Authors: Eric Keto, Wesley Andres Watters
Abstract: Moving objects have characteristic signatures in multi-spectral images made by Earth observation satellites that use push broom scanning. While the general concept is applicable to all satellites of this type, each satellite design has its own unique imaging system and requires unique methods to analyze the characteristic signatures. We assess the feasibility of detecting moving objects and measuring their velocities in one particular archive of satellite images made by Planet Labs Corporation with their constellation of SuperDove satellites. Planet Labs data presents a particular challenge in that the images in the archive are mosaics of individual exposures and therefore do not have unique time stamps. We explain how the timing information can be restored indirectly. Our results indicate that the movement of common transportation vehicles, airplanes, cars, and boats, can be detected and measured.
Authors: Phan Thi-Thu-Hong, Vo Quoc-Trinh, Nguyen Huu-Du
Abstract: In the grain industry, the identification of seed purity is a crucial task as it is an important factor in evaluating the quality of seeds. For rice seeds, this property allows for the reduction of unexpected influences of other varieties on rice yield, nutrient composition, and price. However, in practice, they are often mixed with seeds from others. This study proposes a novel method for automatically identifying the rice seed purity of a certain rice variety based on hybrid machine learning algorithms. The main idea is to use deep learning architectures for extracting important features from the raw data and then use machine learning algorithms for classification. Several experiments are conducted following a practical implementation to evaluate the performance of the proposed model. The obtained results show that the novel method improves significantly the performance of existing methods. Thus, it can be applied to design effective identification systems for rice seed purity.
Authors: Wanaiu Huang
Abstract: Semantic information is vital for human interaction, and decoding it from brain activity enables non-invasive clinical augmentative and alternative communication. While there has been significant progress in reconstructing visual images, few studies have focused on the language aspect. To address this gap, leveraging the powerful capabilities of the decoder-based vision-language pretrained model CoCa, this paper proposes BrainChat, a simple yet effective generative framework aimed at rapidly accomplishing semantic information decoding tasks from brain activity, including fMRI question answering and fMRI captioning. BrainChat employs the self-supervised approach of Masked Brain Modeling to encode sparse fMRI data, obtaining a more compact embedding representation in the latent space. Subsequently, BrainChat bridges the gap between modalities by applying contrastive loss, resulting in aligned representations of fMRI, image, and text embeddings. Furthermore, the fMRI embeddings are mapped to the generative Brain Decoder via cross-attention layers, where they guide the generation of textual content about fMRI in a regressive manner by minimizing caption loss. Empirically, BrainChat exceeds the performance of existing state-of-the-art methods in the fMRI captioning task and, for the first time, implements fMRI question answering. Additionally, BrainChat is highly flexible and can achieve high performance without image data, making it better suited for real-world scenarios with limited data.
Authors: Feng Wang, Haihang Ruan, Zhihuang Xie, Ronggang Wang, Xiangyu Yue
Abstract: Recently, Neural Video Compression (NVC) techniques have achieved remarkable performance, even surpassing the best traditional lossy video codec. However, most existing NVC methods heavily rely on transmitting Motion Vector (MV) to generate accurate contextual features, which has the following drawbacks. (1) Compressing and transmitting MV requires specialized MV encoder and decoder, which makes modules redundant. (2) Due to the existence of MV Encoder-Decoder, the training strategy is complex. In this paper, we present a noval Single Stream NVC framework (SSNVC), which removes complex MV Encoder-Decoder structure and uses a one-stage training strategy. SSNVC implicitly use temporal information by adding previous entropy model feature to current entropy model and using previous two frame to generate predicted motion information at the decoder side. Besides, we enhance the frame generator to generate higher quality reconstructed frame. Experiments demonstrate that SSNVC can achieve state-of-the-art performance on multiple benchmarks, and can greatly simplify compression process as well as training process.
Authors: Mengfei Li, Xiaoxiao Long, Yixun Liang, Weiyu Li, Yuan Liu, Peng Li, Xiaowei Chi, Xingqun Qi, Wei Xue, Wenhan Luo, Qifeng Liu, Yike Guo
Abstract: Despite recent advancements in the Large Reconstruction Model (LRM) demonstrating impressive results, when extending its input from single image to multiple images, it exhibits inefficiencies, subpar geometric and texture quality, as well as slower convergence speed than expected. It is attributed to that, LRM formulates 3D reconstruction as a naive images-to-3D translation problem, ignoring the strong 3D coherence among the input images. In this paper, we propose a Multi-view Large Reconstruction Model (M-LRM) designed to efficiently reconstruct high-quality 3D shapes from multi-views in a 3D-aware manner. Specifically, we introduce a multi-view consistent cross-attention scheme to enable M-LRM to accurately query information from the input images. Moreover, we employ the 3D priors of the input multi-view images to initialize the tri-plane tokens. Compared to LRM, the proposed M-LRM can produce a tri-plane NeRF with $128 \times 128$ resolution and generate 3D shapes of high fidelity. Experimental studies demonstrate that our model achieves a significant performance gain and faster training convergence than LRM. Project page: https://murphylmf.github.io/M-LRM/
Authors: Anurag Ghosh, Robert Tamburo, Shen Zheng, Juan R. Alvarez-Padilla, Hailiang Zhu, Michael Cardei, Nicholas Dunn, Christoph Mertz, Srinivasa G. Narasimhan
Abstract: Perceiving and navigating through work zones is challenging and under-explored, even with major strides in self-driving research. An important reason is the lack of open datasets for developing new algorithms to address this long-tailed scenario. We propose the ROADWork dataset to learn how to recognize, observe and analyze and drive through work zones. We find that state-of-the-art foundation models perform poorly on work zones. With our dataset, we improve upon detecting work zone objects (+26.2 AP), while discovering work zones with higher precision (+32.5%) at a much higher discovery rate (12.8 times), significantly improve detecting (+23.9 AP) and reading (+14.2% 1-NED) work zone signs and describing work zones (+36.7 SPICE). We also compute drivable paths from work zone navigation videos and show that it is possible to predict navigational goals and pathways such that 53.6% goals have angular error (AE) < 0.5 degrees (+9.9 %) and 75.3% pathways have AE < 0.5 degrees (+8.1 %).
Authors: Joshua Tokarsky, Ibrahim Abdulhafiz, Satya Ayyalasomayajula, Mostafa Mohsen, Navya G. Rao, Adam Forbes
Abstract: Autonomous driving has experienced remarkable progress, bolstered by innovations in computational hardware and sophisticated deep learning methodologies. The foundation of these advancements rests on the availability and quality of datasets, which are crucial for the development and refinement of dependable and versatile autonomous driving algorithms. While numerous datasets have been developed to support the evolution of autonomous driving perception technologies, few offer the diversity required to thoroughly test and enhance system robustness under varied weather conditions. Many public datasets lack the comprehensive coverage of challenging weather scenarios and detailed, high-resolution data, which are critical for training and validating advanced autonomous-driving perception models. In this paper, we introduce PLT-D3; a Dynamic-weather Driving Dataset, designed specifically to enhance autonomous driving systems' adaptability to diverse weather conditions. PLT-D3 provides high-fidelity stereo depth and scene flow ground truth data generated using Unreal Engine 5. In particular, this dataset includes synchronized high-resolution stereo image sequences that replicate a wide array of dynamic weather scenarios including rain, snow, fog, and diverse lighting conditions, offering an unprecedented level of realism in simulation-based testing. The primary aim of PLT-D3 is to address the scarcity of comprehensive training and testing resources that can simulate real-world weather variations. Benchmarks have been established for several critical autonomous driving tasks using PLT-D3, such as depth estimation, optical flow and scene-flow to measure and enhance the performance of state-of-the-art models.
Authors: Selvia Nafaa, Hafsa Essam, Karim Ashour, Doaa Emad, Rana Mohamed, Mohammed Elhenawy, Huthaifa I. Ashqar, Abdallah A. Hassan, Taqwa I. Alhadidi
Abstract: Monitoring asset conditions is a crucial factor in building efficient transportation asset management. Because of substantial advances in image processing, traditional manual classification has been largely replaced by semi-automatic/automatic techniques. As a result, automated asset detection and classification techniques are required. This paper proposes a methodology to detect and classify roadway pavement cracks using the well-known You Only Look Once (YOLO) version five (YOLOv5) and version 8 (YOLOv8) algorithms. Experimental results indicated that the precision of pavement crack detection reaches up to 67.3% under different illumination conditions and image sizes. The findings of this study can assist highway agencies in accurately detecting and classifying asset conditions under different illumination conditions. This will reduce the cost and time that are associated with manual inspection, which can greatly reduce the cost of highway asset maintenance.
Authors: Duc Pham, Matthew Hansen, F\'elicie Dhellemmens, Jens Krause, Pia Bideau
Abstract: Easily accessible sensors, like drones with diverse onboard sensors, have greatly expanded studying animal behavior in natural environments. Yet, analyzing vast, unlabeled video data, often spanning hours, remains a challenge for machine learning, especially in computer vision. Existing approaches often analyze only a few frames. Our focus is on long-term animal behavior analysis. To address this challenge, we utilize classical probabilistic methods for state estimation, such as particle filtering. By incorporating recent advancements in semantic object segmentation, we enable continuous tracking of rapidly evolving object formations, even in scenarios with limited data availability. Particle filters offer a provably optimal algorithmic structure for recursively adding new incoming information. We propose a novel approach for tracking schools of fish in the open ocean from drone videos. Our framework not only performs classical object tracking in 2D, instead it tracks the position and spatial expansion of the fish school in world coordinates by fusing video data and the drone's on board sensor information (GPS and IMU). The presented framework for the first time allows researchers to study collective behavior of fish schools in its natural social and environmental context in a non-invasive and scalable way.
Authors: Kai Wang, Shijian Deng, Jing Shi, Dimitrios Hatzinakos, Yapeng Tian
Abstract: Recent Diffusion Transformers (DiTs) have shown impressive capabilities in generating high-quality single-modality content, including images, videos, and audio. However, it is still under-explored whether the transformer-based diffuser can efficiently denoise the Gaussian noises towards superb multimodal content creation. To bridge this gap, we introduce AV-DiT, a novel and efficient audio-visual diffusion transformer designed to generate high-quality, realistic videos with both visual and audio tracks. To minimize model complexity and computational costs, AV-DiT utilizes a shared DiT backbone pre-trained on image-only data, with only lightweight, newly inserted adapters being trainable. This shared backbone facilitates both audio and video generation. Specifically, the video branch incorporates a trainable temporal attention layer into a frozen pre-trained DiT block for temporal consistency. Additionally, a small number of trainable parameters adapt the image-based DiT block for audio generation. An extra shared DiT block, equipped with lightweight parameters, facilitates feature interaction between audio and visual modalities, ensuring alignment. Extensive experiments on the AIST++ and Landscape datasets demonstrate that AV-DiT achieves state-of-the-art performance in joint audio-visual generation with significantly fewer tunable parameters. Furthermore, our results highlight that a single shared image generative backbone with modality-specific adaptations is sufficient for constructing a joint audio-video generator. Our source code and pre-trained models will be released.
Authors: Ayman Al-Kababji, Faycal Bensaali, Sarada Prasad Dakua, Yassine Himeur
Abstract: Artificial Intelligence (AI) is a pervasive research topic, permeating various sectors and applications. In this study, we harness the power of AI, specifically convolutional neural networks (ConvNets), for segmenting liver tissues. It also focuses on developing a user-friendly graphical user interface (GUI) tool, "AI Radiologist", enabling clinicians to effectively delineate different liver tissues (parenchyma, tumors, and vessels), thereby saving lives. This endeavor bridges the gap between academic research and practical, industrial applications. The GUI is a single-page application and is designed using the PyQt5 Python framework. The offline-available AI Radiologist resorts to three ConvNet models trained to segment all liver tissues. With respect to the Dice metric, the best liver ConvNet scores 98.16%, the best tumor ConvNet scores 65.95%, and the best vessel ConvNet scores 51.94%. It outputs 2D slices of the liver, tumors, and vessels, along with 3D interpolations in .obj and .mtl formats, which can be visualized/printed using any 3D-compatible software. Thus, the AI Radiologist offers a convenient tool for clinicians to perform liver tissue segmentation and 3D interpolation employing state-of-the-art models for tissues segmentation. With the provided capacity to select the volumes and pre-trained models, the clinicians can leave the rest to the AI Radiologist.
Authors: Can Akbas, Irem Su Arin, Sinan Onal
Abstract: Recent advancements in quality control across various industries have increasingly utilized the integration of video cameras and image processing for effective defect detection. A critical barrier to progress is the scarcity of comprehensive datasets featuring annotated defects, which are essential for developing and refining automated defect detection models. This systematic review, spanning from 2015 to 2023, identifies 15 publicly available datasets and critically examines them to assess their effectiveness and applicability for benchmarking and model development. Our findings reveal a diverse landscape of datasets, such as NEU-CLS, NEU-DET, DAGM, KolektorSDD, PCB Defect Dataset, and the Hollow Cylindrical Defect Detection Dataset, each with unique strengths and limitations in terms of image quality, defect type representation, and real-world applicability. The goal of this systematic review is to consolidate these datasets in a single location, providing researchers who seek such publicly available resources with a comprehensive reference.
Authors: Yayan Zhao, Mingwei Li, Matthew Berger
Abstract: We present CUPID: a visualization method for the contextual understanding of prompt-conditioned image distributions. CUPID targets the visual analysis of distributions produced by modern text-to-image generative models, wherein a user can specify a scene via natural language, and the model generates a set of images, each intended to satisfy the user's description. CUPID is designed to help understand the resulting distribution, using contextual cues to facilitate analysis: objects mentioned in the prompt, novel, synthesized objects not explicitly mentioned, and their potential relationships. Central to CUPID is a novel method for visualizing high-dimensional distributions, wherein contextualized embeddings of objects, those found within images, are mapped to a low-dimensional space via density-based embeddings. We show how such embeddings allows one to discover salient styles of objects within a distribution, as well as identify anomalous, or rare, object styles. Moreover, we introduce conditional density embeddings, whereby conditioning on a given object allows one to compare object dependencies within the distribution. We employ CUPID for analyzing image distributions produced by large-scale diffusion models, where our experimental results offer insights on language misunderstanding from such models and biases in object composition, while also providing an interface for discovery of typical, or rare, synthesized scenes.
Authors: Yayan Zhao, Mingwei Li, Matthew Berger
Abstract: In recent years, considerable work has been devoted to explaining predictive, deep learning-based models, and in turn how to evaluate explanations. An important class of evaluation methods are ones that are human-centered, which typically require the communication of explanations through visualizations. And while visualization plays a critical role in perceiving and understanding model explanations, how visualization design impacts human perception of explanations remains poorly understood. In this work, we study the graphical perception of model explanations, specifically, saliency-based explanations for visual recognition models. We propose an experimental design to investigate how human perception is influenced by visualization design, wherein we study the task of alignment assessment, or whether a saliency map aligns with an object in an image. Our findings show that factors related to visualization design decisions, the type of alignment, and qualities of the saliency map all play important roles in how humans perceive saliency-based visual explanations.
Authors: Zhengzhe Liu, Qing Liu, Chirui Chang, Jianming Zhang, Daniil Pakhomov, Haitian Zheng, Zhe Lin, Daniel Cohen-Or, Chi-Wing Fu
Abstract: Deoccluding the hidden portions of objects in a scene is a formidable task, particularly when addressing real-world scenes. In this paper, we present a new self-supervised PArallel visible-to-COmplete diffusion framework, named PACO, a foundation model for object-level scene deocclusion. Leveraging the rich prior of pre-trained models, we first design the parallel variational autoencoder, which produces a full-view feature map that simultaneously encodes multiple complete objects, and the visible-to-complete latent generator, which learns to implicitly predict the full-view feature map from partial-view feature map and text prompts extracted from the incomplete objects in the input image. To train PACO, we create a large-scale dataset with 500k samples to enable self-supervised learning, avoiding tedious annotations of the amodal masks and occluded regions. At inference, we devise a layer-wise deocclusion strategy to improve efficiency while maintaining the deocclusion quality. Extensive experiments on COCOA and various real-world scenes demonstrate the superior capability of PACO for scene deocclusion, surpassing the state of the arts by a large margin. Our method can also be extended to cross-domain scenes and novel categories that are not covered by the training set. Further, we demonstrate the deocclusion applicability of PACO in single-view 3D scene reconstruction and object recomposition.
Authors: Md. Shariful Islam, SM Shaqib, Shahriar Sultan Ramit, Shahrun Akter Khushbu, Mr. Abdus Sattar, Dr. Sheak Rashed Haider Noor
Abstract: In the construction sector, ensuring worker safety is of the utmost significance. In this study, a deep learning-based technique is presented for identifying safety gear worn by construction workers, such as helmets, goggles, jackets, gloves, and footwears. The recommended approach uses the YOLO v7 (You Only Look Once) object detection algorithm to precisely locate these safety items. The dataset utilized in this work consists of labeled images split into training, testing and validation sets. Each image has bounding box labels that indicate where the safety equipment is located within the image. The model is trained to identify and categorize the safety equipment based on the labeled dataset through an iterative training approach. We used custom dataset to train this model. Our trained model performed admirably well, with good precision, recall, and F1-score for safety equipment recognition. Also, the model's evaluation produced encouraging results, with a mAP@0.5 score of 87.7\%. The model performs effectively, making it possible to quickly identify safety equipment violations on building sites. A thorough evaluation of the outcomes reveals the model's advantages and points up potential areas for development. By offering an automatic and trustworthy method for safety equipment detection, this research makes a contribution to the fields of computer vision and workplace safety. The proposed deep learning-based approach will increase safety compliance and reduce the risk of accidents in the construction industry
Authors: SM Shaqib, Alaya Parvin Alo, Shahriar Sultan Ramit, Afraz Ul Haque Rupak, Sadman Sadik Khan, Mr. Md. Sadekur Rahman
Abstract: In order to ensure traffic safety through a reduction in fatalities and accidents, vehicle speed detection is essential. Relentless driving practices are discouraged by the enforcement of speed restrictions, which are made possible by accurate monitoring of vehicle speeds. Road accidents remain one of the leading causes of death in Bangladesh. The Bangladesh Passenger Welfare Association stated in 2023 that 7,902 individuals lost their lives in traffic accidents during the course of the year. Efficient vehicle speed detection is essential to maintaining traffic safety. Reliable speed detection can also help gather important traffic data, which makes it easier to optimize traffic flow and provide safer road infrastructure. The YOLOv8 model can recognize and track cars in videos with greater speed and accuracy when trained under close supervision. By providing insights into the application of supervised learning in object identification for vehicle speed estimation and concentrating on the particular traffic conditions and safety concerns in Bangladesh, this work represents a noteworthy contribution to the area. The MAE was 3.5 and RMSE was 4.22 between the predicted speed of our model and the actual speed or the ground truth measured by the speedometer Promising increased efficiency and wider applicability in a variety of traffic conditions, the suggested solution offers a financially viable substitute for conventional approaches.
Authors: Md. Mahmudul Hasan, SM Shaqib, Ms. Sharmin Akter, Rabiul Alam, Afraz Ul Haque, Shahrun akter khushbu
Abstract: The purpose of the Insect Detection System for Crop and Plant Health is to keep an eye out for and identify insect infestations in farming areas. By utilizing cutting-edge technology like computer vision and machine learning, the system seeks to identify hazardous insects early and accurately. This would enable prompt response to save crops and maintain optimal plant health. The Method of this study includes Data Acquisition, Preprocessing, Data splitting, Model Implementation and Model evaluation. Different models like MobileNetV2, ResNet152V2, Xecption, Custom CNN was used in this study. In order to categorize insect photos, a Convolutional Neural Network (CNN) based on the ResNet152V2 architecture is constructed and evaluated in this work. Achieving 99% training accuracy and 97% testing accuracy, ResNet152V2 demonstrates superior performance among four implemented models. The results highlight its potential for real-world applications in insect classification and entomology studies, emphasizing efficiency and accuracy. To ensure food security and sustain agricultural output globally, finding insects is crucial. Cutting-edge technology, such as ResNet152V2 models, greatly influence automating and improving the accuracy of insect identification. Efficient insect detection not only minimizes crop losses but also enhances agricultural productivity, contributing to sustainable food production. This underscores the pivotal role of technology in addressing challenges related to global food security.
Authors: Vivek Chavan, Oliver Heimann, J\"org Kr\"uger
Abstract: Egocentric vision aims to capture and analyse the world from the first-person perspective. We explore the possibilities for egocentric wearable devices to improve and enhance industrial use cases w.r.t. data collection, annotation, labelling and downstream applications. This would contribute to easier data collection and allow users to provide additional context. We envision that this approach could serve as a supplement to the traditional industrial Machine Vision workflow. Code, Dataset and related resources will be available at: https://github.com/Vivek9Chavan/EgoVis24
Authors: Yufan Zhu, Chongzhi Ran, Mingtao Feng, Weisheng Dong, Antonio M. L\'opez, Guangming Shi
Abstract: Virtual engines have the capability to generate dense depth maps for various synthetic scenes, making them invaluable for training depth estimation models. However, synthetic colors often exhibit significant discrepancies compared to real-world colors, thereby posing challenges for depth estimation in real-world scenes, particularly in complex and uncertain environments encountered in unsupervised monocular depth estimation tasks. To address this issue, we propose Back2Color, a framework that predicts realistic colors from depth utilizing a model trained on real-world data, thus facilitating the transformation of synthetic colors into real-world counterparts. Additionally, by employing the Syn-Real CutMix method for joint training with both real-world unsupervised and synthetic supervised depth samples, we achieve improved performance in monocular depth estimation for real-world scenes. Moreover, to comprehensively address the impact of non-rigid motions on depth estimation, we propose an auto-learning uncertainty temporal-spatial fusion method (Auto-UTSF), which integrates the benefits of unsupervised learning in both temporal and spatial dimensions. Furthermore, we design a depth estimation network (VADepth) based on the Vision Attention Network. Our Back2Color framework demonstrates state-of-the-art performance, as evidenced by improvements in performance metrics and the production of fine-grained details in our predictions, particularly on challenging datasets such as Cityscapes for unsupervised depth estimation.
Authors: Sandeep Mishra, Oindrila Saha, Alan C. Bovik
Abstract: Recent advancements in text-to-3D generation have demonstrated the ability to generate high quality 3D assets. However while generating animals these methods underperform, often portraying inaccurate anatomy and geometry. Towards ameliorating this defect, we present C3DAG, a novel pose-Controlled text-to-3D Animal Generation framework which generates a high quality 3D animal consistent with a given pose. We also introduce an automatic 3D shape creator tool, that allows dynamic pose generation and modification via a web-based tool, and that generates a 3D balloon animal using simple geometries. A NeRF is then initialized using this 3D shape using depth-controlled SDS. In the next stage, the pre-trained NeRF is fine-tuned using quadruped-pose-controlled SDS. The pipeline that we have developed not only produces geometrically and anatomically consistent results, but also renders highly controlled 3D animals, unlike prior methods which do not allow fine-grained pose control.
Authors: Zihui Xue, Mi Luo, Changan Chen, Kristen Grauman
Abstract: We study the problem of precisely swapping objects in videos, with a focus on those interacted with by hands, given one user-provided reference object image. Despite the great advancements that diffusion models have made in video editing recently, these models often fall short in handling the intricacies of hand-object interactions (HOI), failing to produce realistic edits -- especially when object swapping results in object shape or functionality changes. To bridge this gap, we present HOI-Swap, a novel diffusion-based video editing framework trained in a self-supervised manner. Designed in two stages, the first stage focuses on object swapping in a single frame with HOI awareness; the model learns to adjust the interaction patterns, such as the hand grasp, based on changes in the object's properties. The second stage extends the single-frame edit across the entire sequence; we achieve controllable motion alignment with the original video by: (1) warping a new sequence from the stage-I edited frame based on sampled motion points and (2) conditioning video generation on the warped sequence. Comprehensive qualitative and quantitative evaluations demonstrate that HOI-Swap significantly outperforms existing methods, delivering high-quality video edits with realistic HOIs.
Authors: Swaminathan Gurumurthy, Karnik Ram, Bingqing Chen, Zachary Manchester, Zico Kolter
Abstract: Various pose estimation and tracking problems in robotics can be decomposed into a correspondence estimation problem (often computed using a deep network) followed by a weighted least squares optimization problem to solve for the poses. Recent work has shown that coupling the two problems by iteratively refining one conditioned on the other's output yields SOTA results across domains. However, training these models has proved challenging, requiring a litany of tricks to stabilize and speed up training. In this work, we take the visual odometry problem as an example and identify three plausible causes: (1) flow loss interference, (2) linearization errors in the bundle adjustment (BA) layer, and (3) dependence of weight gradients on the BA residual. We show how these issues result in noisy and higher variance gradients, potentially leading to a slow down in training and instabilities. We then propose a simple, yet effective solution to reduce the gradient variance by using the weights predicted by the network in the inner optimization loop to weight the correspondence objective in the training problem. This helps the training objective `focus' on the more important points, thereby reducing the variance and mitigating the influence of outliers. We show that the resulting method leads to faster training and can be more flexibly trained in varying training setups without sacrificing performance. In particular we show $2$--$2.5\times$ training speedups over a baseline visual odometry model we modify.
Authors: Ivan Skorokhodov, Willi Menapace, Aliaksandr Siarohin, Sergey Tulyakov
Abstract: Diffusion models have demonstrated remarkable performance in image and video synthesis. However, scaling them to high-resolution inputs is challenging and requires restructuring the diffusion pipeline into multiple independent components, limiting scalability and complicating downstream applications. This makes it very efficient during training and unlocks end-to-end optimization on high-resolution videos. We improve PDMs in two principled ways. First, to enforce consistency between patches, we develop deep context fusion -- an architectural technique that propagates the context information from low-scale to high-scale patches in a hierarchical manner. Second, to accelerate training and inference, we propose adaptive computation, which allocates more network capacity and computation towards coarse image details. The resulting model sets a new state-of-the-art FVD score of 66.32 and Inception Score of 87.68 in class-conditional video generation on UCF-101 $256^2$, surpassing recent methods by more than 100%. Then, we show that it can be rapidly fine-tuned from a base $36\times 64$ low-resolution generator for high-resolution $64 \times 288 \times 512$ text-to-video synthesis. To the best of our knowledge, our model is the first diffusion-based architecture which is trained on such high resolutions entirely end-to-end. Project webpage: https://snap-research.github.io/hpdm.
