and naturally extends to distilled diffusion models. Experimental results confirm that our method significantly enhances performance in text-to-image generation, DDIM inversion, editing, and solving inverse problems, suggesting a wide-ranging impact and potential applications in various fields that utilize text guidance. Project Page: https://cfgpp-diffusion.github.io/.
Authors: Ziran Zhang, Yongrui Ma, Yueting Chen, Feng Zhang, Jinwei Gu, Tianfan Xue, Shi Guo
Abstract: Video Frame Interpolation (VFI) is important for video enhancement, frame rate up-conversion, and slow-motion generation. The introduction of event cameras, which capture per-pixel brightness changes asynchronously, has significantly enhanced VFI capabilities, particularly for high-speed, nonlinear motions. However, these event-based methods encounter challenges in low-light conditions, notably trailing artifacts and signal latency, which hinder their direct applicability and generalization. Addressing these issues, we propose a novel per-scene optimization strategy tailored for low-light conditions. This approach utilizes the internal statistics of a sequence to handle degraded event data under low-light conditions, improving the generalizability to different lighting and camera settings. To evaluate its robustness in low-light condition, we further introduce EVFI-LL, a unique RGB+Event dataset captured under low-light conditions. Our results demonstrate state-of-the-art performance in low-light environments. Project page: https://naturezhanghn.github.io/sim2real.
Authors: Abdul Mohaimen Al Radi, Prothito Shovon Majumder, Md. Mosaddek Khan
Abstract: Blind image deblurring is the process of recovering a sharp image from a blurred one without prior knowledge about the blur kernel. It is a small data problem, since the key challenge lies in estimating the unknown degrees of blur from a single image or limited data, instead of learning from large datasets. The solution depends heavily on developing algorithms that effectively model the image degradation process. We introduce a method that leverages a prior which targets the blur kernel to achieve effective deblurring across a wide range of image types. In our extensive empirical analysis, our algorithm achieves results that are competitive with the state-of-the-art blind image deblurring algorithms, and it offers up to two times faster inference, making it a highly efficient solution.
Authors: Zhenyi Liao, Qingsong Xie, Chen Chen, Hannan Lu, Zhijie Deng
Abstract: Diffusion models (DMs) have achieved significant success in generating imaginative images given textual descriptions. However, they are likely to fall short when it comes to real-life scenarios with intricate details. The low-quality, unrealistic human faces in text-to-image generation are one of the most prominent issues, hindering the wide application of DMs in practice. Targeting addressing such an issue, we first assess the face quality of generations from popular pre-trained DMs with the aid of human annotators and then evaluate the alignment between existing metrics with human judgments. Observing that existing metrics can be unsatisfactory for quantifying face quality, we develop a novel metric named FaceScore (FS) by fine-tuning the widely used ImageReward on a dataset of (win, loss) face pairs cheaply crafted by an inpainting pipeline of DMs. Extensive studies reveal FS enjoys a superior alignment with humans. On the other hand, FS opens up the door for enhancing DMs for better face generation. With FS offering image ratings, we can easily perform preference learning algorithms to refine DMs like SDXL. Comprehensive experiments verify the efficacy of our approach for improving face quality. The code is released at https://github.com/OPPO-Mente-Lab/FaceScore.
Authors: Zuo-Liang Zhu, Beibei Wang, Jian Yang
Abstract: 3D Gaussian Splatting (3DGS) has shown a powerful capability for novel view synthesis due to its detailed expressive ability and highly efficient rendering speed. Unfortunately, creating relightable 3D assets with 3DGS is still problematic, particularly for reflective objects, as its discontinuous representation raises difficulties in constraining geometries. Inspired by previous works, the signed distance field (SDF) can serve as an effective way for geometry regularization. However, a direct incorporation between Gaussians and SDF significantly slows training. To this end, we propose GS-ROR for reflective objects relighting with 3DGS aided by SDF priors. At the core of our method is the mutual supervision of the depth and normal between deferred Gaussians and SDF, which avoids the expensive volume rendering of SDF. Thanks to this mutual supervision, the learned deferred Gaussians are well-constrained with a minimal time cost. As the Gaussians are rendered in a deferred shading mode, while the alpha-blended Gaussians are smooth, individual Gaussians may still be outliers, yielding floater artifacts. Therefore, we further introduce an SDF-aware pruning strategy to remove Gaussian outliers, which are located distant from the surface defined by SDF, avoiding the floater issue. Consequently, our method outperforms the existing Gaussian-based inverse rendering methods in terms of relighting quality. Our method also exhibits competitive relighting quality compared to NeRF-based methods with at most 25% of training time and allows rendering at 200+ frames per second on an RTX4090.
Authors: William Berman, Alexander Peysakhovich
Abstract: We train a model to generate images from multimodal prompts of interleaved text and images such as "a
Authors: Yoon Gyo Jung, Jaewoo Park, Xingbo Dong, Hojin Park, Andrew Beng Jin Teoh, Octavia Camps
Abstract: Understanding the vulnerability of face recognition systems to malicious attacks is of critical importance. Previous works have focused on reconstructing face images that can penetrate a targeted verification system. Even in the white-box scenario, however, naively reconstructed images misrepresent the identity information, hence the attacks are easily neutralized once the face system is updated or changed. In this paper, we aim to reconstruct face images which are capable of transferring face attacks on unseen encoders. We term this problem as Face Reconstruction Transfer Attack (FRTA) and show that it can be formulated as an out-of-distribution (OOD) generalization problem. Inspired by its OOD nature, we propose to solve FRTA by Averaged Latent Search and Unsupervised Validation with pseudo target (ALSUV). To strengthen the reconstruction attack on OOD unseen encoders, ALSUV reconstructs the face by searching the latent of amortized generator StyleGAN2 through multiple latent optimization, latent optimization trajectory averaging, and unsupervised validation with a pseudo target. We demonstrate the efficacy and generalization of our method on widely used face datasets, accompanying it with extensive ablation studies and visually, qualitatively, and quantitatively analyses. The source code will be released.
