Authors: Amber Yijia Zheng, Raymond A. Yeh
Abstract: Model immunization is an emerging direction that aims to mitigate the potential risk of misuse associated with open-sourced models and advancing adaptation methods. The idea is to make the released models' weights difficult to fine-tune on certain harmful applications, hence the name ``immunized''. Recent work on model immunization focuses on the single-concept setting. However, models need to be immunized against multiple concepts in real-world situations. To address this gap, we propose an immunization algorithm that, simultaneously, learns a single ``difficult initialization'' for adaptation methods over a set of concepts. We achieve this by incorporating a differentiable merging layer that combines a set of model weights adapted over multiple concepts. In our experiments, we demonstrate the effectiveness of multi-concept immunization by generalizing prior work's experiment setup of re-learning and personalization adaptation to multiple concepts.
Authors: Yatian Pang, Peng Jin, Shuo Yang, Bin Lin, Bin Zhu, Zhenyu Tang, Liuhan Chen, Francis E. H. Tay, Ser-Nam Lim, Harry Yang, Li Yuan
Abstract: Autoregressive models, built based on the Next Token Prediction (NTP) paradigm, show great potential in developing a unified framework that integrates both language and vision tasks. In this work, we rethink the NTP for autoregressive image generation and propose a novel Next Patch Prediction (NPP) paradigm. Our key idea is to group and aggregate image tokens into patch tokens containing high information density. With patch tokens as a shorter input sequence, the autoregressive model is trained to predict the next patch, thereby significantly reducing the computational cost. We further propose a multi-scale coarse-to-fine patch grouping strategy that exploits the natural hierarchical property of image data. Experiments on a diverse range of models (100M-1.4B parameters) demonstrate that the next patch prediction paradigm could reduce the training cost to around 0.6 times while improving image generation quality by up to 1.0 FID score on the ImageNet benchmark. We highlight that our method retains the original autoregressive model architecture without introducing additional trainable parameters or specifically designing a custom image tokenizer, thus ensuring flexibility and seamless adaptation to various autoregressive models for visual generation.
Authors: Ho Kei Cheng, Masato Ishii, Akio Hayakawa, Takashi Shibuya, Alexander Schwing, Yuki Mitsufuji
Abstract: We propose to synthesize high-quality and synchronized audio, given video and optional text conditions, using a novel multimodal joint training framework MMAudio. In contrast to single-modality training conditioned on (limited) video data only, MMAudio is jointly trained with larger-scale, readily available text-audio data to learn to generate semantically aligned high-quality audio samples. Additionally, we improve audio-visual synchrony with a conditional synchronization module that aligns video conditions with audio latents at the frame level. Trained with a flow matching objective, MMAudio achieves new video-to-audio state-of-the-art among public models in terms of audio quality, semantic alignment, and audio-visual synchronization, while having a low inference time (1.23s to generate an 8s clip) and just 157M parameters. MMAudio also achieves surprisingly competitive performance in text-to-audio generation, showing that joint training does not hinder single-modality performance. Code and demo are available at: https://hkchengrex.github.io/MMAudio
Authors: Aneesha Guna, Parth Ganeriwala, Siddhartha Bhattacharyya
Abstract: With the advancement of deep learning methods it is imperative that autonomous systems will increasingly become intelligent with the inclusion of advanced machine learning algorithms to execute a variety of autonomous operations. One such task involves the design and evaluation for a subsystem of the perception system for object detection and tracking. The challenge in the creation of software to solve the task is in discovering the need for a dataset, annotation of the dataset, selection of features, integration and refinement of existing algorithms, while evaluating performance metrics through training and testing. This research effort focuses on the development of a machine learning pipeline emphasizing the inclusion of assurance methods with increasing automation. In the process, a new dataset was created by collecting videos of moving object such as Roomba vacuum cleaner, emulating search and rescue (SAR) for indoor environment. Individual frames were extracted from the videos and labeled using a combination of manual and automated techniques. This annotated dataset was refined for accuracy by initially training it on YOLOv4. After the refinement of the dataset it was trained on a second YOLOv4 and a Mask R-CNN model, which is deployed on a Parrot Mambo drone to perform real-time object detection and tracking. Experimental results demonstrate the effectiveness of the models in accurately detecting and tracking the Roomba across multiple trials, achieving an average loss of 0.1942 and 96% accuracy.
Authors: Abdullah Al Rahat, Hemanth Venkateswara
Abstract: This paper proposes a dataset augmentation method by fine-tuning pre-trained diffusion models. Generating images using a pre-trained diffusion model with textual conditioning often results in domain discrepancy between real data and generated images. We propose a fine-tuning approach where we adapt the diffusion model by conditioning it with real images and novel text embeddings. We introduce a unique procedure called Mixing Visual Concepts (MVC) where we create novel text embeddings from image captions. The MVC enables us to generate multiple images which are diverse and yet similar to the real data enabling us to perform effective dataset augmentation. We perform comprehensive qualitative and quantitative evaluations with the proposed dataset augmentation approach showcasing both coarse-grained and finegrained changes in generated images. Our approach outperforms state-of-the-art augmentation techniques on benchmark classification tasks.
Authors: Meghana Karri, Amit Soni Arya, Koushik Biswas, Nicol`o Gennaro, Vedat Cicek, Gorkem Durak, Yuri S. Velichko, Ulas Bagci
Abstract: This work proposes a novel framework, Uncertainty-Guided Cross Attention Ensemble Mean Teacher (UG-CEMT), for achieving state-of-the-art performance in semi-supervised medical image segmentation. UG-CEMT leverages the strengths of co-training and knowledge distillation by combining a Cross-attention Ensemble Mean Teacher framework (CEMT) inspired by Vision Transformers (ViT) with uncertainty-guided consistency regularization and Sharpness-Aware Minimization emphasizing uncertainty. UG-CEMT improves semi-supervised performance while maintaining a consistent network architecture and task setting by fostering high disparity between sub-networks. Experiments demonstrate significant advantages over existing methods like Mean Teacher and Cross-pseudo Supervision in terms of disparity, domain generalization, and medical image segmentation performance. UG-CEMT achieves state-of-the-art results on multi-center prostate MRI and cardiac MRI datasets, where object segmentation is particularly challenging. Our results show that using only 10\% labeled data, UG-CEMT approaches the performance of fully supervised methods, demonstrating its effectiveness in exploiting unlabeled data for robust medical image segmentation. The code is publicly available at \url{https://github.com/Meghnak13/UG-CEMT}
Authors: Zeeshan Nisar, Thomas Lampert
Abstract: Histopathology, the microscopic examination of tissue samples, is essential for disease diagnosis and prognosis. Accurate segmentation and identification of key regions in histopathology images are crucial for developing automated solutions. However, state-of-art deep learning segmentation methods like UNet require extensive labels, which is both costly and time-consuming, particularly when dealing with multiple stainings. To mitigate this, multi-stain segmentation methods such as MDS1 and UDAGAN have been developed, which reduce the need for labels by requiring only one (source) stain to be labelled. Nonetheless, obtaining source stain labels can still be challenging, and segmentation models fail when they are unavailable. This article shows that through self-supervised pre-training, including SimCLR, BYOL, and a novel approach, HR-CS-CO, the performance of these segmentation methods (UNet, MDS1, and UDAGAN) can be retained even with 95% fewer labels. Notably, with self-supervised pre-training and using only 5% labels, the performance drops are minimal: 5.9% for UNet, 4.5% for MDS1, and 6.2% for UDAGAN, compared to their respective fully supervised counterparts (without pre-training, using 100% labels). The code is available from https://github.com/zeeshannisar/improve_kidney_glomeruli_segmentation [to be made public upon acceptance].
URLs: https://github.com/zeeshannisar/improve_kidney_glomeruli_segmentation
Authors: Austin Stone, Hagen Soltau, Robert Geirhos, Xi Yi, Ye Xia, Bingyi Cao, Kaifeng Chen, Abhijit Ogale, Jonathon Shlens
Abstract: Visual imagery does not consist of solitary objects, but instead reflects the composition of a multitude of fluid concepts. While there have been great advances in visual representation learning, such advances have focused on building better representations for a small number of discrete objects bereft of an understanding of how these objects are interacting. One can observe this limitation in representations learned through captions or contrastive learning -- where the learned model treats an image essentially as a bag of words. Several works have attempted to address this limitation through the development of bespoke learned architectures to directly address the shortcomings in compositional learning. In this work, we focus on simple, and scalable approaches. In particular, we demonstrate that by substantially improving weakly labeled data, i.e. captions, we can vastly improve the performance of standard contrastive learning approaches. Previous CLIP models achieved near chance rate on challenging tasks probing compositional learning. However, our simple approach boosts performance of CLIP substantially and surpasses all bespoke architectures. Furthermore, we showcase our results on a relatively new captioning benchmark derived from DOCCI. We demonstrate through a series of ablations that a standard CLIP model trained with enhanced data may demonstrate impressive performance on image retrieval tasks.
Authors: Zhuowen Shen, Yuan Liu, Zhang Chen, Zhong Li, Jiepeng Wang, Yongqing Liang, Zhengming Yu, Jingdong Zhang, Yi Xu, Scott Schaefer, Xin Li, Wenping Wang
Abstract: Gaussian splatting has achieved impressive improvements for both novel-view synthesis and surface reconstruction from multi-view images. However, current methods still struggle to reconstruct high-quality surfaces from only sparse view input images using Gaussian splatting. In this paper, we propose a novel method called SolidGS to address this problem. We observed that the reconstructed geometry can be severely inconsistent across multi-views, due to the property of Gaussian function in geometry rendering. This motivates us to consolidate all Gaussians by adopting a more solid kernel function, which effectively improves the surface reconstruction quality. With the additional help of geometrical regularization and monocular normal estimation, our method achieves superior performance on the sparse view surface reconstruction than all the Gaussian splatting methods and neural field methods on the widely used DTU, Tanks-and-Temples, and LLFF datasets.
Authors: Vahid Zehtab, David B. Lindell, Marcus A. Brubaker, Michael S. Brown
Abstract: 3D color lookup tables (LUTs) enable precise color manipulation by mapping input RGB values to specific output RGB values. 3D LUTs are instrumental in various applications, including video editing, in-camera processing, photographic filters, computer graphics, and color processing for displays. While an individual LUT does not incur a high memory overhead, software and devices may need to store dozens to hundreds of LUTs that can take over 100 MB. This work aims to develop a neural network architecture that can encode hundreds of LUTs in a single compact representation. To this end, we propose a model with a memory footprint of less than 0.25 MB that can reconstruct 512 LUTs with only minor color distortion ($\bar{\Delta}E_M$ $\leq$ 2.0) over the entire color gamut. We also show that our network can weight colors to provide further quality gains on natural image colors ($\bar{\Delta}{E}_M$ $\leq$ 1.0). Finally, we show that minor modifications to the network architecture enable a bijective encoding that produces LUTs that are invertible, allowing for reverse color processing. Our code is available at https://github.com/vahidzee/ennelut.
Authors: Pou-Chun Kung, Xianling Zhang, Katherine A. Skinner, Nikita Jaipuria
Abstract: Photorealistic 3D scene reconstruction plays an important role in autonomous driving, enabling the generation of novel data from existing datasets to simulate safety-critical scenarios and expand training data without additional acquisition costs. Gaussian Splatting (GS) facilitates real-time, photorealistic rendering with an explicit 3D Gaussian representation of the scene, providing faster processing and more intuitive scene editing than the implicit Neural Radiance Fields (NeRFs). While extensive GS research has yielded promising advancements in autonomous driving applications, they overlook two critical aspects: First, existing methods mainly focus on low-speed and feature-rich urban scenes and ignore the fact that highway scenarios play a significant role in autonomous driving. Second, while LiDARs are commonplace in autonomous driving platforms, existing methods learn primarily from images and use LiDAR only for initial estimates or without precise sensor modeling, thus missing out on leveraging the rich depth information LiDAR offers and limiting the ability to synthesize LiDAR data. In this paper, we propose a novel GS method for dynamic scene synthesis and editing with improved scene reconstruction through LiDAR supervision and support for LiDAR rendering. Unlike prior works that are tested mostly on urban datasets, to the best of our knowledge, we are the first to focus on the more challenging and highly relevant highway scenes for autonomous driving, with sparse sensor views and monotone backgrounds.
Authors: Minseok Son, Inyong Koo, Jinyoung Park, Changick Kim
Abstract: When trained with severely imbalanced data, deep neural networks often struggle to accurately recognize classes with only a few samples. Previous studies in long-tailed recognition have attempted to rebalance biased learning using known sample distributions, primarily addressing different classification difficulties at the class level. However, these approaches often overlook the instance difficulty variation within each class. In this paper, we propose a difficulty-aware balancing margin (DBM) loss, which considers both class imbalance and instance difficulty. DBM loss comprises two components: a class-wise margin to mitigate learning bias caused by imbalanced class frequencies, and an instance-wise margin assigned to hard positive samples based on their individual difficulty. DBM loss improves class discriminativity by assigning larger margins to more difficult samples. Our method seamlessly combines with existing approaches and consistently improves performance across various long-tailed recognition benchmarks.
Authors: Saehyung Lee, Seunghyun Yoon, Trung Bui, Jing Shi, Sungroh Yoon
Abstract: Multimodal large language models (MLLMs) excel at generating highly detailed captions but often produce hallucinations. Our analysis reveals that existing hallucination detection methods struggle with detailed captions. We attribute this to the increasing reliance of MLLMs on their generated text, rather than the input image, as the sequence length grows. To address this issue, we propose a multiagent approach that leverages LLM-MLLM collaboration to correct given captions. Additionally, we introduce an evaluation framework and a benchmark dataset to facilitate the systematic analysis of detailed captions. Our experiments demonstrate that our proposed evaluation method better aligns with human judgments of factuality than existing metrics and that existing approaches to improve the MLLM factuality may fall short in hyper-detailed image captioning tasks. In contrast, our proposed method significantly enhances the factual accuracy of captions, even improving those generated by GPT-4V. Finally, we highlight a limitation of VQA-centric benchmarking by demonstrating that an MLLM's performance on VQA benchmarks may not correlate with its ability to generate detailed image captions.