Authors: Prithwijit Chowdhury, Mohit Prabhushankar, Ghassan AlRegib, Mohamed Deriche
Abstract: Explainable AI (XAI) has revolutionized the field of deep learning by empowering users to have more trust in neural network models. The field of XAI allows users to probe the inner workings of these algorithms to elucidate their decision-making processes. The rise in popularity of XAI has led to the advent of different strategies to produce explanations, all of which only occasionally agree. Thus several objective evaluation metrics have been devised to decide which of these modules give the best explanation for specific scenarios. The goal of the paper is twofold: (i) we employ the notions of necessity and sufficiency from causal literature to come up with a novel explanatory technique called SHifted Adversaries using Pixel Elimination(SHAPE) which satisfies all the theoretical and mathematical criteria of being a valid explanation, (ii) we show that SHAPE is, infact, an adversarial explanation that fools causal metrics that are employed to measure the robustness and reliability of popular importance based visual XAI methods. Our analysis shows that SHAPE outperforms popular explanatory techniques like GradCAM and GradCAM++ in these tests and is comparable to RISE, raising questions about the sanity of these metrics and the need for human involvement for an overall better evaluation.
Authors: Andrea Burns, Kate Saenko, Bryan A. Plummer
Abstract: Mobile app user interfaces (UIs) are rich with action, text, structure, and image content that can be utilized to learn generic UI representations for tasks like automating user commands, summarizing content, and evaluating the accessibility of user interfaces. Prior work has learned strong visual representations with local or global captioning losses, but fails to retain both granularities. To combat this, we propose Textual Foresight, a novel pretraining objective for learning UI screen representations. Textual Foresight generates global text descriptions of future UI states given a current UI and local action taken. Our approach requires joint reasoning over elements and entire screens, resulting in improved UI features: on generation tasks, UI agents trained with Textual Foresight outperform state-of-the-art by 2% with 28x fewer images. We train with our newly constructed mobile app dataset, OpenApp, which results in the first public dataset for app UI representation learning. OpenApp enables new baselines, and we find Textual Foresight improves average task performance over them by 5.7% while having access to 2x less data.
Authors: Yuru Xiao, Xianming Liu, Deming Zhai, Kui Jiang, Junjun Jiang, Xiangyang Ji
Abstract: Neural Radiance Fields (NeRF) with hybrid representations have shown impressive capabilities in reconstructing scenes for view synthesis, delivering high efficiency. Nonetheless, their performance significantly drops with sparse view inputs, due to the issue of overfitting. While various regularization strategies have been devised to address these challenges, they often depend on inefficient assumptions or are not compatible with hybrid models. There is a clear need for a method that maintains efficiency and improves resilience to sparse views within a hybrid framework. In this paper, we introduce an accurate and efficient few-shot neural rendering method named Spatial Annealing smoothing regularized NeRF (SANeRF), which is specifically designed for a pre-filtering-driven hybrid representation architecture. We implement an exponential reduction of the sample space size from an initially large value. This methodology is crucial for stabilizing the early stages of the training phase and significantly contributes to the enhancement of the subsequent process of detail refinement. Our extensive experiments reveal that, by adding merely one line of code, SANeRF delivers superior rendering quality and much faster reconstruction speed compared to current few-shot NeRF methods. Notably, SANeRF outperforms FreeNeRF by 0.3 dB in PSNR on the Blender dataset, while achieving 700x faster reconstruction speed.
Authors: Sina Tayebati, Theja Tulabandhula, Amit R. Trivedi
Abstract: In this work, we propose a disruptively frugal LiDAR perception dataflow that generates rather than senses parts of the environment that are either predictable based on the extensive training of the environment or have limited consequence to the overall prediction accuracy. Therefore, the proposed methodology trades off sensing energy with training data for low-power robotics and autonomous navigation to operate frugally with sensors, extending their lifetime on a single battery charge. Our proposed generative pre-training strategy for this purpose, called as radially masked autoencoding (R-MAE), can also be readily implemented in a typical LiDAR system by selectively activating and controlling the laser power for randomly generated angular regions during on-field operations. Our extensive evaluations show that pre-training with R-MAE enables focusing on the radial segments of the data, thereby capturing spatial relationships and distances between objects more effectively than conventional procedures. Therefore, the proposed methodology not only reduces sensing energy but also improves prediction accuracy. For example, our extensive evaluations on Waymo, nuScenes, and KITTI datasets show that the approach achieves over a 5% average precision improvement in detection tasks across datasets and over a 4% accuracy improvement in transferring domains from Waymo and nuScenes to KITTI. In 3D object detection, it enhances small object detection by up to 4.37% in AP at moderate difficulty levels in the KITTI dataset. Even with 90% radial masking, it surpasses baseline models by up to 5.59% in mAP/mAPH across all object classes in the Waymo dataset. Additionally, our method achieves up to 3.17% and 2.31% improvements in mAP and NDS, respectively, on the nuScenes dataset, demonstrating its effectiveness with both single and fused LiDAR-camera modalities. https://github.com/sinatayebati/Radial_MAE.
Authors: Abhay Rawat, Shubham Dokania, Astitva Srivastava, Shuaib Ahmed, Haiwen Feng, Rahul Tallamraju
Abstract: Recent advancements in generative models have unlocked the capabilities to render photo-realistic data in a controllable fashion. Trained on the real data, these generative models are capable of producing realistic samples with minimal to no domain gap, as compared to the traditional graphics rendering. However, using the data generated using such models for training downstream tasks remains under-explored, mainly due to the lack of 3D consistent annotations. Moreover, controllable generative models are learned from massive data and their latent space is often too vast to obtain meaningful sample distributions for downstream task with limited generation. To overcome these challenges, we extract 3D consistent annotations from an existing controllable generative model, making the data useful for downstream tasks. Our experiments show competitive performance against state-of-the-art models using only generated synthetic data, demonstrating potential for solving downstream tasks. Project page: https://synth-forge.github.io
Authors: Elaheh Baharlouei, Mahsa Shafaei, Yigeng Zhang, Hugo Jair Escalante, Thamar Solorio
Abstract: We address the challenge of detecting questionable content in online media, specifically the subcategory of comic mischief. This type of content combines elements such as violence, adult content, or sarcasm with humor, making it difficult to detect. Employing a multimodal approach is vital to capture the subtle details inherent in comic mischief content. To tackle this problem, we propose a novel end-to-end multimodal system for the task of comic mischief detection. As part of this contribution, we release a novel dataset for the targeted task consisting of three modalities: video, text (video captions and subtitles), and audio. We also design a HIerarchical Cross-attention model with CAPtions (HICCAP) to capture the intricate relationships among these modalities. The results show that the proposed approach makes a significant improvement over robust baselines and state-of-the-art models for comic mischief detection and its type classification. This emphasizes the potential of our system to empower users, to make informed decisions about the online content they choose to see. In addition, we conduct experiments on the UCF101, HMDB51, and XD-Violence datasets, comparing our model against other state-of-the-art approaches showcasing the outstanding performance of our proposed model in various scenarios.
Authors: Isaac Lin, Tianye Wang, Shang Gao, Shiming Tang, Tai Sing Lee
Abstract: Convolutional neural networks (CNNs) have been shown to be the state-of-the-art approach for modeling the transfer functions of visual cortical neurons. Cortical neurons in the primary visual cortex are are sensitive to contextual information mediated by extensive horizontal and feedback connections. Standard CNNs can integrate global spatial image information to model such contextual modulation via two mechanisms: successive rounds of convolutions and a fully connected readout layer. In this paper, we find that non-local networks or self-attention (SA) mechanisms, theoretically related to context-dependent flexible gating mechanisms observed in the primary visual cortex, improve neural response predictions over parameter-matched CNNs in two key metrics: tuning curve correlation and tuning peak. We factorize networks to determine the relative contribution of each context mechanism. This reveals that information in the local receptive field is most important for modeling the overall tuning curve, but surround information is critically necessary for characterizing the tuning peak. We find that self-attention can replace subsequent spatial-integration convolutions when learned in an incremental manner, and is further enhanced in the presence of a fully connected readout layer, suggesting that the two context mechanisms are complementary. Finally, we find that learning a receptive-field-centric model with self-attention, before incrementally learning a fully connected readout, yields a more biologically realistic model in terms of center-surround contributions.
Authors: Arman Zarei, Keivan Rezaei, Samyadeep Basu, Mehrdad Saberi, Mazda Moayeri, Priyatham Kattakinda, Soheil Feizi
Abstract: Recent text-to-image diffusion-based generative models have the stunning ability to generate highly detailed and photo-realistic images and achieve state-of-the-art low FID scores on challenging image generation benchmarks. However, one of the primary failure modes of these text-to-image generative models is in composing attributes, objects, and their associated relationships accurately into an image. In our paper, we investigate this compositionality-based failure mode and highlight that imperfect text conditioning with CLIP text-encoder is one of the primary reasons behind the inability of these models to generate high-fidelity compositional scenes. In particular, we show that (i) there exists an optimal text-embedding space that can generate highly coherent compositional scenes which shows that the output space of the CLIP text-encoder is sub-optimal, and (ii) we observe that the final token embeddings in CLIP are erroneous as they often include attention contributions from unrelated tokens in compositional prompts. Our main finding shows that the best compositional improvements can be achieved (without harming the model's FID scores) by fine-tuning {\it only} a simple linear projection on CLIP's representation space in Stable-Diffusion variants using a small set of compositional image-text pairs. This result demonstrates that the sub-optimality of the CLIP's output space is a major error source. We also show that re-weighting the erroneous attention contributions in CLIP can also lead to improved compositional performances, however these improvements are often less significant than those achieved by solely learning a linear projection head, highlighting erroneous attentions to be only a minor error source.
Authors: Maryam Berijanian, Katrina Gensterblum, Doruk Alp Mutlu, Katelyn Reagan, Andrew Hart, Dirk Colbry
Abstract: This work introduces two new distance metrics for comparing labeled arrays, which are common outputs of image segmentation algorithms. Each pixel in an image is assigned a label, with binary segmentation providing only two labels ('foreground' and 'background'). These can be represented by a simple binary matrix and compared using pixel differences. However, many segmentation algorithms output multiple regions in a labeled array. We propose two distance metrics, named LAD and MADLAD, that calculate the distance between two labeled images. By doing so, the accuracy of different image segmentation algorithms can be evaluated by measuring their outputs against a 'ground truth' labeling. Both proposed metrics, operating with a complexity of $O(N)$ for images with $N$ pixels, are designed to quickly identify similar labeled arrays, even when different labeling methods are used. Comparisons are made between images labeled manually and those labeled by segmentation algorithms. This evaluation is crucial when searching through a space of segmentation algorithms and their hyperparameters via a genetic algorithm to identify the optimal solution for automated segmentation, which is the goal in our lab, SEE-Insight. By measuring the distance from the ground truth, these metrics help determine which algorithm provides the most accurate segmentation.
Authors: Jiacheng Liu, Hang Zhou, Shida Wei, Rui Ma
Abstract: In this paper, we address the problem of plausible object placement for the challenging task of realistic image composition. We propose DiffPop, the first framework that utilizes plausibility-guided denoising diffusion probabilistic model to learn the scale and spatial relations among multiple objects and the corresponding scene image. First, we train an unguided diffusion model to directly learn the object placement parameters in a self-supervised manner. Then, we develop a human-in-the-loop pipeline which exploits human labeling on the diffusion-generated composite images to provide the weak supervision for training a structural plausibility classifier. The classifier is further used to guide the diffusion sampling process towards generating the plausible object placement. Experimental results verify the superiority of our method for producing plausible and diverse composite images on the new Cityscapes-OP dataset and the public OPA dataset, as well as demonstrate its potential in applications such as data augmentation and multi-object placement tasks. Our dataset and code will be released.
Authors: Rupayan Mallick, Amr Abdalla, Sarah Adel Bargal
Abstract: We present FaithFill, a diffusion-based inpainting object completion approach for realistic generation of missing object parts. Typically, multiple reference images are needed to achieve such realistic generation, otherwise the generation would not faithfully preserve shape, texture, color, and background. In this work, we propose a pipeline that utilizes only a single input reference image -having varying lighting, background, object pose, and/or viewpoint. The singular reference image is used to generate multiple views of the object to be inpainted. We demonstrate that FaithFill produces faithful generation of the object's missing parts, together with background/scene preservation, from a single reference image. This is demonstrated through standard similarity metrics, human judgement, and GPT evaluation. Our results are presented on the DreamBooth dataset, and a novel proposed dataset.
Authors: Se Jin Park, Chae Won Kim, Hyeongseop Rha, Minsu Kim, Joanna Hong, Jeong Hun Yeo, Yong Man Ro
Abstract: In this paper, we introduce a novel Face-to-Face spoken dialogue model. It processes audio-visual speech from user input and generates audio-visual speech as the response, marking the initial step towards creating an avatar chatbot system without relying on intermediate text. To this end, we newly introduce MultiDialog, the first large-scale multimodal (i.e., audio and visual) spoken dialogue corpus containing 340 hours of approximately 9,000 dialogues, recorded based on the open domain dialogue dataset, TopicalChat. The MultiDialog contains parallel audio-visual recordings of conversation partners acting according to the given script with emotion annotations, which we expect to open up research opportunities in multimodal synthesis. Our Face-to-Face spoken dialogue model incorporates a textually pretrained large language model and adapts it into the audio-visual spoken dialogue domain by incorporating speech-text joint pretraining. Through extensive experiments, we validate the effectiveness of our model in facilitating a face-to-face conversation. Demo and data are available at https://multidialog.github.io and https://huggingface.co/datasets/IVLLab/MultiDialog, respectively.
URLs: https://multidialog.github.io, https://huggingface.co/datasets/IVLLab/MultiDialog,
Authors: Seyd Teymoor Seydi
Abstract: Hyperspectral image classification is a crucial but challenging task due to the high dimensionality and complex spatial-spectral correlations inherent in hyperspectral data. This paper employs Wavelet-based Kolmogorov-Arnold Network (wav-kan) architecture tailored for efficient modeling of these intricate dependencies. Inspired by the Kolmogorov-Arnold representation theorem, Wav-KAN incorporates wavelet functions as learnable activation functions, enabling non-linear mapping of the input spectral signatures. The wavelet-based activation allows Wav-KAN to effectively capture multi-scale spatial and spectral patterns through dilations and translations. Experimental evaluation on three benchmark hyperspectral datasets (Salinas, Pavia, Indian Pines) demonstrates the superior performance of Wav-KAN compared to traditional multilayer perceptrons (MLPs) and the recently proposed Spline-based KAN (Spline-KAN) model. In this work we are: (1) conducting more experiments on additional hyperspectral datasets (Pavia University, WHU-Hi, and Urban Hyperspectral Image) to further validate the generalizability of Wav-KAN; (2) developing a multiresolution Wav-KAN architecture to capture scale-invariant features; (3) analyzing the effect of dimensional reduction techniques on classification performance; (4) exploring optimization methods for tuning the hyperparameters of KAN models; and (5) comparing Wav-KAN with other state-of-the-art models in hyperspectral image classification.
Authors: Hongsong Wang, Yin Zhu, Xin Geng
Abstract: Dance plays an important role as an artistic form and expression in human culture, yet the creation of dance remains a challenging task. Most dance generation methods primarily rely solely on music, seldom taking into consideration intrinsic attributes such as music style or genre. In this work, we introduce Flexible Dance Generation with Style Description Prompts (DGSDP), a diffusion-based framework suitable for diversified tasks of dance generation by fully leveraging the semantics of music style. The core component of this framework is Music-Conditioned Style-Aware Diffusion (MCSAD), which comprises a Transformer-based network and a music Style Modulation module. The MCSAD seemly integrates music conditions and style description prompts into the dance generation framework, ensuring that generated dances are consistent with the music content and style. To facilitate flexible dance generation and accommodate different tasks, a spatial-temporal masking strategy is effectively applied in the backward diffusion process. The proposed framework successfully generates realistic dance sequences that are accurately aligned with music for a variety of tasks such as long-term generation, dance in-betweening, dance inpainting, and etc. We hope that this work has the potential to inspire dance generation and creation, with promising applications in entertainment, art, and education.
Authors: Zhichao Jiang, Hongsong Wang, Xi Teng, Baopu Li
Abstract: 3D face alignment is a very challenging and fundamental problem in computer vision. Existing deep learning-based methods manually design different networks to regress either parameters of a 3D face model or 3D positions of face vertices. However, designing such networks relies on expert knowledge, and these methods often struggle to produce consistent results across various face poses. To address this limitation, we employ Neural Architecture Search (NAS) to automatically discover the optimal architecture for 3D face alignment. We propose a novel Multi-path One-shot Neural Architecture Search (MONAS) framework that leverages multi-scale features and contextual information to enhance face alignment across various poses. The MONAS comprises two key algorithms: Multi-path Networks Unbiased Sampling Based Training and Simulated Annealing based Multi-path One-shot Search. Experimental results on three popular benchmarks demonstrate the superior performance of the MONAS for both sparse alignment and dense alignment.
Authors: He Liu, Yikai Wang, Huaping Liu, Fuchun Sun, Anbang Yao
Abstract: Data-free knowledge distillation is able to utilize the knowledge learned by a large teacher network to augment the training of a smaller student network without accessing the original training data, avoiding privacy, security, and proprietary risks in real applications. In this line of research, existing methods typically follow an inversion-and-distillation paradigm in which a generative adversarial network on-the-fly trained with the guidance of the pre-trained teacher network is used to synthesize a large-scale sample set for knowledge distillation. In this paper, we reexamine this common data-free knowledge distillation paradigm, showing that there is considerable room to improve the overall training efficiency through a lens of ``small-scale inverted data for knowledge distillation". In light of three empirical observations indicating the importance of how to balance class distributions in terms of synthetic sample diversity and difficulty during both data inversion and distillation processes, we propose Small Scale Data-free Knowledge Distillation SSD-KD. In formulation, SSD-KD introduces a modulating function to balance synthetic samples and a priority sampling function to select proper samples, facilitated by a dynamic replay buffer and a reinforcement learning strategy. As a result, SSD-KD can perform distillation training conditioned on an extremely small scale of synthetic samples (e.g., 10X less than the original training data scale), making the overall training efficiency one or two orders of magnitude faster than many mainstream methods while retaining superior or competitive model performance, as demonstrated on popular image classification and semantic segmentation benchmarks. The code is available at https://github.com/OSVAI/SSD-KD.
Authors: Chao Li, Anbang Yao
Abstract: Dynamic convolution learns a linear mixture of n static kernels weighted with their input-dependent attentions, demonstrating superior performance than normal convolution. However, it increases the number of convolutional parameters by n times, and thus is not parameter efficient. This leads to no research progress that can allow researchers to explore the setting n>100 (an order of magnitude larger than the typical setting n<10) for pushing forward the performance boundary of dynamic convolution while enjoying parameter efficiency. To fill this gap, in this paper, we propose KernelWarehouse, a more general form of dynamic convolution, which redefines the basic concepts of ``kernels", ``assembling kernels" and ``attention function" through the lens of exploiting convolutional parameter dependencies within the same layer and across neighboring layers of a ConvNet. We testify the effectiveness of KernelWarehouse on ImageNet and MS-COCO datasets using various ConvNet architectures. Intriguingly, KernelWarehouse is also applicable to Vision Transformers, and it can even reduce the model size of a backbone while improving the model accuracy. For instance, KernelWarehouse (n=4) achieves 5.61%|3.90%|4.38% absolute top-1 accuracy gain on the ResNet18|MobileNetV2|DeiT-Tiny backbone, and KernelWarehouse (n=1/4) with 65.10% model size reduction still achieves 2.29% gain on the ResNet18 backbone. The code and models are available at https://github.com/OSVAI/KernelWarehouse.
Authors: Jun Bai, Di Wu, Tristan Shelley, Peter Schubel, David Twine, John Russell, Xuesen Zeng, Ji Zhang
Abstract: Material defects (MD) represent a primary challenge affecting product performance and giving rise to safety issues in related products. The rapid and accurate identification and localization of MD constitute crucial research endeavours in addressing contemporary challenges associated with MD. Although conventional non-destructive testing methods such as ultrasonic and X-ray approaches have mitigated issues related to low efficiency in manual inspections, they struggle to meet the diverse requirements of high precision, real-time speed, automation, and intelligence. In recent years, propelled by the swift advancement of machine learning (ML) technologies, particularly exemplified by deep learning, ML has swiftly emerged as the core technology and a prominent research direction for material defect detection (MDD). Through a comprehensive review of the latest literature, we systematically survey the ML techniques applied in MDD into five categories: unsupervised learning, supervised learning, semi-supervised learning, reinforcement learning, and generative learning. We provide a detailed analysis of the main principles and techniques used, together with the advantages and potential challenges associated with these techniques. Furthermore, the survey focuses on the techniques for defect detection in composite materials, which are important types of materials enjoying increasingly wide application in various industries such as aerospace, automotive, construction, and renewable energy. Finally, the survey explores potential future directions in MDD utilizing ML technologies. This comprehensive survey not only consolidates existing literature on ML-based MDD technologies but also serves as a foundational reference for future researchers and industrial practitioners, providing valuable insights and guidance in developing advanced and efficient MDD systems.
Authors: Jiadong Liang, Feng Lu
Abstract: Vivid talking face generation holds immense potential applications across diverse multimedia domains, such as film and game production. While existing methods accurately synchronize lip movements with input audio, they typically ignore crucial alignments between emotion and facial cues, which include expression, gaze, and head pose. These alignments are indispensable for synthesizing realistic videos. To address these issues, we propose a two-stage audio-driven talking face generation framework that employs 3D facial landmarks as intermediate variables. This framework achieves collaborative alignment of expression, gaze, and pose with emotions through self-supervised learning. Specifically, we decompose this task into two key steps, namely speech-to-landmarks synthesis and landmarks-to-face generation. The first step focuses on simultaneously synthesizing emotionally aligned facial cues, including normalized landmarks that represent expressions, gaze, and head pose. These cues are subsequently reassembled into relocated facial landmarks. In the second step, these relocated landmarks are mapped to latent key points using self-supervised learning and then input into a pretrained model to create high-quality face images. Extensive experiments on the MEAD dataset demonstrate that our model significantly advances the state-of-the-art performance in both visual quality and emotional alignment.
Authors: Fengtian Lang, Ruiye Ming, Zikang Yuan, Xin Yang
Abstract: In this work, we propose a fast and robust Image Feature Triangle Descriptor (IFTD) based on the STD method, aimed at improving the efficiency and accuracy of place recognition in driving scenarios. We extract keypoints from BEV projection image of point cloud and construct these keypoints into triangle descriptors. By matching these feature triangles, we achieved precise place recognition and calculated the 4-DOF pose estimation between two keyframes. Furthermore, we employ image similarity inspection to perform the final place recognition. Experimental results on three public datasets demonstrate that our IFTD can achieve greater robustness and accuracy than state-of-the-art methods with low computational overhead.
Authors: Jie Feng, Xiaojian Zhong, Di Li, Weisheng Dong, Ronghua Shang, Licheng Jiao
Abstract: Band selection plays a crucial role in hyperspectral image classification by removing redundant and noisy bands and retaining discriminative ones. However, most existing deep learning-based methods are aimed at dealing with a specific band selection dataset, and need to retrain parameters for new datasets, which significantly limits their generalizability.To address this issue, a novel multi-teacher multi-objective meta-learning network (M$^3$BS) is proposed for zero-shot hyperspectral band selection. In M$^3$BS, a generalizable graph convolution network (GCN) is constructed to generate dataset-agnostic base, and extract compatible meta-knowledge from multiple band selection tasks. To enhance the ability of meta-knowledge extraction, multiple band selection teachers are introduced to provide diverse high-quality experiences.strategy Finally, subsequent classification tasks are attached and jointly optimized with multi-teacher band selection tasks through multi-objective meta-learning in an end-to-end trainable way. Multi-objective meta-learning guarantees to coordinate diverse optimization objectives automatically and adapt to various datasets simultaneously. Once the optimization is accomplished, the acquired meta-knowledge can be directly transferred to unseen datasets without any retraining or fine-tuning. Experimental results demonstrate the effectiveness and efficiency of our proposed method on par with state-of-the-art baselines for zero-shot hyperspectral band selection.
Authors: Senyan Xu, Zhijing Sun, Jiaying Zhu, Yurui Zhu, Xueyang Fu, Zheng-Jun Zha
Abstract: Hybrid Event-Based Vision Sensor (HybridEVS) is a novel sensor integrating traditional frame-based and event-based sensors, offering substantial benefits for applications requiring low-light, high dynamic range, and low-latency environments, such as smartphones and wearable devices. Despite its potential, the lack of Image signal processing (ISP) pipeline specifically designed for HybridEVS poses a significant challenge. To address this challenge, in this study, we propose a coarse-to-fine framework named DemosaicFormer which comprises coarse demosaicing and pixel correction. Coarse demosaicing network is designed to produce a preliminary high-quality estimate of the RGB image from the HybridEVS raw data while the pixel correction network enhances the performance of image restoration and mitigates the impact of defective pixels. Our key innovation is the design of a Multi-Scale Gating Module (MSGM) applying the integration of cross-scale features, which allows feature information to flow between different scales. Additionally, the adoption of progressive training and data augmentation strategies further improves model's robustness and effectiveness. Experimental results show superior performance against the existing methods both qualitatively and visually, and our DemosaicFormer achieves the best performance in terms of all the evaluation metrics in the MIPI 2024 challenge on Demosaic for Hybridevs Camera. The code is available at https://github.com/QUEAHREN/DemosaicFormer.