Authors: Juncheng Ma, Peiwen Sun, Yaoting Wang, Di Hu
Abstract: Audio-Visual Segmentation (AVS) aims to achieve pixel-level localization of sound sources in videos, while Audio-Visual Semantic Segmentation (AVSS), as an extension of AVS, further pursues semantic understanding of audio-visual scenes. However, since the AVSS task requires the establishment of audio-visual correspondence and semantic understanding simultaneously, we observe that previous methods have struggled to handle this mashup of objectives in end-to-end training, resulting in insufficient learning and sub-optimization. Therefore, we propose a two-stage training strategy called \textit{Stepping Stones}, which decomposes the AVSS task into two simple subtasks from localization to semantic understanding, which are fully optimized in each stage to achieve step-by-step global optimization. This training strategy has also proved its generalization and effectiveness on existing methods. To further improve the performance of AVS tasks, we propose a novel framework Adaptive Audio Visual Segmentation, in which we incorporate an adaptive audio query generator and integrate masked attention into the transformer decoder, facilitating the adaptive fusion of visual and audio features. Extensive experiments demonstrate that our methods achieve state-of-the-art results on all three AVS benchmarks. The project homepage can be accessed at https://gewu-lab.github.io/stepping_stones/.
Authors: Florent Brondolo, Samuel Beaussant
Abstract: Recent advancements in computer vision have significantly improved image analysis tasks. Yet, deep learning models often struggle when applied to domains outside their training distribution, such as in geosciences, where domain-specific data can be scarce. This study investigates the classification, segmentation, and interpretability of CT-scan images of rock samples, focusing on the application of modern computer vision techniques to geoscientific tasks. We compare a range of segmentation methods to assess their efficacy, efficiency, and adaptability in geological image analysis. The methods evaluated include Otsu thresholding, clustering techniques (K-means, fuzzy C-means), a supervised machine learning approach (Random Forest), and deep learning models (UNet, ResNet152, and DINOv2), using ten binary sandstone datasets and three multi-class calcite datasets. DINOv2 was selected for its promising results in feature extraction and its potential applicability in geoscientific tasks, prompting further assessment of its interpretability and effectiveness in processing CT-scanned rock data. For classification, a non-fine-tuned DINOv2 demonstrates strong performance in classifying rock images, even when the CT-scans are outside its original training set. In segmentation tasks, thresholding and clustering techniques, though computationally efficient, produce subpar results despite preprocessing efforts. In contrast, supervised methods achieve better performance. While deep learning methods demand greater computational resources, they require minimal intervention and offer superior generalization. A LoRA fine-tuned DINOv2, in particular, excels in out-of-distribution segmentation and outperforms other methods in multi-class tasks, even with limited data. Notably, the segmentation masks generated by DINOv2 often appear more accurate than the original targets, based on visual inspection.
Authors: Vlad Sobal, Mark Ibrahim, Randall Balestriero, Vivien Cabannes, Diane Bouchacourt, Pietro Astolfi, Kyunghyun Cho, Yann LeCun
Abstract: Learning good representations involves capturing the diverse ways in which data samples relate. Contrastive loss - an objective matching related samples - underlies methods from self-supervised to multimodal learning. Contrastive losses, however, can be viewed more broadly as modifying a similarity graph to indicate how samples should relate in the embedding space. This view reveals a shortcoming in contrastive learning: the similarity graph is binary, as only one sample is the related positive sample. Crucially, similarities \textit{across} samples are ignored. Based on this observation, we revise the standard contrastive loss to explicitly encode how a sample relates to others. We experiment with this new objective, called $\mathbb{X}$-Sample Contrastive, to train vision models based on similarities in class or text caption descriptions. Our study spans three scales: ImageNet-1k with 1 million, CC3M with 3 million, and CC12M with 12 million samples. The representations learned via our objective outperform both contrastive self-supervised and vision-language models trained on the same data across a range of tasks. When training on CC12M, we outperform CLIP by $0.6\%$ on both ImageNet and ImageNet Real. Our objective appears to work particularly well in lower-data regimes, with gains over CLIP of $16.8\%$ on ImageNet and $18.1\%$ on ImageNet Real when training with CC3M. Finally, our objective seems to encourage the model to learn representations that separate objects from their attributes and backgrounds, with gains of $3.3$-$5.6$\% over CLIP on ImageNet9. We hope the proposed solution takes a small step towards developing richer learning objectives for understanding sample relations in foundation models.
Authors: Kevin Qinghong Lin, Pengchuan Zhang, Difei Gao, Xide Xia, Joya Chen, Ziteng Gao, Jinheng Xie, Xuhong Xiao, Mike Zheng Shou
Abstract: Narrative videos, such as movies, pose significant challenges in video understanding due to their rich contexts (characters, dialogues, storylines) and diverse demands (identify who, relationship, and reason). In this paper, we introduce MovieSeq, a multimodal language model developed to address the wide range of challenges in understanding video contexts. Our core idea is to represent videos as interleaved multimodal sequences (including images, plots, videos, and subtitles), either by linking external knowledge databases or using offline models (such as whisper for subtitles). Through instruction-tuning, this approach empowers the language model to interact with videos using interleaved multimodal instructions. For example, instead of solely relying on video as input, we jointly provide character photos alongside their names and dialogues, allowing the model to associate these elements and generate more comprehensive responses. To demonstrate its effectiveness, we validate MovieSeq's performance on six datasets (LVU, MAD, Movienet, CMD, TVC, MovieQA) across five settings (video classification, audio description, video-text retrieval, video captioning, and video question-answering). The code will be public at https://github.com/showlab/MovieSeq.
Authors: He Wang, Lei Xie
Abstract: This paper delineates the visual speech recognition (VSR) system introduced by the NPU-ASLP (Team 237) in the second Chinese Continuous Visual Speech Recognition Challenge (CNVSRC 2024), engaging in all four tracks, including the fixed and open tracks of Single-Speaker VSR Task and Multi-Speaker VSR Task. In terms of data processing, we leverage the lip motion extractor from the baseline1 to produce multiscale video data. Besides, various augmentation techniques are applied during training, encompassing speed perturbation, random rotation, horizontal flipping, and color transformation. The VSR model adopts an end-to-end architecture with joint CTC/attention loss, introducing Enhanced ResNet3D visual frontend, E-Branchformer encoder, and Bi-directional Transformer decoder. Our approach yields a 30.47% CER for the Single-Speaker Task and 34.30% CER for the Multi-Speaker Task, securing second place in the open track of the Single-Speaker Task and first place in the other three tracks.