Authors: Joshua Springer, Gylfi {\TH}\'or Gu{\dh}mundsson, Marcel Kyas
Abstract: A remaining challenge in multirotor drone flight is the autonomous identification of viable landing sites in unstructured environments. One approach to solve this problem is to create lightweight, appearance-based terrain classifiers that can segment a drone's RGB images into safe and unsafe regions. However, such classifiers require data sets of images and masks that can be prohibitively expensive to create. We propose a pipeline to automatically generate synthetic data sets to train these classifiers, leveraging modern drones' ability to survey terrain automatically and the ability to automatically calculate landing safety masks from terrain models derived from such surveys. We then train a U-Net on the synthetic data set, test it on real-world data for validation, and demonstrate it on our drone platform in real-time.
Authors: Hengjia Li, Yang Liu, Yibo Zhao, Haoran Cheng, Yang Yang, Linxuan Xia, Zekai Luo, Qibo Qiu, Boxi Wu, Tu Zheng, Zheng Yang, Deng Cai
Abstract: Recently, 3D generative domain adaptation has emerged to adapt the pre-trained generator to other domains without collecting massive datasets and camera pose distributions. Typically, they leverage large-scale pre-trained text-to-image diffusion models to synthesize images for the target domain and then fine-tune the 3D model. However, they suffer from the tedious pipeline of data generation, which inevitably introduces pose bias between the source domain and synthetic dataset. Furthermore, they are not generalized to support one-shot image-guided domain adaptation, which is more challenging due to the more severe pose bias and additional identity bias introduced by the single image reference. To address these issues, we propose GCA-3D, a generalized and consistent 3D domain adaptation method without the intricate pipeline of data generation. Different from previous pipeline methods, we introduce multi-modal depth-aware score distillation sampling loss to efficiently adapt 3D generative models in a non-adversarial manner. This multi-modal loss enables GCA-3D in both text prompt and one-shot image prompt adaptation. Besides, it leverages per-instance depth maps from the volume rendering module to mitigate the overfitting problem and retain the diversity of results. To enhance the pose and identity consistency, we further propose a hierarchical spatial consistency loss to align the spatial structure between the generated images in the source and target domain. Experiments demonstrate that GCA-3D outperforms previous methods in terms of efficiency, generalization, pose accuracy, and identity consistency.
Authors: Jiaxin Wu, Wengyu Zhang, Xiao-Yong Wei, Qing Li
Abstract: In this paper, we present our methods and results for the Video-To-Text (VTT) task at TRECVid 2024, exploring the capabilities of Vision-Language Models (VLMs) like LLaVA and LLaVA-NeXT-Video in generating natural language descriptions for video content. We investigate the impact of fine-tuning VLMs on VTT datasets to enhance description accuracy, contextual relevance, and linguistic consistency. Our analysis reveals that fine-tuning substantially improves the model's ability to produce more detailed and domain-aligned text, bridging the gap between generic VLM tasks and the specialized needs of VTT. Experimental results demonstrate that our fine-tuned model outperforms baseline VLMs across various evaluation metrics, underscoring the importance of domain-specific tuning for complex VTT tasks.
Authors: Jiaxin Wu, Yiyang Jiang, Xiao-Yong Wei, Qing Li
Abstract: Video Corpus Visual Answer Localization (VCVAL) includes question-related video retrieval and visual answer localization in the videos. Specifically, we use text-to-text retrieval to find relevant videos for a medical question based on the similarity of video transcript and answers generated by GPT4. For the visual answer localization, the start and end timestamps of the answer are predicted by the alignments on both visual content and subtitles with queries. For the Query-Focused Instructional Step Captioning (QFISC) task, the step captions are generated by GPT4. Specifically, we provide the video captions generated by the LLaVA-Next-Video model and the video subtitles with timestamps as context, and ask GPT4 to generate step captions for the given medical query. We only submit one run for evaluation and it obtains a F-score of 11.92 and mean IoU of 9.6527.
Authors: Aroj Subedi, Pradip Ganesh, Sandip Mishra
Abstract: Contour map has contour lines that are significant in building a Digital Elevation Model (DEM). During the digitization and pre-processing of contour maps, the contour line intersects with each other or break apart resulting in broken contour segments. These broken segments impose a greater risk while building DEM leading to a faulty model. In this project, a simple yet efficient mechanism is used to match and reconnect the endpoints of the broken segments accurately and efficiently. The matching of the endpoints is done using the concept of minimum Euclidean distance and gradient direction while the Cubic Hermite spline interpolation technique is used to reconnect the endpoints by estimating the values using a mathematical function that minimizes overall surface curvature resulting in a smooth curve. The purpose of this work is to reconnect the broken contour lines generated during the digitization of the contour map, to help build the most appropriate digital elevation model for the corresponding contour map.
Authors: Chen Duan, Qianyi Jiang, Pei Fu, Jiamin Chen, Shengxi Li, Zining Wang, Shan Guo, Junfeng Luo
Abstract: In the field of scene text spotting, previous OCR methods primarily relied on image encoders and pre-trained text information, but they often overlooked the advantages of incorporating human language instructions. To address this gap, we propose InstructOCR, an innovative instruction-based scene text spotting model that leverages human language instructions to enhance the understanding of text within images. Our framework employs both text and image encoders during training and inference, along with instructions meticulously designed based on text attributes. This approach enables the model to interpret text more accurately and flexibly. Extensive experiments demonstrate the effectiveness of our model and we achieve state-of-the-art results on widely used benchmarks. Furthermore, the proposed framework can be seamlessly applied to scene text VQA tasks. By leveraging instruction strategies during pre-training, the performance on downstream VQA tasks can be significantly improved, with a 2.6% increase on the TextVQA dataset and a 2.1% increase on the ST-VQA dataset. These experimental results provide insights into the benefits of incorporating human language instructions for OCR-related tasks.
Authors: Ke Yan, Qing Cai, Fan Zhang, Ziyan Cao, Zhi Liu
Abstract: Although semi-supervised learning has made significant advances in the field of medical image segmentation, fully annotating a volumetric sample slice by slice remains a costly and time-consuming task. Even worse, most of the existing approaches pay much attention to image-level information and ignore semantic features, resulting in the inability to perceive weak boundaries. To address these issues, we propose a novel Semantic-Guided Triplet Co-training (SGTC) framework, which achieves high-end medical image segmentation by only annotating three orthogonal slices of a few volumetric samples, significantly alleviating the burden of radiologists. Our method consist of two main components. Specifically, to enable semantic-aware, fine-granular segmentation and enhance the quality of pseudo-labels, a novel semantic-guided auxiliary learning mechanism is proposed based on the pretrained CLIP. In addition, focusing on a more challenging but clinically realistic scenario, a new triple-view disparity training strategy is proposed, which uses sparse annotations (i.e., only three labeled slices of a few volumes) to perform co-training between three sub-networks, significantly improving the robustness. Extensive experiments on three public medical datasets demonstrate that our method outperforms most state-of-the-art semi-supervised counterparts under sparse annotation settings. The source code is available at https://github.com/xmeimeimei/SGTC.
Authors: Qi Zang, Jiayi Yang, Shuang Wang, Dong Zhao, Wenjun Yi, Zhun Zhong
Abstract: Data-driven deep learning models have enabled tremendous progress in change detection (CD) with the support of pixel-level annotations. However, collecting diverse data and manually annotating them is costly, laborious, and knowledge-intensive. Existing generative methods for CD data synthesis show competitive potential in addressing this issue but still face the following limitations: 1) difficulty in flexibly controlling change events, 2) dependence on additional data to train the data generators, 3) focus on specific change detection tasks. To this end, this paper focuses on the semantic CD (SCD) task and develops a multi-temporal SCD data generator ChangeDiff by exploring powerful diffusion models. ChangeDiff innovatively generates change data in two steps: first, it uses text prompts and a text-to-layout (T2L) model to create continuous layouts, and then it employs layout-to-image (L2I) to convert these layouts into images. Specifically, we propose multi-class distribution-guided text prompts (MCDG-TP), allowing for layouts to be generated flexibly through controllable classes and their corresponding ratios. Subsequently, to generalize the T2L model to the proposed MCDG-TP, a class distribution refinement loss is further designed as training supervision. %For the former, a multi-classdistribution-guided text prompt (MCDG-TP) is proposed to complement via controllable classes and ratios. To generalize the text-to-image diffusion model to the proposed MCDG-TP, a class distribution refinement loss is designed as training supervision. For the latter, MCDG-TP in three modes is proposed to synthesize new layout masks from various texts. Our generated data shows significant progress in temporal continuity, spatial diversity, and quality realism, empowering change detectors with accuracy and transferability. The code is available at https://github.com/DZhaoXd/ChangeDiff
Authors: Yixiong Huo, Guangfeng Jiang, Hongyang Wei, Ji Liu, Song Zhang, Han Liu, Xingliang Huang, Mingjie Lu, Jinzhang Peng, Dong Li, Lu Tian, Emad Barsoum
Abstract: 3D Gaussian Splatting (3D GS) has gained popularity due to its faster rendering speed and high-quality novel view synthesis. Some researchers have explored using 3D GS for reconstructing driving scenes. However, these methods often rely on various data types, such as depth maps, 3D boxes, and trajectories of moving objects. Additionally, the lack of annotations for synthesized images limits their direct application in downstream tasks. To address these issues, we propose EGSRAL, a 3D GS-based method that relies solely on training images without extra annotations. EGSRAL enhances 3D GS's capability to model both dynamic objects and static backgrounds and introduces a novel adaptor for auto labeling, generating corresponding annotations based on existing annotations. We also propose a grouping strategy for vanilla 3D GS to address perspective issues in rendering large-scale, complex scenes. Our method achieves state-of-the-art performance on multiple datasets without any extra annotation. For example, the PSNR metric reaches 29.04 on the nuScenes dataset. Moreover, our automated labeling can significantly improve the performance of 2D/3D detection tasks. Code is available at https://github.com/jiangxb98/EGSRAL.
Authors: Yichun Tai, Zhenzhen Huang, Tao Peng, Zhijiang Zhang
Abstract: Current saliency-based defect detection methods show promise in industrial settings, but the unpredictability of defects in steel production environments complicates dataset creation, hampering model performance. Existing data augmentation approaches using generative models often require pixel-level annotations, which are time-consuming and resource-intensive. To address this, we introduce DefFiller, a mask-conditioned defect generation method that leverages a layout-to-image diffusion model. DefFiller generates defect samples paired with mask conditions, eliminating the need for pixel-level annotations and enabling direct use in model training. We also develop an evaluation framework to assess the quality of generated samples and their impact on detection performance. Experimental results on the SD-Saliency-900 dataset demonstrate that DefFiller produces high-quality defect images that accurately match the provided mask conditions, significantly enhancing the performance of saliency-based defect detection models trained on the augmented dataset.
Authors: Takero Yoshida, Yuikazu Ito, Yoshihiro Fujiwara, Shinji Tsuchida, Daisuke Sugiyama, Daisuke Matsuoka
Abstract: Japan Agency for Marine-Earth Science and Technology (JAMSTEC) has made available the JAMSTEC Earth Deep-sea Image (J-EDI), a deep-sea video and image archive (https://www.godac.jamstec.go.jp/jedi/e/index.html). This archive serves as a valuable resource for researchers and scholars interested in deep-sea imagery. The dataset comprises images and videos of deep-sea phenomena, predominantly of marine organisms, but also of the seafloor and physical processes. In this study, we propose J-EDI QA, a benchmark for understanding images of deep-sea organisms using a multimodal large language model (LLM). The benchmark is comprised of 100 images, accompanied by questions and answers with four options by JAMSTEC researchers for each image. The QA pairs are provided in Japanese, and the benchmark assesses the ability to understand deep-sea species in Japanese. In the evaluation presented in this paper, OpenAI o1 achieved a 50% correct response rate. This result indicates that even with the capabilities of state-of-the-art models as of December 2024, deep-sea species comprehension is not yet at an expert level. Further advances in deep-sea species-specific LLMs are therefore required.
Authors: Yuhao Li, Jianping Li, Zhen Dong, Yuan Wang, Bisheng Yang
Abstract: Image to point cloud global localization is crucial for robot navigation in GNSS-denied environments and has become increasingly important for multi-robot map fusion and urban asset management. The modality gap between images and point clouds poses significant challenges for cross-modality fusion. Current cross-modality global localization solutions either require modality unification, which leads to information loss, or rely on engineered training schemes to encode multi-modality features, which often lack feature alignment and relation consistency. To address these limitations, we propose, SaliencyI2PLoc, a novel contrastive learning based architecture that fuses the saliency map into feature aggregation and maintains the feature relation consistency on multi-manifold spaces. To alleviate the pre-process of data mining, the contrastive learning framework is applied which efficiently achieves cross-modality feature mapping. The context saliency-guided local feature aggregation module is designed, which fully leverages the contribution of the stationary information in the scene generating a more representative global feature. Furthermore, to enhance the cross-modality feature alignment during contrastive learning, the consistency of relative relationships between samples in different manifold spaces is also taken into account. Experiments conducted on urban and highway scenario datasets demonstrate the effectiveness and robustness of our method. Specifically, our method achieves a Recall@1 of 78.92% and a Recall@20 of 97.59% on the urban scenario evaluation dataset, showing an improvement of 37.35% and 18.07%, compared to the baseline method. This demonstrates that our architecture efficiently fuses images and point clouds and represents a significant step forward in cross-modality global localization. The project page and code will be released.