Authors: Ruitao Xie, Jingbang Chen, Limai Jiang, Rui Xiao, Yi Pan, Yunpeng Cai
Abstract: Image classification is a primary task in data analysis where explainable models are crucially demanded in various applications. Although amounts of methods have been proposed to obtain explainable knowledge from the black-box classifiers, these approaches lack the efficiency of extracting global knowledge regarding the classification task, thus is vulnerable to local traps and often leads to poor accuracy. In this study, we propose a generative explanation model that combines the advantages of global and local knowledge for explaining image classifiers. We develop a representation learning method called class association embedding (CAE), which encodes each sample into a pair of separated class-associated and individual codes. Recombining the individual code of a given sample with altered class-associated code leads to a synthetic real-looking sample with preserved individual characters but modified class-associated features and possibly flipped class assignments. A building-block coherency feature extraction algorithm is proposed that efficiently separates class-associated features from individual ones. The extracted feature space forms a low-dimensional manifold that visualizes the classification decision patterns. Explanation on each individual sample can be then achieved in a counter-factual generation manner which continuously modifies the sample in one direction, by shifting its class-associated code along a guided path, until its classification outcome is changed. We compare our method with state-of-the-art ones on explaining image classification tasks in the form of saliency maps, demonstrating that our method achieves higher accuracies. The code is available at https://github.com/xrt11/XAI-CODE.
Authors: Chengyu Fang, Chunming He, Fengyang Xiao, Yulun Zhang, Longxiang Tang, Yuelin Zhang, Kai Li, Xiu Li
Abstract: Real-world Image Dehazing (RID) aims to alleviate haze-induced degradation in real-world settings. This task remains challenging due to the complexities in accurately modeling real haze distributions and the scarcity of paired real-world data. To address these challenges, we first introduce a cooperative unfolding network that jointly models atmospheric scattering and image scenes, effectively integrating physical knowledge into deep networks to restore haze-contaminated details. Additionally, we propose the first RID-oriented iterative mean-teacher framework, termed the Coherence-based Label Generator, to generate high-quality pseudo labels for network training. Specifically, we provide an optimal label pool to store the best pseudo-labels during network training, leveraging both global and local coherence to select high-quality candidates and assign weights to prioritize haze-free regions. We verify the effectiveness of our method, with experiments demonstrating that it achieves state-of-the-art performance on RID tasks. Code will be available at \url{https://github.com/cnyvfang/CORUN-Colabator}.
Authors: Chanda Grover Kamra, Indra Deep Mastan, Nitin Kumar, Debayan Gupta
Abstract: Recent developments in self-supervised learning (SSL) have made it possible to learn data representations without the need for annotations. Inspired by the non-contrastive SSL approach (SimSiam), we introduce a novel framework SIMSAM to compute the Semantic Affinity Matrix, which is significant for unsupervised image segmentation. Given an image, SIMSAM first extracts features using pre-trained DINO-ViT, then projects the features to predict the correlations of dense features in a non-contrastive way. We show applications of the Semantic Affinity Matrix in object segmentation and semantic segmentation tasks. Our code is available at https://github.com/chandagrover/SimSAM.
Authors: Jiaxin Deng, Junbiao Pang, Baochang Zhang
Abstract: Sharpness-Aware Minimization (SAM) has emerged as a promising approach for effectively reducing the generalization error. However, SAM incurs twice the computational cost compared to base optimizer (e.g., SGD). We propose Asymptotic Unbiased Sampling with respect to iterations to accelerate SAM (AUSAM), which maintains the model's generalization capacity while significantly enhancing computational efficiency. Concretely, we probabilistically sample a subset of data points beneficial for SAM optimization based on a theoretically guaranteed criterion, i.e., the Gradient Norm of each Sample (GNS). We further approximate the GNS by the difference in loss values before and after perturbation in SAM. As a plug-and-play, architecture-agnostic method, our approach consistently accelerates SAM across a range of tasks and networks, i.e., classification, human pose estimation and network quantization. On CIFAR10/100 and Tiny-ImageNet, AUSAM achieves results comparable to SAM while providing a speedup of over 70%. Compared to recent dynamic data pruning methods, AUSAM is better suited for SAM and excels in maintaining performance. Additionally, AUSAM accelerates optimization in human pose estimation and model quantization without sacrificing performance, demonstrating its broad practicality.
Authors: Yinan Deng, Jiahui Wang, Jingyu Zhao, Jianyu Dou, Yi Yang, Yufeng Yue
Abstract: In recent years, there has been a surge of interest in open-vocabulary 3D scene reconstruction facilitated by visual language models (VLMs), which showcase remarkable capabilities in open-set retrieval. However, existing methods face some limitations: they either focus on learning point-wise features, resulting in blurry semantic understanding, or solely tackle object-level reconstruction, thereby overlooking the intricate details of the object's interior. To address these challenges, we introduce OpenObj, an innovative approach to build open-vocabulary object-level Neural Radiance Fields (NeRF) with fine-grained understanding. In essence, OpenObj establishes a robust framework for efficient and watertight scene modeling and comprehension at the object-level. Moreover, we incorporate part-level features into the neural fields, enabling a nuanced representation of object interiors. This approach captures object-level instances while maintaining a fine-grained understanding. The results on multiple datasets demonstrate that OpenObj achieves superior performance in zero-shot semantic segmentation and retrieval tasks. Additionally, OpenObj supports real-world robotics tasks at multiple scales, including global movement and local manipulation.
Authors: Kyeongjin Ahn, Sungwon Han, Sungwon Park, Jihee Kim, Sangyoon Park, Meeyoung Cha
Abstract: The increasing frequency and intensity of natural disasters demand more sophisticated approaches for rapid and precise damage assessment. To tackle this issue, researchers have developed various methods on disaster benchmark datasets from satellite imagery to aid in detecting disaster damage. However, the diverse nature of geographical landscapes and disasters makes it challenging to apply existing methods to regions unseen during training. We present DAVI (Disaster Assessment with VIsion foundation model), which overcomes domain disparities and detects structural damage (e.g., building) without requiring ground-truth labels of the target region. DAVI integrates task-specific knowledge from a model trained on source regions with an image segmentation foundation model to generate pseudo labels of possible damage in the target region. It then employs a two-stage refinement process, targeting both the pixel and overall image, to more accurately pinpoint changes in disaster-struck areas based on before-and-after images. Comprehensive evaluations demonstrate that DAVI achieves exceptional performance across diverse terrains (e.g., USA and Mexico) and disaster types (e.g., wildfires, hurricanes, and earthquakes). This confirms its robustness in assessing disaster impact without dependence on ground-truth labels.
Authors: Shimin Chen, Yitian Yuan, Shaoxiang Chen, Zequn Jie, Lin Ma
Abstract: Amidst the advancements in image-based Large Vision-Language Models (image-LVLM), the transition to video-based models (video-LVLM) is hindered by the limited availability of quality video data. This paper addresses the challenge by leveraging the visual commonalities between images and videos to efficiently evolve image-LVLMs into video-LVLMs. We present a cost-effective video-LVLM that enhances model architecture, introduces innovative training strategies, and identifies the most effective types of video instruction data. Our innovative weighted token sampler significantly compresses the visual token numbers of each video frame, effectively cutting computational expenses. We also find that judiciously using just 10% of the video data, compared to prior video-LVLMs, yields impressive results during various training phases. Moreover, we delve into the influence of video instruction data in limited-resource settings, highlighting the significance of incorporating video training data that emphasizes temporal understanding to enhance model performance. The resulting Fewer Tokens and Fewer Videos LVLM (FTFV-LVLM) exhibits exceptional performance across video and image benchmarks, validating our model's design and training approaches.
Authors: Anjali Raj, Adway Mitra, Manjira Sinha
Abstract: The major Sustainable Development Goals (SDG) 2030, set by the United Nations Development Program (UNDP), include sustainable cities and communities, no poverty, and reduced inequalities. However, millions of people live in slums or informal settlements with poor living conditions in many major cities around the world, especially in less developed countries. To emancipate these settlements and their inhabitants through government intervention, accurate data about slum location and extent is required. While ground survey data is the most reliable, such surveys are costly and time-consuming. An alternative is remotely sensed data obtained from very high-resolution (VHR) imagery. With the advancement of new technology, remote sensing based mapping of slums has emerged as a prominent research area. The parallel rise of Artificial Intelligence, especially Deep Learning has added a new dimension to this field as it allows automated analysis of satellite imagery to identify complex spatial patterns associated with slums. This article offers a detailed review and meta-analysis of research on slum mapping using remote sensing imagery from 2014 to 2024, with a special focus on deep learning approaches. Our analysis reveals a trend towards increasingly complex neural network architectures, with advancements in data preprocessing and model training techniques significantly enhancing slum identification accuracy. We have attempted to identify key methodologies that are effective across diverse geographic contexts. While acknowledging the transformative impact Convolutional Neural Networks (CNNs) in slum detection, our review underscores the absence of a universally optimal model, suggesting the need for context-specific adaptations. We also identify prevailing challenges in this field, such as data limitations and a lack of model explainability and suggest potential strategies for overcoming these.
Authors: Weihan Wang, Zehai He, Wenyi Hong, Yean Cheng, Xiaohan Zhang, Ji Qi, Shiyu Huang, Bin Xu, Yuxiao Dong, Ming Ding, Jie Tang
Abstract: Recent progress in multimodal large language models has markedly enhanced the understanding of short videos (typically under one minute), and several evaluation datasets have emerged accordingly. However, these advancements fall short of meeting the demands of real-world applications such as embodied intelligence for long-term decision-making, in-depth movie reviews and discussions, and live sports commentary, all of which require comprehension of long videos spanning several hours. To address this gap, we introduce LVBench, a benchmark specifically designed for long video understanding. Our dataset comprises publicly sourced videos and encompasses a diverse set of tasks aimed at long video comprehension and information extraction. LVBench is designed to challenge multimodal models to demonstrate long-term memory and extended comprehension capabilities. Our extensive evaluations reveal that current multimodal models still underperform on these demanding long video understanding tasks. Through LVBench, we aim to spur the development of more advanced models capable of tackling the complexities of long video comprehension. Our data and code are publicly available at: https://lvbench.github.io.
Authors: Xiangyang Yang, Dan Zeng, Xucheng Wang, You Wu, Hengzhou Ye, Shuiwang Li
Abstract: Empowered by transformer-based models, visual tracking has advanced significantly. However, the slow speed of current trackers limits their applicability on devices with constrained computational resources. To address this challenge, we introduce ABTrack, an adaptive computation framework that adaptively bypassing transformer blocks for efficient visual tracking. The rationale behind ABTrack is rooted in the observation that semantic features or relations do not uniformly impact the tracking task across all abstraction levels. Instead, this impact varies based on the characteristics of the target and the scene it occupies. Consequently, disregarding insignificant semantic features or relations at certain abstraction levels may not significantly affect the tracking accuracy. We propose a Bypass Decision Module (BDM) to determine if a transformer block should be bypassed, which adaptively simplifies the architecture of ViTs and thus speeds up the inference process. To counteract the time cost incurred by the BDMs and further enhance the efficiency of ViTs, we innovatively adapt a pruning technique to reduce the dimension of the latent representation of tokens in each transformer block. Extensive experiments on multiple tracking benchmarks validate the effectiveness and generality of the proposed method and show that it achieves state-of-the-art performance. Code is released at: \href{https://github.com/1HykhqV3rU/ABTrack}
Authors: Sasidhar Alavala, Anil Kumar Vadde, Aparnamala Kancheti, Subrahmanyam Gorthi
Abstract: In this paper, we present our approach to the Auto WCEBleedGen Challenge V2 2024. Our solution combines the Swin Transformer for the initial classification of bleeding frames and RT-DETR for further detection of bleeding in Wireless Capsule Endoscopy (WCE), enhanced by a series of image preprocessing steps. These steps include converting images to Lab colour space, applying Contrast Limited Adaptive Histogram Equalization (CLAHE) for better contrast, and using Gaussian blur to suppress artefacts. The Swin Transformer utilizes a tiered architecture with shifted windows to efficiently manage self-attention calculations, focusing on local windows while enabling cross-window interactions. RT-DETR features an efficient hybrid encoder for fast processing of multi-scale features and an uncertainty-minimal query selection for enhanced accuracy. The class activation maps by Ablation-CAM are plausible to the model's decisions. On the validation set, this approach achieves a classification accuracy of 98.5% (best among the other state-of-the-art models) compared to 91.7% without any pre-processing and an $\text{AP}_{50}$ of 66.7% compared to 65.0% with state-of-the-art YOLOv8. On the test set, this approach achieves a classification accuracy and F1 score of 87.0% and 89.0% respectively.
Authors: Nikhil Kumar, Avinash Upadhyay, Shreya Sharma, Manoj Sharma, Pravendra Singh
Abstract: This paper presents a novel mid-wave infrared (MWIR) small target detection dataset (MWIRSTD) comprising 14 video sequences containing approximately 1053 images with annotated targets of three distinct classes of small objects. Captured using cooled MWIR imagers, the dataset offers a unique opportunity for researchers to develop and evaluate state-of-the-art methods for small object detection in realistic MWIR scenes. Unlike existing datasets, which primarily consist of uncooled thermal images or synthetic data with targets superimposed onto the background or vice versa, MWIRSTD provides authentic MWIR data with diverse targets and environments. Extensive experiments on various traditional methods and deep learning-based techniques for small target detection are performed on the proposed dataset, providing valuable insights into their efficacy. The dataset and code are available at https://github.com/avinres/MWIRSTD.
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. 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: Lixian Zhang, Yi Zhao, Runmin Dong, Jinxiao Zhang, Shuai Yuan, Shilei Cao, Mengxuan Chen, Juepeng Zheng, Weijia Li, Wei Liu, Litong Feng, Haohuan Fu
Abstract: Vast amounts of remote sensing (RS) data provide Earth observations across multiple dimensions, encompassing critical spatial, temporal, and spectral information which is essential for addressing global-scale challenges such as land use monitoring, disaster prevention, and environmental change mitigation. Despite various pre-training methods tailored to the characteristics of RS data, a key limitation persists: the inability to effectively integrate spatial, temporal, and spectral information within a single unified model. To unlock the potential of RS data, we construct a Spatial-Temporal-Spectral Structured Dataset (STSSD) characterized by the incorporation of multiple RS sources, diverse coverage, unified locations within image sets, and heterogeneity within images. Building upon this structured dataset, we propose an Anchor-Aware Masked AutoEncoder method (A$^{2}$-MAE), leveraging intrinsic complementary information from the different kinds of images and geo-information to reconstruct the masked patches during the pre-training phase. A$^{2}$-MAE integrates an anchor-aware masking strategy and a geographic encoding module to comprehensively exploit the properties of RS images. Specifically, the proposed anchor-aware masking strategy dynamically adapts the masking process based on the meta-information of a pre-selected anchor image, thereby facilitating the training on images captured by diverse types of RS sources within one model. Furthermore, we propose a geographic encoding method to leverage accurate spatial patterns, enhancing the model generalization capabilities for downstream applications that are generally location-related. Extensive experiments demonstrate our method achieves comprehensive improvements across various downstream tasks compared with existing RS pre-training methods, including image classification, semantic segmentation, and change detection tasks.
Authors: Haoji Zhang, Yiqin Wang, Yansong Tang, Yong Liu, Jiashi Feng, Jifeng Dai, Xiaojie Jin
Abstract: Benefiting from the advancements in large language models and cross-modal alignment, existing multi-modal video understanding methods have achieved prominent performance in offline scenario. However, online video streams, as one of the most common media forms in the real world, have seldom received attention. Compared to offline videos, the 'dynamic' nature of online video streams poses challenges for the direct application of existing models and introduces new problems, such as the storage of extremely long-term information, interaction between continuous visual content and 'asynchronous' user questions. Therefore, in this paper we present Flash-VStream, a video-language model that simulates the memory mechanism of human. Our model is able to process extremely long video streams in real-time and respond to user queries simultaneously. Compared to existing models, Flash-VStream achieves significant reductions in inference latency and VRAM consumption, which is intimately related to performing understanding of online streaming video. In addition, given that existing video understanding benchmarks predominantly concentrate on offline scenario, we propose VStream-QA, a novel question answering benchmark specifically designed for online video streaming understanding. Comparisons with popular existing methods on the proposed benchmark demonstrate the superiority of our method for such challenging setting. To verify the generalizability of our approach, we further evaluate it on existing video understanding benchmarks and achieves state-of-the-art performance in offline scenarios as well. All code, models, and datasets are available at the https://invinciblewyq.github.io/vstream-page/
Authors: Tobias Dorszewski, S{\o}ren A. Fuglsang, Jens Hjortkj{\ae}r
Abstract: Communicating in noisy, multi-talker environments is challenging, especially for people with hearing impairments. Egocentric video data can potentially be used to identify a user's conversation partners, which could be used to inform selective acoustic amplification of relevant speakers. Recent introduction of datasets and tasks in computer vision enable progress towards analyzing social interactions from an egocentric perspective. Building on this, we focus on the task of identifying conversation partners from egocentric video and describe a suitable dataset. Our dataset comprises 69 hours of egocentric video of diverse multi-conversation scenarios where each individual was assigned one or more conversation partners, providing the labels for our computer vision task. This dataset enables the development and assessment of algorithms for identifying conversation partners and evaluating related approaches. Here, we describe the dataset alongside initial baseline results of this ongoing work, aiming to contribute to the exciting advancements in egocentric video analysis for social settings.
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. Both the dataset and the source code will be made publicly available upon publication. Project page: https://naturezhanghn.github.io/sim2real.
Authors: Runyi Yu, Tianyu He, Ailing Zeng, Yuchi Wang, Junliang Guo, Xu Tan, Chang Liu, Jie Chen, Jiang Bian
Abstract: We aim to edit the lip movements in talking video according to the given speech while preserving the personal identity and visual details. The task can be decomposed into two sub-problems: (1) speech-driven lip motion generation and (2) visual appearance synthesis. Current solutions handle the two sub-problems within a single generative model, resulting in a challenging trade-off between lip-sync quality and visual details preservation. Instead, we propose to disentangle the motion and appearance, and then generate them one by one with a speech-to-motion diffusion model and a motion-conditioned appearance generation model. However, there still remain challenges in each stage, such as motion-aware identity preservation in (1) and visual details preservation in (2). Therefore, to preserve personal identity, we adopt landmarks to represent the motion, and further employ a landmark-based identity loss. To capture motion-agnostic visual details, we use separate encoders to encode the lip, non-lip appearance and motion, and then integrate them with a learned fusion module. We train MyTalk on a large-scale and diverse dataset. Experiments show that our method generalizes well to the unknown, even out-of-domain person, in terms of both lip sync and visual detail preservation. We encourage the readers to watch the videos on our project page (https://Ingrid789.github.io/MyTalk/).
Authors: Yu Wen Pao, Li Chang Lai, Hong-Yi Lin
Abstract: Local feature extractors are the cornerstone of many computer vision tasks. However, their vulnerability to adversarial attacks can significantly compromise their effectiveness. This paper discusses approaches to attack sophisticated local feature extraction algorithms and models to achieve two distinct goals: (1) forcing a match between originally non-matching image regions, and (2) preventing a match between originally matching regions. At the end of the paper, we discuss the performance and drawbacks of different patch generation methods.
Authors: Yihong Xu, \'Eloi Zablocki, Alexandre Boulch, Gilles Puy, Mickael Chen, Florent Bartoccioni, Nermin Samet, Oriane Sim\'eoni, Spyros Gidaris, Tuan-Hung Vu, Andrei Bursuc, Eduardo Valle, Renaud Marlet, Matthieu Cord
Abstract: Motion forecasting is crucial in autonomous driving systems to anticipate the future trajectories of surrounding agents such as pedestrians, vehicles, and traffic signals. In end-to-end forecasting, the model must jointly detect from sensor data (cameras or LiDARs) the position and past trajectories of the different elements of the scene and predict their future location. We depart from the current trend of tackling this task via end-to-end training from perception to forecasting and we use a modular approach instead. Following a recent study, we individually build and train detection, tracking, and forecasting modules. We then only use consecutive finetuning steps to integrate the modules better and alleviate compounding errors. Our study reveals that this simple yet effective approach significantly improves performance on the end-to-end forecasting benchmark. Consequently, our solution ranks first in the Argoverse 2 end-to-end Forecasting Challenge held at CVPR 2024 Workshop on Autonomous Driving (WAD), with 63.82 mAPf. We surpass forecasting results by +17.1 points over last year's winner and by +13.3 points over this year's runner-up. This remarkable performance in forecasting can be explained by our modular paradigm, which integrates finetuning strategies and significantly outperforms the end-to-end-trained counterparts.
Authors: R\'emi Michel, Mohamed Tamaazousti
Abstract: Distribution of colors and patterns in images is observed through cascades that adjust spatial resolution and dynamics. Cascades of colors reveal the emergent universal property that Fully Colored Images (FCIs) of natural scenes adhere to the debated continuous linear log-scale law (slope $-2.00 \pm 0.01$) (L1). Cascades of discrete $2 \times 2$ patterns are derived from pixel squares reductions onto the seven unlabeled rotation-free textures (0000, 0001, 0011, 0012, 0101, 0102, 0123). They exhibit an unparalleled universal entropy maximum of $1.74 \pm 0.013$ at some dynamics regardless of spatial scale (L2). Patterns also adhere to the Integral Fluctuation Theorem ($1.00 \pm 0.01$) (L3), pivotal in studies of chaotic systems. Images with fewer colors exhibit quadratic shift and bias from L1 and L3 but adhere to L2. Randomized Hilbert fractals FCIs better match the laws than basic-to-AI-based simulations. Those results are of interest in Neural Networks, out of equilibrium physics and spectral imagery.
Authors: Hualian Sheng, Sijia Cai, Na Zhao, Bing Deng, Qiao Liang, Min-Jian Zhao, Jieping Ye
Abstract: The field of 3D object detection from point clouds is rapidly advancing in computer vision, aiming to accurately and efficiently detect and localize objects in three-dimensional space. Current 3D detectors commonly fall short in terms of flexibility and scalability, with ample room for advancements in performance. In this paper, our objective is to address these limitations by introducing two frameworks for 3D object detection with minimal hand-crafted design. Firstly, we propose CT3D, which sequentially performs raw-point-based embedding, a standard Transformer encoder, and a channel-wise decoder for point features within each proposal. Secondly, we present an enhanced network called CT3D++, which incorporates geometric and semantic fusion-based embedding to extract more valuable and comprehensive proposal-aware information. Additionally, CT3D ++ utilizes a point-to-key bidirectional encoder for more efficient feature encoding with reduced computational cost. By replacing the corresponding components of CT3D with these novel modules, CT3D++ achieves state-of-the-art performance on both the KITTI dataset and the large-scale Way\-mo Open Dataset. The source code for our frameworks will be made accessible at https://github.com/hlsheng1/CT3D-plusplus.
Authors: Irene Huang, Wei Lin, M. Jehanzeb Mirza, Jacob A. Hansen, Sivan Doveh, Victor Ion Butoi, Roei Herzig, Assaf Arbelle, Hilde Kuhene, Trevor Darrel, Chuang Gan, Aude Oliva, Rogerio Feris, Leonid Karlinsky
Abstract: Compositional Reasoning (CR) entails grasping the significance of attributes, relations, and word order. Recent Vision-Language Models (VLMs), comprising a visual encoder and a Large Language Model (LLM) decoder, have demonstrated remarkable proficiency in such reasoning tasks. This prompts a crucial question: have VLMs effectively tackled the CR challenge? We conjecture that existing CR benchmarks may not adequately push the boundaries of modern VLMs due to the reliance on an LLM-only negative text generation pipeline. Consequently, the negatives produced either appear as outliers from the natural language distribution learned by VLMs' LLM decoders or as improbable within the corresponding image context. To address these limitations, we introduce ConMe -- a compositional reasoning benchmark and a novel data generation pipeline leveraging VLMs to produce `hard CR Q&A'. Through a new concept of VLMs conversing with each other to collaboratively expose their weaknesses, our pipeline autonomously generates, evaluates, and selects challenging compositional reasoning questions, establishing a robust CR benchmark, also subsequently validated manually. Our benchmark provokes a noteworthy, up to 33%, decrease in CR performance compared to preceding benchmarks, reinstating the CR challenge even for state-of-the-art VLMs.
Authors: Francesco Tassone, Luca Maiano, Irene Amerini
Abstract: Generative techniques continue to evolve at an impressively high rate, driven by the hype about these technologies. This rapid advancement severely limits the application of deepfake detectors, which, despite numerous efforts by the scientific community, struggle to achieve sufficiently robust performance against the ever-changing content. To address these limitations, in this paper, we propose an analysis of two continuous learning techniques on a Short and a Long sequence of fake media. Both sequences include a complex and heterogeneous range of deepfakes generated from GANs, computer graphics techniques, and unknown sources. Our study shows that continual learning could be important in mitigating the need for generalizability. In fact, we show that, although with some limitations, continual learning methods help to maintain good performance across the entire training sequence. For these techniques to work in a sufficiently robust way, however, it is necessary that the tasks in the sequence share similarities. In fact, according to our experiments, the order and similarity of the tasks can affect the performance of the models over time. To address this problem, we show that it is possible to group tasks based on their similarity. This small measure allows for a significant improvement even in longer sequences. This result suggests that continual techniques can be combined with the most promising detection methods, allowing them to catch up with the latest generative techniques. In addition to this, we propose an overview of how this learning approach can be integrated into a deepfake detection pipeline for continuous integration and continuous deployment (CI/CD). This allows you to keep track of different funds, such as social networks, new generative tools, or third-party datasets, and through the integration of continuous learning, allows constant maintenance of the detectors.
Authors: Taekbeom Lee, Youngseok Jang, H. Jin Kim
Abstract: Neural implicit representation has attracted attention in 3D reconstruction through various success cases. For further applications such as scene understanding or editing, several works have shown progress towards object compositional reconstruction. Despite their superior performance in observed regions, their performance is still limited in reconstructing objects that are partially observed. To better treat this problem, we introduce category-level neural fields that learn meaningful common 3D information among objects belonging to the same category present in the scene. Our key idea is to subcategorize objects based on their observed shape for better training of the category-level model. Then we take advantage of the neural field to conduct the challenging task of registering partially observed objects by selecting and aligning against representative objects selected by ray-based uncertainty. Experiments on both simulation and real-world datasets demonstrate that our method improves the reconstruction of unobserved parts for several categories.