Authors: Sho Ozaki, Shizuo Kaji, Toshikazu Imae, Kanabu Nawa, Hideomi Yamashita, Keiichi Nakagawa
Abstract: Image-generative artificial intelligence (AI) has garnered significant attention in recent years. In particular, the diffusion model, a core component of generative AI, produces high-quality images with rich diversity. In this study, we proposed a novel computed tomography (CT) reconstruction method by combining the denoising diffusion probabilistic model with iterative CT reconstruction. In sharp contrast to previous studies, we optimized the fidelity loss of CT reconstruction with respect to the latent variable of the diffusion model, instead of the image and model parameters. To suppress the changes in anatomical structures produced by the diffusion model, we shallowed the diffusion and reverse processes and fixed a set of added noises in the reverse process to make it deterministic during the inference. We demonstrated the effectiveness of the proposed method through the sparse-projection CT reconstruction of 1/10 projection data. Despite the simplicity of the implementation, the proposed method has the potential to reconstruct high-quality images while preserving the patient's anatomical structures and was found to outperform existing methods, including iterative reconstruction, iterative reconstruction with total variation, and the diffusion model alone in terms of quantitative indices such as the structural similarity index and peak signal-to-noise ratio. We also explored further sparse-projection CT reconstruction using 1/20 projection data with the same trained diffusion model. As the number of iterations increased, the image quality improved comparable to that of 1/10 sparse-projection CT reconstruction. In principle, this method can be widely applied not only to CT but also to other imaging modalities.
Authors: Junho Moon, Haejun Chung, Ikbeom Jang
Abstract: Facial wrinkle detection plays a crucial role in cosmetic dermatology. Precise manual segmentation of facial wrinkles is challenging and time-consuming, with inherent subjectivity leading to inconsistent results among graders. To address this issue, we propose two solutions. First, we build and release the first public facial wrinkle dataset, 'FFHQ-Wrinkle', an extension of the NVIDIA FFHQ dataset. It includes 1,000 images with human labels and 50,000 images with automatically generated weak labels. This dataset could serve as a foundation for the research community to develop advanced wrinkle detection algorithms. Second, we introduce a simple training strategy utilizing texture maps, applicable to various segmentation models, to detect wrinkles across the face. Our two-stage training strategy first pretrain models on a large dataset with weak labels (N=50k), or masked texture maps generated through computer vision techniques, without human intervention. We then finetune the models using human-labeled data (N=1k), which consists of manually labeled wrinkle masks. The network takes as input a combination of RGB and masked texture map of the image, comprising four channels, in finetuning. We effectively combine labels from multiple annotators to minimize subjectivity in manual labeling. Our strategies demonstrate improved segmentation performance in facial wrinkle segmentation both quantitatively and visually compared to existing pretraining methods. The dataset is available at https://github.com/labhai/ffhq-wrinkle-dataset.
Authors: Julius Pesonen, Teemu Hakala, V\"ain\"o Karjalainen, Niko Koivum\"aki, Lauri Markelin, Anna-Maria Raita-Hakola, Juha Suomalainen, Ilkka P\"ol\"onen, Eija Honkavaara
Abstract: Early detection of wildfires is essential to prevent large-scale fires resulting in extensive environmental, structural, and societal damage. Uncrewed aerial vehicles (UAVs) can cover large remote areas effectively with quick deployment requiring minimal infrastructure and equipping them with small cameras and computers enables autonomous real-time detection. In remote areas, however, the UAVs are limited to on-board computing for detection due to the lack of high-bandwidth mobile networks. This limits the detection to methods which are light enough for the on-board computer alone. For accurate camera-based localisation, segmentation of the detected smoke is essential but training data for deep learning-based wildfire smoke segmentation is limited. This study shows how small specialised segmentation models can be trained using only bounding box labels, leveraging zero-shot foundation model supervision. The method offers the advantages of needing only fairly easily obtainable bounding box labels and requiring training solely for the smaller student network. The proposed method achieved 63.3% mIoU on a manually annotated and diverse wildfire dataset. The used model can perform in real-time at ~25 fps with a UAV-carried NVIDIA Jetson Orin NX computer while reliably recognising smoke, demonstrated at real-world forest burning events. Code is available at https://gitlab.com/fgi_nls/public/wildfire-real-time-segmentation
URLs: https://gitlab.com/fgi_nls/public/wildfire-real-time-segmentation
Authors: Jinheng Xie, Weijia Mao, Zechen Bai, David Junhao Zhang, Weihao Wang, Kevin Qinghong Lin, Yuchao Gu, Zhijie Chen, Zhenheng Yang, Mike Zheng Shou
Abstract: We present a unified transformer, i.e., Show-o, that unifies multimodal understanding and generation. Unlike fully autoregressive models, Show-o unifies autoregressive and (discrete) diffusion modeling to adaptively handle inputs and outputs of various and mixed modalities. The unified model flexibly supports a wide range of vision-language tasks including visual question-answering, text-to-image generation, text-guided inpainting/extrapolation, and mixed-modality generation. Across various benchmarks, it demonstrates comparable or superior performance to existing individual models with an equivalent or larger number of parameters tailored for understanding or generation. This significantly highlights its potential as a next-generation foundation model. Code and models are released at https://github.com/showlab/Show-o.
Authors: Sadegh Rahmaniboldaji, Filip Rybansky, Quoc Vuong, Frank Guerin, Andrew Gilbert
Abstract: Detecting actions in videos, particularly within cluttered scenes, poses significant challenges due to the limitations of 2D frame analysis from a camera perspective. Unlike human vision, which benefits from 3D understanding, recognizing actions in such environments can be difficult. This research introduces a novel approach integrating 3D features and depth maps alongside RGB features to enhance action recognition accuracy. Our method involves processing estimated depth maps through a separate branch from the RGB feature encoder and fusing the features to understand the scene and actions comprehensively. Using the Side4Video framework and VideoMamba, which employ CLIP and VisionMamba for spatial feature extraction, our approach outperformed our implementation of the Side4Video network on the Something-Something V2 dataset. Our code is available at: https://github.com/SadeghRahmaniB/DEAR
Authors: Manuel Alejandro Diaz-Zapata (CHROMA), Wenqian Liu (CHROMA, UGA), Robin Baruffa (CHROMA), Christian Laugier (CHROMA)
Abstract: Current research in semantic bird's-eye view segmentation for autonomous driving focuses solely on optimizing neural network models using a single dataset, typically nuScenes. This practice leads to the development of highly specialized models that may fail when faced with different environments or sensor setups, a problem known as domain shift. In this paper, we conduct a comprehensive cross-dataset evaluation of state-of-the-art BEV segmentation models to assess their performance across different training and testing datasets and setups, as well as different semantic categories. We investigate the influence of different sensors, such as cameras and LiDAR, on the models' ability to generalize to diverse conditions and scenarios. Additionally, we conduct multi-dataset training experiments that improve models' BEV segmentation performance compared to single-dataset training. Our work addresses the gap in evaluating BEV segmentation models under cross-dataset validation. And our findings underscore the importance of enhancing model generalizability and adaptability to ensure more robust and reliable BEV segmentation approaches for autonomous driving applications. The code for this paper available at https://github.com/manueldiaz96/beval .