Authors: Xiaoting Zhang, Tao Wang, Junhao Ji
Abstract: While large-scale face datasets have advanced deep learning-based face analysis, they also raise privacy concerns due to the sensitive personal information they contain. Recent schemes have implemented differential privacy to protect face datasets. However, these schemes generally treat each image as a separate database, which does not fully meet the core requirements of differential privacy. In this paper, we propose a semantic-level differential privacy protection scheme that applies to the entire face dataset. Unlike pixel-level differential privacy approaches, our scheme guarantees that semantic privacy in faces is not compromised. The key idea is to convert unstructured data into structured data to enable the application of differential privacy. Specifically, we first extract semantic information from the face dataset to build an attribute database, then apply differential perturbations to obscure this attribute data, and finally use an image synthesis model to generate a protected face dataset. Extensive experimental results show that our scheme can maintain visual naturalness and balance the privacy-utility trade-off compared to the mainstream schemes.
Authors: Yuzhi Wu, Jun Liu, Guangfeng Jiang, Weijian Liu, Danilo Orlando
Abstract: As a cost-effective and robust technology, automotive radar has seen steady improvement during the last years, making it an appealing complement to commonly used sensors like camera and LiDAR in autonomous driving. Radio frequency data with rich semantic information are attracting more and more attention. Most current radar-based models take radio frequency image sequences as the input. However, these models heavily rely on convolutional neural networks and leave out the spatial-temporal semantic context during the encoding stage. To solve these problems, we propose a model called Mask-RadarNet to fully utilize the hierarchical semantic features from the input radar data. Mask-RadarNet exploits the combination of interleaved convolution and attention operations to replace the traditional architecture in transformer-based models. In addition, patch shift is introduced to the Mask-RadarNet for efficient spatial-temporal feature learning. By shifting part of patches with a specific mosaic pattern in the temporal dimension, Mask-RadarNet achieves competitive performance while reducing the computational burden of the spatial-temporal modeling. In order to capture the spatial-temporal semantic contextual information, we design the class masking attention module (CMAM) in our encoder. Moreover, a lightweight auxiliary decoder is added to our model to aggregate prior maps generated from the CMAM. Experiments on the CRUW dataset demonstrate the superiority of the proposed method to some state-of-the-art radar-based object detection algorithms. With relatively lower computational complexity and fewer parameters, the proposed Mask-RadarNet achieves higher recognition accuracy for object detection in autonomous driving.
Authors: Guanzhong Zeng, Jingjing Wang, Zefu Xu, Pengwei Yin, Wenqi Ren, Di Xie, Jiang Zhu
Abstract: Gaze estimation methods encounter significant performance deterioration when being evaluated across different domains, because of the domain gap between the testing and training data. Existing methods try to solve this issue by reducing the deviation of data distribution, however, they ignore the existence of label deviation in the data due to the acquisition mechanism of the gaze label and the individual physiological differences. In this paper, we first point out that the influence brought by the label deviation cannot be ignored, and propose a gaze label alignment algorithm (GLA) to eliminate the label distribution deviation. Specifically, we first train the feature extractor on all domains to get domain invariant features, and then select an anchor domain to train the gaze regressor. We predict the gaze label on remaining domains and use a mapping function to align the labels. Finally, these aligned labels can be used to train gaze estimation models. Therefore, our method can be combined with any existing method. Experimental results show that our GLA method can effectively alleviate the label distribution shift, and SOTA gaze estimation methods can be further improved obviously.
Authors: Jen-Hao Rick Chang, Yuyang Wang, Miguel Angel Bautista Martin, Jiatao Gu, Josh Susskind, Oncel Tuzel
Abstract: We introduce Shape Tokens, a 3D representation that is continuous, compact, and easy to incorporate into machine learning models. Shape Tokens act as conditioning vectors that represent shape information in a 3D flow-matching model. The flow-matching model is trained to approximate probability density functions corresponding to delta functions concentrated on the surfaces of shapes in 3D. By attaching Shape Tokens to various machine learning models, we can generate new shapes, convert images to 3D, align 3D shapes with text and images, and render shapes directly at variable, user specified, resolution. Moreover, Shape Tokens enable a systematic analysis of geometric properties such as normal, density, and deformation field. Across all tasks and experiments, utilizing Shape Tokens demonstrate strong performance compared to existing baselines.
Authors: Jiahe Wan
Abstract: Compositional understanding allows visual language models to interpret complex relationships between objects, attributes, and relations in images and text. However, most existing methods often rely on hard negative examples and fine-tuning, which can overestimate improvements and are limited by the difficulty of obtaining hard negatives. In this work, we introduce Zero-Shot Compositional Understanding (ZS-CU), a novel task that enhances compositional understanding without requiring hard negative training data. We propose YUKINO (Yielded Compositional Understanding Knowledge via Textual Inversion with NO), which uses textual inversion to map unlabeled images to pseudo-tokens in a pre-trained CLIP model. We propose introducing "no" logical regularization to address the issue of token interaction in inversion. Additionally, we suggest using knowledge distillation to reduce the time complexity of textual inversion. Experimental results show that YUKINO outperforms the existing multi-modal SOTA models by over 8% on the SugarCREPE benchmark, and also achieves significant improvements in image retrieval tasks.
Authors: Kushagra Srivastava, Damodar Datta Kancharla, Rizvi Tahereen, Pradeep Kumar Ramancharla, Ravi Kiran Sarvadevabhatla, Harikumar Kandath
Abstract: Crack segmentation plays a crucial role in ensuring the structural integrity and seismic safety of civil structures. However, existing crack segmentation algorithms encounter challenges in maintaining accuracy with domain shifts across datasets. To address this issue, we propose a novel deep network that employs incremental training with unsupervised domain adaptation (UDA) using adversarial learning, without a significant drop in accuracy in the source domain. Our approach leverages an encoder-decoder architecture, consisting of both domain-invariant and domain-specific parameters. The encoder learns shared crack features across all domains, ensuring robustness to domain variations. Simultaneously, the decoder's domain-specific parameters capture domain-specific features unique to each domain. By combining these components, our model achieves improved crack segmentation performance. Furthermore, we introduce BuildCrack, a new crack dataset comparable to sub-datasets of the well-established CrackSeg9K dataset in terms of image count and crack percentage. We evaluate our proposed approach against state-of-the-art UDA methods using different sub-datasets of CrackSeg9K and our custom dataset. Our experimental results demonstrate a significant improvement in crack segmentation accuracy and generalization across target domains compared to other UDA methods - specifically, an improvement of 0.65 and 2.7 mIoU on source and target domains respectively.
Authors: Xiuli Bi, Jian Lu, Bo Liu, Xiaodong Cun, Yong Zhang, Weisheng Li, Bin Xiao
Abstract: Benefiting from large-scale pre-training of text-video pairs, current text-to-video (T2V) diffusion models can generate high-quality videos from the text description. Besides, given some reference images or videos, the parameter-efficient fine-tuning method, i.e. LoRA, can generate high-quality customized concepts, e.g., the specific subject or the motions from a reference video. However, combining the trained multiple concepts from different references into a single network shows obvious artifacts. To this end, we propose CustomTTT, where we can joint custom the appearance and the motion of the given video easily. In detail, we first analyze the prompt influence in the current video diffusion model and find the LoRAs are only needed for the specific layers for appearance and motion customization. Besides, since each LoRA is trained individually, we propose a novel test-time training technique to update parameters after combination utilizing the trained customized models. We conduct detailed experiments to verify the effectiveness of the proposed methods. Our method outperforms several state-of-the-art works in both qualitative and quantitative evaluations.
Authors: Xiaohan Zhang, Sebastian Starke, Vladimir Guzov, Zhensong Zhang, Eduardo P\'erez Pellitero, Gerard Pons-Moll
Abstract: Synthesizing natural human motion that adapts to complex environments while allowing creative control remains a fundamental challenge in motion synthesis. Existing models often fall short, either by assuming flat terrain or lacking the ability to control motion semantics through text. To address these limitations, we introduce SCENIC, a diffusion model designed to generate human motion that adapts to dynamic terrains within virtual scenes while enabling semantic control through natural language. The key technical challenge lies in simultaneously reasoning about complex scene geometry while maintaining text control. This requires understanding both high-level navigation goals and fine-grained environmental constraints. The model must ensure physical plausibility and precise navigation across varied terrain, while also preserving user-specified text control, such as ``carefully stepping over obstacles" or ``walking upstairs like a zombie." Our solution introduces a hierarchical scene reasoning approach. At its core is a novel scene-dependent, goal-centric canonicalization that handles high-level goal constraint, and is complemented by an ego-centric distance field that captures local geometric details. This dual representation enables our model to generate physically plausible motion across diverse 3D scenes. By implementing frame-wise text alignment, our system achieves seamless transitions between different motion styles while maintaining scene constraints. Experiments demonstrate our novel diffusion model generates arbitrarily long human motions that both adapt to complex scenes with varying terrain surfaces and respond to textual prompts. Additionally, we show SCENIC can generalize to four real-scene datasets. Our code, dataset, and models will be released at \url{https://virtualhumans.mpi-inf.mpg.de/scenic/}.
Authors: Xiang Fang, Arvind Easwaran, Blaise Genest, Ponnuthurai Nagaratnam Suganthan
Abstract: This paper focuses on a significant yet challenging task: out-of-distribution detection (OOD detection), which aims to distinguish and reject test samples with semantic shifts, so as to prevent models trained on in-distribution (ID) data from producing unreliable predictions. Although previous works have made decent success, they are ineffective for real-world challenging applications since these methods simply regard all unlabeled data as OOD data and ignore the case that different datasets have different label granularity. For example, "cat" on CIFAR-10 and "tabby cat" on Tiny-ImageNet share the same semantics but have different labels due to various label granularity. To this end, in this paper, we propose a novel Adaptive Hierarchical Graph Cut network (AHGC) to deeply explore the semantic relationship between different images. Specifically, we construct a hierarchical KNN graph to evaluate the similarities between different images based on the cosine similarity. Based on the linkage and density information of the graph, we cut the graph into multiple subgraphs to integrate these semantics-similar samples. If the labeled percentage in a subgraph is larger than a threshold, we will assign the label with the highest percentage to unlabeled images. To further improve the model generalization, we augment each image into two augmentation versions, and maximize the similarity between the two versions. Finally, we leverage the similarity score for OOD detection. Extensive experiments on two challenging benchmarks (CIFAR- 10 and CIFAR-100) illustrate that in representative cases, AHGC outperforms state-of-the-art OOD detection methods by 81.24% on CIFAR-100 and by 40.47% on CIFAR-10 in terms of "FPR95", which shows the effectiveness of our AHGC.
Authors: Mengshi Qi, Yuxin Yang, Huadong Ma
Abstract: Effective modeling of group interactions and dynamic semantic intentions is crucial for forecasting behaviors like trajectories or movements. In complex scenarios like sports, agents' trajectories are influenced by group interactions and intentions, including team strategies and opponent actions. To this end, we propose a novel diffusion-based trajectory prediction framework that integrates group-level interactions into a conditional diffusion model, enabling the generation of diverse trajectories aligned with specific group activity. To capture dynamic semantic intentions, we frame group interaction prediction as a cooperative game, using Banzhaf interaction to model cooperation trends. We then fuse semantic intentions with enhanced agent embeddings, which are refined through both global and local aggregation. Furthermore, we expand the NBA SportVU dataset by adding human annotations of team-level tactics for trajectory and tactic prediction tasks. Extensive experiments on three widely-adopted datasets demonstrate that our model outperforms state-of-the-art methods. Our source code and data are available at https://github.com/aurora-xin/Group2Int-trajectory.
Authors: Xinzhe Li, Jiahui Zhan, Shengfeng He, Yangyang Xu, Junyu Dong, Huaidong Zhang, Yong Du
Abstract: Personalized image generation has made significant strides in adapting content to novel concepts. However, a persistent challenge remains: balancing the accurate reconstruction of unseen concepts with the need for editability according to the prompt, especially when dealing with the complex nuances of facial features. In this study, we delve into the temporal dynamics of the text-to-image conditioning process, emphasizing the crucial role of stage partitioning in introducing new concepts. We present PersonaMagic, a stage-regulated generative technique designed for high-fidelity face customization. Using a simple MLP network, our method learns a series of embeddings within a specific timestep interval to capture face concepts. Additionally, we develop a Tandem Equilibrium mechanism that adjusts self-attention responses in the text encoder, balancing text description and identity preservation, improving both areas. Extensive experiments confirm the superiority of PersonaMagic over state-of-the-art methods in both qualitative and quantitative evaluations. Moreover, its robustness and flexibility are validated in non-facial domains, and it can also serve as a valuable plug-in for enhancing the performance of pretrained personalization models.
Authors: Yu Tian, Yixuan Li, Baoliang Chen, Hanwei Zhu, Shiqi Wang, Sam Kwong
Abstract: Assessing the quality of artificial intelligence-generated images (AIGIs) plays a crucial role in their application in real-world scenarios. However, traditional image quality assessment (IQA) algorithms primarily focus on low-level visual perception, while existing IQA works on AIGIs overemphasize the generated content itself, neglecting its effectiveness in real-world applications. To bridge this gap, we propose AIGI-VC, a quality assessment database for AI-Generated Images in Visual Communication, which studies the communicability of AIGIs in the advertising field from the perspectives of information clarity and emotional interaction. The dataset consists of 2,500 images spanning 14 advertisement topics and 8 emotion types. It provides coarse-grained human preference annotations and fine-grained preference descriptions, benchmarking the abilities of IQA methods in preference prediction, interpretation, and reasoning. We conduct an empirical study of existing representative IQA methods and large multi-modal models on the AIGI-VC dataset, uncovering their strengths and weaknesses.