Authors: Zhensong Xu, Jiangtao Yao, Chengjing Wu, Ting Liu, Luoqi Liu
Abstract: Complex video object segmentation serves as a fundamental task for a wide range of downstream applications such as video editing and automatic data annotation. Here we present the 2nd place solution in the MOSE track of PVUW 2024. To mitigate problems caused by tiny objects, similar objects and fast movements in MOSE. We use instance segmentation to generate extra pretraining data from the valid and test set of MOSE. The segmented instances are combined with objects extracted from COCO to augment the training data and enhance semantic representation of the baseline model. Besides, motion blur is added during training to increase robustness against image blur induced by motion. Finally, we apply test time augmentation (TTA) and memory strategy to the inference stage. Our method ranked 2nd in the MOSE track of PVUW 2024, with a $\mathcal{J}$ of 0.8007, a $\mathcal{F}$ of 0.8683 and a $\mathcal{J}$\&$\mathcal{F}$ of 0.8345.
Authors: Yuanshen Guan, Ruikang Xu, Mingde Yao, Ruisheng Gao, Lizhi Wang, Zhiwei Xiong
Abstract: High dynamic range (HDR) video reconstruction aims to generate HDR videos from low dynamic range (LDR) frames captured with alternating exposures. Most existing works solely rely on the regression-based paradigm, leading to adverse effects such as ghosting artifacts and missing details in saturated regions. In this paper, we propose a diffusion-promoted method for HDR video reconstruction, termed HDR-V-Diff, which incorporates a diffusion model to capture the HDR distribution. As such, HDR-V-Diff can reconstruct HDR videos with realistic details while alleviating ghosting artifacts. However, the direct introduction of video diffusion models would impose massive computational burden. Instead, to alleviate this burden, we first propose an HDR Latent Diffusion Model (HDR-LDM) to learn the distribution prior of single HDR frames. Specifically, HDR-LDM incorporates a tonemapping strategy to compress HDR frames into the latent space and a novel exposure embedding to aggregate the exposure information into the diffusion process. We then propose a Temporal-Consistent Alignment Module (TCAM) to learn the temporal information as a complement for HDR-LDM, which conducts coarse-to-fine feature alignment at different scales among video frames. Finally, we design a Zero-Init Cross-Attention (ZiCA) mechanism to effectively integrate the learned distribution prior and temporal information for generating HDR frames. Extensive experiments validate that HDR-V-Diff achieves state-of-the-art results on several representative datasets.
Authors: James Willoughby, Irina Voiculescu
Abstract: Segmentation has become a crucial pre-processing step to many refined downstream tasks, and particularly so in the medical domain. Even with recent improvements in segmentation models, many segmentation tasks remain difficult. When multiple organs are segmented simultaneously, difficulties are due not only to the limited availability of labelled data, but also to class imbalance. In this work we propose dynamic class-based loss strategies to mitigate the effects of highly imbalanced training data. We show how our approach improves segmentation performance on a challenging Multi-Class 3D Abdominal Organ dataset.
Authors: Sha Luo, Sang Jung Kim, Zening Duan, Kaiping Chen
Abstract: In the evolving landscape of computer vision (CV) technologies, the automatic detection and interpretation of gender and emotion in images is a critical area of study. This paper investigates social biases in CV models, emphasizing the limitations of traditional evaluation metrics such as precision, recall, and accuracy. These metrics often fall short in capturing the complexities of gender and emotion, which are fluid and culturally nuanced constructs. Our study proposes a sociotechnical framework for evaluating CV models, incorporating both technical performance measures and considerations of social fairness. Using a dataset of 5,570 images related to vaccination and climate change, we empirically compared the performance of various CV models, including traditional models like DeepFace and FER, and generative models like GPT-4 Vision. Our analysis involved manually validating the gender and emotional expressions in a subset of images to serve as benchmarks. Our findings reveal that while GPT-4 Vision outperforms other models in technical accuracy for gender classification, it exhibits discriminatory biases, particularly in response to transgender and non-binary personas. Furthermore, the model's emotion detection skew heavily towards positive emotions, with a notable bias towards associating female images with happiness, especially when prompted by male personas. These findings underscore the necessity of developing more comprehensive evaluation criteria that address both validity and discriminatory biases in CV models. Our proposed framework provides guidelines for researchers to critically assess CV tools, ensuring their application in communication research is both ethical and effective. The significant contribution of this study lies in its emphasis on a sociotechnical approach, advocating for CV technologies that support social good and mitigate biases rather than perpetuate them.
Authors: Jordy Van Landeghem, Subhajit Maity, Ayan Banerjee, Matthew Blaschko, Marie-Francine Moens, Josep Llad\'os, Sanket Biswas
Abstract: This work explores knowledge distillation (KD) for visually-rich document (VRD) applications such as document layout analysis (DLA) and document image classification (DIC). While VRD research is dependent on increasingly sophisticated and cumbersome models, the field has neglected to study efficiency via model compression. Here, we design a KD experimentation methodology for more lean, performant models on document understanding (DU) tasks that are integral within larger task pipelines. We carefully selected KD strategies (response-based, feature-based) for distilling knowledge to and from backbones with different architectures (ResNet, ViT, DiT) and capacities (base, small, tiny). We study what affects the teacher-student knowledge gap and find that some methods (tuned vanilla KD, MSE, SimKD with an apt projector) can consistently outperform supervised student training. Furthermore, we design downstream task setups to evaluate covariate shift and the robustness of distilled DLA models on zero-shot layout-aware document visual question answering (DocVQA). DLA-KD experiments result in a large mAP knowledge gap, which unpredictably translates to downstream robustness, accentuating the need to further explore how to efficiently obtain more semantic document layout awareness.
Authors: Carlos Garcia Ling, Konrad Tollmar, Linus Gisslen
Abstract: In this paper, we present a method using Deep Convolutional Neural Networks (DCNNs) to detect common glitches in video games. The problem setting consists of an image (800x800 RGB) as input to be classified into one of five defined classes, normal image, or one of four different kinds of glitches (stretched, low resolution, missing and placeholder textures). Using a supervised approach, we train a ShuffleNetV2 using generated data. This work focuses on detecting texture graphical anomalies achieving arguably good performance with an accuracy of 86.8\%, detecting 88\% of the glitches with a false positive rate of 8.7\%, and with the models being able to generalize and detect glitches even in unseen objects. We apply a confidence measure as well to tackle the issue with false positives as well as an effective way of aggregating images to achieve better detection in production. The main use of this work is the partial automatization of graphical testing in the final stages of video game development.
Authors: Naoto Inoue, Kento Masui, Wataru Shimoda, Kota Yamaguchi
Abstract: Automatic generation of graphic designs has recently received considerable attention. However, the state-of-the-art approaches are complex and rely on proprietary datasets, which creates reproducibility barriers. In this paper, we propose an open framework for automatic graphic design called OpenCOLE, where we build a modified version of the pioneering COLE and train our model exclusively on publicly available datasets. Based on GPT4V evaluations, our model shows promising performance comparable to the original COLE. We release the pipeline and training results to encourage open development.
Authors: Orest Kupyn, Christian Rupprecht
Abstract: We present a method for expanding a dataset by incorporating knowledge from the wide distribution of pre-trained latent diffusion models. Data augmentations typically incorporate inductive biases about the image formation process into the training (e.g. translation, scaling, colour changes, etc.). Here, we go beyond simple pixel transformations and introduce the concept of instance-level data augmentation by repainting parts of the image at the level of object instances. The method combines a conditional diffusion model with depth and edge maps control conditioning to seamlessly repaint individual objects inside the scene, being applicable to any segmentation or detection dataset. Used as a data augmentation method, it improves the performance and generalization of the state-of-the-art salient object detection, semantic segmentation and object detection models. By redrawing all privacy-sensitive instances (people, license plates, etc.), the method is also applicable for data anonymization. We also release fully synthetic and anonymized expansions for popular datasets: COCO, Pascal VOC and DUTS.
Authors: Dujuan Zhou, Zizhao Yuan
Abstract: Spline wavelets have shown favorable characteristics for localizing in both time and frequency. In this paper, we propose a new biorthogonal cubic special spline wavelet (BCSSW), based on the Cohen-Daubechies-Feauveau wavelet construction method and the cubic special spline algorithm. BCSSW has better properties in compact support, symmetry, and frequency domain characteristics. However, current mainstream detection operators usually ignore the uncertain representation of regional pixels and global structures. To solve these problems, we propose a structural uncertainty-aware and multi-structure operator fusion detection algorithm (EDBSW) based on a new BCSSW spline wavelet. By constructing a spline wavelet that efficiently handles edge effects, we utilize structural uncertainty-aware modulus maxima to detect highly uncertain edge samples. The proposed wavelet detection operator utilizes the multi-structure morphological operator and fusion reconstruction strategy to effectively address anti-noise processing and edge information of different frequencies. Numerous experiments have demonstrated its excellent performance in reducing noise and capturing edge structure details.
Authors: Dongsu Zhang, Francis Williams, Zan Gojcic, Karsten Kreis, Sanja Fidler, Young Min Kim, Amlan Kar
Abstract: We aim to generate fine-grained 3D geometry from large-scale sparse LiDAR scans, abundantly captured by autonomous vehicles (AV). Contrary to prior work on AV scene completion, we aim to extrapolate fine geometry from unlabeled and beyond spatial limits of LiDAR scans, taking a step towards generating realistic, high-resolution simulation-ready 3D street environments. We propose hierarchical Generative Cellular Automata (hGCA), a spatially scalable conditional 3D generative model, which grows geometry recursively with local kernels following, in a coarse-to-fine manner, equipped with a light-weight planner to induce global consistency. Experiments on synthetic scenes show that hGCA generates plausible scene geometry with higher fidelity and completeness compared to state-of-the-art baselines. Our model generalizes strongly from sim-to-real, qualitatively outperforming baselines on the Waymo-open dataset. We also show anecdotal evidence of the ability to create novel objects from real-world geometric cues even when trained on limited synthetic content. More results and details can be found on https://research.nvidia.com/labs/toronto-ai/hGCA/.
Authors: Yasod Ginige, Ransika Gunasekara, Darsha Hewavitharana, Manjula Ariyarathne, Ranga Rodrigo, Peshala Jayasekara
Abstract: Maritime surveillance is vital to mitigate illegal activities such as drug smuggling, illegal fishing, and human trafficking. Vision-based maritime surveillance is challenging mainly due to visibility issues at night, which results in failures in re-identifying vessels and detecting suspicious activities. In this paper, we introduce a thermal, vision-based approach for maritime surveillance with object tracking, vessel re-identification, and suspicious activity detection capabilities. For vessel re-identification, we propose a novel viewpoint-independent algorithm which compares features of the sides of the vessel separately (separate side-spaces) leveraging shape information in the absence of color features. We propose techniques to adapt tracking and activity detection algorithms for the thermal domain and train them using a thermal dataset we created. This dataset will be the first publicly available benchmark dataset for thermal maritime surveillance. Our system is capable of re-identifying vessels with an 81.8% Top1 score and identifying suspicious activities with a 72.4\% frame mAP score; a new benchmark for each task in the thermal domain.
Authors: Yitao Xu, Tong Zhang, Sabine S\"usstrunk
Abstract: Vision Transformers (ViTs) have demonstrated remarkable performance in image classification tasks, particularly when equipped with local information via region attention or convolutions. While such architectures improve the feature aggregation from different granularities, they often fail to contribute to the robustness of the networks. Neural Cellular Automata (NCA) enables the modeling of global cell representations through local interactions, with its training strategies and architecture design conferring strong generalization ability and robustness against noisy inputs. In this paper, we propose Adaptor Neural Cellular Automata (AdaNCA) for Vision Transformer that uses NCA as plug-in-play adaptors between ViT layers, enhancing ViT's performance and robustness against adversarial samples as well as out-of-distribution inputs. To overcome the large computational overhead of standard NCAs, we propose Dynamic Interaction for more efficient interaction learning. Furthermore, we develop an algorithm for identifying the most effective insertion points for AdaNCA based on our analysis of AdaNCA placement and robustness improvement. With less than a 3% increase in parameters, AdaNCA contributes to more than 10% absolute improvement in accuracy under adversarial attacks on the ImageNet1K benchmark. Moreover, we demonstrate with extensive evaluations across 8 robustness benchmarks and 4 ViT architectures that AdaNCA, as a plug-in-play module, consistently improves the robustness of ViTs.
Authors: Yunhao Li, Xiaoqiong Liu, Luke Liu, Heng Fan, Libo Zhang
Abstract: Vision-Language MOT is a crucial tracking problem and has drawn increasing attention recently. It aims to track objects based on human language commands, replacing the traditional use of templates or pre-set information from training sets in conventional tracking tasks. Despite various efforts, a key challenge lies in the lack of a clear understanding of why language is used for tracking, which hinders further development in this field. In this paper, we address this challenge by introducing Language-Guided MOT, a unified task framework, along with a corresponding large-scale benchmark, termed LaMOT, which encompasses diverse scenarios and language descriptions. Specially, LaMOT comprises 1,660 sequences from 4 different datasets and aims to unify various Vision-Language MOT tasks while providing a standardized evaluation platform. To ensure high-quality annotations, we manually assign appropriate descriptive texts to each target in every video and conduct careful inspection and correction. To the best of our knowledge, LaMOT is the first benchmark dedicated to Language-Guided MOT. Additionally, we propose a simple yet effective tracker, termed LaMOTer. By establishing a unified task framework, providing challenging benchmarks, and offering insights for future algorithm design and evaluation, we expect to contribute to the advancement of research in Vision-Language MOT. We will release the data at https://github.com/Nathan-Li123/LaMOT.
Authors: Nikolaos-Antonios Ypsilantis, Kaifeng Chen, Andr\'e Araujo, Ond\v{r}ej Chum
Abstract: Universal image representations are critical in enabling real-world fine-grained and instance-level recognition applications, where objects and entities from any domain must be identified at large scale. Despite recent advances, existing methods fail to capture important domain-specific knowledge, while also ignoring differences in data distribution across different domains. This leads to a large performance gap between efficient universal solutions and expensive approaches utilising a collection of specialist models, one for each domain. In this work, we make significant strides towards closing this gap, by introducing a new learning technique, dubbed UDON (Universal Dynamic Online DistillatioN). UDON employs multi-teacher distillation, where each teacher is specialized in one domain, to transfer detailed domain-specific knowledge into the student universal embedding. UDON's distillation approach is not only effective, but also very efficient, by sharing most model parameters between the student and all teachers, where all models are jointly trained in an online manner. UDON also comprises a sampling technique which adapts the training process to dynamically allocate batches to domains which are learned slower and require more frequent processing. This boosts significantly the learning of complex domains which are characterised by a large number of classes and long-tail distributions. With comprehensive experiments, we validate each component of UDON, and showcase significant improvements over the state of the art in the recent UnED benchmark. Code: https://github.com/nikosips/UDON .
Authors: Hai Ci, Yiren Song, Pei Yang, Jinheng Xie, Mike Zheng Shou
Abstract: Watermarking is crucial for protecting the copyright of AI-generated images. We propose WMAdapter, a diffusion model watermark plugin that takes user-specified watermark information and allows for seamless watermark imprinting during the diffusion generation process. WMAdapter is efficient and robust, with a strong emphasis on high generation quality. To achieve this, we make two key designs: (1) We develop a contextual adapter structure that is lightweight and enables effective knowledge transfer from heavily pretrained post-hoc watermarking models. (2) We introduce an extra finetuning step and design a hybrid finetuning strategy to further improve image quality and eliminate tiny artifacts. Empirical results demonstrate that WMAdapter offers strong flexibility, exceptional image generation quality and competitive watermark robustness.
Authors: Abdul Mohaimen Al Radi, Prothito Shovon Majumder, Syed Mumtahin Mahmud, Mahdi Mohd Hossain Noki, Md. Haider Ali, Md. Mosaddek Khan
Abstract: Blind image deblurring is the process of deriving a sharp image and a blur kernel from a blurred image. Blurry images are typically modeled as the convolution of a sharp image with a blur kernel, necessitating the estimation of the unknown blur kernel to perform blind image deblurring effectively. Existing approaches primarily focus on domain-specific features of images, such as salient edges, dark channels, and light streaks. These features serve as probabilistic priors to enhance the estimation of the blur kernel. For improved generality, we propose a novel prior (ReLU sparsity prior) that estimates blur kernel effectively across all distributions of images (natural, facial, text, low-light, saturated etc). Our approach demonstrates superior efficiency, with inference times up to three times faster, while maintaining high accuracy in PSNR, SSIM, and error ratio metrics. We also observe noticeable improvement in the performance of the state-of-the-art architectures (in terms of aforementioned metrics) in deep learning based approaches when our method is used as a post-processing unit.
Authors: Sanket Biswas, Rajiv Jain, Vlad I. Morariu, Jiuxiang Gu, Puneet Mathur, Curtis Wigington, Tong Sun, Josep Llad\'os
Abstract: While the generation of document layouts has been extensively explored, comprehensive document generation encompassing both layout and content presents a more complex challenge. This paper delves into this advanced domain, proposing a novel approach called DocSynthv2 through the development of a simple yet effective autoregressive structured model. Our model, distinct in its integration of both layout and textual cues, marks a step beyond existing layout-generation approaches. By focusing on the relationship between the structural elements and the textual content within documents, we aim to generate cohesive and contextually relevant documents without any reliance on visual components. Through experimental studies on our curated benchmark for the new task, we demonstrate the ability of our model combining layout and textual information in enhancing the generation quality and relevance of documents, opening new pathways for research in document creation and automated design. Our findings emphasize the effectiveness of autoregressive models in handling complex document generation tasks.
Authors: Shiwei Wu, Chao Zhang, Joya Chen, Tong Xu, Likang Wu, Yao Hu, Enhong Chen
Abstract: People's social relationships are often manifested through their surroundings, with certain objects or interactions acting as symbols for specific relationships, e.g., wedding rings, roses, hugs, or holding hands. This brings unique challenges to recognizing social relationships, requiring understanding and capturing the essence of these contexts from visual appearances. However, current methods of social relationship understanding rely on the basic classification paradigm of detected persons and objects, which fails to understand the comprehensive context and often overlooks decisive social factors, especially subtle visual cues. To highlight the social-aware context and intricate details, we propose a novel approach that recognizes \textbf{Con}textual \textbf{So}cial \textbf{R}elationships (\textbf{ConSoR}) from a social cognitive perspective. Specifically, to incorporate social-aware semantics, we build a lightweight adapter upon the frozen CLIP to learn social concepts via our novel multi-modal side adapter tuning mechanism. Further, we construct social-aware descriptive language prompts (e.g., scene, activity, objects, emotions) with social relationships for each image, and then compel ConSoR to concentrate more intensively on the decisive visual social factors via visual-linguistic contrasting. Impressively, ConSoR outperforms previous methods with a 12.2\% gain on the People-in-Social-Context (PISC) dataset and a 9.8\% increase on the People-in-Photo-Album (PIPA) benchmark. Furthermore, we observe that ConSoR excels at finding critical visual evidence to reveal social relationships.
Authors: Weizhao He, Yang Zhang, Wei Zhuo, Linlin Shen, Jiaqi Yang, Songhe Deng, Liang Sun
Abstract: Few-shot semantic segmentation (FSS) endeavors to segment unseen classes with only a few labeled samples. Current FSS methods are commonly built on the assumption that their training and application scenarios share similar domains, and their performances degrade significantly while applied to a distinct domain. To this end, we propose to leverage the cutting-edge foundation model, the Segment Anything Model (SAM), for generalization enhancement. The SAM however performs unsatisfactorily on domains that are distinct from its training data, which primarily comprise natural scene images, and it does not support automatic segmentation of specific semantics due to its interactive prompting mechanism. In our work, we introduce APSeg, a novel auto-prompt network for cross-domain few-shot semantic segmentation (CD-FSS), which is designed to be auto-prompted for guiding cross-domain segmentation. Specifically, we propose a Dual Prototype Anchor Transformation (DPAT) module that fuses pseudo query prototypes extracted based on cycle-consistency with support prototypes, allowing features to be transformed into a more stable domain-agnostic space. Additionally, a Meta Prompt Generator (MPG) module is introduced to automatically generate prompt embeddings, eliminating the need for manual visual prompts. We build an efficient model which can be applied directly to target domains without fine-tuning. Extensive experiments on four cross-domain datasets show that our model outperforms the state-of-the-art CD-FSS method by 5.24% and 3.10% in average accuracy on 1-shot and 5-shot settings, respectively.
Authors: Tianqi Chen, Jun Hou, Yinchi Zhou, Huidong Xie, Xiongchao Chen, Qiong Liu, Xueqi Guo, Menghua Xia, James S. Duncan, Chi Liu, Bo Zhou
Abstract: Positron Emission Tomography (PET) is an important clinical imaging tool but inevitably introduces radiation hazards to patients and healthcare providers. Reducing the tracer injection dose and eliminating the CT acquisition for attenuation correction can reduce the overall radiation dose, but often results in PET with high noise and bias. Thus, it is desirable to develop 3D methods to translate the non-attenuation-corrected low-dose PET (NAC-LDPET) into attenuation-corrected standard-dose PET (AC-SDPET). Recently, diffusion models have emerged as a new state-of-the-art deep learning method for image-to-image translation, better than traditional CNN-based methods. However, due to the high computation cost and memory burden, it is largely limited to 2D applications. To address these challenges, we developed a novel 2.5D Multi-view Averaging Diffusion Model (MADM) for 3D image-to-image translation with application on NAC-LDPET to AC-SDPET translation. Specifically, MADM employs separate diffusion models for axial, coronal, and sagittal views, whose outputs are averaged in each sampling step to ensure the 3D generation quality from multiple views. To accelerate the 3D sampling process, we also proposed a strategy to use the CNN-based 3D generation as a prior for the diffusion model. Our experimental results on human patient studies suggested that MADM can generate high-quality 3D translation images, outperforming previous CNN-based and Diffusion-based baseline methods.
Authors: Juncheng Wu, Zhangkai Ni, Hanli Wang, Wenhan Yang, Yuyin Zhou, Shiqi Wang
Abstract: Image deep features extracted by pre-trained networks are known to contain rich and informative representations. In this paper, we present Deep Degradation Response (DDR), a method to quantify changes in image deep features under varying degradation conditions. Specifically, our approach facilitates flexible and adaptive degradation, enabling the controlled synthesis of image degradation through text-driven prompts. Extensive evaluations demonstrate the versatility of DDR as an image descriptor, with strong correlations observed with key image attributes such as complexity, colorfulness, sharpness, and overall quality. Moreover, we demonstrate the efficacy of DDR across a spectrum of applications. It excels as a blind image quality assessment metric, outperforming existing methodologies across multiple datasets. Additionally, DDR serves as an effective unsupervised learning objective in image restoration tasks, yielding notable advancements in image deblurring and single-image super-resolution. Our code will be made available.
Authors: Michele Mazzamuto, Antonino Furnari, Giovanni Maria Farinella
Abstract: In this paper, we address the challenge of unsupervised mistake detection in egocentric video through the analysis of gaze signals, a critical component for advancing user assistance in smart glasses. Traditional supervised methods, reliant on manually labeled mistakes, suffer from domain-dependence and scalability issues. This research introduces an unsupervised method for detecting mistakes in videos of human activities, overcoming the challenges of domain-specific requirements and the necessity for annotated data. By analyzing unusual gaze patterns that signal user disorientation during tasks, we propose a gaze completion model that forecasts eye gaze trajectories from incomplete inputs. The difference between the anticipated and observed gaze paths acts as an indicator for identifying errors. Our method is validated on the EPIC-Tent dataset, showing its superiority compared to current one-class supervised and unsupervised techniques.
Authors: Maximilian Pittner, Joel Janai, Alexandru P. Condurache
Abstract: Monocular 3D lane detection has become a fundamental problem in the context of autonomous driving, which comprises the tasks of finding the road surface and locating lane markings. One major challenge lies in a flexible but robust line representation capable of modeling complex lane structures, while still avoiding unpredictable behavior. While previous methods rely on fully data-driven approaches, we instead introduce a novel approach LaneCPP that uses a continuous 3D lane detection model leveraging physical prior knowledge about the lane structure and road geometry. While our sophisticated lane model is capable of modeling complex road structures, it also shows robust behavior since physical constraints are incorporated by means of a regularization scheme that can be analytically applied to our parametric representation. Moreover, we incorporate prior knowledge about the road geometry into the 3D feature space by modeling geometry-aware spatial features, guiding the network to learn an internal road surface representation. In our experiments, we show the benefits of our contributions and prove the meaningfulness of using priors to make 3D lane detection more robust. The results show that LaneCPP achieves state-of-the-art performance in terms of F-Score and geometric errors.
Authors: Xinzhi Mu, Li Chen, Bohan Chen, Shuyang Gu, Jianmin Bao, Dong Chen, Ji Li, Yuhui Yuan
Abstract: Recently, the application of modern diffusion-based text-to-image generation models for creating artistic fonts, traditionally the domain of professional designers, has garnered significant interest. Diverging from the majority of existing studies that concentrate on generating artistic typography, our research aims to tackle a novel and more demanding challenge: the generation of text effects for multilingual fonts. This task essentially requires generating coherent and consistent visual content within the confines of a font-shaped canvas, as opposed to a traditional rectangular canvas. To address this task, we introduce a novel shape-adaptive diffusion model capable of interpreting the given shape and strategically planning pixel distributions within the irregular canvas. To achieve this, we curate a high-quality shape-adaptive image-text dataset and incorporate the segmentation mask as a visual condition to steer the image generation process within the irregular-canvas. This approach enables the traditionally rectangle canvas-based diffusion model to produce the desired concepts in accordance with the provided geometric shapes. Second, to maintain consistency across multiple letters, we also present a training-free, shape-adaptive effect transfer method for transferring textures from a generated reference letter to others. The key insights are building a font effect noise prior and propagating the font effect information in a concatenated latent space. The efficacy of our FontStudio system is confirmed through user preference studies, which show a marked preference (78% win-rates on aesthetics) for our system even when compared to the latest unrivaled commercial product, Adobe Firefly.