Authors: Zanlin Ni, Yulin Wang, Renping Zhou, Rui Lu, Jiayi Guo, Jinyi Hu, Zhiyuan Liu, Yuan Yao, Gao Huang
Abstract: Recent studies have demonstrated the effectiveness of token-based methods for visual content generation. As a representative work, non-autoregressive Transformers (NATs) are able to synthesize images with decent quality in a small number of steps. However, NATs usually necessitate configuring a complicated generation policy comprising multiple manually-designed scheduling rules. These heuristic-driven rules are prone to sub-optimality and come with the requirements of expert knowledge and labor-intensive efforts. Moreover, their one-size-fits-all nature cannot flexibly adapt to the diverse characteristics of each individual sample. To address these issues, we propose AdaNAT, a learnable approach that automatically configures a suitable policy tailored for every sample to be generated. In specific, we formulate the determination of generation policies as a Markov decision process. Under this framework, a lightweight policy network for generation can be learned via reinforcement learning. Importantly, we demonstrate that simple reward designs such as FID or pre-trained reward models, may not reliably guarantee the desired quality or diversity of generated samples. Therefore, we propose an adversarial reward design to guide the training of policy networks effectively. Comprehensive experiments on four benchmark datasets, i.e., ImageNet-256 & 512, MS-COCO, and CC3M, validate the effectiveness of AdaNAT. Code and pre-trained models will be released at https://github.com/LeapLabTHU/AdaNAT.
Authors: Xiaobin Lu, Xiaobin Hu, Jun Luo, Ben Zhu, Yaping Ruan, Wenqi Ren
Abstract: Blind face restoration endeavors to restore a clear face image from a degraded counterpart. Recent approaches employing Generative Adversarial Networks (GANs) as priors have demonstrated remarkable success in this field. However, these methods encounter challenges in achieving a balance between realism and fidelity, particularly in complex degradation scenarios. To inherit the exceptional realism generative ability of the diffusion model and also constrained by the identity-aware fidelity, we propose a novel diffusion-based framework by embedding the 3D facial priors as structure and identity constraints into a denoising diffusion process. Specifically, in order to obtain more accurate 3D prior representations, the 3D facial image is reconstructed by a 3D Morphable Model (3DMM) using an initial restored face image that has been processed by a pretrained restoration network. A customized multi-level feature extraction method is employed to exploit both structural and identity information of 3D facial images, which are then mapped into the noise estimation process. In order to enhance the fusion of identity information into the noise estimation, we propose a Time-Aware Fusion Block (TAFB). This module offers a more efficient and adaptive fusion of weights for denoising, considering the dynamic nature of the denoising process in the diffusion model, which involves initial structure refinement followed by texture detail enhancement. Extensive experiments demonstrate that our network performs favorably against state-of-the-art algorithms on synthetic and real-world datasets for blind face restoration. The Code is released on our project page at https://github.com/838143396/3Diffusion.
Authors: Gonglin Chen, Jinsen Wu, Haiwei Chen, Wenbin Teng, Zhiyuan Gao, Andrew Feng, Rongjun Qin, Yajie Zhao
Abstract: Establishing consistent and dense correspondences across multiple images is crucial for Structure from Motion (SfM) systems. Significant view changes, such as air-to-ground with very sparse view overlap, pose an even greater challenge to the correspondence solvers. We present a novel optimization-based approach that significantly enhances existing feature matching methods by introducing geometry cues in addition to color cues. This helps fill gaps when there is less overlap in large-scale scenarios. Our method formulates geometric verification as an optimization problem, guiding feature matching within detector-free methods and using sparse correspondences from detector-based methods as anchor points. By enforcing geometric constraints via the Sampson Distance, our approach ensures that the denser correspondences from detector-free methods are geometrically consistent and more accurate. This hybrid strategy significantly improves correspondence density and accuracy, mitigates multi-view inconsistencies, and leads to notable advancements in camera pose accuracy and point cloud density. It outperforms state-of-the-art feature matching methods on benchmark datasets and enables feature matching in challenging extreme large-scale settings.
Authors: Tim Bader, Leon Eisemann, Adrian Pogorzelski, Namrata Jangid, Attila-Balazs Kis
Abstract: The increasing accuracy reports of metric monocular depth estimation models lead to a growing interest from the automotive domain. Current model evaluations do not provide deeper insights into the models' performance, also in relation to safety-critical or unseen classes. Within this paper, we present a novel approach for the evaluation of depth estimation models. Our proposed metric leverages three components, a class-wise component, an edge and corner image feature component, and a global consistency retaining component. Classes are further weighted on their distance in the scene and on criticality for automotive applications. In the evaluation, we present the benefits of our metric through comparison to classical metrics, class-wise analytics, and the retrieval of critical situations. The results show that our metric provides deeper insights into model results while fulfilling safety-critical requirements. We release the code and weights on the following repository: https://github.com/leisemann/ca_mmde
Authors: Mohammadmahdi Honarmand, Muhammad Abdullah Jamal, Omid Mohareri
Abstract: We introduce VidLPRO, a novel video-language (VL) pre-training framework designed specifically for robotic and laparoscopic surgery. While existing surgical VL models primarily rely on contrastive learning, we propose a more comprehensive approach to capture the intricate temporal dynamics and align video with language. VidLPRO integrates video-text contrastive learning, video-text matching, and masked language modeling objectives to learn rich VL representations. To support this framework, we present GenSurg+, a carefully curated dataset derived from GenSurgery, comprising 17k surgical video clips paired with captions generated by GPT-4 using transcripts extracted by the Whisper model. This dataset addresses the need for large-scale, high-quality VL data in the surgical domain. Extensive experiments on benchmark datasets, including Cholec80 and AutoLaparo, demonstrate the efficacy of our approach. VidLPRO achieves state-of-the-art performance in zero-shot surgical phase recognition, significantly outperforming existing surgical VL models such as SurgVLP and HecVL. Our model demonstrates improvements of up to 21.5\% in accuracy and 15.7% in F1 score, setting a new benchmark in the field. Notably, VidLPRO exhibits robust performance even with single-frame inference, while effectively scaling with increased temporal context. Ablation studies reveal the impact of frame sampling strategies on model performance and computational efficiency. These results underscore VidLPRO's potential as a foundation model for surgical video understanding.