Authors: Xiang Fang, Wanlong Fang, Changshuo Wang, Daizong Liu, Keke Tang, Jianfeng Dong, Pan Zhou, Beibei Li
Abstract: Given some video-query pairs with untrimmed videos and sentence queries, temporal sentence grounding (TSG) aims to locate query-relevant segments in these videos. Although previous respectable TSG methods have achieved remarkable success, they train each video-query pair separately and ignore the relationship between different pairs. We observe that the similar video/query content not only helps the TSG model better understand and generalize the cross-modal representation but also assists the model in locating some complex video-query pairs. Previous methods follow a single-thread framework that cannot co-train different pairs and usually spends much time re-obtaining redundant knowledge, limiting their real-world applications. To this end, in this paper, we pose a brand-new setting: Multi-Pair TSG, which aims to co-train these pairs. In particular, we propose a novel video-query co-training approach, Multi-Thread Knowledge Transfer Network, to locate a variety of video-query pairs effectively and efficiently. Firstly, we mine the spatial and temporal semantics across different queries to cooperate with each other. To learn intra- and inter-modal representations simultaneously, we design a cross-modal contrast module to explore the semantic consistency by a self-supervised strategy. To fully align visual and textual representations between different pairs, we design a prototype alignment strategy to 1) match object prototypes and phrase prototypes for spatial alignment, and 2) align activity prototypes and sentence prototypes for temporal alignment. Finally, we develop an adaptive negative selection module to adaptively generate a threshold for cross-modal matching. Extensive experiments show the effectiveness and efficiency of our proposed method.
Authors: Zihan Ding, Chi Jin, Difan Liu, Haitian Zheng, Krishna Kumar Singh, Qiang Zhang, Yan Kang, Zhe Lin, Yuchen Liu
Abstract: Diffusion probabilistic models have shown significant progress in video generation; however, their computational efficiency is limited by the large number of sampling steps required. Reducing sampling steps often compromises video quality or generation diversity. In this work, we introduce a distillation method that combines variational score distillation and consistency distillation to achieve few-step video generation, maintaining both high quality and diversity. We also propose a latent reward model fine-tuning approach to further enhance video generation performance according to any specified reward metric. This approach reduces memory usage and does not require the reward to be differentiable. Our method demonstrates state-of-the-art performance in few-step generation for 10-second videos (128 frames at 12 FPS). The distilled student model achieves a score of 82.57 on VBench, surpassing the teacher model as well as baseline models Gen-3, T2V-Turbo, and Kling. One-step distillation accelerates the teacher model's diffusion sampling by up to 278.6 times, enabling near real-time generation. Human evaluations further validate the superior performance of our 4-step student models compared to teacher model using 50-step DDIM sampling.
Authors: Xiantao Hu, Ying Tai, Xu Zhao, Chen Zhao, Zhenyu Zhang, Jun Li, Bineng Zhong, Jian Yang
Abstract: Multimodal tracking has garnered widespread attention as a result of its ability to effectively address the inherent limitations of traditional RGB tracking. However, existing multimodal trackers mainly focus on the fusion and enhancement of spatial features or merely leverage the sparse temporal relationships between video frames. These approaches do not fully exploit the temporal correlations in multimodal videos, making it difficult to capture the dynamic changes and motion information of targets in complex scenarios. To alleviate this problem, we propose a unified multimodal spatial-temporal tracking approach named STTrack. In contrast to previous paradigms that solely relied on updating reference information, we introduced a temporal state generator (TSG) that continuously generates a sequence of tokens containing multimodal temporal information. These temporal information tokens are used to guide the localization of the target in the next time state, establish long-range contextual relationships between video frames, and capture the temporal trajectory of the target. Furthermore, at the spatial level, we introduced the mamba fusion and background suppression interactive (BSI) modules. These modules establish a dual-stage mechanism for coordinating information interaction and fusion between modalities. Extensive comparisons on five benchmark datasets illustrate that STTrack achieves state-of-the-art performance across various multimodal tracking scenarios. Code is available at: https://github.com/NJU-PCALab/STTrack.
Authors: David Calhas, Jo\~ao Marques, Arlindo L. Oliveira
Abstract: The biological brain has inspired multiple advances in machine learning. However, most state-of-the-art models in computer vision do not operate like the human brain, simply because they are not capable of changing or improving their decisions/outputs based on a deeper analysis. The brain is recurrent, while these models are not. It is therefore relevant to explore what would be the impact of adding recurrent mechanisms to existing state-of-the-art architectures and to answer the question of whether recurrency can improve existing architectures. To this end, we build on a feed-forward segmentation model and explore multiple types of recurrency for image segmentation. We explore self-organizing, relational, and memory retrieval types of recurrency that minimize a specific energy function. In our experiments, we tested these models on artificial and medical imaging data, while analyzing the impact of high levels of noise and few-shot learning settings. Our results do not validate our initial hypothesis that recurrent models should perform better in these settings, suggesting that these recurrent architectures, by themselves, are not sufficient to surpass state-of-the-art feed-forward versions and that additional work needs to be done on the topic.
Authors: Dexter Neo, Tsuhan Chen
Abstract: Large Vision-Language Models (LVLMs) have made remarkable developments along with the recent surge of large language models. Despite their advancements, LVLMs have a tendency to generate plausible yet inaccurate or inconsistent information based on the provided source content. This phenomenon, also known as ``hallucinations" can have serious downstream implications during the deployment of LVLMs. To address this, we present VORD a simple and effective method that alleviates hallucinations by calibrating token predictions based on ordinal relationships between modified image pairs. VORD is presented in two forms: 1.) a minimalist training-free variant which eliminates implausible tokens from modified image pairs, and 2.) a trainable objective function that penalizes unlikely tokens. Our experiments demonstrate that VORD delivers better calibration and effectively mitigates object hallucinations on a wide-range of LVLM benchmarks.
Authors: Yiheng Jiang, Haotian Zhang, Li Li, Dong Liu, Zhu Li
Abstract: In the field of autonomous driving, a variety of sensor data types exist, each representing different modalities of the same scene. Therefore, it is feasible to utilize data from other sensors to facilitate image compression. However, few techniques have explored the potential benefits of utilizing inter-modality correlations to enhance the image compression performance. In this paper, motivated by the recent success of learned image compression, we propose a new framework that uses sparse point clouds to assist in learned image compression in the autonomous driving scenario. We first project the 3D sparse point cloud onto a 2D plane, resulting in a sparse depth map. Utilizing this depth map, we proceed to predict camera images. Subsequently, we use these predicted images to extract multi-scale structural features. These features are then incorporated into learned image compression pipeline as additional information to improve the compression performance. Our proposed framework is compatible with various mainstream learned image compression models, and we validate our approach using different existing image compression methods. The experimental results show that incorporating point cloud assistance into the compression pipeline consistently enhances the performance.
Authors: Hyunsoo Lee, Minsoo Kang, Bohyung Han
Abstract: We present a simple but effective training-free approach for text-driven image-to-image translation based on a pretrained text-to-image diffusion model. Our goal is to generate an image that aligns with the target task while preserving the structure and background of a source image. To this end, we derive the representation guidance with a combination of two objectives: maximizing the similarity to the target prompt based on the CLIP score and minimizing the structural distance to the source latent variable. This guidance improves the fidelity of the generated target image to the given target prompt while maintaining the structure integrity of the source image. To incorporate the representation guidance component, we optimize the target latent variable of diffusion model's reverse process with the guidance. Experimental results demonstrate that our method achieves outstanding image-to-image translation performance on various tasks when combined with the pretrained Stable Diffusion model.
Authors: Yi Zhang, Chun-Wun Cheng, Junyi He, Zhihai He, Carola-Bibiane Sch\"onlieb, Yuyan Chen, Angelica I Aviles-Rivero
Abstract: We introduce SONO, a novel method leveraging Second-Order Neural Ordinary Differential Equations (Second-Order NODEs) to enhance cross-modal few-shot learning. By employing a simple yet effective architecture consisting of a Second-Order NODEs model paired with a cross-modal classifier, SONO addresses the significant challenge of overfitting, which is common in few-shot scenarios due to limited training examples. Our second-order approach can approximate a broader class of functions, enhancing the model's expressive power and feature generalization capabilities. We initialize our cross-modal classifier with text embeddings derived from class-relevant prompts, streamlining training efficiency by avoiding the need for frequent text encoder processing. Additionally, we utilize text-based image augmentation, exploiting CLIP's robust image-text correlation to enrich training data significantly. Extensive experiments across multiple datasets demonstrate that SONO outperforms existing state-of-the-art methods in few-shot learning performance.
Authors: Cheng Wang, Ziyang Feng, Pin Zhang, Manjiang Cao, Yiming Yuan, Tengfei Chang
Abstract: Electromyography (EMG) signals are widely used in human motion recognition and medical rehabilitation, yet their variability and susceptibility to noise significantly limit the reliability of myoelectric control systems. Existing recognition algorithms often fail to handle unfamiliar actions effectively, leading to system instability and errors. This paper proposes a novel framework based on Generative Adversarial Networks (GANs) to enhance the robustness and usability of myoelectric control systems by enabling open-set recognition. The method incorporates a GAN-based discriminator to identify and reject unknown actions, maintaining system stability by preventing misclassifications. Experimental evaluations on publicly available and self-collected datasets demonstrate a recognition accuracy of 97.6\% for known actions and a 23.6\% improvement in Active Error Rate (AER) after rejecting unknown actions. The proposed approach is computationally efficient and suitable for deployment on edge devices, making it practical for real-world applications.
Authors: Xinyue Chen, Miaojing Shi, Zijian Zhou, Lianghua He, Sophia Tsoka
Abstract: Generalized few-shot semantic segmentation (GFSS) aims to segment objects of both base and novel classes, using sufficient samples of base classes and few samples of novel classes. Representative GFSS approaches typically employ a two-phase training scheme, involving base class pre-training followed by novel class fine-tuning, to learn the classifiers for base and novel classes respectively. Nevertheless, distribution gap exists between base and novel classes in this process. To narrow this gap, we exploit effective knowledge transfer from base to novel classes. First, a novel prototype modulation module is designed to modulate novel class prototypes by exploiting the correlations between base and novel classes. Second, a novel classifier calibration module is proposed to calibrate the weight distribution of the novel classifier according to that of the base classifier. Furthermore, existing GFSS approaches suffer from a lack of contextual information for novel classes due to their limited samples, we thereby introduce a context consistency learning scheme to transfer the contextual knowledge from base to novel classes. Extensive experiments on PASCAL-5$^i$ and COCO-20$^i$ demonstrate that our approach significantly enhances the state of the art in the GFSS setting. The code is available at: https://github.com/HHHHedy/GFSS-EKT.
Authors: Mikko Impi\"o, Philipp M. Rehsen, Jenni Raitoharju
Abstract: The amount of image datasets collected for environmental monitoring purposes has increased in the past years as computer vision assisted methods have gained interest. Computer vision applications rely on high-quality datasets, making data curation important. However, data curation is often done ad-hoc and the methods used are rarely published. We present a method for curating large-scale image datasets of invertebrates that contain multiple images of the same taxa and/or specimens and have relatively uniform background in the images. Our approach is based on extracting feature embeddings with pretrained deep neural networks, and using these embeddings to find visually most distinct images by comparing their embeddings to the group prototype embedding. Also, we show that a simple area-based size comparison approach is able to find a lot of common erroneous images, such as images containing detached body parts and misclassified samples. In addition to the method, we propose using novel metrics for evaluating human-in-the-loop outlier detection methods. The implementations of the proposed curation methods, as well as a benchmark dataset containing annotated erroneous images, are publicly available in https://github.com/mikkoim/taxonomist-studio.
Authors: Aiwen Jiang, Hourong Chen, Zhiwen Chen, Jihua Ye, Mingwen Wang
Abstract: Recent efforts on image restoration have focused on developing "all-in-one" models that can handle different degradation types and levels within single model. However, most of mainstream Transformer-based ones confronted with dilemma between model capabilities and computation burdens, since self-attention mechanism quadratically increase in computational complexity with respect to image size, and has inadequacies in capturing long-range dependencies. Most of Mamba-related ones solely scanned feature map in spatial dimension for global modeling, failing to fully utilize information in channel dimension. To address aforementioned problems, this paper has proposed to fully utilize complementary advantages from Mamba and Transformer without sacrificing computation efficiency. Specifically, the selective scanning mechanism of Mamba is employed to focus on spatial modeling, enabling capture long-range spatial dependencies under linear complexity. The self-attention mechanism of Transformer is applied to focus on channel modeling, avoiding high computation burdens that are in quadratic growth with image's spatial dimensions. Moreover, to enrich informative prompts for effective image restoration, multi-dimensional prompt learning modules are proposed to learn prompt-flows from multi-scale encoder/decoder layers, benefiting for revealing underlying characteristic of various degradations from both spatial and channel perspectives, therefore, enhancing the capabilities of "all-in-one" model to solve various restoration tasks. Extensive experiment results on several image restoration benchmark tasks such as image denoising, dehazing, and deraining, have demonstrated that the proposed method can achieve new state-of-the-art performance, compared with many popular mainstream methods. Related source codes and pre-trained parameters will be public on github https://github.com/12138-chr/MTAIR.
Authors: Kai Brandenbusch
Abstract: The generation of images of realistic looking, readable handwritten text is a challenging task which is referred to as handwritten text generation (HTG). Given a string and examples from a writer, the goal is to synthesize an image depicting the correctly spelled word in handwriting with the calligraphic style of the desired writer. An important application of HTG is the generation of training images in order to adapt downstream models for new data sets. With their success in natural image generation, diffusion models (DMs) have become the state-of-the-art approach in HTG. In this work, we present an extension of a latent DM for HTG to enable generation of writing styles not seen during training by learning style conditioning with a masked auto encoder. Our proposed content encoder allows for different ways of conditioning the DM on textual and calligraphic features. Additionally, we employ classifier-free guidance and explore the influence on the quality of the generated training images. For adapting the model to a new unlabeled data set, we propose a semi-supervised training scheme. We evaluate our approach on the IAM-database and use the RIMES-database to examine the generation of data not seen during training achieving improvements in this particularly promising application of DMs for HTG.