Authors: Jiannan Wu, Muyan Zhong, Sen Xing, Zeqiang Lai, Zhaoyang Liu, Wenhai Wang, Zhe Chen, Xizhou Zhu, Lewei Lu, Tong Lu, Ping Luo, Yu Qiao, Jifeng Dai
Abstract: We present VisionLLM v2, an end-to-end generalist multimodal large model (MLLM) that unifies visual perception, understanding, and generation within a single framework. Unlike traditional MLLMs limited to text output, VisionLLM v2 significantly broadens its application scope. It excels not only in conventional visual question answering (VQA) but also in open-ended, cross-domain vision tasks such as object localization, pose estimation, and image generation and editing. To this end, we propose a new information transmission mechanism termed "super link", as a medium to connect MLLM with task-specific decoders. It not only allows flexible transmission of task information and gradient feedback between the MLLM and multiple downstream decoders but also effectively resolves training conflicts in multi-tasking scenarios. In addition, to support the diverse range of tasks, we carefully collected and combed training data from hundreds of public vision and vision-language tasks. In this way, our model can be joint-trained end-to-end on hundreds of vision language tasks and generalize to these tasks using a set of shared parameters through different user prompts, achieving performance comparable to task-specific models. We believe VisionLLM v2 will offer a new perspective on the generalization of MLLMs.
Authors: Xuehai He, Weixi Feng, Kaizhi Zheng, Yujie Lu, Wanrong Zhu, Jiachen Li, Yue Fan, Jianfeng Wang, Linjie Li, Zhengyuan Yang, Kevin Lin, William Yang Wang, Lijuan Wang, Xin Eric Wang
Abstract: Multimodal Language Language Models (MLLMs) demonstrate the emerging abilities of "world models" -- interpreting and reasoning about complex real-world dynamics. To assess these abilities, we posit videos are the ideal medium, as they encapsulate rich representations of real-world dynamics and causalities. To this end, we introduce MMWorld, a new benchmark for multi-discipline, multi-faceted multimodal video understanding. MMWorld distinguishes itself from previous video understanding benchmarks with two unique advantages: (1) multi-discipline, covering various disciplines that often require domain expertise for comprehensive understanding; (2) multi-faceted reasoning, including explanation, counterfactual thinking, future prediction, etc. MMWorld consists of a human-annotated dataset to evaluate MLLMs with questions about the whole videos and a synthetic dataset to analyze MLLMs within a single modality of perception. Together, MMWorld encompasses 1,910 videos across seven broad disciplines and 69 subdisciplines, complete with 6,627 question-answer pairs and associated captions. The evaluation includes 2 proprietary and 10 open-source MLLMs, which struggle on MMWorld (e.g., GPT-4V performs the best with only 52.3\% accuracy), showing large room for improvement. Further ablation studies reveal other interesting findings such as models' different skill sets from humans. We hope MMWorld can serve as an essential step towards world model evaluation in videos.
Authors: Qingyun Li, Zhe Chen, Weiyun Wang, Wenhai Wang, Shenglong Ye, Zhenjiang Jin, Guanzhou Chen, Yinan He, Zhangwei Gao, Erfei Cui, Jiashuo Yu, Hao Tian, Jiasheng Zhou, Chao Xu, Bin Wang, Xingjian Wei, Wei Li, Wenjian Zhang, Bo Zhang, Pinlong Cai, Licheng Wen, Xiangchao Yan, Pei Chu, Yi Wang, Min Dou, Changyao Tian, Xizhou Zhu, Lewei Lu, Yushi Chen, Junjun He, Tong Lu, Yali Wang, Limin Wang, Dahua Lin, Yu Qiao, Botian Shi, Conghui He, Jifeng Dai
Abstract: Image-text interleaved data, consisting of multiple images and texts arranged in a natural document format, aligns with the presentation paradigm of internet data and closely resembles human reading habits. Recent studies have shown that such data aids multimodal in-context learning and maintains the capabilities of large language models during multimodal fine-tuning. However, the limited scale and diversity of current image-text interleaved data restrict the development of multimodal large language models. In this paper, we introduce OmniCorpus, a 10 billion-scale image-text interleaved dataset. Using an efficient data engine, we filter and extract large-scale high-quality documents, which contain 8.6 billion images and 1,696 billion text tokens. Compared to counterparts (e.g., MMC4, OBELICS), our dataset 1) has 15 times larger scales while maintaining good data quality; 2) features more diverse sources, including both English and non-English websites as well as video-centric websites; 3) is more flexible, easily degradable from an image-text interleaved format to pure text corpus and image-text pairs. Through comprehensive analysis and experiments, we validate the quality, usability, and effectiveness of the proposed dataset. We hope this could provide a solid data foundation for future multimodal model research. Code and data are released at https://github.com/OpenGVLab/OmniCorpus.
Authors: Ayush Roy, Payel Pramanik, Dmitrii Kaplun, Sergei Antonov, Ram Sarkar
Abstract: Accurate nuclei segmentation in histopathological images is crucial for cancer diagnosis. Automating this process offers valuable support to clinical experts, as manual annotation is time-consuming and prone to human errors. However, automating nuclei segmentation presents challenges due to uncertain cell boundaries, intricate staining, and diverse structures. In this paper, we present a segmentation approach that combines the U-Net architecture with a DenseNet-121 backbone, harnessing the strengths of both to capture comprehensive contextual and spatial information. Our model introduces the Wavelet-guided channel attention module to enhance cell boundary delineation, along with a learnable weighted global attention module for channel-specific attention. The decoder module, composed of an upsample block and convolution block, further refines segmentation in handling staining patterns. The experimental results conducted on two publicly accessible histopathology datasets, namely Monuseg and TNBC, underscore the superiority of our proposed model, demonstrating its potential to advance histopathological image analysis and cancer diagnosis. The code is made available at: https://github.com/AyushRoy2001/AWGUNET.
Authors: Benjamin Biggs, Arjun Seshadri, Yang Zou, Achin Jain, Aditya Golatkar, Yusheng Xie, Alessandro Achille, Ashwin Swaminathan, Stefano Soatto
Abstract: We present Diffusion Soup, a compartmentalization method for Text-to-Image Generation that averages the weights of diffusion models trained on sharded data. By construction, our approach enables training-free continual learning and unlearning with no additional memory or inference costs, since models corresponding to data shards can be added or removed by re-averaging. We show that Diffusion Soup samples from a point in weight space that approximates the geometric mean of the distributions of constituent datasets, which offers anti-memorization guarantees and enables zero-shot style mixing. Empirically, Diffusion Soup outperforms a paragon model trained on the union of all data shards and achieves a 30% improvement in Image Reward (.34 $\to$ .44) on domain sharded data, and a 59% improvement in IR (.37 $\to$ .59) on aesthetic data. In both cases, souping also prevails in TIFA score (respectively, 85.5 $\to$ 86.5 and 85.6 $\to$ 86.8). We demonstrate robust unlearning -- removing any individual domain shard only lowers performance by 1% in IR (.45 $\to$ .44) -- and validate our theoretical insights on anti-memorization using real data. Finally, we showcase Diffusion Soup's ability to blend the distinct styles of models finetuned on different shards, resulting in the zero-shot generation of hybrid styles.
Authors: Parsa Mirdehghan, Brandon Buscaino, Maxx Wu, Doug Charlton, Mohammad E. Mousa-Pasandi, Kiriakos N. Kutulakos, David B. Lindell
Abstract: The advent of the digital age has driven the development of coherent optical modems -- devices that modulate the amplitude and phase of light in multiple polarization states. These modems transmit data through fiber optic cables that are thousands of kilometers in length at data rates exceeding one terabit per second. This remarkable technology is made possible through near-THz-rate programmable control and sensing of the full optical wavefield. While coherent optical modems form the backbone of telecommunications networks around the world, their extraordinary capabilities also provide unique opportunities for imaging. Here, we introduce full-wavefield lidar: a new imaging modality that repurposes off-the-shelf coherent optical modems to simultaneously measure distance, axial velocity, and polarization. We demonstrate this modality by combining a 74 GHz-bandwidth coherent optical modem with free-space coupling optics and scanning mirrors. We develop a time-resolved image formation model for this system and formulate a maximum-likelihood reconstruction algorithm to recover depth, velocity, and polarization information at each scene point from the modem's raw transmitted and received symbols. Compared to existing lidars, full-wavefield lidar promises improved mm-scale ranging accuracy from brief, microsecond exposure times, reliable velocimetry, and robustness to intererence from ambient light or other lidar signals.
Authors: Yaoteng Tan, Zikui Cai, M. Salman Asif
Abstract: We introduce transformation-dependent adversarial attacks, a new class of threats where a single additive perturbation can trigger diverse, controllable mis-predictions by systematically transforming the input (e.g., scaling, blurring, compression). Unlike traditional attacks with static effects, our perturbations embed metamorphic properties to enable different adversarial attacks as a function of the transformation parameters. We demonstrate the transformation-dependent vulnerability across models (e.g., convolutional networks and vision transformers) and vision tasks (e.g., image classification and object detection). Our proposed geometric and photometric transformations enable a range of targeted errors from one crafted input (e.g., higher than 90% attack success rate for classifiers). We analyze effects of model architecture and type/variety of transformations on attack effectiveness. This work forces a paradigm shift by redefining adversarial inputs as dynamic, controllable threats. We highlight the need for robust defenses against such multifaceted, chameleon-like perturbations that current techniques are ill-prepared for.
Authors: Wei-Tung Lin, Yong-Xiang Lin, Jyun-Wei Chen, Kai-Lung Hua
Abstract: Underwater Image Enhancement (UIE) is critical for marine research and exploration but hindered by complex color distortions and severe blurring. Recent deep learning-based methods have achieved remarkable results, yet these methods struggle with high computational costs and insufficient global modeling, resulting in locally under- or over- adjusted regions. We present PixMamba, a novel architecture, designed to overcome these challenges by leveraging State Space Models (SSMs) for efficient global dependency modeling. Unlike convolutional neural networks (CNNs) with limited receptive fields and transformer networks with high computational costs, PixMamba efficiently captures global contextual information while maintaining computational efficiency. Our dual-level strategy features the patch-level Efficient Mamba Net (EMNet) for reconstructing enhanced image feature and the pixel-level PixMamba Net (PixNet) to ensure fine-grained feature capturing and global consistency of enhanced image that were previously difficult to obtain. PixMamba achieves state-of-the-art performance across various underwater image datasets and delivers visually superior results. Code is available at: https://github.com/weitunglin/pixmamba.
Authors: Quanfeng Lu, Wenqi Shao, Zitao Liu, Fanqing Meng, Boxuan Li, Botong Chen, Siyuan Huang, Kaipeng Zhang, Yu Qiao, Ping Luo
Abstract: Smartphone users often navigate across multiple applications (apps) to complete tasks such as sharing content between social media platforms. Autonomous Graphical User Interface (GUI) navigation agents can enhance user experience in communication, entertainment, and productivity by streamlining workflows and reducing manual intervention. However, prior GUI agents often trained with datasets comprising simple tasks that can be completed within a single app, leading to poor performance in cross-app navigation. To address this problem, we introduce GUI Odyssey, a comprehensive dataset for training and evaluating cross-app navigation agents. GUI Odyssey consists of 7,735 episodes from 6 mobile devices, spanning 6 types of cross-app tasks, 201 apps, and 1.4K app combos. Leveraging GUI Odyssey, we developed OdysseyAgent, a multimodal cross-app navigation agent by fine-tuning the Qwen-VL model with a history resampling module. Extensive experiments demonstrate OdysseyAgent's superior accuracy compared to existing models. For instance, OdysseyAgent surpasses fine-tuned Qwen-VL and zero-shot GPT-4V by 1.44\% and 55.49\% in-domain accuracy, and 2.29\% and 48.14\% out-of-domain accuracy on average. The dataset and code will be released in \url{https://github.com/OpenGVLab/GUI-Odyssey}.
Authors: Kam Woh Ng, Xiatian Zhu, Yi-Zhe Song, Tao Xiang
Abstract: Existing fine-grained hashing methods typically lack code interpretability as they compute hash code bits holistically using both global and local features. To address this limitation, we propose ConceptHash, a novel method that achieves sub-code level interpretability. In ConceptHash, each sub-code corresponds to a human-understandable concept, such as an object part, and these concepts are automatically discovered without human annotations. Specifically, we leverage a Vision Transformer architecture and introduce concept tokens as visual prompts, along with image patch tokens as model inputs. Each concept is then mapped to a specific sub-code at the model output, providing natural sub-code interpretability. To capture subtle visual differences among highly similar sub-categories (e.g., bird species), we incorporate language guidance to ensure that the learned hash codes are distinguishable within fine-grained object classes while maintaining semantic alignment. This approach allows us to develop hash codes that exhibit similarity within families of species while remaining distinct from species in other families. Extensive experiments on four fine-grained image retrieval benchmarks demonstrate that ConceptHash outperforms previous methods by a significant margin, offering unique sub-code interpretability as an additional benefit. Code at: https://github.com/kamwoh/concepthash.
Authors: Maxime Pietrantoni, Gabriela Csurka, Martin Humenberger, Torsten Sattler
Abstract: Visual localization techniques rely upon some underlying scene representation to localize against. These representations can be explicit such as 3D SFM map or implicit, such as a neural network that learns to encode the scene. The former requires sparse feature extractors and matchers to build the scene representation. The latter might lack geometric grounding not capturing the 3D structure of the scene well enough. This paper proposes to jointly learn the scene representation along with a 3D dense feature field and a 2D feature extractor whose outputs are embedded in the same metric space. Through a contrastive framework we align this volumetric field with the image-based extractor and regularize the latter with a ranking loss from learned surface information. We learn the underlying geometry of the scene with an implicit field through volumetric rendering and design our feature field to leverage intermediate geometric information encoded in the implicit field. The resulting features are discriminative and robust to viewpoint change while maintaining rich encoded information. Visual localization is then achieved by aligning the image-based features and the rendered volumetric features. We show the effectiveness of our approach on real-world scenes, demonstrating that our approach outperforms prior and concurrent work on leveraging implicit scene representations for localization.
Authors: Zhao Mandi, Yijia Weng, Dominik Bauer, Shuran Song
Abstract: We present Real2Code, a novel approach to reconstructing articulated objects via code generation. Given visual observations of an object, we first reconstruct its part geometry using an image segmentation model and a shape completion model. We then represent the object parts with oriented bounding boxes, which are input to a fine-tuned large language model (LLM) to predict joint articulation as code. By leveraging pre-trained vision and language models, our approach scales elegantly with the number of articulated parts, and generalizes from synthetic training data to real world objects in unstructured environments. Experimental results demonstrate that Real2Code significantly outperforms previous state-of-the-art in reconstruction accuracy, and is the first approach to extrapolate beyond objects' structural complexity in the training set, and reconstructs objects with up to 10 articulated parts. When incorporated with a stereo reconstruction model, Real2Code also generalizes to real world objects from a handful of multi-view RGB images, without the need for depth or camera information.
Authors: Yuxuan Xue, Xianghui Xie, Riccardo Marin, Gerard Pons-Moll
Abstract: Creating realistic avatars from a single RGB image is an attractive yet challenging problem. Due to its ill-posed nature, recent works leverage powerful prior from 2D diffusion models pretrained on large datasets. Although 2D diffusion models demonstrate strong generalization capability, they cannot provide multi-view shape priors with guaranteed 3D consistency. We propose Human 3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion. Our key insight is that 2D multi-view diffusion and 3D reconstruction models provide complementary information for each other, and by coupling them in a tight manner, we can fully leverage the potential of both models. We introduce a novel image-conditioned generative 3D Gaussian Splats reconstruction model that leverages the priors from 2D multi-view diffusion models, and provides an explicit 3D representation, which further guides the 2D reverse sampling process to have better 3D consistency. Experiments show that our proposed framework outperforms state-of-the-art methods and enables the creation of realistic avatars from a single RGB image, achieving high-fidelity in both geometry and appearance. Extensive ablations also validate the efficacy of our design, (1) multi-view 2D priors conditioning in generative 3D reconstruction and (2) consistency refinement of sampling trajectory via the explicit 3D representation. Our code and models will be released on https://yuxuan-xue.com/human-3diffusion.
Authors: Junbao Zhou, Ziqi Pang, Yu-Xiong Wang
Abstract: With recent video object segmentation (VOS) benchmarks evolving to challenging scenarios, we revisit a simple but overlooked strategy: restricting the size of memory banks. This diverges from the prevalent practice of expanding memory banks to accommodate extensive historical information. Our specially designed "memory deciphering" study offers a pivotal insight underpinning such a strategy: expanding memory banks, while seemingly beneficial, actually increases the difficulty for VOS modules to decode relevant features due to the confusion from redundant information. By restricting memory banks to a limited number of essential frames, we achieve a notable improvement in VOS accuracy. This process balances the importance and freshness of frames to maintain an informative memory bank within a bounded capacity. Additionally, restricted memory banks reduce the training-inference discrepancy in memory lengths compared with continuous expansion. This fosters new opportunities in temporal reasoning and enables us to introduce the previously overlooked "temporal positional embedding." Finally, our insights are embodied in "RMem" ("R" for restricted), a simple yet effective VOS modification that excels at challenging VOS scenarios and establishes new state of the art for object state changes (on the VOST dataset) and long videos (on the Long Videos dataset). Our code and demo are available at https://restricted-memory.github.io/.
Authors: Xianhang Li, Haoqin Tu, Mude Hui, Zeyu Wang, Bingchen Zhao, Junfei Xiao, Sucheng Ren, Jieru Mei, Qing Liu, Huangjie Zheng, Yuyin Zhou, Cihang Xie
Abstract: Web-crawled image-text pairs are inherently noisy. Prior studies demonstrate that semantically aligning and enriching textual descriptions of these pairs can significantly enhance model training across various vision-language tasks, particularly text-to-image generation. However, large-scale investigations in this area remain predominantly closed-source. Our paper aims to bridge this community effort, leveraging the powerful and \textit{open-sourced} LLaMA-3, a GPT-4 level LLM. Our recaptioning pipeline is simple: first, we fine-tune a LLaMA-3-8B powered LLaVA-1.5 and then employ it to recaption 1.3 billion images from the DataComp-1B dataset. Our empirical results confirm that this enhanced dataset, Recap-DataComp-1B, offers substantial benefits in training advanced vision-language models. For discriminative models like CLIP, we observe enhanced zero-shot performance in cross-modal retrieval tasks. For generative models like text-to-image Diffusion Transformers, the generated images exhibit a significant improvement in alignment with users' text instructions, especially in following complex queries. Our project page is https://www.haqtu.me/Recap-Datacomp-1B/
Authors: Hanwen Jiang, Qixing Huang, Georgios Pavlakos
Abstract: The default strategy for training single-view Large Reconstruction Models (LRMs) follows the fully supervised route using large-scale datasets of synthetic 3D assets or multi-view captures. Although these resources simplify the training procedure, they are hard to scale up beyond the existing datasets and they are not necessarily representative of the real distribution of object shapes. To address these limitations, in this paper, we introduce Real3D, the first LRM system that can be trained using single-view real-world images. Real3D introduces a novel self-training framework that can benefit from both the existing synthetic data and diverse single-view real images. We propose two unsupervised losses that allow us to supervise LRMs at the pixel- and semantic-level, even for training examples without ground-truth 3D or novel views. To further improve performance and scale up the image data, we develop an automatic data curation approach to collect high-quality examples from in-the-wild images. Our experiments show that Real3D consistently outperforms prior work in four diverse evaluation settings that include real and synthetic data, as well as both in-domain and out-of-domain shapes. Code and model can be found here: https://hwjiang1510.github.io/Real3D/
Authors: Yingyan Li, Lue Fan, Jiawei He, Yuqi Wang, Yuntao Chen, Zhaoxiang Zhang, Tieniu Tan
Abstract: End-to-end autonomous driving has garnered widespread attention. Current end-to-end approaches largely rely on the supervision from perception tasks such as detection, tracking, and map segmentation to aid in learning scene representations. However, these methods require extensive annotations, hindering the data scalability. To address this challenge, we propose a novel self-supervised method to enhance end-to-end driving without the need for costly labels. Specifically, our framework \textbf{LAW} uses a LAtent World model to predict future latent features based on the predicted ego actions and the latent feature of the current frame. The predicted latent features are supervised by the actually observed features in the future. This supervision jointly optimizes the latent feature learning and action prediction, which greatly enhances the driving performance. As a result, our approach achieves state-of-the-art performance in both open-loop and closed-loop benchmarks without costly annotations.
Authors: Raphael Tang, Xinyu Zhang, Lixinyu Xu, Yao Lu, Wenyan Li, Pontus Stenetorp, Jimmy Lin, Ferhan Ture
Abstract: Diffusion models are the state of the art in text-to-image generation, but their perceptual variability remains understudied. In this paper, we examine how prompts affect image variability in black-box diffusion-based models. We propose W1KP, a human-calibrated measure of variability in a set of images, bootstrapped from existing image-pair perceptual distances. Current datasets do not cover recent diffusion models, thus we curate three test sets for evaluation. Our best perceptual distance outperforms nine baselines by up to 18 points in accuracy, and our calibration matches graded human judgements 78% of the time. Using W1KP, we study prompt reusability and show that Imagen prompts can be reused for 10-50 random seeds before new images become too similar to already generated images, while Stable Diffusion XL and DALL-E 3 can be reused 50-200 times. Lastly, we analyze 56 linguistic features of real prompts, finding that the prompt's length, CLIP embedding norm, concreteness, and word senses influence variability most. As far as we are aware, we are the first to analyze diffusion variability from a visuolinguistic perspective. Our project page is at http://w1kp.com
URLs: http://w1kp.com
Authors: Yi-Fan Zhang, Qingsong Wen, Chaoyou Fu, Xue Wang, Zhang Zhang, Liang Wang, Rong Jin
Abstract: Seeing clearly with high resolution is a foundation of Large Multimodal Models (LMMs), which has been proven to be vital for visual perception and reasoning. Existing works usually employ a straightforward resolution upscaling method, where the image consists of global and local branches, with the latter being the sliced image patches but resized to the same resolution as the former. This means that higher resolution requires more local patches, resulting in exorbitant computational expenses, and meanwhile, the dominance of local image tokens may diminish the global context. In this paper, we dive into the problems and propose a new framework as well as an elaborate optimization strategy. Specifically, we extract contextual information from the global view using a mixture of adapters, based on the observation that different adapters excel at different tasks. With regard to local patches, learnable query embeddings are introduced to reduce image tokens, the most important tokens accounting for the user question will be further selected by a similarity-based selector. Our empirical results demonstrate a `less is more' pattern, where \textit{utilizing fewer but more informative local image tokens leads to improved performance}. Besides, a significant challenge lies in the training strategy, as simultaneous end-to-end training of the global mining block and local compression block does not yield optimal results. We thus advocate for an alternating training way, ensuring balanced learning between global and local aspects. Finally, we also introduce a challenging dataset with high requirements for image detail, enhancing the training of the local compression layer. The proposed method, termed LMM with Sophisticated Tasks, Local image compression, and Mixture of global Experts (SliME), achieves leading performance across various benchmarks with only 2 million training data.
Authors: Vishnu Jaganathan, Hannah Hanyun Huang, Muhammad Zubair Irshad, Varun Jampani, Amit Raj, Zsolt Kira
Abstract: Recently many techniques have emerged to create high quality 3D assets and scenes. When it comes to editing of these objects, however, existing approaches are either slow, compromise on quality, or do not provide enough customization. We introduce a novel approach to quickly edit a 3D model from a single reference view. Our technique first segments the edit image, and then matches semantically corresponding regions across chosen segmented dataset views using DINO features. A color or texture change from a particular region of the edit image can then be applied to other views automatically in a semantically sensible manner. These edited views act as an updated dataset to further train and re-style the 3D scene. The end-result is therefore an edited 3D model. Our framework enables a wide variety of editing tasks such as manual local edits, correspondence based style transfer from any example image, and a combination of different styles from multiple example images. We use Gaussian Splats as our primary 3D representation due to their speed and ease of local editing, but our technique works for other methods such as NeRFs as well. We show through multiple examples that our method produces higher quality results while offering fine-grained control of editing. Project page: ice-gaussian.github.io
Authors: Bin Huang, Changchen Zhao, Zimeng Liu, Shenda Hong, Baochang Zhang, Wenjin Wang, Hui Liu
Abstract: The widespread outbreak of the COVID-19 pandemic has sounded a warning about the globalization challenges in public health. In this context, the establishment of large-scale public health datasets, of medical models, and of decision-making systems with a human-centric approach holds strategic significance. Recently, groundbreaking advancements have emerged in AI methods for physiological signal monitoring and disease diagnosis based on camera sensors. These approaches, requiring no specialized medical equipment, offer convenient manners of collecting large-scale medical data in response to public health events. Not only do these methods facilitate the acquisition of unbiased datasets, but also enable the development of fair large medical models (LMMs). Therefore, we outline a prospective framework and heuristic vision for a public health large medical model (PHLMM) utilizing visual-based physiological monitoring (VBPM) technology. The PHLMM can be considered as a "convenient and universal" framework for public health, advancing the United Nations' "Sustainable Development Goals 2030", particularly in its promotion of Universal Health Coverage (UHC) in low- and middle-income countries. Furthermore, this paper provides an outlook on the crucial application prospects of PHLMM in response to public health challenges and its significant role in the field of AI for medicine (AI4medicine). In summary, PHLMM serves as a solution for constructing a large-scale medical database and LMM, eliminating the issue of dataset bias and unfairness in AI models. The outcomes will contribute to the establishment of an LMM framework for public health, acting as a crucial bridge for advancing AI4medicine.
Authors: Michel Adamic (McGill University), Wellington Avelino (McGill University), Anna Brandenberger (Massachusetts Institute of Technology), Bryan Chiang (Stanford University), Hunter Davis (McGill University), Stephen Fay (McGill University), Andrew Gregory (McGill University), Aayush Gupta (McGill University), Raphael Hotter (McGill University), Grace Jiang (McGill University), Fiona Leng (McGill University), Stephen Polcyn (McGill University), Thomas Ribeiro (McGill University), Paul Scotti (Princeton University), Michelle Wang (McGill University), Marley Xiong (University of Waterloo), Jonathan Xu (University of Waterloo)
Abstract: We demonstrate the possibility of reconstructing images from fNIRS brain activity and start building a prototype to match the required specs. By training an image reconstruction model on downsampled fMRI data, we discovered that cm-scale spatial resolution is sufficient for image generation. We obtained 71% retrieval accuracy with 1-cm resolution, compared to 93% on the full-resolution fMRI, and 20% with 2-cm resolution. With simulations and high-density tomography, we found that time-domain fNIRS can achieve 1-cm resolution, compared to 2-cm resolution for continuous-wave fNIRS. Lastly, we share designs for a prototype time-domain fNIRS device, consisting of a laser driver, a single photon detector, and a time-to-digital converter system.