Authors: Lele Chang, Peilin Liu, Qinghai Guo, Fei Wen
Abstract: Recently, self-supervised learning (SSL) has been extensively studied. Theoretically, mutual information maximization (MIM) is an optimal criterion for SSL, with a strong theoretical foundation in information theory. However, it is difficult to directly apply MIM in SSL since the data distribution is not analytically available in applications. In practice, many existing methods can be viewed as approximate implementations of the MIM criterion. This work shows that, based on the invariance property of MI, explicit MI maximization can be applied to SSL under a generic distribution assumption, i.e., a relaxed condition of the data distribution. We further illustrate this by analyzing the generalized Gaussian distribution. Based on this result, we derive a loss function based on the MIM criterion using only second-order statistics. We implement the new loss for SSL and demonstrate its effectiveness via extensive experiments.
Authors: Ren-Di Wu, Yu-Yen Lin, Huei-Fang Yang
Abstract: Composed image retrieval (CIR), which formulates the query as a combination of a reference image and modified text, has emerged as a new form of image search due to its enhanced ability to capture users' intentions. However, training a CIR model in a supervised manner typically requires labor-intensive collection of (reference image, text modifier, target image) triplets. While existing zero-shot CIR (ZS-CIR) methods eliminate the need for training on specific downstream datasets, they still require additional pretraining with large-scale image-text pairs. In this paper, we introduce a training-free approach for ZS-CIR. Our approach, \textbf{Wei}ghted \textbf{Mo}dality fusion and similarity for \textbf{CIR} (WeiMoCIR), operates under the assumption that image and text modalities can be effectively combined using a simple weighted average. This allows the query representation to be constructed directly from the reference image and text modifier. To further enhance retrieval performance, we employ multimodal large language models (MLLMs) to generate image captions for the database images and incorporate these textual captions into the similarity computation by combining them with image information using a weighted average. Our approach is simple, easy to implement, and its effectiveness is validated through experiments on the FashionIQ and CIRR datasets.
Authors: Zeyu Cai, Duotun Wang, Yixun Liang, Zhijing Shao, Ying-Cong Chen, Xiaohang Zhan, Zeyu Wang
Abstract: Score Distillation Sampling (SDS) has emerged as a prevalent technique for text-to-3D generation, enabling 3D content creation by distilling view-dependent information from text-to-2D guidance. However, they frequently exhibit shortcomings such as over-saturated color and excess smoothness. In this paper, we conduct a thorough analysis of SDS and refine its formulation, finding that the core design is to model the distribution of rendered images. Following this insight, we introduce a novel strategy called Variational Distribution Mapping (VDM), which expedites the distribution modeling process by regarding the rendered images as instances of degradation from diffusion-based generation. This special design enables the efficient training of variational distribution by skipping the calculations of the Jacobians in the diffusion U-Net. We also introduce timestep-dependent Distribution Coefficient Annealing (DCA) to further improve distilling precision. Leveraging VDM and DCA, we use Gaussian Splatting as the 3D representation and build a text-to-3D generation framework. Extensive experiments and evaluations demonstrate the capability of VDM and DCA to generate high-fidelity and realistic assets with optimization efficiency.
Authors: Wei Wu, Xi Guo, Weixuan Tang, Tingxuan Huang, Chiyu Wang, Dongyue Chen, Chenjing Ding
Abstract: Recent advancements in generative models have provided promising solutions for synthesizing realistic driving videos, which are crucial for training autonomous driving perception models. However, existing approaches often struggle with multi-view video generation due to the challenges of integrating 3D information while maintaining spatial-temporal consistency and effectively learning from a unified model. We propose DriveScape, an end-to-end framework for multi-view, 3D condition-guided video generation, capable of producing 1024 x 576 high-resolution videos at 10Hz. Unlike other methods limited to 2Hz due to the 3D box annotation frame rate, DriveScape overcomes this with its ability to operate under sparse conditions. Our Bi-Directional Modulated Transformer (BiMot) ensures precise alignment of 3D structural information, maintaining spatial-temporal consistency. DriveScape excels in video generation performance, achieving state-of-the-art results on the nuScenes dataset with an FID score of 8.34 and an FVD score of 76.39. Our project homepage: https://metadrivescape.github.io/papers_project/drivescapev1/index.html
URLs: https://metadrivescape.github.io/papers_project/drivescapev1/index.html
Authors: Junzhou Chen, Zirui Zhang, Jing Yu, Heqiang Huang, Ronghui Zhang, Xuemiao Xu, Bin Sheng, Hong Yan
Abstract: Driver distraction remains a leading cause of traffic accidents, posing a critical threat to road safety globally. As intelligent transportation systems evolve, accurate and real-time identification of driver distraction has become essential. However, existing methods struggle to capture both global contextual and fine-grained local features while contending with noisy labels in training datasets. To address these challenges, we propose DSDFormer, a novel framework that integrates the strengths of Transformer and Mamba architectures through a Dual State Domain Attention (DSDA) mechanism, enabling a balance between long-range dependencies and detailed feature extraction for robust driver behavior recognition. Additionally, we introduce Temporal Reasoning Confident Learning (TRCL), an unsupervised approach that refines noisy labels by leveraging spatiotemporal correlations in video sequences. Our model achieves state-of-the-art performance on the AUC-V1, AUC-V2, and 100-Driver datasets and demonstrates real-time processing efficiency on the NVIDIA Jetson AGX Orin platform. Extensive experimental results confirm that DSDFormer and TRCL significantly improve both the accuracy and robustness of driver distraction detection, offering a scalable solution to enhance road safety.