Authors: Chun Gu, Xiaofei Wei, Zixuan Zeng, Yuxuan Yao, Li Zhang
Abstract: In inverse rendering, accurately modeling visibility and indirect radiance for incident light is essential for capturing secondary effects. Due to the absence of a powerful Gaussian ray tracer, previous 3DGS-based methods have either adopted a simplified rendering equation or used learnable parameters to approximate incident light, resulting in inaccurate material and lighting estimations. To this end, we introduce inter-reflective Gaussian splatting (IRGS) for inverse rendering. To capture inter-reflection, we apply the full rendering equation without simplification and compute incident radiance on the fly using the proposed differentiable 2D Gaussian ray tracing. Additionally, we present an efficient optimization scheme to handle the computational demands of Monte Carlo sampling for rendering equation evaluation. Furthermore, we introduce a novel strategy for querying the indirect radiance of incident light when relighting the optimized scenes. Extensive experiments on multiple standard benchmarks validate the effectiveness of IRGS, demonstrating its capability to accurately model complex inter-reflection effects.
Authors: Yue Guo, Haoxiang Liao, Haibin Ling, Bingyao Huang
Abstract: Underwater image restoration aims to remove geometric and color distortions due to water refraction, absorption and scattering. Previous studies focus on restoring either color or the geometry, but to our best knowledge, not both. However, in practice it may be cumbersome to address the two rectifications one-by-one. In this paper, we propose NeuroPump, a self-supervised method to simultaneously optimize and rectify underwater geometry and color as if water were pumped out. The key idea is to explicitly model refraction, absorption and scattering in Neural Radiance Field (NeRF) pipeline, such that it not only performs simultaneous geometric and color rectification, but also enables to synthesize novel views and optical effects by controlling the decoupled parameters. In addition, to address issue of lack of real paired ground truth images, we propose an underwater 360 benchmark dataset that has real paired (i.e., with and without water) images. Our method clearly outperforms other baselines both quantitatively and qualitatively.
Authors: Akshit Singh, Karan Bhakuni, Rajendra Nagar
Abstract: Neural distance fields (NDF) have emerged as a powerful tool for addressing challenges in 3D computer vision and graphics downstream problems. While significant progress has been made to learn NDF from various kind of sensor data, a crucial aspect that demands attention is the supervision of neural fields during training as the ground-truth NDFs are not available for large-scale outdoor scenes. Previous works have utilized various forms of expected signed distance to guide model learning. Yet, these approaches often need to pay more attention to critical considerations of surface geometry and are limited to small-scale implementations. To this end, we propose a novel methodology leveraging second-order derivatives of the signed distance field for improved neural field learning. Our approach addresses limitations by accurately estimating signed distance, offering a more comprehensive understanding of underlying geometry. To assess the efficacy of our methodology, we conducted comparative evaluations against prevalent methods for mapping and localization tasks, which are primary application areas of NDF. Our results demonstrate the superiority of the proposed approach, highlighting its potential for advancing the capabilities of neural distance fields in computer vision and graphics applications.
Authors: Zhenghao Gao, Shengjie Xu, Meixi Chen, Fangyao Zhao
Abstract: Contemporary adversarial attack methods face significant limitations in cross-model transferability and practical applicability. We present Watertox, an elegant adversarial attack framework achieving remarkable effectiveness through architectural diversity and precision-controlled perturbations. Our two-stage Fast Gradient Sign Method combines uniform baseline perturbations ($\epsilon_1 = 0.1$) with targeted enhancements ($\epsilon_2 = 0.4$). The framework leverages an ensemble of complementary architectures, from VGG to ConvNeXt, synthesizing diverse perspectives through an innovative voting mechanism. Against state-of-the-art architectures, Watertox reduces model accuracy from 70.6% to 16.0%, with zero-shot attacks achieving up to 98.8% accuracy reduction against unseen architectures. These results establish Watertox as a significant advancement in adversarial methodologies, with promising applications in visual security systems and CAPTCHA generation.
Authors: Andrea Moglia, Elia Clement Nastasio, Luca Mainardi, Pietro Cerveri
Abstract: Problem: Pancreas radiological imaging is challenging due to the small size, blurred boundaries, and variability of shape and position of the organ among patients. Goal: In this work we present MiniGPT-Pancreas, a Multimodal Large Language Model (MLLM), as an interactive chatbot to support clinicians in pancreas cancer diagnosis by integrating visual and textual information. Methods: MiniGPT-v2, a general-purpose MLLM, was fine-tuned in a cascaded way for pancreas detection, tumor classification, and tumor detection with multimodal prompts combining questions and computed tomography scans from the National Institute of Health (NIH), and Medical Segmentation Decathlon (MSD) datasets. The AbdomenCT-1k dataset was used to detect the liver, spleen, kidney, and pancreas. Results: MiniGPT-Pancreas achieved an Intersection over Union (IoU) of 0.595 and 0.550 for the detection of pancreas on NIH and MSD datasets, respectively. For the pancreas cancer classification task on the MSD dataset, accuracy, precision, and recall were 0.876, 0.874, and 0.878, respectively. When evaluating MiniGPT-Pancreas on the AbdomenCT-1k dataset for multi-organ detection, the IoU was 0.8399 for the liver, 0.722 for the kidney, 0.705 for the spleen, and 0.497 for the pancreas. For the pancreas tumor detection task, the IoU score was 0.168 on the MSD dataset. Conclusions: MiniGPT-Pancreas represents a promising solution to support clinicians in the classification of pancreas images with pancreas tumors. Future research is needed to improve the score on the detection task, especially for pancreas tumors.
Authors: Gautier Evennou, Antoine Chaffin, Vivien Chappelier, Ewa Kijak
Abstract: The rise of the generative models quality during the past years enabled the generation of edited variations of images at an important scale. To counter the harmful effects of such technology, the Image Difference Captioning (IDC) task aims to describe the differences between two images. While this task is successfully handled for simple 3D rendered images, it struggles on real-world images. The reason is twofold: the training data-scarcity, and the difficulty to capture fine-grained differences between complex images. To address those issues, we propose in this paper a simple yet effective framework to both adapt existing image captioning models to the IDC task and augment IDC datasets. We introduce BLIP2IDC, an adaptation of BLIP2 to the IDC task at low computational cost, and show it outperforms two-streams approaches by a significant margin on real-world IDC datasets. We also propose to use synthetic augmentation to improve the performance of IDC models in an agnostic fashion. We show that our synthetic augmentation strategy provides high quality data, leading to a challenging new dataset well-suited for IDC named Syned1.
Authors: Bradley Scott, Clarisse de Vries, Aiden Durrant, Nir Oren, Edward Chadwick, Dimitra Blana
Abstract: In this study, we investigated whether transfer learning from macaque monkeys could improve human pose estimation. Current state-of-the-art pose estimation techniques, often employing deep neural networks, can match human annotation in non-clinical datasets. However, they underperform in novel situations, limiting their generalisability to clinical populations with pathological movement patterns. Clinical datasets are not widely available for AI training due to ethical challenges and a lack of data collection. We observe that data from other species may be able to bridge this gap by exposing the network to a broader range of motion cues. We found that utilising data from other species and undertaking transfer learning improved human pose estimation in terms of precision and recall compared to the benchmark, which was trained on humans only. Compared to the benchmark, fewer human training examples were needed for the transfer learning approach (1,000 vs 19,185). These results suggest that macaque pose estimation can improve human pose estimation in clinical situations. Future work should further explore the utility of pose estimation trained with monkey data in clinical populations.
Authors: Simon Langer, Jessica Ritter, Rickmer Braren, Daniel Rueckert, Paul Hager
Abstract: Modern deep learning-based clinical imaging workflows rely on accurate labels of the examined anatomical region. Knowing the anatomical region is required to select applicable downstream models and to effectively generate cohorts of high quality data for future medical and machine learning research efforts. However, this information may not be available in externally sourced data or generally contain data entry errors. To address this problem, we show the effectiveness of self-supervised methods such as SimCLR and BYOL as well as supervised contrastive deep learning methods in assigning one of 14 anatomical region classes in our in-house dataset of 48,434 skeletal radiographs. We achieve a strong linear evaluation accuracy of 96.6% with a single model and 97.7% using an ensemble approach. Furthermore, only a few labeled instances (1% of the training set) suffice to achieve an accuracy of 92.2%, enabling usage in low-label and thus low-resource scenarios. Our model can be used to correct data entry mistakes: a follow-up analysis of the test set errors of our best-performing single model by an expert radiologist identified 35% incorrect labels and 11% out-of-domain images. When accounted for, the radiograph anatomical region labelling performance increased -- without and with an ensemble, respectively -- to a theoretical accuracy of 98.0% and 98.8%.
Authors: Bowen Dong, Zitong Huang, Guanglei Yang, Lei Zhang, Wangmeng Zuo
Abstract: Open-world (OW) recognition and detection models show strong zero- and few-shot adaptation abilities, inspiring their use as initializations in continual learning methods to improve performance. Despite promising results on seen classes, such OW abilities on unseen classes are largely degenerated due to catastrophic forgetting. To tackle this challenge, we propose an open-world continual object detection task, requiring detectors to generalize to old, new, and unseen categories in continual learning scenarios. Based on this task, we present a challenging yet practical OW-COD benchmark to assess detection abilities. The goal is to motivate OW detectors to simultaneously preserve learned classes, adapt to new classes, and maintain open-world capabilities under few-shot adaptations. To mitigate forgetting in unseen categories, we propose MR-GDINO, a strong, efficient and scalable baseline via memory and retrieval mechanisms within a highly scalable memory pool. Experimental results show that existing continual detectors suffer from severe forgetting for both seen and unseen categories. In contrast, MR-GDINO largely mitigates forgetting with only 0.1% activated extra parameters, achieving state-of-the-art performance for old, new, and unseen categories.
Authors: Jungho Lee, Suhwan Cho, Taeoh Kim, Ho-Deok Jang, Minhyeok Lee, Geonho Cha, Dongyoon Wee, Dogyoon Lee, Sangyoun Lee
Abstract: 3D Gaussian Splatting (3DGS) has attracted significant attention for its high-quality novel view rendering, inspiring research to address real-world challenges. While conventional methods depend on sharp images for accurate scene reconstruction, real-world scenarios are often affected by defocus blur due to finite depth of field, making it essential to account for realistic 3D scene representation. In this study, we propose CoCoGaussian, a Circle of Confusion-aware Gaussian Splatting that enables precise 3D scene representation using only defocused images. CoCoGaussian addresses the challenge of defocus blur by modeling the Circle of Confusion (CoC) through a physically grounded approach based on the principles of photographic defocus. Exploiting 3D Gaussians, we compute the CoC diameter from depth and learnable aperture information, generating multiple Gaussians to precisely capture the CoC shape. Furthermore, we introduce a learnable scaling factor to enhance robustness and provide more flexibility in handling unreliable depth in scenes with reflective or refractive surfaces. Experiments on both synthetic and real-world datasets demonstrate that CoCoGaussian achieves state-of-the-art performance across multiple benchmarks.
Authors: Jiadong Pan, Hongcheng Gao, Liang Li, Zheng-Jun Zha, Qingming Huang, Jiebo Luo
Abstract: Diffusion models (DMs) have demonstrated exceptional performance in text-to-image (T2I) tasks, leading to their widespread use. With the introduction of classifier-free guidance (CFG), the quality of images generated by DMs is improved. However, DMs can generate more harmful images by maliciously guiding the image generation process through CFG. Some safe guidance methods aim to mitigate the risk of generating harmful images but often reduce the quality of clean image generation. To address this issue, we introduce the Harmful Guidance Redirector (HGR), which redirects harmful CFG direction while preserving clean CFG direction during image generation, transforming CFG into SafeCFG and achieving high safety and quality generation. We train HGR to redirect multiple harmful CFG directions simultaneously, demonstrating its ability to eliminate various harmful elements while preserving high-quality generation. Additionally, we find that HGR can detect image harmfulness, allowing for unsupervised fine-tuning of safe diffusion models without pre-defined clean or harmful labels. Experimental results show that by incorporating HGR, images generated by diffusion models achieve both high quality and strong safety, and safe DMs trained through unsupervised methods according to the harmfulness detected by HGR also exhibit good safety performance. The codes will be publicly available.
Authors: Henry Cording, Yves Plancherel, Pablo Brito-Parada
Abstract: Very high resolution (VHR) mapping through remote sensing (RS) imagery presents a new opportunity to inform decision-making and sustainable practices in countless domains. Efficient processing of big VHR data requires automated tools applicable to numerous geographic regions and features. Contemporary RS studies address this challenge by employing deep learning (DL) models for specific datasets or features, which limits their applicability across contexts. The present research aims to overcome this limitation by introducing EcoMapper, a scalable solution to segment arbitrary features in VHR RS imagery. EcoMapper fully automates processing of geospatial data, DL model training, and inference. Models trained with EcoMapper successfully segmented two distinct features in a real-world UAV dataset, achieving scores competitive with prior studies which employed context-specific models. To evaluate EcoMapper, many additional models were trained on permutations of principal field survey characteristics (FSCs). A relationship was discovered allowing derivation of optimal ground sampling distance from feature size, termed Cording Index (CI). A comprehensive methodology for field surveys was developed to ensure DL methods can be applied effectively to collected data. The EcoMapper code accompanying this work is available at https://github.com/hcording/ecomapper .