Authors: Bahram Alidaee, Haibo Wang, Hugh Sloan
Abstract: Graph theory has been a powerful tool in solving difficult and complex problems arising in all disciplines. In particular, graph matching is a classical problem in pattern analysis with enormous applications. Many graph problems have been formulated as a mathematical program and then solved using exact, heuristic, and/or approximated-guaranteed procedures. On the other hand, graph theory has been a powerful tool in visualizing and understanding complex mathematical programming problems, especially integer programs. Formulating a graph problem as a natural integer program (IP) is often a challenging task. However, an IP formulation of the problem has many advantages. Several researchers have noted the need for natural IP formulation of graph theoretic problems. The present study aims to provide a unified framework for IP formulation of graph-matching problems. Although there are many surveys on graph matching problems, none is concerned with IP formulation. This paper is the first to provide a comprehensive IP formulation for such problems. The framework includes a variety of graph optimization problems in the literature. While these problems have been studied by different research communities, however, the framework presented here helps to bring efforts from different disciplines to tackle such diverse and complex problems. We hope the present study can significantly help to simplify some of the difficult problems arising in practice, especially in pattern analysis.
Authors: Mahtab Bigverdi, Burkhard Hockendorf, Heming Yao, Phil Hanslovsky, Romain Lopez, David Richmond
Abstract: Optical pooled screening (OPS) combines automated microscopy and genetic perturbations to systematically study gene function in a scalable and cost-effective way. Leveraging the resulting data requires extracting biologically informative representations of cellular perturbation phenotypes from images. We employ a style-transfer approach to learn gene-level feature representations from images of genetically perturbed cells obtained via OPS. Our method outperforms widely used engineered features in clustering gene representations according to gene function, demonstrating its utility for uncovering latent biological relationships. This approach offers a promising alternative to investigate the role of genes in health and disease.
Authors: Hang Min, Gorane Santamaria Hormaechea, Prabhakar Ramachandran, Jason Dowling
Abstract: Multiparametric magnetic resonance imaging (mpMRI) is a key tool for assessing breast cancer progression. Although deep learning has been applied to automate tumor segmentation in breast MRI, the effect of sequence combinations in mpMRI remains under-investigated. This study explores the impact of different combinations of T2-weighted (T2w), dynamic contrast-enhanced MRI (DCE-MRI) and diffusion-weighted imaging (DWI) with apparent diffusion coefficient (ADC) map on breast tumor segmentation using nnU-Net. Evaluated on a multicenter mpMRI dataset, the nnU-Net model using DCE sequences achieved a Dice similarity coefficient (DSC) of 0.69 $\pm$ 0.18 for functional tumor volume (FTV) segmentation. For whole tumor mask (WTM) segmentation, adding the predicted FTV to DWI and ADC map improved the DSC from 0.57 $\pm$ 0.24 to 0.60 $\pm$ 0.21. Adding T2w did not yield significant improvement, which still requires further investigation under a more standardized imaging protocol. This study serves as a foundation for future work on predicting breast cancer treatment response using mpMRI.
Authors: Lin Zuo, Yongqi Ding, Mengmeng Jing, Kunshan Yang, Yunqian Yu
Abstract: Spiking neural networks (SNNs) have attracted considerable attention for their event-driven, low-power characteristics and high biological interpretability. Inspired by knowledge distillation (KD), recent research has improved the performance of the SNN model with a pre-trained teacher model. However, additional teacher models require significant computational resources, and it is tedious to manually define the appropriate teacher network architecture. In this paper, we explore cost-effective self-distillation learning of SNNs to circumvent these concerns. Without an explicit defined teacher, the SNN generates pseudo-labels and learns consistency during training. On the one hand, we extend the timestep of the SNN during training to create an implicit temporal ``teacher" that guides the learning of the original ``student", i.e., the temporal self-distillation. On the other hand, we guide the output of the weak classifier at the intermediate stage by the final output of the SNN, i.e., the spatial self-distillation. Our temporal-spatial self-distillation (TSSD) learning method does not introduce any inference overhead and has excellent generalization ability. Extensive experiments on the static image datasets CIFAR10/100 and ImageNet as well as the neuromorphic datasets CIFAR10-DVS and DVS-Gesture validate the superior performance of the TSSD method. This paper presents a novel manner of fusing SNNs with KD, providing insights into high-performance SNN learning methods.
Authors: Zhenhuan Zhou, Along He, Yanlin Wu, Rui Yao, Xueshuo Xie, Tao Li
Abstract: In medical images, various types of lesions often manifest significant differences in their shape and texture. Accurate medical image segmentation demands deep learning models with robust capabilities in multi-scale and boundary feature learning. However, previous networks still have limitations in addressing the above issues. Firstly, previous networks simultaneously fuse multi-level features or employ deep supervision to enhance multi-scale learning. However, this may lead to feature redundancy and excessive computational overhead, which is not conducive to network training and clinical deployment. Secondly, the majority of medical image segmentation networks exclusively learn features in the spatial domain, disregarding the abundant global information in the frequency domain. This results in a bias towards low-frequency components, neglecting crucial high-frequency information. To address these problems, we introduce SF-UNet, a spatial-frequency dual-domain attention network. It comprises two main components: the Multi-scale Progressive Channel Attention (MPCA) block, which progressively extract multi-scale features across adjacent encoder layers, and the lightweight Frequency-Spatial Attention (FSA) block, with only 0.05M parameters, enabling concurrent learning of texture and boundary features from both spatial and frequency domains. We validate the effectiveness of the proposed SF-UNet on three public datasets. Experimental results show that compared to previous state-of-the-art (SOTA) medical image segmentation networks, SF-UNet achieves the best performance, and achieves up to 9.4\% and 10.78\% improvement in DSC and IOU. Codes will be released at https://github.com/nkicsl/SF-UNet.
Authors: Sasidhar Alavala, Subrahmanyam Gorthi
Abstract: In this paper, we present our approach to the 3D CBCT Challenge 2024, a part of ICASSP SP Grand Challenges 2024. Improvement in Cone Beam Computed Tomography (CBCT) reconstruction has been achieved by integrating Swin Image Restoration (SwinIR) based sinogram and image enhancement modules. The proposed methodology uses Nesterov Accelerated Gradient Descent (NAG) to solve the least squares (NAG-LS) problem in CT image reconstruction. The integration of sinogram and image enhancement modules aims to enhance image clarity and preserve fine details, offering a promising solution for both low dose and clinical dose CBCT reconstruction. The averaged mean squared error (MSE) over the validation dataset has decreased significantly, in the case of low dose by one-fifth and clinical dose by one-tenth. Our solution is one of the top 5 approaches in this challenge.
Authors: Jayneel Parekh, Pegah Khayatan, Mustafa Shukor, Alasdair Newson, Matthieu Cord
Abstract: Large multimodal models (LMMs) combine unimodal encoders and large language models (LLMs) to perform multimodal tasks. Despite recent advancements towards the interpretability of these models, understanding internal representations of LMMs remains largely a mystery. In this paper, we present a novel framework for the interpretation of LMMs. We propose a dictionary learning based approach, applied to the representation of tokens. The elements of the learned dictionary correspond to our proposed concepts. We show that these concepts are well semantically grounded in both vision and text. Thus we refer to these as "multi-modal concepts". We qualitatively and quantitatively evaluate the results of the learnt concepts. We show that the extracted multimodal concepts are useful to interpret representations of test samples. Finally, we evaluate the disentanglement between different concepts and the quality of grounding concepts visually and textually. We will publicly release our code.
Authors: Anvar Kurmukov, Valeria Chernina, Regina Gareeva, Maria Dugova, Ekaterina Petrash, Olga Aleshina, Maxim Pisov, Boris Shirokikh, Valentin Samokhin, Vladislav Proskurov, Stanislav Shimovolos, Maria Basova, Mikhail Goncahrov, Eugenia Soboleva, Maria Donskova, Farukh Yaushev, Alexey Shevtsov, Alexey Zakharov, Talgat Saparov, Victor Gombolevskiy, Mikhail Belyaev
Abstract: Interpretation of chest computed tomography (CT) is time-consuming. Previous studies have measured the time-saving effect of using a deep-learning-based aid (DLA) for CT interpretation. We evaluated the joint impact of a multi-pathology DLA on the time and accuracy of radiologists' reading. 40 radiologists were randomly split into three experimental arms: control (10), who interpret studies without assistance; informed group (10), who were briefed about DLA pathologies, but performed readings without it; and the experimental group (20), who interpreted half studies with DLA, and half without. Every arm used the same 200 CT studies retrospectively collected from BIMCV-COVID19 dataset; each radiologist provided readings for 20 CT studies. We compared interpretation time, and accuracy of participants diagnostic report with respect to 12 pathological findings. Mean reading time per study was 15.6 minutes [SD 8.5] in the control arm, 13.2 minutes [SD 8.7] in the informed arm, 14.4 [SD 10.3] in the experimental arm without DLA, and 11.4 minutes [SD 7.8] in the experimental arm with DLA. Mean sensitivity and specificity were 41.5 [SD 30.4], 86.8 [SD 28.3] in the control arm; 53.5 [SD 22.7], 92.3 [SD 9.4] in the informed non-assisted arm; 63.2 [SD 16.4], 92.3 [SD 8.2] in the experimental arm without DLA; and 91.6 [SD 7.2], 89.9 [SD 6.0] in the experimental arm with DLA. DLA speed up interpretation time per study by 2.9 minutes (CI95 [1.7, 4.3], p<0.0005), increased sensitivity by 28.4 (CI95 [23.4, 33.4], p<0.0005), and decreased specificity by 2.4 (CI95 [0.6, 4.3], p=0.13). Of 20 radiologists in the experimental arm, 16 have improved reading time and sensitivity, two improved their time with a marginal drop in sensitivity, and two participants improved sensitivity with increased time. Overall, DLA introduction decreased reading time by 20.6%.
Authors: Rongyuan Wu, Lingchen Sun, Zhiyuan Ma, Lei Zhang
Abstract: The pre-trained text-to-image diffusion models have been increasingly employed to tackle the real-world image super-resolution (Real-ISR) problem due to their powerful generative image priors. Most of the existing methods start from random noise to reconstruct the high-quality (HQ) image under the guidance of the given low-quality (LQ) image. While promising results have been achieved, such Real- ISR methods require multiple diffusion steps to reproduce the HQ image, increasing the computational cost. Meanwhile, the random noise introduces uncertainty in the output, which is unfriendly to image restoration tasks. To address these issues, we propose a one-step effective diffusion network, namely OSEDiff, for the Real- ISR problem. We argue that the LQ image contains rich information to restore its HQ counterpart, and hence the given LQ image can be directly taken as the starting point for diffusion, eliminating the uncertainty introduced by random noise sampling. We finetune the pre-trained diffusion network with trainable layers to adapt it to complex image degradations. To ensure that the one-step diffusion model could yield HQ Real-ISR output, we apply variational score distillation in the latent space to conduct KL-divergence regularization. As a result, our OSEDiff model can efficiently and effectively generate HQ images in just one diffusion step. Our experiments demonstrate that OSEDiff achieves comparable or even better Real-ISR results, in terms of both objective metrics and subjective evaluations, than previous diffusion model based Real-ISR methods that require dozens or hundreds of steps. The source codes will be released at https://github.com/cswry/OSEDiff.
Authors: Maxime Di Folco, Cosmin I. Bercea, Julia A. Schnabel
Abstract: Interpretability is essential in medical imaging to ensure that clinicians can comprehend and trust artificial intelligence models. Several approaches have been recently considered to encode attributes in the latent space to enhance its interpretability. Notably, attribute regularization aims to encode a set of attributes along the dimensions of a latent representation. However, this approach is based on Variational AutoEncoder and suffers from blurry reconstruction. In this paper, we propose an Attributed-regularized Soft Introspective Variational Autoencoder that combines attribute regularization of the latent space within the framework of an adversarially trained variational autoencoder. We demonstrate on short-axis cardiac Magnetic Resonance images of the UK Biobank the ability of the proposed method to address blurry reconstruction issues of variational autoencoder methods while preserving the latent space interpretability.
Authors: Zhihao Li, Yufei Wang, Alex Kot, Bihan Wen
Abstract: Novel view synthesis from raw images provides superior high dynamic range (HDR) information compared to reconstructions from low dynamic range RGB images. However, the inherent noise in unprocessed raw images compromises the accuracy of 3D scene representation. Our study reveals that 3D Gaussian Splatting (3DGS) is particularly susceptible to this noise, leading to numerous elongated Gaussian shapes that overfit the noise, thereby significantly degrading reconstruction quality and reducing inference speed, especially in scenarios with limited views. To address these issues, we introduce a novel self-supervised learning framework designed to reconstruct HDR 3DGS from a limited number of noisy raw images. This framework enhances 3DGS by integrating a noise extractor and employing a noise-robust reconstruction loss that leverages a noise distribution prior. Experimental results show that our method outperforms LDR/HDR 3DGS and previous state-of-the-art (SOTA) self-supervised and supervised pre-trained models in both reconstruction quality and inference speed on the RawNeRF dataset across a broad range of training views. Code can be found in \url{https://lizhihao6.github.io/Raw3DGS}.
Authors: Xueyuan Chen, Dongchao Yang, Dingdong Wang, Xixin Wu, Zhiyong Wu, Helen Meng
Abstract: Dysarthric speech reconstruction (DSR) aims to transform dysarthric speech into normal speech. It still suffers from low speaker similarity and poor prosody naturalness. In this paper, we propose a multi-modal DSR model by leveraging neural codec language modeling to improve the reconstruction results, especially for the speaker similarity and prosody naturalness. Our proposed model consists of: (i) a multi-modal content encoder to extract robust phoneme embeddings from dysarthric speech with auxiliary visual inputs; (ii) a speaker codec encoder to extract and normalize the speaker-aware codecs from the dysarthric speech, in order to provide original timbre and normal prosody; (iii) a codec language model based speech decoder to reconstruct the speech based on the extracted phoneme embeddings and normalized codecs. Evaluations on the commonly used UASpeech corpus show that our proposed model can achieve significant improvements in terms of speaker similarity and prosody naturalness.
Authors: Daniel Coelho, Miguel Oliveira, Vitor Santos, Antonio M. Lopez
Abstract: The development of Autonomous Driving (AD) systems in simulated environments like CARLA is crucial for advancing real-world automotive technologies. To drive innovation, CARLA introduced Leaderboard 2.0, significantly more challenging than its predecessor. However, current AD methods have struggled to achieve satisfactory outcomes due to a lack of sufficient ground truth data. Human driving logs provided by CARLA are insufficient, and previously successful expert agents like Autopilot and Roach, used for collecting datasets, have seen reduced effectiveness under these more demanding conditions. To overcome these data limitations, we introduce PRIBOOT, an expert agent that leverages limited human logs with privileged information. We have developed a novel BEV representation specifically tailored to meet the demands of this new benchmark and processed it as an RGB image to facilitate the application of transfer learning techniques, instead of using a set of masks. Additionally, we propose the Infraction Rate Score (IRS), a new evaluation metric designed to provide a more balanced assessment of driving performance over extended routes. PRIBOOT is the first model to achieve a Route Completion (RC) of 75% in Leaderboard 2.0, along with a Driving Score (DS) and IRS of 20% and 45%, respectively. With PRIBOOT, researchers can now generate extensive datasets, potentially solving the data availability issues that have hindered progress in this benchmark.
Authors: Hashmat Shadab Malik, Numan Saeed, Asif Hanif, Muzammal Naseer, Mohammad Yaqub, Salman Khan, Fahad Shahbaz Khan
Abstract: Volumetric medical segmentation models have achieved significant success on organ and tumor-based segmentation tasks in recent years. However, their vulnerability to adversarial attacks remains largely unexplored, raising serious concerns regarding the real-world deployment of tools employing such models in the healthcare sector. This underscores the importance of investigating the robustness of existing models. In this context, our work aims to empirically examine the adversarial robustness across current volumetric segmentation architectures, encompassing Convolutional, Transformer, and Mamba-based models. We extend this investigation across four volumetric segmentation datasets, evaluating robustness under both white box and black box adversarial attacks. Overall, we observe that while both pixel and frequency-based attacks perform reasonably well under white box setting, the latter performs significantly better under transfer-based black box attacks. Across our experiments, we observe transformer-based models show higher robustness than convolution-based models with Mamba-based models being the most vulnerable. Additionally, we show that large-scale training of volumetric segmentation models improves the model's robustness against adversarial attacks. The code and pretrained models will be made available at https://github.com/HashmatShadab/Robustness-of-Volumetric-Medical-Segmentation-Models.
URLs: https://github.com/HashmatShadab/Robustness-of-Volumetric-Medical-Segmentation-Models.
Authors: Bin Jiang, Zhihao Li, M. Salman Asif, Xun Cao, Zhan Ma
Abstract: The event camera's low power consumption and ability to capture microsecond brightness changes make it attractive for various computer vision tasks. Existing event representation methods typically convert events into frames, voxel grids, or spikes for deep neural networks (DNNs). However, these approaches often sacrifice temporal granularity or require specialized devices for processing. This work introduces a novel token-based event representation, where each event is considered a fundamental processing unit termed an event-token. This approach preserves the sequence's intricate spatiotemporal attributes at the event level. Moreover, we propose a Three-way Attention mechanism in the Event Transformer Block (ETB) to collaboratively construct temporal and spatial correlations between events. We compare our proposed token-based event representation extensively with other prevalent methods for object classification and optical flow estimation. The experimental results showcase its competitive performance while demanding minimal computational resources on standard devices. Our code is publicly accessible at \url{https://github.com/NJUVISION/EventTransformer}.
Authors: Dominik Zimny, Joanna Waczy\'nska, Tomasz Trzci\'nski, Przemys{\l}aw Spurek
Abstract: Contemporary registration devices for 3D visual information, such as LIDARs and various depth cameras, capture data as 3D point clouds. In turn, such clouds are challenging to be processed due to their size and complexity. Existing methods address this problem by fitting a mesh to the point cloud and rendering it instead. This approach, however, leads to the reduced fidelity of the resulting visualization and misses color information of the objects crucial in computer graphics applications. In this work, we propose to mitigate this challenge by representing 3D objects as Neural Radiance Fields (NeRFs). We leverage a hypernetwork paradigm and train the model to take a 3D point cloud with the associated color values and return a NeRF network's weights that reconstruct 3D objects from input 2D images. Our method provides efficient 3D object representation and offers several advantages over the existing approaches, including the ability to condition NeRFs and improved generalization beyond objects seen in training. The latter we also confirmed in the results of our empirical evaluation.
Authors: Khoa D. Doan, Jianwen Xie, Yaxuan Zhu, Yang Zhao, Ping Li
Abstract: Leveraging supervised information can lead to superior retrieval performance in the image hashing domain but the performance degrades significantly without enough labeled data. One effective solution to boost performance is to employ generative models, such as Generative Adversarial Networks (GANs), to generate synthetic data in an image hashing model. However, GAN-based methods are difficult to train, which prevents the hashing approaches from jointly training the generative models and the hash functions. This limitation results in sub-optimal retrieval performance. To overcome this limitation, we propose a novel framework, the generative cooperative hashing network, which is based on energy-based cooperative learning. This framework jointly learns a powerful generative representation of the data and a robust hash function via two components: a top-down contrastive pair generator that synthesizes contrastive images and a bottom-up multipurpose descriptor that simultaneously represents the images from multiple perspectives, including probability density, hash code, latent code, and category. The two components are jointly learned via a novel likelihood-based cooperative learning scheme. We conduct experiments on several real-world datasets and show that the proposed method outperforms the competing hashing supervised methods, achieving up to 10\% relative improvement over the current state-of-the-art supervised hashing methods, and exhibits a significantly better performance in out-of-distribution retrieval.
Authors: Xiaolong Tang, Shuo Ye, Yufeng Shi, Tianheng Hu, Qinmu Peng, Xinge You
Abstract: Filter pruning has gained widespread adoption for the purpose of compressing and speeding up convolutional neural networks (CNNs). However, existing approaches are still far from practical applications due to biased filter selection and heavy computation cost. This paper introduces a new filter pruning method that selects filters in an interpretable, multi-perspective, and lightweight manner. Specifically, we evaluate the contributions of filters from both individual and overall perspectives. For the amount of information contained in each filter, a new metric called information capacity is proposed. Inspired by the information theory, we utilize the interpretable entropy to measure the information capacity, and develop a feature-guided approximation process. For correlations among filters, another metric called information independence is designed. Since the aforementioned metrics are evaluated in a simple but effective way, we can identify and prune the least important filters with less computation cost. We conduct comprehensive experiments on benchmark datasets employing various widely-used CNN architectures to evaluate the performance of our method. For instance, on ILSVRC-2012, our method outperforms state-of-the-art methods by reducing FLOPs by 77.4% and parameters by 69.3% for ResNet-50 with only a minor decrease in accuracy of 2.64%.
Authors: Jiani Huang, Ziyang Li, Mayur Naik, Ser-Nam Lim
Abstract: We propose LASER, a neuro-symbolic approach to learn semantic video representations that capture rich spatial and temporal properties in video data by leveraging high-level logic specifications. In particular, we formulate the problem in terms of alignment between raw videos and spatio-temporal logic specifications. The alignment algorithm leverages a differentiable symbolic reasoner and a combination of contrastive, temporal, and semantics losses. It effectively and efficiently trains low-level perception models to extract a fine-grained video representation in the form of a spatio-temporal scene graph that conforms to the desired high-level specification. To practically reduce the manual effort of obtaining ground truth labels, we derive logic specifications from captions by employing a large language model with a generic prompting template. In doing so, we explore a novel methodology that weakly supervises the learning of spatio-temporal scene graphs with widely accessible video-caption data. We evaluate our method on three datasets with rich spatial and temporal specifications: 20BN-Something-Something, MUGEN, and OpenPVSG. We demonstrate that our method learns better fine-grained video semantics than existing baselines.
Authors: Yunze Man, Liang-Yan Gui, Yu-Xiong Wang
Abstract: Closing the domain gap between training and deployment and incorporating multiple sensor modalities are two challenging yet critical topics for self-driving. Existing work only focuses on single one of the above topics, overlooking the simultaneous domain and modality shift which pervasively exists in real-world scenarios. A model trained with multi-sensor data collected in Europe may need to run in Asia with a subset of input sensors available. In this work, we propose DualCross, a cross-modality cross-domain adaptation framework to facilitate the learning of a more robust monocular bird's-eye-view (BEV) perception model, which transfers the point cloud knowledge from a LiDAR sensor in one domain during the training phase to the camera-only testing scenario in a different domain. This work results in the first open analysis of cross-domain cross-sensor perception and adaptation for monocular 3D tasks in the wild. We benchmark our approach on large-scale datasets under a wide range of domain shifts and show state-of-the-art results against various baselines.
Authors: Mingzhao Yang, Shangchao Su, Bin Li, Xiangyang Xue
Abstract: Recently, semi-supervised federated learning (semi-FL) has been proposed to handle the commonly seen real-world scenarios with labeled data on the server and unlabeled data on the clients. However, existing methods face several challenges such as communication costs, data heterogeneity, and training pressure on client devices. To address these challenges, we introduce the powerful diffusion models (DM) into semi-FL and propose FedDISC, a Federated Diffusion-Inspired Semi-supervised Co-training method. Specifically, we first extract prototypes of the labeled server data and use these prototypes to predict pseudo-labels of the client data. For each category, we compute the cluster centroids and domain-specific representations to signify the semantic and stylistic information of their distributions. After adding noise, these representations are sent back to the server, which uses the pre-trained DM to generate synthetic datasets complying with the client distributions and train a global model on it. With the assistance of vast knowledge within DM, the synthetic datasets have comparable quality and diversity to the client images, subsequently enabling the training of global models that achieve performance equivalent to or even surpassing the ceiling of supervised centralized training. FedDISC works within one communication round, does not require any local training, and involves very minimal information uploading, greatly enhancing its practicality. Extensive experiments on three large-scale datasets demonstrate that FedDISC effectively addresses the semi-FL problem on non-IID clients and outperforms the compared SOTA methods. Sufficient visualization experiments also illustrate that the synthetic dataset generated by FedDISC exhibits comparable diversity and quality to the original client dataset, with a neglectable possibility of leaking privacy-sensitive information of the clients.
Authors: Siyi Du, Nourhan Bayasi, Ghassan Hamarneh, Rafeef Garbi
Abstract: Skin lesion segmentation (SLS) plays an important role in skin lesion analysis. Vision transformers (ViTs) are considered an auspicious solution for SLS, but they require more training data compared to convolutional neural networks (CNNs) due to their inherent parameter-heavy structure and lack of some inductive biases. To alleviate this issue, current approaches fine-tune pre-trained ViT backbones on SLS datasets, aiming to leverage the knowledge learned from a larger set of natural images to lower the amount of skin training data needed. However, fully fine-tuning all parameters of large backbones is computationally expensive and memory intensive. In this paper, we propose AViT, a novel efficient strategy to mitigate ViTs' data-hunger by transferring any pre-trained ViTs to the SLS task. Specifically, we integrate lightweight modules (adapters) within the transformer layers, which modulate the feature representation of a ViT without updating its pre-trained weights. In addition, we employ a shallow CNN as a prompt generator to create a prompt embedding from the input image, which grasps fine-grained information and CNN's inductive biases to guide the segmentation task on small datasets. Our quantitative experiments on 4 skin lesion datasets demonstrate that AViT achieves competitive, and at times superior, performance to SOTA but with significantly fewer trainable parameters. Our code is available at https://github.com/siyi-wind/AViT.