Authors: Quang-Huy Che, Duc-Tri Le, Vinh-Tiep Nguyen
Abstract: Data augmentation is a widely used technique for creating training data for tasks that require labeled data, such as semantic segmentation. This method benefits pixel-wise annotation tasks requiring much effort and intensive labor. Traditional data augmentation methods involve simple transformations like rotations and flips to create new images from existing ones. However, these new images may lack diversity along the main semantic axes in the data and not change high-level semantic properties. To address this issue, generative models have emerged as an effective solution for augmenting data by generating synthetic images. Controllable generative models offer a way to augment data for semantic segmentation tasks using a prompt and visual reference from the original image. However, using these models directly presents challenges, such as creating an effective prompt and visual reference to generate a synthetic image that accurately reflects the content and structure of the original. In this work, we introduce an effective data augmentation method for semantic segmentation using the Controllable Diffusion Model. Our proposed method includes efficient prompt generation using Class-Prompt Appending and Visual Prior Combination to enhance attention to labeled classes in real images. These techniques allow us to generate images that accurately depict segmented classes in the real image. In addition, we employ the class balancing algorithm to ensure efficiency when merging the synthetic and original images to generate balanced data for the training dataset. We evaluated our method on the PASCAL VOC datasets and found it highly effective for synthesizing images in semantic segmentation.
Authors: Ang He, Xiaobo Li, Ximei Wu, Chengyue Su, Jing Chen, Sheng Xu, Xiaobin Guo
Abstract: Unmanned aerial vehicles (UAVs) equipped with thermal infrared (TIR) cameras play a crucial role in combating nocturnal wildlife poaching. However, TIR images often face challenges such as jitter, and wildlife overlap, necessitating UAVs to possess the capability to identify blurred and overlapping small targets. Current traditional lightweight networks deployed on UAVs struggle to extract features from blurry small targets. To address this issue, we developed ALSS-YOLO, an efficient and lightweight detector optimized for TIR aerial images. Firstly, we propose a novel Adaptive Lightweight Channel Split and Shuffling (ALSS) module. This module employs an adaptive channel split strategy to optimize feature extraction and integrates a channel shuffling mechanism to enhance information exchange between channels. This improves the extraction of blurry features, crucial for handling jitter-induced blur and overlapping targets. Secondly, we developed a Lightweight Coordinate Attention (LCA) module that employs adaptive pooling and grouped convolution to integrate feature information across dimensions. This module ensures lightweight operation while maintaining high detection precision and robustness against jitter and target overlap. Additionally, we developed a single-channel focus module to aggregate the width and height information of each channel into four-dimensional channel fusion, which improves the feature representation efficiency of infrared images. Finally, we modify the localization loss function to emphasize the loss value associated with small objects to improve localization accuracy. Extensive experiments on the BIRDSAI and ISOD TIR UAV wildlife datasets show that ALSS-YOLO achieves state-of-the-art performance, Our code is openly available at https://github.com/helloworlder8/computer_vision.
Authors: Charles Meyers, Mohammad Reza Saleh Sedghpour, Tommy L\"ofstedt, Erik Elmroth
Abstract: Machine learning models -- deep neural networks in particular -- have performed remarkably well on benchmark datasets across a wide variety of domains. However, the ease of finding adversarial counter-examples remains a persistent problem when training times are measured in hours or days and the time needed to find a successful adversarial counter-example is measured in seconds. Much work has gone into generating and defending against these adversarial counter-examples, however the relative costs of attacks and defences are rarely discussed. Additionally, machine learning research is almost entirely guided by test/train metrics, but these would require billions of samples to meet industry standards. The present work addresses the problem of understanding and predicting how particular model hyper-parameters influence the performance of a model in the presence of an adversary. The proposed approach uses survival models, worst-case examples, and a cost-aware analysis to precisely and accurately reject a particular model change during routine model training procedures rather than relying on real-world deployment, expensive formal verification methods, or accurate simulations of very complicated systems (\textit{e.g.}, digitally recreating every part of a car or a plane). Through an evaluation of many pre-processing techniques, adversarial counter-examples, and neural network configurations, the conclusion is that deeper models do offer marginal gains in survival times compared to more shallow counterparts. However, we show that those gains are driven more by the model inference time than inherent robustness properties. Using the proposed methodology, we show that ResNet is hopelessly insecure against even the simplest of white box attacks.
Authors: Zhuoyuan Li, Zikun Yuan, Li Li, Dong Liu, Xiaohu Tang, Feng Wu
Abstract: In modern video coding standards, block-based inter prediction is widely adopted, which brings high compression efficiency. However, in natural videos, there are usually multiple moving objects of arbitrary shapes, resulting in complex motion fields that are difficult to represent compactly. This problem has been tackled by more flexible block partitioning methods in the Versatile Video Coding (VVC) standard, but the more flexible partitions require more overhead bits to signal and still cannot be made arbitrarily shaped. To address this limitation, we propose an object segmentation-assisted inter prediction method (SAIP), where objects in the reference frames are segmented by some advanced technologies. With a proper indication, the object segmentation mask is translated from the reference frame to the current frame as the arbitrary-shaped partition of different regions without any extra signal. Using the segmentation mask, motion compensation is separately performed for different regions, achieving higher prediction accuracy. The segmentation mask is further used to code the motion vectors of different regions more efficiently. Moreover, the segmentation mask is considered in the joint rate-distortion optimization for motion estimation and partition estimation to derive the motion vector of different regions and partition more accurately. The proposed method is implemented into the VVC reference software, VTM version 12.0. Experimental results show that the proposed method achieves up to 1.98%, 1.14%, 0.79%, and on average 0.82%, 0.49%, 0.37% BD-rate reduction for common test sequences, under the Low-delay P, Low-delay B, and Random Access configurations, respectively.
Authors: Kang Liu, Zhuoqi Ma, Mengmeng Liu, Zhicheng Jiao, Xiaolu Kang, Qiguang Miao, Kun Xie
Abstract: A radiology report comprises presentation-style vocabulary, which ensures clarity and organization, and factual vocabulary, which provides accurate and objective descriptions based on observable findings. While manually writing these reports is time-consuming and labor-intensive, automatic report generation offers a promising alternative. A critical step in this process is to align radiographs with their corresponding reports. However, existing methods often rely on complete reports for alignment, overlooking the impact of presentation-style vocabulary. To address this issue, we propose FSE, a two-stage Factual Serialization Enhancement method. In Stage 1, we introduce factuality-guided contrastive learning for visual representation by maximizing the semantic correspondence between radiographs and corresponding factual descriptions. In Stage 2, we present evidence-driven report generation that enhances diagnostic accuracy by integrating insights from similar historical cases structured as factual serialization. Experiments on MIMIC-CXR and IU X-ray datasets across specific and general scenarios demonstrate that FSE outperforms state-of-the-art approaches in both natural language generation and clinical efficacy metrics. Ablation studies further emphasize the positive effects of factual serialization in Stage 1 and Stage 2. The code is available at https://github.com/mk-runner/FSE.