Authors: Shaoyan Pan, Yikang Liu, Lin Zhao, Eric Z. Chen, Xiao Chen, Terrence Chen, Shanhui Sun
Abstract: The accurate segmentation of guidewires in interventional cardiac fluoroscopy videos is crucial for computer-aided navigation tasks. Although deep learning methods have demonstrated high accuracy and robustness in wire segmentation, they require substantial annotated datasets for generalizability, underscoring the need for extensive labeled data to enhance model performance. To address this challenge, we propose the Segmentation-guided Frame-consistency Video Diffusion Model (SF-VD) to generate large collections of labeled fluoroscopy videos, augmenting the training data for wire segmentation networks. SF-VD leverages videos with limited annotations by independently modeling scene distribution and motion distribution. It first samples the scene distribution by generating 2D fluoroscopy images with wires positioned according to a specified input mask, and then samples the motion distribution by progressively generating subsequent frames, ensuring frame-to-frame coherence through a frame-consistency strategy. A segmentation-guided mechanism further refines the process by adjusting wire contrast, ensuring a diverse range of visibility in the synthesized image. Evaluation on a fluoroscopy dataset confirms the superior quality of the generated videos and shows significant improvements in guidewire segmentation.
Authors: Xinwei Ju, Rema Daher, Razvan Caramalau, Baoru Huang, Danail Stoyanov, Francisco Vasconcelos
Abstract: Colorectal cancer (CRC) remains a leading cause of cancer-related deaths worldwide, with polyp removal being an effective early screening method. However, navigating the colon for thorough polyp detection poses significant challenges. To advance camera navigation in colonoscopy, we propose the Semantic Segmentation for Tools and Fold Edges in Colonoscopy (SegCol) Challenge. This challenge introduces a dataset from the EndoMapper repository, featuring manually annotated, pixel-level semantic labels for colon folds and endoscopic tools across selected frames from 96 colonoscopy videos. By providing fold edges as anatomical landmarks and depth discontinuity information from both fold and tool labels, the dataset is aimed to improve depth perception and localization methods. Hosted as part of the Endovis Challenge at MICCAI 2024, SegCol aims to drive innovation in colonoscopy navigation systems. Details are available at https://www.synapse.org/Synapse:syn54124209/wiki/626563, and code resources at https://github.com/surgical-vision/segcol_challenge .
URLs: https://www.synapse.org/Synapse:syn54124209/wiki/626563,, https://github.com/surgical-vision/segcol_challenge
Authors: Ahmet Bahaddin Ersoz
Abstract: The integration of Large Vision-Language Models (LVLMs) such as OpenAI's GPT-4 Vision into various sectors has marked a significant evolution in the field of artificial intelligence, particularly in the analysis and interpretation of visual data. This paper explores the practical application of GPT-4 Vision in the construction industry, focusing on its capabilities in monitoring and tracking the progress of construction projects. Utilizing high-resolution aerial imagery of construction sites, the study examines how GPT-4 Vision performs detailed scene analysis and tracks developmental changes over time. The findings demonstrate that while GPT-4 Vision is proficient in identifying construction stages, materials, and machinery, it faces challenges with precise object localization and segmentation. Despite these limitations, the potential for future advancements in this technology is considerable. This research not only highlights the current state and opportunities of using LVLMs in construction but also discusses future directions for enhancing the model's utility through domain-specific training and integration with other computer vision techniques and digital twins.
Authors: Songhua Liu, Zhenxiong Tan, Xinchao Wang
Abstract: Diffusion Transformers (DiT) have become a leading architecture in image generation. However, the quadratic complexity of attention mechanisms, which are responsible for modeling token-wise relationships, results in significant latency when generating high-resolution images. To address this issue, we aim at a linear attention mechanism in this paper that reduces the complexity of pre-trained DiTs to linear. We begin our exploration with a comprehensive summary of existing efficient attention mechanisms and identify four key factors crucial for successful linearization of pre-trained DiTs: locality, formulation consistency, high-rank attention maps, and feature integrity. Based on these insights, we introduce a convolution-like local attention strategy termed CLEAR, which limits feature interactions to a local window around each query token, and thus achieves linear complexity. Our experiments indicate that, by fine-tuning the attention layer on merely 10K self-generated samples for 10K iterations, we can effectively transfer knowledge from a pre-trained DiT to a student model with linear complexity, yielding results comparable to the teacher model. Simultaneously, it reduces attention computations by 99.5% and accelerates generation by 6.3 times for generating 8K-resolution images. Furthermore, we investigate favorable properties in the distilled attention layers, such as zero-shot generalization cross various models and plugins, and improved support for multi-GPU parallel inference. Models and codes are available here: https://github.com/Huage001/CLEAR.
Authors: Xiaohu Huang, Hao Zhou, Kai Han
Abstract: In this paper, we introduce PruneVid, a visual token pruning method designed to enhance the efficiency of multi-modal video understanding. Large Language Models (LLMs) have shown promising performance in video tasks due to their extended capabilities in comprehending visual modalities. However, the substantial redundancy in video data presents significant computational challenges for LLMs. To address this issue, we introduce a training-free method that 1) minimizes video redundancy by merging spatial-temporal tokens, and 2) leverages LLMs' reasoning capabilities to selectively prune visual features relevant to question tokens, enhancing model efficiency. We validate our method across multiple video benchmarks, which demonstrate that PruneVid can prune over 80% of tokens while maintaining competitive performance combined with different model networks. This highlights its superior effectiveness and efficiency compared to existing pruning methods. Code: https://github.com/Visual-AI/PruneVid.
Authors: Krithika Iyer, Shireen Elhabian, Sarang Joshi
Abstract: Image registration is a core task in computational anatomy that establishes correspondences between images. Invertible deformable registration, which computes a deformation field and handles complex, non-linear transformation, is essential for tracking anatomical variations, especially in neuroimaging applications where inter-subject differences and longitudinal changes are key. Analyzing the deformation fields is challenging due to their non-linearity, limiting statistical analysis. However, traditional approaches for analyzing deformation fields are computationally expensive, sensitive to initialization, and prone to numerical errors, especially when the deformation is far from the identity. To address these limitations, we propose the Log-Euclidean Diffeomorphic Autoencoder (LEDA), an innovative framework designed to compute the principal logarithm of deformation fields by efficiently predicting consecutive square roots. LEDA operates within a linearized latent space that adheres to the diffeomorphisms group action laws, enhancing our model's robustness and applicability. We also introduce a loss function to enforce inverse consistency, ensuring accurate latent representations of deformation fields. Extensive experiments with the OASIS-1 dataset demonstrate the effectiveness of LEDA in accurately modeling and analyzing complex non-linear deformations while maintaining inverse consistency. Additionally, we evaluate its ability to capture and incorporate clinical variables, enhancing its relevance for clinical applications.
Authors: Vishnu Teja Kunde, Jean-Francois Chamberland, Siddharth Agarwal
Abstract: Robust and fine localization algorithms are crucial for autonomous driving. For the production of such vehicles as a commodity, affordable sensing solutions and reliable localization algorithms must be designed. This work considers scenarios where the sensor data comes from images captured by an inexpensive camera mounted on the vehicle and where the vehicle contains a fine global map. Such localization algorithms typically involve finding the section in the global map that best matches the captured image. In harsh environments, both the global map and the captured image can be noisy. Because of physical constraints on camera placement, the image captured by the camera can be viewed as a noisy perspective transformed version of the road in the global map. Thus, an optimal algorithm should take into account the unequal noise power in various regions of the captured image, and the intrinsic uncertainty in the global map due to environmental variations. This article briefly reviews two matching methods: (i) standard inner product (SIP) and (ii) normalized mutual information (NMI). It then proposes novel and principled modifications to improve the performance of these algorithms significantly in noisy environments. These enhancements are inspired by the physical constraints associated with autonomous vehicles. They are grounded in statistical signal processing and, in some context, are provably better. Numerical simulations demonstrate the effectiveness of such modifications.
Authors: Laura Weihl, Bilal Wehbe, Andrzej W\k{a}sowski
Abstract: Autonomous inspection of infrastructure on land and in water is a quickly growing market, with applications including surveying constructions, monitoring plants, and tracking environmental changes in on- and off-shore wind energy farms. For Autonomous Underwater Vehicles and Unmanned Aerial Vehicles overfitting of controllers to simulation conditions fundamentally leads to poor performance in the operation environment. There is a pressing need for more diverse and realistic test data that accurately represents the challenges faced by these systems. We address the challenge of generating perception test data for autonomous systems by leveraging Neural Radiance Fields to generate realistic and diverse test images, and integrating them into a metamorphic testing framework for vision components such as vSLAM and object detection. Our tool, N2R-Tester, allows training models of custom scenes and rendering test images from perturbed positions. An experimental evaluation of N2R-Tester on eight different vision components in AUVs and UAVs demonstrates the efficacy and versatility of the approach.
Authors: Enis Baty, Alejandro Hern\'andez D\'iaz, Chris Bridges, Rebecca Davidson, Steve Eckersley, Simon Hadfield
Abstract: State-Space Models (SSMs) have recently emerged as a powerful and efficient alternative to the long-standing transformer architecture. However, existing SSM conceptualizations retain deeply rooted biases from their roots in natural language processing. This constrains their ability to appropriately model the spatially-dependent characteristics of visual inputs. In this paper, we address these limitations by re-deriving modern selective state-space techniques, starting from a natively multidimensional formulation. Currently, prior works attempt to apply natively 1D SSMs to 2D data (i.e. images) by relying on arbitrary combinations of 1D scan directions to capture spatial dependencies. In contrast, Mamba2D improves upon this with a single 2D scan direction that factors in both dimensions of the input natively, effectively modelling spatial dependencies when constructing hidden states. Mamba2D shows comparable performance to prior adaptations of SSMs for vision tasks, on standard image classification evaluations with the ImageNet-1K dataset.
Authors: Jannik Els\"a{\ss}er, Laura Weihl, Veronika Cheplygina, Lisbeth Tangaa Nielsen
Abstract: Seagrass meadows play a crucial role in marine ecosystems, providing important services such as carbon sequestration, water quality improvement, and habitat provision. Monitoring the distribution and abundance of seagrass is essential for environmental impact assessments and conservation efforts. However, the current manual methods of analyzing underwater video transects to assess seagrass coverage are time-consuming and subjective. This work explores the use of deep learning models to automate the process of seagrass detection and coverage estimation from underwater video data. A dataset of over 8,300 annotated underwater images was created, and several deep learning architectures, including ResNet, InceptionNetV3, DenseNet, and Vision Transformer, were evaluated for the task of binary classification of ``Eelgrass Present'' and ``Eelgrass Absent'' images. The results demonstrate that deep learning models, particularly the Vision Transformer, can achieve high performance in predicting eelgrass presence, with AUROC scores exceeding 0.95 on the final test dataset. The use of transfer learning and the application of the Deep WaveNet underwater image enhancement model further improved the models' capabilities. The proposed methodology allows for the efficient processing of large volumes of video data, enabling the acquisition of much more detailed information on seagrass distributions compared to current manual methods. This information is crucial for environmental impact assessments and monitoring programs, as seagrasses are important indicators of coastal ecosystem health. Overall, this project demonstrates the value that deep learning can bring to the field of marine ecology and environmental monitoring.
Authors: Mingliang Liang, Martha Larson
Abstract: Vision Language Models (VLMs) can be trained more efficiently if training sets can be reduced in size. Recent work has shown the benefits of masking text during VLM training using a variety of approaches: truncation, random masking, block masking and syntax masking. In this paper, we show that the best masking strategy changes over training epochs and that, given sufficient training epochs, word frequency information is what you need to achieve the best performance. Experiments on a large range of data sets demonstrate the advantages of our approach, called Contrastive Language-Image Pre-training with word Frequency Masking (CLIPF). The benefits are particularly evident as the number of input tokens decreases. We analyze the impact of CLIPF vs. other masking approaches on word frequency balance and discuss the apparently critical contribution of CLIPF in maintaining word frequency balance across POS categories.
Authors: Shijie Wang, Samaneh Azadi, Rohit Girdhar, Saketh Rambhatla, Chen Sun, Xi Yin
Abstract: Text-Image-to-Video (TI2V) generation aims to generate a video from an image following a text description, which is also referred to as text-guided image animation. Most existing methods struggle to generate videos that align well with the text prompts, particularly when motion is specified. To overcome this limitation, we introduce MotiF, a simple yet effective approach that directs the model's learning to the regions with more motion, thereby improving the text alignment and motion generation. We use optical flow to generate a motion heatmap and weight the loss according to the intensity of the motion. This modified objective leads to noticeable improvements and complements existing methods that utilize motion priors as model inputs. Additionally, due to the lack of a diverse benchmark for evaluating TI2V generation, we propose TI2V Bench, a dataset consists of 320 image-text pairs for robust evaluation. We present a human evaluation protocol that asks the annotators to select an overall preference between two videos followed by their justifications. Through a comprehensive evaluation on TI2V Bench, MotiF outperforms nine open-sourced models, achieving an average preference of 72%. The TI2V Bench is released in https://wang-sj16.github.io/motif/.
Authors: Ruojin Cai, Jason Y. Zhang, Philipp Henzler, Zhengqi Li, Noah Snavely, Ricardo Martin-Brualla
Abstract: Pairwise pose estimation from images with little or no overlap is an open challenge in computer vision. Existing methods, even those trained on large-scale datasets, struggle in these scenarios due to the lack of identifiable correspondences or visual overlap. Inspired by the human ability to infer spatial relationships from diverse scenes, we propose a novel approach, InterPose, that leverages the rich priors encoded within pre-trained generative video models. We propose to use a video model to hallucinate intermediate frames between two input images, effectively creating a dense, visual transition, which significantly simplifies the problem of pose estimation. Since current video models can still produce implausible motion or inconsistent geometry, we introduce a self-consistency score that evaluates the consistency of pose predictions from sampled videos. We demonstrate that our approach generalizes among three state-of-the-art video models and show consistent improvements over the state-of-the-art DUSt3R on four diverse datasets encompassing indoor, outdoor, and object-centric scenes. Our findings suggest a promising avenue for improving pose estimation models by leveraging large generative models trained on vast amounts of video data, which is more readily available than 3D data. See our project page for results: https://inter-pose.github.io/.