Authors: Ao Li, Le Zhang, Yun Liu, Ce Zhu
Abstract: Transformer-based methods have exhibited remarkable potential in single image super-resolution (SISR) by effectively extracting long-range dependencies. However, most of the current research in this area has prioritized the design of transformer blocks to capture global information, while overlooking the importance of incorporating high-frequency priors, which we believe could be beneficial. In our study, we conducted a series of experiments and found that transformer structures are more adept at capturing low-frequency information, but have limited capacity in constructing high-frequency representations when compared to their convolutional counterparts. Our proposed solution, the cross-refinement adaptive feature modulation transformer (CRAFT), integrates the strengths of both convolutional and transformer structures. It comprises three key components: the high-frequency enhancement residual block (HFERB) for extracting high-frequency information, the shift rectangle window attention block (SRWAB) for capturing global information, and the hybrid fusion block (HFB) for refining the global representation. To tackle the inherent intricacies of transformer structures, we introduce a frequency-guided post-training quantization (PTQ) method aimed at enhancing CRAFT's efficiency. These strategies incorporate adaptive dual clipping and boundary refinement. To further amplify the versatility of our proposed approach, we extend our PTQ strategy to function as a general quantization method for transformer-based SISR techniques. Our experimental findings showcase CRAFT's superiority over current state-of-the-art methods, both in full-precision and quantization scenarios. These results underscore the efficacy and universality of our PTQ strategy.
Authors: Yang Zhao, Yanwu Xu, Zhisheng Xiao, Haolin Jia, Tingbo Hou
Abstract: The deployment of large-scale text-to-image diffusion models on mobile devices is impeded by their substantial model size and slow inference speed. In this paper, we propose \textbf{MobileDiffusion}, a highly efficient text-to-image diffusion model obtained through extensive optimizations in both architecture and sampling techniques. We conduct a comprehensive examination of model architecture design to reduce redundancy, enhance computational efficiency, and minimize model's parameter count, while preserving image generation quality. Additionally, we employ distillation and diffusion-GAN finetuning techniques on MobileDiffusion to achieve 8-step and 1-step inference respectively. Empirical studies, conducted both quantitatively and qualitatively, demonstrate the effectiveness of our proposed techniques. MobileDiffusion achieves a remarkable \textbf{sub-second} inference speed for generating a $512\times512$ image on mobile devices, establishing a new state of the art.
Authors: Ju He, Qihang Yu, Inkyu Shin, Xueqing Deng, Alan Yuille, Xiaohui Shen, Liang-Chieh Chen
Abstract: Video segmentation requires consistently segmenting and tracking objects over time. Due to the quadratic dependency on input size, directly applying self-attention to video segmentation with high-resolution input features poses significant challenges, often leading to insufficient GPU memory capacity. Consequently, modern video segmenters either extend an image segmenter without incorporating any temporal attention or resort to window space-time attention in a naive manner. In this work, we present Axial-VS, a general and simple framework that enhances video segmenters by tracking objects along axial trajectories. The framework tackles video segmentation through two sub-tasks: short-term within-clip segmentation and long-term cross-clip tracking. In the first step, Axial-VS augments an off-the-shelf clip-level video segmenter with the proposed axial-trajectory attention, sequentially tracking objects along the height- and width-trajectories within a clip, thereby enhancing temporal consistency by capturing motion trajectories. The axial decomposition significantly reduces the computational complexity for dense features, and outperforms the window space-time attention in segmentation quality. In the second step, we further employ axial-trajectory attention to the object queries in clip-level segmenters, which are learned to encode object information, thereby aiding object tracking across different clips and achieving consistent segmentation throughout the video. Without bells and whistles, Axial-VS showcases state-of-the-art results on video segmentation benchmarks, emphasizing its effectiveness in addressing the limitations of modern clip-level video segmenters. Code and models are available at https://github.com/TACJu/Axial-VS.
Authors: Andr\'es Villa, Juan Carlos Le\'on Alc\'azar, Alvaro Soto, Bernard Ghanem
Abstract: Large Vision and Language Models have enabled significant advances in fully supervised and zero-shot visual tasks. These large architectures serve as the baseline to what is currently known as Instruction Tuning Large Vision and Language models (IT-LVLMs). IT-LVLMs are general-purpose multi-modal assistants whose responses are modulated by natural language instructions and visual data. Despite this versatility, IT-LVLM effectiveness in fundamental computer vision problems remains unclear, primarily due to the absence of a standardized evaluation benchmark. This paper introduces a Multi-modal Evaluation Benchmark named MERLIM, a scalable test-bed to assess the capabilities of IT-LVLMs on fundamental computer vision tasks. MERLIM contains over 300K image-question pairs and has a strong focus on detecting cross-modal "hallucination" events in IT-LVLMs. Our results bring important insights on the performance of state-of-the-art IT-LVMLs including limitations at identifying fine-grained visual concepts, object hallucinations across tasks, and biases towards the language query. Our findings also suggest that these models have weak visual grounding, but manage to make adequate guesses from global visual patterns or language biases contained in the LLM component.
Authors: Zhi Zhang, Qizhe Zhang, Zijun Gao, Renrui Zhang, Ekaterina Shutova, Shiji Zhou, Shanghang Zhang
Abstract: With the growing size of pre-trained models, full fine-tuning and storing all the parameters for various downstream tasks is costly and infeasible. In this paper, we propose a new parameter-efficient fine-tuning method, Gradient-based Parameter Selection (GPS), demonstrating that only tuning a few selected parameters from the pre-trained model while keeping the remainder of the model frozen can generate similar or better performance compared with the full model fine-tuning method. Different from the existing popular and state-of-the-art parameter-efficient fine-tuning approaches, our method does not introduce any additional parameters and computational costs during both the training and inference stages. Another advantage is the model-agnostic and non-destructive property, which eliminates the need for any other design specific to a particular model. Compared with the full fine-tuning, GPS achieves 3.33% (91.78% vs. 88.45%, FGVC) and 9.61% (73.1% vs. 65.57%, VTAB) improvement of the accuracy with tuning only 0.36% parameters of the pre-trained model on average over 24 image classification tasks; it also demonstrates a significant improvement of 17% and 16.8% in mDice and mIoU, respectively, on medical image segmentation task. Moreover, GPS achieves state-of-the-art performance compared with existing PEFT methods.
Authors: Dawid Malarz, Weronika Smolak, Jacek Tabor, S{\l}awomir Tadeja, Przemys{\l}aw Spurek
Abstract: Neural Radiance Fields (NeRFs) have demonstrated the remarkable potential of neural networks to capture the intricacies of 3D objects. By encoding the shape and color information within neural network weights, NeRFs excel at producing strikingly sharp novel views of 3D objects. Recently, numerous generalizations of NeRFs utilizing generative models have emerged, expanding its versatility. In contrast, Gaussian Splatting (GS) offers a similar render quality with faster training and inference as it does not need neural networks to work. It encodes information about the 3D objects in the set of Gaussian distributions that can be rendered in 3D similarly to classical meshes. Unfortunately, GS are difficult to condition since they usually require circa hundred thousand Gaussian components. To mitigate the caveats of both models, we propose a hybrid model Viewing Direction Gaussian Splatting (VDGS) that uses GS representation of the 3D object's shape and NeRF-based encoding of color and opacity. Our model uses Gaussian distributions with trainable positions (i.e. means of Gaussian), shape (i.e. covariance of Gaussian), color and opacity, and a neural network that takes Gaussian parameters and viewing direction to produce changes in the said color and opacity. As a result, our model better describes shadows, light reflections, and the transparency of 3D objects without adding additional texture and light components.
Authors: Weirong Chen, Le Chen, Rui Wang, Marc Pollefeys
Abstract: Visual odometry estimates the motion of a moving camera based on visual input. Existing methods, mostly focusing on two-view point tracking, often ignore the rich temporal context in the image sequence, thereby overlooking the global motion patterns and providing no assessment of the full trajectory reliability. These shortcomings hinder performance in scenarios with occlusion, dynamic objects, and low-texture areas. To address these challenges, we present the Long-term Effective Any Point Tracking (LEAP) module. LEAP innovatively combines visual, inter-track, and temporal cues with mindfully selected anchors for dynamic track estimation. Moreover, LEAP's temporal probabilistic formulation integrates distribution updates into a learnable iterative refinement module to reason about point-wise uncertainty. Based on these traits, we develop LEAP-VO, a robust visual odometry system adept at handling occlusions and dynamic scenes. Our mindful integration showcases a novel practice by employing long-term point tracking as the front-end. Extensive experiments demonstrate that the proposed pipeline significantly outperforms existing baselines across various visual odometry benchmarks.
Authors: Sunyi Zheng, Xiaonan Cui, Yuxuan Sun, Jingxiong Li, Honglin Li, Yunlong Zhang, Pingyi Chen, Xueping Jing, Zhaoxiang Ye, Lin Yang
Abstract: Accurate image classification and retrieval are of importance for clinical diagnosis and treatment decision-making. The recent contrastive language-image pretraining (CLIP) model has shown remarkable proficiency in understanding natural images. Drawing inspiration from CLIP, PathCLIP is specifically designed for pathology image analysis, utilizing over 200,000 image and text pairs in training. While the performance the PathCLIP is impressive, its robustness under a wide range of image corruptions remains unknown. Therefore, we conduct an extensive evaluation to analyze the performance of PathCLIP on various corrupted images from the datasets of Osteosarcoma and WSSS4LUAD. In our experiments, we introduce seven corruption types including brightness, contrast, Gaussian blur, resolution, saturation, hue, and markup at four severity levels. Through experiments, we find that PathCLIP is relatively robustness to image corruptions and surpasses OpenAI-CLIP and PLIP in zero-shot classification. Among the seven corruptions, blur and resolution can cause server performance degradation of the PathCLIP. This indicates that ensuring the quality of images is crucial before conducting a clinical test. Additionally, we assess the robustness of PathCLIP in the task of image-image retrieval, revealing that PathCLIP performs less effectively than PLIP on Osteosarcoma but performs better on WSSS4LUAD under diverse corruptions. Overall, PathCLIP presents impressive zero-shot classification and retrieval performance for pathology images, but appropriate care needs to be taken when using it. We hope this study provides a qualitative impression of PathCLIP and helps understand its differences from other CLIP models.
Authors: Youjia Wang, Yiwen Wu, Hengan Zhou, Hongyang Lin, Xingyue Peng, Yingwenqi Jiang, Yingsheng Zhu, Guanpeng Long, Yatu Zhang, Jingya Wang, Lan Xu, Jingyi Yu
Abstract: For facial motion capture and analysis, the dominated solutions are generally based on visual cues, which cannot protect privacy and are vulnerable to occlusions. Inertial measurement units (IMUs) serve as potential rescues yet are mainly adopted for full-body motion capture. In this paper, we propose IMUSE to fill the gap, a novel path for facial expression capture using purely IMU signals, significantly distant from previous visual solutions.The key design in our IMUSE is a trilogy. We first design micro-IMUs to suit facial capture, companion with an anatomy-driven IMU placement scheme. Then, we contribute a novel IMU-ARKit dataset, which provides rich paired IMU/visual signals for diverse facial expressions and performances. Such unique multi-modality brings huge potential for future directions like IMU-based facial behavior analysis. Moreover, utilizing IMU-ARKit, we introduce a strong baseline approach to accurately predict facial blendshape parameters from purely IMU signals. The IMUSE framework empowers us to perform accurate facial capture in scenarios where visual methods falter and simultaneously safeguard user privacy. We conduct extensive experiments about both the IMU configuration and technical components to validate the effectiveness of our IMUSE approach. Notably, IMUSE enables various potential and novel applications, i.e., facial capture against occlusions or in a moving performance. We will release our dataset and implementations to enrich more possibilities of facial capture and analysis in our community.
Authors: Tao Yang, Cuiling Lan, Yan Lu, Nanning zheng
Abstract: Disentangled representation learning strives to extract the intrinsic factors within observed data. Factorizing these representations in an unsupervised manner is notably challenging and usually requires tailored loss functions or specific structural designs. In this paper, we introduce a new perspective and framework, demonstrating that diffusion models with cross-attention can serve as a powerful inductive bias to facilitate the learning of disentangled representations. We propose to encode an image to a set of concept tokens and treat them as the condition of the latent diffusion for image reconstruction, where cross-attention over the concept tokens is used to bridge the interaction between the encoder and diffusion. Without any additional regularization, this framework achieves superior disentanglement performance on the benchmark datasets, surpassing all previous methods with intricate designs. We have conducted comprehensive ablation studies and visualization analysis, shedding light on the functioning of this model. This is the first work to reveal the potent disentanglement capability of diffusion models with cross-attention, requiring no complex designs. We anticipate that our findings will inspire more investigation on exploring diffusion for disentangled representation learning towards more sophisticated data analysis and understanding.
Authors: Jianrui Zhang, Mu Cai, Tengyang Xie, Yong Jae Lee
Abstract: We propose CounterCurate, a framework to comprehensively improve the visio-linguistic compositional reasoning capability for both contrastive and generative multimodal models. In particular, we identify two critical under-explored problems: the neglect of the physically grounded reasoning (counting and position understanding) and the potential of using highly capable text and image generation models for semantic counterfactual fine-tuning. Our work pioneers an approach that addresses these gaps. We first spotlight the near-chance performance of multimodal models like CLIP and LLaVA in physically grounded compositional reasoning. We then apply simple data augmentation using grounded image generation model GLIGEN to generate fine-tuning data, resulting in significant performance improvements: +33% and +37% for CLIP and LLaVA, respectively, on our newly curated Flickr30k-Positions benchmark. Moreover, we exploit the capabilities of high-performing text generation and image generation models, specifically GPT-4V and DALLE-3, to curate challenging semantic counterfactuals, thereby further enhancing compositional reasoning capabilities on benchmarks such as SugarCrepe, where CounterCurate outperforms GPT-4V. To facilitate future research, we release our code, dataset, benchmark, and checkpoints at https://countercurate.github.io.
Authors: Gabriel Toshio Hirokawa Higa, Rodrigo Stuqui Monzani, Jorge Fernando da Silva Cecatto, Maria Fernanda Balestieri Mariano de Souza, Vanessa Aparecida de Moraes Weber, Hemerson Pistori, Edson Takashi Matsubara
Abstract: Smart indoor tourist attractions, such as smart museums and aquariums, usually require a significant investment in indoor localization devices. The smartphone Global Positional Systems use is unsuitable for scenarios where dense materials such as concrete and metal block weaken the GPS signals, which is the most common scenario in an indoor tourist attraction. Deep learning makes it possible to perform region-wise indoor localization using smartphone images. This approach does not require any investment in infrastructure, reducing the cost and time to turn museums and aquariums into smart museums or smart aquariums. This paper proposes using deep learning algorithms to classify locations using smartphone camera images for indoor tourism attractions. We evaluate our proposal in a real-world scenario in Brazil. We extensively collect images from ten different smartphones to classify biome-themed fish tanks inside the Pantanal Biopark, creating a new dataset of 3654 images. We tested seven state-of-the-art neural networks, three being transformer-based, achieving precision around 90% on average and recall and f-score around 89% on average. The results indicate good feasibility of the proposal in a most indoor tourist attractions.
Authors: Maciej K Wozniak, Mattias Hansson, Marko Thiel, Patric Jensfelt
Abstract: In this study, we address a gap in existing unsupervised domain adaptation approaches on LiDAR-based 3D object detection, which have predominantly concentrated on adapting between established, high-density autonomous driving datasets. We focus on sparser point clouds, capturing scenarios from different perspectives: not just from vehicles on the road but also from mobile robots on sidewalks, which encounter significantly different environmental conditions and sensor configurations. We introduce Unsupervised Adversarial Domain Adaptation for 3D Object Detection (UADA3D). UADA3D does not depend on pre-trained source models or teacher-student architectures. Instead, it uses an adversarial approach to directly learn domain-invariant features. We demonstrate its efficacy in various adaptation scenarios, showing significant improvements in both self-driving car and mobile robot domains. Our code is open-source and will be available soon.
Authors: Sophia Sirko-Galouchenko, Alexandre Boulch, Spyros Gidaris, Andrei Bursuc, Antonin Vobecky, Patrick P\'erez, Renaud Marlet
Abstract: We introduce a self-supervised pretraining method, called OccFeat, for camera-only Bird's-Eye-View (BEV) segmentation networks. With OccFeat, we pretrain a BEV network via occupancy prediction and feature distillation tasks. Occupancy prediction provides a 3D geometric understanding of the scene to the model. However, the geometry learned is class-agnostic. Hence, we add semantic information to the model in the 3D space through distillation from a self-supervised pretrained image foundation model. Models pretrained with our method exhibit improved BEV semantic segmentation performance, particularly in low-data scenarios. Moreover, empirical results affirm the efficacy of integrating feature distillation with 3D occupancy prediction in our pretraining approach. Repository: https://github.com/valeoai/Occfeat
Authors: Muhammad Ahmad, Salvatore Distifano, Adil Mehmood Khan, Manuel Mazzara, Chenyu Li, Jing Yao, Hao Li, Jagannath Aryal, Gemine Vivone, Danfeng Hong
Abstract: Hyperspectral Image Classification (HSC) is a challenging task due to the high dimensionality and complex nature of Hyperspectral (HS) data. Traditional Machine Learning approaches while effective, face challenges in real-world data due to varying optimal feature sets, subjectivity in human-driven design, biases, and limitations. Traditional approaches encounter the curse of dimensionality, struggle with feature selection and extraction, lack spatial information consideration, exhibit limited robustness to noise, face scalability issues, and may not adapt well to complex data distributions. In recent years, DL techniques have emerged as powerful tools for addressing these challenges. This survey provides a comprehensive overview of the current trends and future prospects in HSC, focusing on the advancements from DL models to the emerging use of Transformers. We review the key concepts, methodologies, and state-of-the-art approaches in DL for HSC. We explore the potential of Transformer-based models in HSC, outlining their benefits and challenges. We also delve into emerging trends in HSC, as well as thorough discussions on Explainable AI and Interoperability concepts along with Diffusion Models (image denoising, feature extraction, and image fusion). Additionally, we address several open challenges and research questions pertinent to HSC. Comprehensive experimental results have been undertaken using three HS datasets to verify the efficacy of various conventional DL models and Transformers. Finally, we outline future research directions and potential applications that can further enhance the accuracy and efficiency of HSC. The Source code is available at \url{https://github.com/mahmad00/Conventional-to-Transformer-for-Hyperspectral-Image-Classification-Survey-2024}.
Authors: David A. Wood, Emily Guilhem, Sina Kafiabadi, Ayisha Al Busaidi, Kishan Dissanayake, Ahmed Hammam, Nina Mansoor, Matthew Townend, Siddharth Agarwal, Yiran Wei, Asif Mazumder, Gareth J. Barker, Peter Sasieni, Sebastien Ourselin, James H. Cole, Thomas C. Booth
Abstract: Artificial neural networks trained on large, expert-labelled datasets are considered state-of-the-art for a range of medical image recognition tasks. However, categorically labelled datasets are time-consuming to generate and constrain classification to a pre-defined, fixed set of classes. For neuroradiological applications in particular, this represents a barrier to clinical adoption. To address these challenges, we present a self-supervised text-vision framework that learns to detect clinically relevant abnormalities in brain MRI scans by directly leveraging the rich information contained in accompanying free-text neuroradiology reports. Our training approach consisted of two-steps. First, a dedicated neuroradiological language model - NeuroBERT - was trained to generate fixed-dimensional vector representations of neuroradiology reports (N = 50,523) via domain-specific self-supervised learning tasks. Next, convolutional neural networks (one per MRI sequence) learnt to map individual brain scans to their corresponding text vector representations by optimising a mean square error loss. Once trained, our text-vision framework can be used to detect abnormalities in unreported brain MRI examinations by scoring scans against suitable query sentences (e.g., 'there is an acute stroke', 'there is hydrocephalus' etc.), enabling a range of classification-based applications including automated triage. Potentially, our framework could also serve as a clinical decision support tool, not only by suggesting findings to radiologists and detecting errors in provisional reports, but also by retrieving and displaying examples of pathologies from historical examinations that could be relevant to the current case based on textual descriptors.
Authors: Jihwan Kim, Junoh Kang, Jinyoung Choi, Bohyung Han
Abstract: We propose a novel inference technique based on a pretrained diffusion model for text-conditional video generation. Our approach, called FIFO-Diffusion, is conceptually capable of generating infinitely long videos without additional training. This is achieved by iteratively performing diagonal denoising, which concurrently processes a series of consecutive frames with increasing noise levels in a queue; our method dequeues a fully denoised frame at the head while enqueuing a new random noise frame at the tail. However, diagonal denoising is a double-edged sword as the frames near the tail can take advantage of cleaner ones by forward reference but such a strategy induces the discrepancy between training and inference. Hence, we introduce latent partitioning to reduce the training-inference gap and lookahead denoising to leverage the benefit of forward referencing. Practically, FIFO-Diffusion consumes a constant amount of memory regardless of the target video length given a baseline model, while well-suited for parallel inference on multiple GPUs. We have demonstrated the promising results and effectiveness of the proposed methods on existing text-to-video generation baselines. Generated video samples and source codes are available at our project page.
Authors: Tomohiro Hayase, Sacha Braun, Hikari Yanagawa, Itsuki Orito, Yuichi Hiroi
Abstract: Social VR platforms enable social, economic, and creative activities by allowing users to create and share their own virtual spaces. In social VR, photography within a VR scene is an important indicator of visitors' activities. Although automatic identification of photo spots within a VR scene can facilitate the process of creating a VR scene and enhance the visitor experience, there are challenges in quantitatively evaluating photos taken in the VR scene and efficiently exploring the large VR scene. We propose PanoTree, an automated photo-spot explorer in VR scenes. To assess the aesthetics of images captured in VR scenes, a deep scoring network is trained on a large dataset of photos collected by a social VR platform to determine whether humans are likely to take similar photos. Furthermore, we propose a Hierarchical Optimistic Optimization (HOO)-based search algorithm to efficiently explore 3D VR spaces with the reward from the scoring network. Our user study shows that the scoring network achieves human-level performance in distinguishing randomly taken images from those taken by humans. In addition, we show applications using the explored photo spots, such as automatic thumbnail generation, support for VR world creation, and visitor flow planning within a VR scene.
Authors: Zhiyuan You, Jinjin Gu, Zheyuan Li, Xin Cai, Kaiwen Zhu, Chao Dong, Tianfan Xue
Abstract: With the rapid advancement of Vision Language Models (VLMs), VLM-based Image Quality Assessment (IQA) seeks to describe image quality linguistically to align with human expression and capture the multifaceted nature of IQA tasks. However, current methods are still far from practical usage. First, prior works focus narrowly on specific sub-tasks or settings, which do not align with diverse real-world applications. Second, their performance is sub-optimal due to limitations in dataset coverage, scale, and quality. To overcome these challenges, we introduce Depicted image Quality Assessment in the Wild (DepictQA-Wild). Our method includes a multi-functional IQA task paradigm that encompasses both assessment and comparison tasks, brief and detailed responses, full-reference and non-reference scenarios. We introduce a ground-truth-informed dataset construction approach to enhance data quality, and scale up the dataset to 495K under the brief-detail joint framework. Consequently, we construct a comprehensive, large-scale, and high-quality dataset, named DQ-495K. We also retain image resolution during training to better handle resolution-related quality issues, and estimate a confidence score that is helpful to filter out low-quality responses. Experimental results demonstrate that DepictQA-Wild significantly outperforms traditional score-based methods, prior VLM-based IQA models, and proprietary GPT-4V in distortion identification, instant rating, and reasoning tasks. Our advantages are further confirmed by real-world applications including assessing the web-downloaded images and ranking model-processed images. Datasets and codes will be released in https://depictqa.github.io/depictqa-wild/.
Authors: Hongen Liu, Di Sun, Jiahao Wang, Yi Liu, Gang Pan
Abstract: Video text spotting (VTS) aims to simultaneously localize, recognize and track text instances in videos. To address the limited recognition capability of end-to-end methods, recent methods track the zero-shot results of state-of-the-art image text spotters directly, and achieve impressive performance. However, owing to the domain gap between different datasets, these methods usually obtain limited tracking trajectories on extreme dataset. Fine-tuning transformer-based text spotters on specific datasets could yield performance enhancements, albeit at the expense of considerable training resources. In this paper, we propose a Language Collaboration and Glyph Perception Model, termed LOGO, an innovative framework designed to enhance the performance of conventional text spotters. To achieve this goal, we design a language synergy classifier (LSC) to explicitly discern text instances from background noise in the recognition stage. Specially, the language synergy classifier can output text content or background code based on the legibility of text regions, thus computing language scores. Subsequently, fusion scores are computed by taking the average of detection scores and language scores, and are utilized to re-score the detection results before tracking. By the re-scoring mechanism, the proposed LSC facilitates the detection of low-resolution text instances while filtering out text-like regions. Moreover, the glyph supervision is introduced to enhance the recognition accuracy of noisy text regions. In addition, we propose the visual position mixture module, which can merge the position information and visual features efficiently, and acquire more discriminative tracking features. Extensive experiments on public benchmarks validate the effectiveness of the proposed method.
Authors: Zhiming Meng, Hui Li, Zeyang Zhang, Zhongwei Shen, Yunlong Yu, Xiaoning Song, Xiaojun Wu
Abstract: Generative models are widely utilized to model the distribution of fused images in the field of infrared and visible image fusion. However, current generative models based fusion methods often suffer from unstable training and slow inference speed. To tackle this problem, a novel fusion method based on consistency model is proposed, termed as CoMoFusion, which can generate the high-quality images and achieve fast image inference speed. In specific, the consistency model is used to construct multi-modal joint features in the latent space with the forward and reverse process. Then, the infrared and visible features extracted by the trained consistency model are fed into fusion module to generate the final fused image. In order to enhance the texture and salient information of fused images, a novel loss based on pixel value selection is also designed. Extensive experiments on public datasets illustrate that our method obtains the SOTA fusion performance compared with the existing fusion methods.
Authors: Jingyun Xue, Hongfa Wang, Qi Tian, Yue Ma, Andong Wang, Zhiyuan Zhao, Shaobo Min, Wenzhe Zhao, Kaihao Zhang, Heung-Yeung Shum, Wei Liu, Mengyang Liu, Wenhan Luo
Abstract: Pose-controllable character video generation is in high demand with extensive applications for fields such as automatic advertising and content creation on social media platforms. While existing character image animation methods using pose sequences and reference images have shown promising performance, they tend to struggle with incoherent animation in complex scenarios, such as multiple character animation and body occlusion. Additionally, current methods request large-scale high-quality videos with stable backgrounds and temporal consistency as training datasets, otherwise, their performance will greatly deteriorate. These two issues hinder the practical utilization of character image animation tools. In this paper, we propose a practical and robust framework Follow-Your-Pose v2, which can be trained on noisy open-sourced videos readily available on the internet. Multi-condition guiders are designed to address the challenges of background stability, body occlusion in multi-character generation, and consistency of character appearance. Moreover, to fill the gap of fair evaluation of multi-character pose animation, we propose a new benchmark comprising approximately 4,000 frames. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods by a margin of over 35\% across 2 datasets and on 7 metrics. Meanwhile, qualitative assessments reveal a significant improvement in the quality of generated video, particularly in scenarios involving complex backgrounds and body occlusion of multi-character, suggesting the superiority of our approach.