Authors: Chuyan Xiong, Chengyu Shen, Xiaoqi Li, Kaichen Zhou, Jiaming Liu, Ruiping Wang, Hao Dong
Abstract: The ability to reflect on and correct failures is crucial for robotic systems to interact stably with real-life objects.Observing the generalization and reasoning capabilities of Multimodal Large Language Models (MLLMs), previous approaches have aimed to utilize these models to enhance robotic systems accordingly.However, these methods typically focus on high-level planning corrections using an additional MLLM, with limited utilization of failed samples to correct low-level contact poses. To address this gap, we propose an Autonomous Interactive Correction (AIC) MLLM, which makes use of previous low-level interaction experiences to correct SE(3) pose predictions. Specifically, AIC MLLM is initially fine-tuned to acquire both pose prediction and feedback prompt comprehension abilities.We carefully design two types of prompt instructions through interactions with objects: 1) visual masks to highlight unmovable parts for position correction, and 2)textual descriptions to indicate potential directions for rotation correction.During inference, a Feedback Information Extraction module is introduced to recognize the failure cause, allowing AIC MLLM to adaptively correct the pose prediction using the corresponding prompts. To further enhance manipulation stability, we devise a Test Time Adaptation strategy that enables AIC MLLM to better adapt to the current scene configuration.Finally, extensive experiments are conducted in both simulated and real-world environments to evaluate the proposed method. The results demonstrate that our AIC MLLM can efficiently correct failure samples by leveraging interaction experience prompts.Real-world demonstration can be found at https://sites.google.com/view/aic-mllm
Authors: Fanfan Liu, Feng Yan, Liming Zheng, Chengjian Feng, Yiyang Huang, Lin Ma
Abstract: Utilizing Vision-Language Models (VLMs) for robotic manipulation represents a novel paradigm, aiming to enhance the model's ability to generalize to new objects and instructions. However, due to variations in camera specifications and mounting positions, existing methods exhibit significant performance disparities across different robotic platforms. To address this challenge, we propose RoboUniView in this paper, an innovative approach that decouples visual feature extraction from action learning. We first learn a unified view representation from multi-perspective views by pre-training on readily accessible data, and then derive actions from this unified view representation to control robotic manipulation. This unified view representation more accurately mirrors the physical world and is not constrained by the robotic platform's camera parameters. Thanks to this methodology, we achieve state-of-the-art performance on the demanding CALVIN benchmark, enhancing the success rate in the $D \to D$ setting from 93.0% to 96.2%, and in the $ABC \to D$ setting from 92.2% to 94.2%. Moreover, our model exhibits outstanding adaptability and flexibility: it maintains high performance under unseen camera parameters, can utilize multiple datasets with varying camera parameters, and is capable of joint cross-task learning across datasets. Code is provided for re-implementation. https://github.com/liufanfanlff/RoboUniview
Authors: Nick John Eliopoulos, Purvish Jajal, James Davis, Gaowen Liu, George K. Thiravathukal, Yung-Hsiang Lu
Abstract: This paper investigates how to efficiently deploy vision transformers on edge devices for small workloads. Recent methods reduce the latency of transformer neural networks by removing or merging tokens, with small accuracy degradation. However, these methods are not designed with edge device deployment in mind: they do not leverage information about the latency-workload trends to improve efficiency. We address this shortcoming in our work. First, we identify factors that affect ViT latency-workload relationships. Second, we determine token pruning schedule by leveraging non-linear latency-workload relationships. Third, we demonstrate a training-free, token pruning method utilizing this schedule. We show other methods may increase latency by 2-30%, while we reduce latency by 9-26%. For similar latency (within 5.2% or 7ms) across devices we achieve 78.6%-84.5% ImageNet1K accuracy, while the state-of-the-art, Token Merging, achieves 45.8%-85.4%.
Authors: Alberto Pirillo, Luca Colombo, Manuel Roveri
Abstract: Quantization has become increasingly pivotal in addressing the steadily increasing computational and memory requirements of Deep Neural Networks (DNNs). By reducing the number of bits used to represent weights and activations (typically from 32-bit floating-point to 16-bit or 8-bit integers), quantization reduces the memory footprint, energy consumption, and execution time of DNN models. However, traditional quantization methods typically focus on the inference of DNNs, while the training process still relies on floating-point operations. To date, only one work in the literature has addressed integer-only training for Multi-Layer Perceptron (MLP) architectures. This work introduces NITRO-D, a new framework for training arbitrarily deep integer-only Convolutional Neural Networks (CNNs) that operate entirely in the integer-only domain for both training and inference. NITRO-D is the first framework in the literature enabling the training of integer-only CNNs without the need to introduce a quantization scheme. Specifically, NITRO-D introduces a novel architecture integrating multiple integer local-loss blocks, which include the proposed NITRO Scaling Layer and the NITRO-ReLU activation function. Additionally, it introduces a novel integer-only learning algorithm derived from Local Error Signals (LES), utilizing IntegerSGD, an optimizer specifically designed to operate in an integer-only context. NITRO-D is implemented in an open-source Python library. Extensive experimental evaluations demonstrate its effectiveness across several state-of-the-art image recognition datasets. Results show significant performance improvements from 2.47% to 5.96% for integer-only MLP architectures over the state-of-the-art solution, and the capability of training integer-only CNN architectures with minimal accuracy degradation from -0.15% to -4.22% compared to floating-point LES.
Authors: Wenhao Li, Zhiyuan Yu, Qijin She, Zhinan Yu, Yuqing Lan, Chenyang Zhu, Ruizhen Hu, Kai Xu
Abstract: The household rearrangement task involves spotting misplaced objects in a scene and accommodate them with proper places. It depends both on common-sense knowledge on the objective side and human user preference on the subjective side. In achieving such task, we propose to mine object functionality with user preference alignment directly from the scene itself, without relying on human intervention. To do so, we work with scene graph representation and propose LLM-enhanced scene graph learning which transforms the input scene graph into an affordance-enhanced graph (AEG) with information-enhanced nodes and newly discovered edges (relations). In AEG, the nodes corresponding to the receptacle objects are augmented with context-induced affordance which encodes what kind of carriable objects can be placed on it. New edges are discovered with newly discovered non-local relations. With AEG, we perform task planning for scene rearrangement by detecting misplaced carriables and determining a proper placement for each of them. We test our method by implementing a tiding robot in simulator and perform evaluation on a new benchmark we build. Extensive evaluations demonstrate that our method achieves state-of-the-art performance on misplacement detection and the following rearrangement planning.