Authors: Shobhita Sundaram, Julia Chae, Yonglong Tian, Sara Beery, Phillip Isola
Abstract: Modern vision models excel at general purpose downstream tasks. It is unclear, however, how they may be used for personalized vision tasks, which are both fine-grained and data-scarce. Recent works have successfully applied synthetic data to general-purpose representation learning, while advances in T2I diffusion models have enabled the generation of personalized images from just a few real examples. Here, we explore a potential connection between these ideas, and formalize the challenge of using personalized synthetic data to learn personalized representations, which encode knowledge about an object of interest and may be flexibly applied to any downstream task relating to the target object. We introduce an evaluation suite for this challenge, including reformulations of two existing datasets and a novel dataset explicitly constructed for this purpose, and propose a contrastive learning approach that makes creative use of image generators. We show that our method improves personalized representation learning for diverse downstream tasks, from recognition to segmentation, and analyze characteristics of image generation approaches that are key to this gain.
Authors: Chenxin Tao, Shiqian Su, Xizhou Zhu, Chenyu Zhang, Zhe Chen, Jiawen Liu, Wenhai Wang, Lewei Lu, Gao Huang, Yu Qiao, Jifeng Dai
Abstract: The rapid advance of Large Language Models (LLMs) has catalyzed the development of Vision-Language Models (VLMs). Monolithic VLMs, which avoid modality-specific encoders, offer a promising alternative to the compositional ones but face the challenge of inferior performance. Most existing monolithic VLMs require tuning pre-trained LLMs to acquire vision abilities, which may degrade their language capabilities. To address this dilemma, this paper presents a novel high-performance monolithic VLM named HoVLE. We note that LLMs have been shown capable of interpreting images, when image embeddings are aligned with text embeddings. The challenge for current monolithic VLMs actually lies in the lack of a holistic embedding module for both vision and language inputs. Therefore, HoVLE introduces a holistic embedding module that converts visual and textual inputs into a shared space, allowing LLMs to process images in the same way as texts. Furthermore, a multi-stage training strategy is carefully designed to empower the holistic embedding module. It is first trained to distill visual features from a pre-trained vision encoder and text embeddings from the LLM, enabling large-scale training with unpaired random images and text tokens. The whole model further undergoes next-token prediction on multi-modal data to align the embeddings. Finally, an instruction-tuning stage is incorporated. Our experiments show that HoVLE achieves performance close to leading compositional models on various benchmarks, outperforming previous monolithic models by a large margin. Model available at https://huggingface.co/OpenGVLab/HoVLE.
Authors: Harshvivek Kashid, Pushpak Bhattacharyya
Abstract: Optical Character Recognition (OCR) technology has revolutionized the digitization of printed text, enabling efficient data extraction and analysis across various domains. Just like Machine Translation systems, OCR systems are prone to errors. In this work, we address the challenge of data generation and post-OCR error correction, specifically for low-resource languages. We propose an approach for synthetic data generation for Devanagari languages, RoundTripOCR, that tackles the scarcity of the post-OCR Error Correction datasets for low-resource languages. We release post-OCR text correction datasets for Hindi, Marathi, Bodo, Nepali, Konkani and Sanskrit. We also present a novel approach for OCR error correction by leveraging techniques from machine translation. Our method involves translating erroneous OCR output into a corrected form by treating the OCR errors as mistranslations in a parallel text corpus, employing pre-trained transformer models to learn the mapping from erroneous to correct text pairs, effectively correcting OCR errors.
Authors: Hannes Westermann, Jaromir Savelka
Abstract: Interacting with the legal system and the government requires the assembly and analysis of various pieces of information that can be spread across different (paper) documents, such as forms, certificates and contracts (e.g. leases). This information is required in order to understand one's legal rights, as well as to fill out forms to file claims in court or obtain government benefits. However, finding the right information, locating the correct forms and filling them out can be challenging for laypeople. Large language models (LLMs) have emerged as a powerful technology that has the potential to address this gap, but still rely on the user to provide the correct information, which may be challenging and error-prone if the information is only available in complex paper documents. We present an investigation into utilizing multi-modal LLMs to analyze images of handwritten paper forms, in order to automatically extract relevant information in a structured format. Our initial results are promising, but reveal some limitations (e.g., when the image quality is low). Our work demonstrates the potential of integrating multi-modal LLMs to support laypeople and self-represented litigants in finding and assembling relevant information.
Authors: Siyuan Zhang, Linbo Xie
Abstract: Output uncertainty indicates whether the probabilistic properties reflect objective characteristics of the model output. Unlike most loss functions and metrics in machine learning, uncertainty pertains to individual samples, but validating it on individual samples is unfeasible. When validated collectively, it cannot fully represent individual sample properties, posing a challenge in calibrating model confidence in a limited data set. Hence, it is crucial to consider confidence calibration characteristics. To counter the adverse effects of the gradual amplification of the classifier output amplitude in supervised learning, we introduce a post-processing parametric calibration method, $\rho$-Norm Scaling, which expands the calibrator expression and mitigates overconfidence due to excessive amplitude while preserving accuracy. Moreover, bin-level objective-based calibrator optimization often results in the loss of significant instance-level information. Therefore, we include probability distribution regularization, which incorporates specific priori information that the instance-level uncertainty distribution after calibration should resemble the distribution before calibration. Experimental results demonstrate the substantial enhancement in the post-processing calibrator for uncertainty calibration with our proposed method.
Authors: Chiu-Han Hsiao, Kai Chen, Tsung-Yu Peng, Wei-Chieh Huang
Abstract: The traditional interpretation of Intravascular Ultrasound (IVUS) images during Percutaneous Coronary Intervention (PCI) is time-intensive and inconsistent, relying heavily on physician expertise. Regulatory restrictions and privacy concerns further hinder data integration across hospital systems, complicating collaborative analysis. To address these challenges, a parallel 2D U-Net model with a multi-stage segmentation architecture has been developed, utilizing federated learning to enable secure data analysis across institutions while preserving privacy. The model segments plaques by identifying and subtracting the External Elastic Membrane (EEM) and lumen areas, with preprocessing converting Cartesian to polar coordinates for improved computational efficiency. Achieving a Dice Similarity Coefficient (DSC) of 0.706, the model effectively identifies plaques and detects circular boundaries in real-time. Collaborative efforts with domain experts enhance plaque burden interpretation through precise quantitative measurements. Future advancements may involve integrating advanced federated learning techniques and expanding datasets to further improve performance and applicability. This adaptable technology holds promise for environments handling sensitive, distributed data, offering potential to optimize outcomes in medical imaging and intervention.
Authors: Reza Shirkavand, Peiran Yu, Shangqian Gao, Gowthami Somepalli, Tom Goldstein, Heng Huang
Abstract: Recent advances in diffusion generative models have yielded remarkable progress. While the quality of generated content continues to improve, these models have grown considerably in size and complexity. This increasing computational burden poses significant challenges, particularly in resource-constrained deployment scenarios such as mobile devices. The combination of model pruning and knowledge distillation has emerged as a promising solution to reduce computational demands while preserving generation quality. However, this technique inadvertently propagates undesirable behaviors, including the generation of copyrighted content and unsafe concepts, even when such instances are absent from the fine-tuning dataset. In this paper, we propose a novel bilevel optimization framework for pruned diffusion models that consolidates the fine-tuning and unlearning processes into a unified phase. Our approach maintains the principal advantages of distillation-namely, efficient convergence and style transfer capabilities-while selectively suppressing the generation of unwanted content. This plug-in framework is compatible with various pruning and concept unlearning methods, facilitating efficient, safe deployment of diffusion models in controlled environments.
Authors: Denis Prokopenko, David F. A. Lloyd, Amedeo Chiribiri, Daniel Rueckert, Joseph V. Hajnal
Abstract: Dynamic fetal heart magnetic resonance imaging (MRI) presents unique challenges due to the fast heart rate of the fetus compared to adult subjects and uncontrolled fetal motion. This requires high temporal and spatial resolutions over a large field of view, in order to encompass surrounding maternal anatomy. In this work, we introduce Dynamic Cardiac Reconstruction Attention Network (DCRA-Net) - a novel deep learning model that employs attention mechanisms in spatial and temporal domains and temporal frequency representation of data to reconstruct the dynamics of the fetal heart from highly accelerated free-running (non-gated) MRI acquisitions. DCRA-Net was trained on retrospectively undersampled complex-valued cardiac MRIs from 42 fetal subjects and separately from 153 adult subjects, and evaluated on data from 14 fetal and 39 adult subjects respectively. Its performance was compared to L+S and k-GIN methods in both fetal and adult cases for an undersampling factor of 8x. The proposed network performed better than the comparators for both fetal and adult data, for both regular lattice and centrally weighted random undersampling. Aliased signals due to the undersampling were comprehensively resolved, and both the spatial details of the heart and its temporal dynamics were recovered with high fidelity. The highest performance was achieved when using lattice undersampling, data consistency and temporal frequency representation, yielding PSNR of 38 for fetal and 35 for adult cases. Our method is publicly available at https://github.com/denproc/DCRA-Net.
Authors: Berke Levent Cesur, Ayse Humeyra Dur Karasayar, Pinar Bulutay, Nilgun Kapucuoglu, Cisel Aydin Mericoz, Handan Eren, Omer Faruk Dilbaz, Javidan Osmanli, Burhan Soner Yetkili, Ibrahim Kulac, Can Fahrettin Koyuncu, Cigdem Gunduz-Demir
Abstract: Cell detection and segmentation are integral parts of automated systems in digital pathology. Encoder-decoder networks have emerged as a promising solution for these tasks. However, training of these networks has typically required full boundary annotations of cells, which are labor-intensive and difficult to obtain on a large scale. However, in many applications, such as cell counting, weaker forms of annotations--such as point annotations or approximate cell counts--can provide sufficient supervision for training. This study proposes a new mixed-supervision approach for training multitask networks in digital pathology by incorporating cell counts derived from the eyeballing process--a quick visual estimation method commonly used by pathologists. This study has two main contributions: (1) It proposes a mixed-supervision strategy for digital pathology that utilizes cell counts obtained by eyeballing as an auxiliary supervisory signal to train a multitask network for the first time. (2) This multitask network is designed to concurrently learn the tasks of cell counting and cell localization, and this study introduces a consistency loss that regularizes training by penalizing inconsistencies between the predictions of these two tasks. Our experiments on two datasets of hematoxylin-eosin stained tissue images demonstrate that the proposed approach effectively utilizes the weakest form of annotation, improving performance when stronger annotations are limited. These results highlight the potential of integrating eyeballing-derived ground truths into the network training, reducing the need for resource-intensive annotations.
Authors: Maniraj Sai Adapa, Marco Zullich, Matias Valdenegro-Toro
Abstract: Deep Learning-based image super-resolution (SR) has been gaining traction with the aid of Generative Adversarial Networks. Models like SRGAN and ESRGAN are constantly ranked between the best image SR tools. However, they lack principled ways for estimating predictive uncertainty. In the present work, we enhance these models using Monte Carlo-Dropout and Deep Ensemble, allowing the computation of predictive uncertainty. When coupled with a prediction, uncertainty estimates can provide more information to the model users, highlighting pixels where the SR output might be uncertain, hence potentially inaccurate, if these estimates were to be reliable. Our findings suggest that these uncertainty estimates are decently calibrated and can hence fulfill this goal, while providing no performance drop with respect to the corresponding models without uncertainty estimation.
Authors: Suhyun Kang, Jungwon Park, Wonseok Lee, Wonjong Rhee
Abstract: Cross-Domain Few-Shot Learning~(CDFSL) methods typically parameterize models with task-agnostic and task-specific parameters. To adapt task-specific parameters, recent approaches have utilized fixed optimization strategies, despite their potential sub-optimality across varying domains or target tasks. To address this issue, we propose a novel adaptation mechanism called Task-Specific Preconditioned gradient descent~(TSP). Our method first meta-learns Domain-Specific Preconditioners~(DSPs) that capture the characteristics of each meta-training domain, which are then linearly combined using task-coefficients to form the Task-Specific Preconditioner. The preconditioner is applied to gradient descent, making the optimization adaptive to the target task. We constrain our preconditioners to be positive definite, guiding the preconditioned gradient toward the direction of steepest descent. Empirical evaluations on the Meta-Dataset show that TSP achieves state-of-the-art performance across diverse experimental scenarios.
Authors: Sascha Saralajew, Ashish Rana, Thomas Villmann, Ammar Shaker
Abstract: Prototype-based classification learning methods are known to be inherently interpretable. However, this paradigm suffers from major limitations compared to deep models, such as lower performance. This led to the development of the so-called deep Prototype-Based Networks (PBNs), also known as prototypical parts models. In this work, we analyze these models with respect to different properties, including interpretability. In particular, we focus on the Classification-by-Components (CBC) approach, which uses a probabilistic model to ensure interpretability and can be used as a shallow or deep architecture. We show that this model has several shortcomings, like creating contradicting explanations. Based on these findings, we propose an extension of CBC that solves these issues. Moreover, we prove that this extension has robustness guarantees and derive a loss that optimizes robustness. Additionally, our analysis shows that most (deep) PBNs are related to (deep) RBF classifiers, which implies that our robustness guarantees generalize to shallow RBF classifiers. The empirical evaluation demonstrates that our deep PBN yields state-of-the-art classification accuracy on different benchmarks while resolving the interpretability shortcomings of other approaches. Further, our shallow PBN variant outperforms other shallow PBNs while being inherently interpretable and exhibiting provable robustness guarantees.