Authors: Qutub Syed Sha, Michael Paulitsch, Karthik Pattabiraman, Korbinian Hagn, Fabian Oboril, Cornelius Buerkle, Kay-Ulrich Scholl, Gereon Hinz, Alois Knoll
Abstract: As transformer-based object detection models progress, their impact in critical sectors like autonomous vehicles and aviation is expected to grow. Soft errors causing bit flips during inference have significantly impacted DNN performance, altering predictions. Traditional range restriction solutions for CNNs fall short for transformers. This study introduces the Global Clipper and Global Hybrid Clipper, effective mitigation strategies specifically designed for transformer-based models. It significantly enhances their resilience to soft errors and reduces faulty inferences to ~ 0\%. We also detail extensive testing across over 64 scenarios involving two transformer models (DINO-DETR and Lite-DETR) and two CNN models (YOLOv3 and SSD) using three datasets, totalling approximately 3.3 million inferences, to assess model robustness comprehensively. Moreover, the paper explores unique aspects of attention blocks in transformers and their operational differences from CNNs.
Authors: Jianing Yang, Xuweiyi Chen, Nikhil Madaan, Madhavan Iyengar, Shengyi Qian, David F. Fouhey, Joyce Chai
Abstract: The integration of language and 3D perception is crucial for developing embodied agents and robots that comprehend and interact with the physical world. While large language models (LLMs) have demonstrated impressive language understanding and generation capabilities, their adaptation to 3D environments (3D-LLMs) remains in its early stages. A primary challenge is the absence of large-scale datasets that provide dense grounding between language and 3D scenes. In this paper, we introduce 3D-GRAND, a pioneering large-scale dataset comprising 40,087 household scenes paired with 6.2 million densely-grounded scene-language instructions. Our results show that instruction tuning with 3D-GRAND significantly enhances grounding capabilities and reduces hallucinations in 3D-LLMs. As part of our contributions, we propose a comprehensive benchmark 3D-POPE to systematically evaluate hallucination in 3D-LLMs, enabling fair comparisons among future models. Our experiments highlight a scaling effect between dataset size and 3D-LLM performance, emphasizing the critical role of large-scale 3D-text datasets in advancing embodied AI research. Notably, our results demonstrate early signals for effective sim-to-real transfer, indicating that models trained on large synthetic data can perform well on real-world 3D scans. Through 3D-GRAND and 3D-POPE, we aim to equip the embodied AI community with essential resources and insights, setting the stage for more reliable and better-grounded 3D-LLMs. Project website: https://3d-grand.github.io
Authors: Pengyang Ling, Jiazi Bu, Pan Zhang, Xiaoyi Dong, Yuhang Zang, Tong Wu, Huaian Chen, Jiaqi Wang, Yi Jin
Abstract: Motion-based controllable text-to-video generation involves motions to control the video generation. Previous methods typically require the training of models to encode motion cues or the fine-tuning of video diffusion models. However, these approaches often result in suboptimal motion generation when applied outside the trained domain. In this work, we propose MotionClone, a training-free framework that enables motion cloning from a reference video to control text-to-video generation. We employ temporal attention in video inversion to represent the motions in the reference video and introduce primary temporal-attention guidance to mitigate the influence of noisy or very subtle motions within the attention weights. Furthermore, to assist the generation model in synthesizing reasonable spatial relationships and enhance its prompt-following capability, we propose a location-aware semantic guidance mechanism that leverages the coarse location of the foreground from the reference video and original classifier-free guidance features to guide the video generation. Extensive experiments demonstrate that MotionClone exhibits proficiency in both global camera motion and local object motion, with notable superiority in terms of motion fidelity, textual alignment, and temporal consistency.
Authors: Xinhao Zhong, Hao Fang, Bin Chen, Xulin Gu, Tao Dai, Meikang Qiu, Shu-Tao Xia
Abstract: Dataset distillation is an emerging dataset reduction method, which condenses large-scale datasets while maintaining task accuracy. Current methods have integrated parameterization techniques to boost synthetic dataset performance by shifting the optimization space from pixel to another informative feature domain. However, they limit themselves to a fixed optimization space for distillation, neglecting the diverse guidance across different informative latent spaces. To overcome this limitation, we propose a novel parameterization method dubbed Hierarchical Generative Latent Distillation (H-GLaD), to systematically explore hierarchical layers within the generative adversarial networks (GANs). This allows us to progressively span from the initial latent space to the final pixel space. In addition, we introduce a novel class-relevant feature distance metric to alleviate the computational burden associated with synthetic dataset evaluation, bridging the gap between synthetic and original datasets. Experimental results demonstrate that the proposed H-GLaD achieves a significant improvement in both same-architecture and cross-architecture performance with equivalent time consumption.
Authors: Qingsong Xie, Zhenyi Liao, Chen chen, Zhijie Deng, Shixiang Tang, Haonan Lu
Abstract: Distilling large latent diffusion models (LDMs) into ones that are fast to sample from is attracting growing research interest. However, the majority of existing methods face a dilemma where they either (i) depend on multiple individual distilled models for different sampling budgets, or (ii) sacrifice generation quality with limited (e.g., 2-4) and/or moderate (e.g., 5-8) sampling steps. To address these, we extend the recent multistep consistency distillation (MCD) strategy to representative LDMs, establishing the Multistep Latent Consistency Models (MLCMs) approach for low-cost high-quality image synthesis. MLCM serves as a unified model for various sampling steps due to the promise of MCD. We further augment MCD with a progressive training strategy to strengthen inter-segment consistency to boost the quality of few-step generations. We take the states from the sampling trajectories of the teacher model as training data for MLCMs to lift the requirements for high-quality training datasets and to bridge the gap between the training and inference of the distilled model. MLCM is compatible with preference learning strategies for further improvement of visual quality and aesthetic appeal. Empirically, MLCM can generate high-quality, delightful images with only 2-8 sampling steps. On the MSCOCO-2017 5K benchmark, MLCM distilled from SDXL gets a CLIP Score of 33.30, Aesthetic Score of 6.19, and Image Reward of 1.20 with only 4 steps, substantially surpassing 4-step LCM [23], 8-step SDXL-Lightning [17], and 8-step HyperSD [33]. We also demonstrate the versatility of MLCMs in applications including controllable generation, image style transfer, and Chinese-to-image generation.
Authors: Jiahua Xu, Si Zuo, Chenfeng Wei, Wei Zhou
Abstract: With the rapid proliferation of autonomous driving, there has been a heightened focus on the research of lidar-based 3D semantic segmentation and object detection methodologies, aiming to ensure the safety of traffic participants. In recent decades, learning-based approaches have emerged, demonstrating remarkable performance gains in comparison to conventional algorithms. However, the segmentation and detection tasks have traditionally been examined in isolation to achieve the best precision. To this end, we propose an efficient multi-task learning framework named LiSD which can address both segmentation and detection tasks, aiming to optimize the overall performance. Our proposed LiSD is a voxel-based encoder-decoder framework that contains a hierarchical feature collaboration module and a holistic information aggregation module. Different integration methods are adopted to keep sparsity in segmentation while densifying features for query initialization in detection. Besides, cross-task information is utilized in an instance-aware refinement module to obtain more accurate predictions. Experimental results on the nuScenes dataset and Waymo Open Dataset demonstrate the effectiveness of our proposed model. It is worth noting that LiSD achieves the state-of-the-art performance of 83.3% mIoU on the nuScenes segmentation benchmark for lidar-only methods.
Authors: Athanasios Tragakis, Marco Aversa, Chaitanya Kaul, Roderick Murray-Smith, Daniele Faccio
Abstract: In this work, we introduce Pixelsmith, a zero-shot text-to-image generative framework to sample images at higher resolutions with a single GPU. We are the first to show that it is possible to scale the output of a pre-trained diffusion model by a factor of 1000, opening the road for gigapixel image generation at no additional cost. Our cascading method uses the image generated at the lowest resolution as a baseline to sample at higher resolutions. For the guidance, we introduce the Slider, a tunable mechanism that fuses the overall structure contained in the first-generated image with enhanced fine details. At each inference step, we denoise patches rather than the entire latent space, minimizing memory demands such that a single GPU can handle the process, regardless of the image's resolution. Our experimental results show that Pixelsmith not only achieves higher quality and diversity compared to existing techniques, but also reduces sampling time and artifacts. The code for our work is available at https://github.com/Thanos-DB/Pixelsmith.
Authors: Long Peng, Wenbo Li, Renjing Pei, Jingjing Ren, Xueyang Fu, Yang Wang, Yang Cao, Zheng-Jun Zha
Abstract: Existing image super-resolution (SR) techniques often fail to generalize effectively in complex real-world settings due to the significant divergence between training data and practical scenarios. To address this challenge, previous efforts have either manually simulated intricate physical-based degradations or utilized learning-based techniques, yet these approaches remain inadequate for producing large-scale, realistic, and diverse data simultaneously. In this paper, we introduce a novel Realistic Decoupled Data Generator (RealDGen), an unsupervised learning data generation framework designed for real-world super-resolution. We meticulously develop content and degradation extraction strategies, which are integrated into a novel content-degradation decoupled diffusion model to create realistic low-resolution images from unpaired real LR and HR images. Extensive experiments demonstrate that RealDGen excels in generating large-scale, high-quality paired data that mirrors real-world degradations, significantly advancing the performance of popular SR models on various real-world benchmarks.
Authors: Ming Hu, Peng Xia, Lin Wang, Siyuan Yan, Feilong Tang, Zhongxing Xu, Yimin Luo, Kaimin Song, Jurgen Leitner, Xuelian Cheng, Jun Cheng, Chi Liu, Kaijing Zhou, Zongyuan Ge
Abstract: Surgical scene perception via videos are critical for advancing robotic surgery, telesurgery, and AI-assisted surgery, particularly in ophthalmology. However, the scarcity of diverse and richly annotated video datasets has hindered the development of intelligent systems for surgical workflow analysis. Existing datasets for surgical workflow analysis, which typically face challenges such as small scale, a lack of diversity in surgery and phase categories, and the absence of time-localized annotations, limit the requirements for action understanding and model generalization validation in complex and diverse real-world surgical scenarios. To address this gap, we introduce OphNet, a large-scale, expert-annotated video benchmark for ophthalmic surgical workflow understanding. OphNet features: 1) A diverse collection of 2,278 surgical videos spanning 66 types of cataract, glaucoma, and corneal surgeries, with detailed annotations for 102 unique surgical phases and 150 granular operations; 2) It offers sequential and hierarchical annotations for each surgery, phase, and operation, enabling comprehensive understanding and improved interpretability; 3) Moreover, OphNet provides time-localized annotations, facilitating temporal localization and prediction tasks within surgical workflows. With approximately 205 hours of surgical videos, OphNet is about 20 times larger than the largest existing surgical workflow analysis benchmark. Our dataset and code have been made available at: \url{https://github.com/minghu0830/OphNet-benchmark}.
Authors: Javier Montalvo, Juan Ignacio Bravo P\'erez-Villar, \'Alvaro Garc\'ia-Mart\'in, Pablo Carballeira, Jes\'us Besc'os
Abstract: Data acquired in space operational conditions is scarce due to the costs and complexity of space operations. This poses a challenge to learning-based visual-based navigation algorithms employed in autonomous spacecraft navigation. Existing datasets, which largely depend on computer-simulated data, have partially filled this gap. However, the image generation tools they use are proprietary, which limits the evaluation of methods to unseen scenarios. Furthermore, these datasets provide limited ground-truth data, primarily focusing on the spacecraft's translation and rotation relative to the camera. To address these limitations, we present SPIN (SPacecraft Imagery for Navigation), an open-source realistic spacecraft image generation tool for relative navigation between two spacecrafts. SPIN provides a wide variety of ground-truth data and allows researchers to employ custom 3D models of satellites, define specific camera-relative poses, and adjust various settings such as camera parameters and environmental illumination conditions. For the task of spacecraft pose estimation, we compare the results of training with a SPIN-generated dataset against existing synthetic datasets. We show a %50 average error reduction in common testbed data (that simulates realistic space conditions). Both the SPIN tool (and source code) and our enhanced version of the synthetic datasets will be publicly released upon paper acceptance on GitHub https://github.com/vpulab/SPIN.
Authors: Gregor Geigle, Radu Timofte, Goran Glava\v{s}
Abstract: Vision-and-language (VL) models with separate encoders for each modality (e.g., CLIP) have become the go-to models for zero-shot image classification and image-text retrieval. They are, however, mostly evaluated in English as multilingual benchmarks are limited in availability. We introduce Babel-ImageNet, a massively multilingual benchmark that offers (partial) translations of ImageNet labels to 100 languages, built without machine translation or manual annotation. We instead automatically obtain reliable translations by linking them -- via shared WordNet synsets -- to BabelNet, a massively multilingual lexico-semantic network. We evaluate 11 public multilingual CLIP models on zero-shot image classification (ZS-IC) on our benchmark, demonstrating a significant gap between English ImageNet performance and that of high-resource languages (e.g., German or Chinese), and an even bigger gap for low-resource languages (e.g., Sinhala or Lao). Crucially, we show that the models' ZS-IC performance highly correlates with their performance in image-text retrieval, validating the use of Babel-ImageNet to evaluate multilingual models for the vast majority of languages without gold image-text data. Finally, we show that the performance of multilingual CLIP can be drastically improved for low-resource languages with parameter-efficient language-specific training. We make our code and data publicly available: \url{https://github.com/gregor-ge/Babel-ImageNet}
Authors: Cuong V. Nguyen, Hieu Minh Duong, Cuong D. Do
Abstract: In practical electrocardiography (ECG) interpretation, the scarcity of well-annotated data is a common challenge. Transfer learning techniques are valuable in such situations, yet the assessment of transferability has received limited attention. To tackle this issue, we introduce MELEP, which stands for Muti-label Expected Log of Empirical Predictions, a measure designed to estimate the effectiveness of knowledge transfer from a pre-trained model to a downstream multi-label ECG diagnosis task. MELEP is generic, working with new target data with different label sets, and computationally efficient, requiring only a single forward pass through the pre-trained model. To the best of our knowledge, MELEP is the first transferability metric specifically designed for multi-label ECG classification problems. Our experiments show that MELEP can predict the performance of pre-trained convolutional and recurrent deep neural networks, on small and imbalanced ECG data. Specifically, we observed strong correlation coefficients (with absolute values exceeding 0.6 in most cases) between MELEP and the actual average F1 scores of the fine-tuned models. Our work highlights the potential of MELEP to expedite the selection of suitable pre-trained models for ECG diagnosis tasks, saving time and effort that would otherwise be spent on fine-tuning these models.
Authors: Benjamin Billot, Neel Dey, Daniel Moyer, Malte Hoffmann, Esra Abaci Turk, Borjan Gagoski, Ellen Grant, Polina Golland
Abstract: Rigid motion tracking is paramount in many medical imaging applications where movements need to be detected, corrected, or accounted for. Modern strategies rely on convolutional neural networks (CNN) and pose this problem as rigid registration. Yet, CNNs do not exploit natural symmetries in this task, as they are equivariant to translations (their outputs shift with their inputs) but not to rotations. Here we propose EquiTrack, the first method that uses recent steerable SE(3)-equivariant CNNs (E-CNN) for motion tracking. While steerable E-CNNs can extract corresponding features across different poses, testing them on noisy medical images reveals that they do not have enough learning capacity to learn noise invariance. Thus, we introduce a hybrid architecture that pairs a denoiser with an E-CNN to decouple the processing of anatomically irrelevant intensity features from the extraction of equivariant spatial features. Rigid transforms are then estimated in closed-form. EquiTrack outperforms state-of-the-art learning and optimisation methods for motion tracking in adult brain MRI and fetal MRI time series. Our code is available at https://github.com/BBillot/EquiTrack.
Authors: Qiannan Wang, Changchun Yin, Lu Zhou, Liming Fang
Abstract: The extensive adoption of Self-supervised learning(SSL) has led to an increased security threat from backdoor attacks. While existing research has mainly focused on backdoor attacks in image classification, there has been limited exploration of their implications for object detection. Object detection plays a critical role in security-sensitive applications, such as autonomous driving, where backdoor attacks seriously threaten human life and property. In this work, we propose the first backdoor attack designed for object detection tasks in SSL scenarios, called Object Transform Attack (SSL-OTA). SSL-OTA employs a trigger capable of altering predictions of the target object to the desired category, encompassing two attacks: Naive Attack(NA) and Dual-Source Blending Attack (DSBA). NA conducts data poisoning during downstream fine-tuning of the object detector, while DSBA additionally injects backdoors into the pre-trained encoder. We establish appropriate metrics and conduct extensive experiments on benchmark datasets, demonstrating the effectiveness of our proposed attack and its resistance to potential defenses. Notably, both NA and DSBA achieve high attack success rates (ASR) at extremely low poisoning rates (0.5%). The results underscore the importance of considering backdoor threats in SSL-based object detection and contribute a novel perspective to the field.
Authors: Daniel Bogdoll, Jing Qin, Moritz Nekolla, Ahmed Abouelazm, Tim Joseph, J. Marius Z\"ollner
Abstract: Reinforcement Learning is a highly active research field with promising advancements. In the field of autonomous driving, however, often very simple scenarios are being examined. Common approaches use non-interpretable control commands as the action space and unstructured reward designs which lack structure. In this work, we introduce Informed Reinforcement Learning, where a structured rulebook is integrated as a knowledge source. We learn trajectories and asses them with a situation-aware reward design, leading to a dynamic reward which allows the agent to learn situations which require controlled traffic rule exceptions. Our method is applicable to arbitrary RL models. We successfully demonstrate high completion rates of complex scenarios with recent model-based agents.
Authors: Xingyu Xu, Yuejie Chi
Abstract: In a great number of tasks in science and engineering, the goal is to infer an unknown image from a small number of measurements collected from a known forward model describing certain sensing or imaging modality. Due to resource constraints, this task is often extremely ill-posed, which necessitates the adoption of expressive prior information to regularize the solution space. Score-based diffusion models, due to its impressive empirical success, have emerged as an appealing candidate of an expressive prior in image reconstruction. In order to accommodate diverse tasks at once, it is of great interest to develop efficient, consistent and robust algorithms that incorporate unconditional score functions of an image prior distribution in conjunction with flexible choices of forward models. This work develops an algorithmic framework for employing score-based diffusion models as an expressive data prior in general nonlinear inverse problems. Motivated by the plug-and-play framework in the imaging community, we introduce a diffusion plug-and-play method (DPnP) that alternatively calls two samplers, a proximal consistency sampler based solely on the likelihood function of the forward model, and a denoising diffusion sampler based solely on the score functions of the image prior. The key insight is that denoising under white Gaussian noise can be solved rigorously via both stochastic (i.e., DDPM-type) and deterministic (i.e., DDIM-type) samplers using the unconditional score functions. We establish both asymptotic and non-asymptotic performance guarantees of DPnP, and provide numerical experiments to illustrate its promise in solving both linear and nonlinear image reconstruction tasks. To the best of our knowledge, DPnP is the first provably-robust posterior sampling method for nonlinear inverse problems using unconditional diffusion priors.
Authors: Hamidreza Kamkari, Brendan Leigh Ross, Jesse C. Cresswell, Anthony L. Caterini, Rahul G. Krishnan, Gabriel Loaiza-Ganem
Abstract: Likelihood-based deep generative models (DGMs) commonly exhibit a puzzling behaviour: when trained on a relatively complex dataset, they assign higher likelihood values to out-of-distribution (OOD) data from simpler sources. Adding to the mystery, OOD samples are never generated by these DGMs despite having higher likelihoods. This two-pronged paradox has yet to be conclusively explained, making likelihood-based OOD detection unreliable. Our primary observation is that high-likelihood regions will not be generated if they contain minimal probability mass. We demonstrate how this seeming contradiction of large densities yet low probability mass can occur around data confined to low-dimensional manifolds. We also show that this scenario can be identified through local intrinsic dimension (LID) estimation, and propose a method for OOD detection which pairs the likelihoods and LID estimates obtained from a pre-trained DGM. Our method can be applied to normalizing flows and score-based diffusion models, and obtains results which match or surpass state-of-the-art OOD detection benchmarks using the same DGM backbones. Our code is available at https://github.com/layer6ai-labs/dgm_ood_detection.
Authors: Amirhossein Abaskohi, Amirhossein Dabiriaghdam, Lele Wang, Giuseppe Carenini
Abstract: Memes, combining text and images, frequently use metaphors to convey persuasive messages, shaping public opinion. Motivated by this, our team engaged in SemEval-2024 Task 4, a hierarchical multi-label classification task designed to identify rhetorical and psychological persuasion techniques embedded within memes. To tackle this problem, we introduced a caption generation step to assess the modality gap and the impact of additional semantic information from images, which improved our result. Our best model utilizes GPT-4 generated captions alongside meme text to fine-tune RoBERTa as the text encoder and CLIP as the image encoder. It outperforms the baseline by a large margin in all 12 subtasks. In particular, it ranked in top-3 across all languages in Subtask 2a, and top-4 in Subtask 2b, demonstrating quantitatively strong performance. The improvement achieved by the introduced intermediate step is likely attributable to the metaphorical essence of images that challenges visual encoders. This highlights the potential for improving abstract visual semantics encoding.
Authors: Tony Lindeberg
Abstract: This paper presents an analysis of properties of two hybrid discretization methods for Gaussian derivatives, based on convolutions with either the normalized sampled Gaussian kernel or the integrated Gaussian kernel followed by central differences. The motivation for studying these discretization methods is that in situations when multiple spatial derivatives of different order are needed at the same scale level, they can be computed significantly more efficiently compared to more direct derivative approximations based on explicit convolutions with either sampled Gaussian kernels or integrated Gaussian kernels. While these computational benefits do also hold for the genuinely discrete approach for computing discrete analogues of Gaussian derivatives, based on convolution with the discrete analogue of the Gaussian kernel followed by central differences, the underlying mathematical primitives for the discrete analogue of the Gaussian kernel, in terms of modified Bessel functions of integer order, may not be available in certain frameworks for image processing, such as when performing deep learning based on scale-parameterized filters in terms of Gaussian derivatives, with learning of the scale levels. In this paper, we present a characterization of the properties of these hybrid discretization methods, in terms of quantitative performance measures concerning the amount of spatial smoothing that they imply, as well as the relative consistency of scale estimates obtained from scale-invariant feature detectors with automatic scale selection, with an emphasis on the behaviour for very small values of the scale parameter, which may differ significantly from corresponding results obtained from the fully continuous scale-space theory, as well as between different types of discretization methods.
Authors: Md Yousuf Harun, Kyungbok Lee, Jhair Gallardo, Giri Krishnan, Christopher Kanan
Abstract: Embeddings produced by pre-trained deep neural networks (DNNs) are widely used; however, their efficacy for downstream tasks can vary widely. We study the factors influencing out-of-distribution (OOD) generalization of pre-trained DNN embeddings through the lens of the tunnel effect hypothesis, which suggests deeper DNN layers compress representations and hinder OOD performance. Contrary to earlier work, we find the tunnel effect is not universal. Based on 10,584 linear probes, we study the conditions that mitigate the tunnel effect by varying DNN architecture, training dataset, image resolution, and augmentations. We quantify each variable's impact using a novel SHAP analysis. Our results emphasize the danger of generalizing findings from toy datasets to broader contexts.
Authors: Mingyuan Meng, Dagan Feng, Lei Bi, Jinman Kim
Abstract: Deformable image registration is a fundamental step for medical image analysis. Recently, transformers have been used for registration and outperformed Convolutional Neural Networks (CNNs). Transformers can capture long-range dependence among image features, which have been shown beneficial for registration. However, due to the high computation/memory loads of self-attention, transformers are typically used at downsampled feature resolutions and cannot capture fine-grained long-range dependence at the full image resolution. This limits deformable registration as it necessitates precise dense correspondence between each image pixel. Multi-layer Perceptrons (MLPs) without self-attention are efficient in computation/memory usage, enabling the feasibility of capturing fine-grained long-range dependence at full resolution. Nevertheless, MLPs have not been extensively explored for image registration and are lacking the consideration of inductive bias crucial for medical registration tasks. In this study, we propose the first correlation-aware MLP-based registration network (CorrMLP) for deformable medical image registration. Our CorrMLP introduces a correlation-aware multi-window MLP block in a novel coarse-to-fine registration architecture, which captures fine-grained multi-range dependence to perform correlation-aware coarse-to-fine registration. Extensive experiments with seven public medical datasets show that our CorrMLP outperforms state-of-the-art deformable registration methods.
Authors: Feiyang Wang, Xingquan Zuo, Hai Huang, Gang Chen
Abstract: Many machine learning models are susceptible to adversarial attacks, with decision-based black-box attacks representing the most critical threat in real-world applications. These attacks are extremely stealthy, generating adversarial examples using hard labels obtained from the target machine learning model. This is typically realized by optimizing perturbation directions, guided by decision boundaries identified through query-intensive exact search, significantly limiting the attack success rate. This paper introduces a novel approach using the Approximation Decision Boundary (ADB) to efficiently and accurately compare perturbation directions without precisely determining decision boundaries. The effectiveness of our ADB approach (ADBA) hinges on promptly identifying suitable ADB, ensuring reliable differentiation of all perturbation directions. For this purpose, we analyze the probability distribution of decision boundaries, confirming that using the distribution's median value as ADB can effectively distinguish different perturbation directions, giving rise to the development of the ADBA-md algorithm. ADBA-md only requires four queries on average to differentiate any pair of perturbation directions, which is highly query-efficient. Extensive experiments on six well-known image classifiers clearly demonstrate the superiority of ADBA and ADBA-md over multiple state-of-the-art black-box attacks. The source code is available at https://github.com/BUPTAIOC/ADBA.