Authors: Maytus Piriyajitakonkij, Sirawaj Itthipuripat, Ian Ballard, Ioannis Pappas
Abstract: In visual decision making, high-level features, such as object categories, have a strong influence on choice. However, the impact of low-level features on behavior is less understood partly due to the high correlation between high- and low-level features in the stimuli presented (e.g., objects of the same category are more likely to share low-level features). To disentangle these effects, we propose a method that de-correlates low- and high-level visual properties in a novel set of stimuli. Our method uses two Convolutional Neural Networks (CNNs) as candidate models of the ventral visual stream: the CORnet-S that has high neural predictivity in high-level, IT-like responses and the VGG-16 that has high neural predictivity in low-level responses. Triplets (root, image1, image2) of stimuli are parametrized by the level of low- and high-level similarity of images extracted from the different layers. These stimuli are then used in a decision-making task where participants are tasked to choose the most similar-to-the-root image. We found that different networks show differing abilities to predict the effects of low-versus-high-level similarity: while CORnet-S outperforms VGG-16 in explaining human choices based on high-level similarity, VGG-16 outperforms CORnet-S in explaining human choices based on low-level similarity. Using Brain-Score, we observed that the behavioral prediction abilities of different layers of these networks qualitatively corresponded to their ability to explain neural activity at different levels of the visual hierarchy. In summary, our algorithm for stimulus set generation enables the study of how different representations in the visual stream affect high-level cognitive behaviors.
Authors: Saghir Alfasly, Ghazal Alabtah, Sobhan Hemati, Krishna Rani Kalari, H. R. Tizhoosh
Abstract: We have tested recently published foundation models for histopathology for image retrieval. We report macro average of F1 score for top-1 retrieval, majority of top-3 retrievals, and majority of top-5 retrievals. We perform zero-shot retrievals, i.e., we do not alter embeddings and we do not train any classifier. As test data, we used diagnostic slides of TCGA, The Cancer Genome Atlas, consisting of 23 organs and 117 cancer subtypes. As a search platform we used Yottixel that enabled us to perform WSI search using patches. Achieved F1 scores show low performance, e.g., for top-5 retrievals, 27% +/- 13% (Yottixel-DenseNet), 42% +/- 14% (Yottixel-UNI), 40%+/-13% (Yottixel-Virchow), 41%+/-13% (Yottixel-GigaPath), and 41%+/-14% (GigaPath WSI).
Authors: Davood Karimi, Camilo Calixto, Haykel Snoussi, Maria Camila Cortes-Albornoz, Clemente Velasco-Annis, Caitlin Rollins, Camilo Jaimes, Ali Gholipour, Simon K. Warfield
Abstract: Diffusion-weighted MRI is increasingly used to study the normal and abnormal development of fetal brain in-utero. Recent studies have shown that dMRI can offer invaluable insights into the neurodevelopmental processes in the fetal stage. However, because of the low data quality and rapid brain development, reliable analysis of fetal dMRI data requires dedicated computational methods that are currently unavailable. The lack of automated methods for fast, accurate, and reproducible data analysis has seriously limited our ability to tap the potential of fetal brain dMRI for medical and scientific applications. In this work, we developed and validated a unified computational framework to (1) segment the brain tissue into white matter, cortical/subcortical gray matter, and cerebrospinal fluid, (2) segment 31 distinct white matter tracts, and (3) parcellate the brain's cortex and delineate the deep gray nuclei and white matter structures into 96 anatomically meaningful regions. We utilized a set of manual, semi-automatic, and automatic approaches to annotate 97 fetal brains. Using these labels, we developed and validated a multi-task deep learning method to perform the three computations. Our evaluations show that the new method can accurately carry out all three tasks, achieving a mean Dice similarity coefficient of 0.865 on tissue segmentation, 0.825 on white matter tract segmentation, and 0.819 on parcellation. The proposed method can greatly advance the field of fetal neuroimaging as it can lead to substantial improvements in fetal brain tractography, tract-specific analysis, and structural connectivity assessment.
Authors: Yingjie Zhou, Zicheng Zhang, Farong Wen, Jun Jia, Yanwei Jiang, Xiaohong Liu, Xiongkuo Min, Guangtao Zhai
Abstract: Although 3D generated content (3DGC) offers advantages in reducing production costs and accelerating design timelines, its quality often falls short when compared to 3D professionally generated content. Common quality issues frequently affect 3DGC, highlighting the importance of timely and effective quality assessment. Such evaluations not only ensure a higher standard of 3DGCs for end-users but also provide critical insights for advancing generative technologies. To address existing gaps in this domain, this paper introduces a novel 3DGC quality assessment dataset, 3DGCQA, built using 7 representative Text-to-3D generation methods. During the dataset's construction, 50 fixed prompts are utilized to generate contents across all methods, resulting in the creation of 313 textured meshes that constitute the 3DGCQA dataset. The visualization intuitively reveals the presence of 6 common distortion categories in the generated 3DGCs. To further explore the quality of the 3DGCs, subjective quality assessment is conducted by evaluators, whose ratings reveal significant variation in quality across different generation methods. Additionally, several objective quality assessment algorithms are tested on the 3DGCQA dataset. The results expose limitations in the performance of existing algorithms and underscore the need for developing more specialized quality assessment methods. To provide a valuable resource for future research and development in 3D content generation and quality assessment, the dataset has been open-sourced in https://github.com/zyj-2000/3DGCQA.
Authors: Buhua Liu, Shitong Shao, Bao Li, Lichen Bai, Zhiqiang Xu, Haoyi Xiong, James Kwok, Sumi Helal, Zeke Xie
Abstract: Diffusion models have emerged as the leading paradigm in generative modeling, excelling in various applications. Despite their success, these models often misalign with human intentions, generating outputs that may not match text prompts or possess desired properties. Inspired by the success of alignment in tuning large language models, recent studies have investigated aligning diffusion models with human expectations and preferences. This work mainly reviews alignment of diffusion models, covering advancements in fundamentals of alignment, alignment techniques of diffusion models, preference benchmarks, and evaluation for diffusion models. Moreover, we discuss key perspectives on current challenges and promising future directions on solving the remaining challenges in alignment of diffusion models. To the best of our knowledge, our work is the first comprehensive review paper for researchers and engineers to comprehend, practice, and research alignment of diffusion models.