Authors: Yan-Ying Chen, Nikos Arechiga, Chenyang Yuan, Matthew Hong, Matt Klenk, Charlene Wu
Abstract: Generative AI is revolutionizing engineering design practices by enabling rapid prototyping and manipulation of designs. One example of design manipulation involves taking two reference design images and using them as prompts to generate a design image that combines aspects of both. Real engineering designs have physical constraints and functional requirements in addition to aesthetic design considerations. Internet-scale foundation models commonly used for image generation, however, are unable to take these physical constraints and functional requirements into consideration as part of the generation process. We consider the problem of generating a design inspired by two input designs, and propose a zero-shot framework toward enforcing physical, functional requirements over the generation process by leveraging a pretrained diffusion model as the backbone. As a case study, we consider the example of rotational symmetry in generation of wheel designs. Automotive wheels are required to be rotationally symmetric for physical stability. We formulate the requirement of rotational symmetry by the use of a symmetrizer, and we use this symmetrizer to guide the diffusion process towards symmetric wheel generations. Our experimental results find that the proposed approach makes generated interpolations with higher realism than methods in related work, as evaluated by Fr\'echet inception distance (FID). We also find that our approach generates designs that more closely satisfy physical and functional requirements than generating without the symmetry guidance.
Authors: Vishwesh Sangarya, Jung-Eun Kim
Abstract: As a strategy for sustainability of deep learning, reusing an existing model by retraining it rather than training a new model from scratch is critical. In this paper, we propose REpresentation Shift QUantifying Estimator (RESQUE), a predictive quantifier to estimate the retraining cost of a model to distributional shifts or change of tasks. It provides a single concise index for an estimate of resources required for retraining the model. Through extensive experiments, we show that RESQUE has a strong correlation with various retraining measures. Our results validate that RESQUE is an effective indicator in terms of epochs, gradient norms, changes of parameter magnitude, energy, and carbon emissions. These measures align well with RESQUE for new tasks, multiple noise types, and varying noise intensities. As a result, RESQUE enables users to make informed decisions for retraining to different tasks/distribution shifts and determine the most cost-effective and sustainable option, allowing for the reuse of a model with a much smaller footprint in the environment. The code for this work is available here: https://github.com/JEKimLab/AAAI2025RESQUE
Authors: Weizhi Xian, Mingliang Zhou, Leong Hou U, Lang Shujun, Bin Fang, Tao Xiang, Zhaowei Shang
Abstract: In this paper, we propose a physically imaging-guided framework for underwater image quality assessment (UIQA), called PIGUIQA. First, we formulate UIQA as a comprehensive problem that considers the combined effects of direct transmission attenuation and backwards scattering on image perception. On this basis, we incorporate advanced physics-based underwater imaging estimation into our method and define distortion metrics that measure the impact of direct transmission attenuation and backwards scattering on image quality. Second, acknowledging the significant content differences across various regions of an image and the varying perceptual sensitivity to distortions in these regions, we design a local perceptual module on the basis of the neighborhood attention mechanism. This module effectively captures subtle features in images, thereby enhancing the adaptive perception of distortions on the basis of local information. Finally, by employing a global perceptual module to further integrate the original image content with underwater image distortion information, the proposed model can accurately predict the image quality score. Comprehensive experiments demonstrate that PIGUIQA achieves state-of-the-art performance in underwater image quality prediction and exhibits strong generalizability. The code for PIGUIQA is available on https://anonymous.4open.science/r/PIGUIQA-A465/
Authors: Renhao Ye, Shiyin Shen, Rafael S. de Souza, Quanfeng Xu, Mi Chen, Zhu Chen, Emille E. O. Ishida, Alberto Krone-Martins, Rupesh Durgesh
Abstract: The DESI Legacy Imaging Surveys (DESI-LIS) comprise three distinct surveys: the Dark Energy Camera Legacy Survey (DECaLS), the Beijing-Arizona Sky Survey (BASS), and the Mayall z-band Legacy Survey (MzLS).The citizen science project Galaxy Zoo DECaLS 5 (GZD-5) has provided extensive and detailed morphology labels for a sample of 253,287 galaxies within the DECaLS survey. This dataset has been foundational for numerous deep learning-based galaxy morphology classification studies. However, due to differences in signal-to-noise ratios and resolutions between the DECaLS images and those from BASS and MzLS (collectively referred to as BMz), a neural network trained on DECaLS images cannot be directly applied to BMz images due to distributional mismatch.In this study, we explore an unsupervised domain adaptation (UDA) method that fine-tunes a source domain model trained on DECaLS images with GZD-5 labels to BMz images, aiming to reduce bias in galaxy morphology classification within the BMz survey. Our source domain model, used as a starting point for UDA, achieves performance on the DECaLS galaxies' validation set comparable to the results of related works. For BMz galaxies, the fine-tuned target domain model significantly improves performance compared to the direct application of the source domain model, reaching a level comparable to that of the source domain. We also release a catalogue of detailed morphology classifications for 248,088 galaxies within the BMz survey, accompanied by usage recommendations.
Authors: Zilin Huang, Zihao Sheng, Yansong Qu, Junwei You, Sikai Chen
Abstract: In recent years, reinforcement learning (RL)-based methods for learning driving policies have gained increasing attention in the autonomous driving community and have achieved remarkable progress in various driving scenarios. However, traditional RL approaches rely on manually engineered rewards, which require extensive human effort and often lack generalizability. To address these limitations, we propose \textbf{VLM-RL}, a unified framework that integrates pre-trained Vision-Language Models (VLMs) with RL to generate reward signals using image observation and natural language goals. The core of VLM-RL is the contrasting language goal (CLG)-as-reward paradigm, which uses positive and negative language goals to generate semantic rewards. We further introduce a hierarchical reward synthesis approach that combines CLG-based semantic rewards with vehicle state information, improving reward stability and offering a more comprehensive reward signal. Additionally, a batch-processing technique is employed to optimize computational efficiency during training. Extensive experiments in the CARLA simulator demonstrate that VLM-RL outperforms state-of-the-art baselines, achieving a 10.5\% reduction in collision rate, a 104.6\% increase in route completion rate, and robust generalization to unseen driving scenarios. Furthermore, VLM-RL can seamlessly integrate almost any standard RL algorithms, potentially revolutionizing the existing RL paradigm that relies on manual reward engineering and enabling continuous performance improvements. The demo video and code can be accessed at: https://zilin-huang.github.io/VLM-RL-website.
Authors: Saleh Momeni, Sahisnu Mazumder, Bing Liu
Abstract: Continual learning (CL) learns a sequence of tasks incrementally. This paper studies the challenging CL setting of class-incremental learning (CIL). CIL has two key challenges: catastrophic forgetting (CF) and inter-task class separation (ICS). Despite numerous proposed methods, these issues remain persistent obstacles. This paper proposes a novel CIL method, called Kernel Linear Discriminant Analysis (KLDA), that can effectively avoid CF and ICS problems. It leverages only the powerful features learned in a foundation model (FM). However, directly using these features proves suboptimal. To address this, KLDA incorporates the Radial Basis Function (RBF) kernel and its Random Fourier Features (RFF) to enhance the feature representations from the FM, leading to improved performance. When a new task arrives, KLDA computes only the mean for each class in the task and updates a shared covariance matrix for all learned classes based on the kernelized features. Classification is performed using Linear Discriminant Analysis. Our empirical evaluation using text and image classification datasets demonstrates that KLDA significantly outperforms baselines. Remarkably, without relying on replay data, KLDA achieves accuracy comparable to joint training of all classes, which is considered the upper bound for CIL performance. The KLDA code is available at https://github.com/salehmomeni/klda.
Authors: Xinyang Tong, Pengxiang Ding, Donglin Wang, Wenjie Zhang, Can Cui, Mingyang Sun, Yiguo Fan, Han Zhao, Hongyin Zhang, Yonghao Dang, Siteng Huang, Shangke Lyu
Abstract: This paper addresses the inherent inference latency challenges associated with deploying multimodal large language models (MLLM) in quadruped vision-language-action (QUAR-VLA) tasks. Our investigation reveals that conventional parameter reduction techniques ultimately impair the performance of the language foundation model during the action instruction tuning phase, making them unsuitable for this purpose. We introduce a novel latency-free quadruped MLLM model, dubbed QUART-Online, designed to enhance inference efficiency without degrading the performance of the language foundation model. By incorporating Action Chunk Discretization (ACD), we compress the original action representation space, mapping continuous action values onto a smaller set of discrete representative vectors while preserving critical information. Subsequently, we fine-tune the MLLM to integrate vision, language, and compressed actions into a unified semantic space. Experimental results demonstrate that QUART-Online operates in tandem with the existing MLLM system, achieving real-time inference in sync with the underlying controller frequency, significantly boosting the success rate across various tasks by 65\%. Our project page is \href{https://quart-online.github.io}https://quart-online.github.io.
URLs: https://quart-online.github.io, https://quart-online.github.io.
Authors: Zhi Gao, Bofei Zhang, Pengxiang Li, Xiaojian Ma, Tao Yuan, Yue Fan, Yuwei Wu, Yunde Jia, Song-Chun Zhu, Qing Li
Abstract: The advancement of large language models (LLMs) prompts the development of multi-modal agents, which are used as a controller to call external tools, providing a feasible way to solve practical tasks. In this paper, we propose a multi-modal agent tuning method that automatically generates multi-modal tool-usage data and tunes a vision-language model (VLM) as the controller for powerful tool-usage reasoning. To preserve the data quality, we prompt the GPT-4o mini model to generate queries, files, and trajectories, followed by query-file and trajectory verifiers. Based on the data synthesis pipeline, we collect the MM-Traj dataset that contains 20K tasks with trajectories of tool usage. Then, we develop the T3-Agent via \underline{T}rajectory \underline{T}uning on VLMs for \underline{T}ool usage using MM-Traj. Evaluations on the GTA and GAIA benchmarks show that the T3-Agent consistently achieves improvements on two popular VLMs: MiniCPM-V-8.5B and {Qwen2-VL-7B}, which outperforms untrained VLMs by $20\%$, showing the effectiveness of the proposed data synthesis pipeline, leading to high-quality data for tool-usage capabilities.
Authors: Yangyang Guo, Ziwei Xu, Xilie Xu, YongKang Wong, Liqiang Nie, Mohan Kankanhalli
Abstract: This technical report introduces our top-ranked solution that employs two approaches, \ie suffix injection and projected gradient descent (PGD) , to address the TiFA workshop MLLM attack challenge. Specifically, we first append the text from an incorrectly labeled option (pseudo-labeled) to the original query as a suffix. Using this modified query, our second approach applies the PGD method to add imperceptible perturbations to the image. Combining these two techniques enables successful attacks on the LLaVA 1.5 model.
Authors: Yifei Sun, Zhanghao Chen, Hao Zheng, Ruiquan Ge, Jin Liu, Wenwen Min, Ahmed Elazab, Xiang Wan, Changmiao Wang
Abstract: The interference of overlapping bones and pulmonary structures can reduce the effectiveness of Chest X-ray (CXR) examinations. Bone suppression techniques have been developed to improve diagnostic accuracy. Dual-energy subtraction (DES) imaging, a common method for bone suppression, is costly and exposes patients to higher radiation levels. Deep learning-based image generation methods have been proposed as alternatives, however, they often fail to produce high-quality and high-resolution images, resulting in the loss of critical lesion information and texture details. To address these issues, in this paper, we introduce an end-to-end framework for bone suppression in high-resolution CXR images, termed BS-LDM. This framework employs a conditional latent diffusion model to generate high-resolution soft tissue images with fine detail and critical lung pathology by performing bone suppression in the latent space. We implement offset noise during the noise addition phase of the training process to better render low-frequency information in soft tissue images. Additionally, we introduce a dynamic clipping strategy during the sampling process to refine pixel intensity in the generated soft tissue images. We compiled a substantial and high-quality bone suppression dataset, SZCH-X-Rays, including high-resolution paired CXR and DES soft tissue images from 818 patients, collected from our partner hospitals. Moreover, we pre-processed 241 pairs of CXR and DES soft tissue images from the JSRT dataset, the largest publicly available dataset. Comprehensive experimental and clinical evaluations demonstrate that BS-LDM exhibits superior bone suppression capabilities, highlighting its significant clinical potential.
Authors: Anna Reithmeir, Veronika Spieker, Vasiliki Sideri-Lampretsa, Daniel Rueckert, Julia A. Schnabel, Veronika A. Zimmer
Abstract: Image registration is fundamental in medical imaging applications, such as disease progression analysis or radiation therapy planning. The primary objective of image registration is to precisely capture the deformation between two or more images, typically achieved by minimizing an optimization problem. Due to its inherent ill-posedness, regularization is a key component in driving the solution toward anatomically meaningful deformations. A wide range of regularization methods has been proposed for both conventional and deep learning-based registration. However, the appropriate application of regularization techniques often depends on the specific registration problem, and no one-fits-all method exists. Despite its importance, regularization is often overlooked or addressed with default approaches, assuming existing methods are sufficient. A comprehensive and structured review remains missing. This review addresses this gap by introducing a novel taxonomy that systematically categorizes the diverse range of proposed regularization methods. It highlights the emerging field of learned regularization, which leverages data-driven techniques to automatically derive deformation properties from the data. Moreover, this review examines the transfer of regularization methods from conventional to learning-based registration, identifies open challenges, and outlines future research directions. By emphasizing the critical role of regularization in image registration, we hope to inspire the research community to reconsider regularization strategies in modern registration algorithms and to explore this rapidly evolving field further.
Authors: Maximilian Fischer, Florian M. Hauptmann, Robin Peretzke, Paul Naser, Peter Neher, Jan-Oliver Neumann, Klaus Maier-Hein
Abstract: Although advances in brain surgery techniques have led to fewer postoperative complications requiring Intensive Care Unit (ICU) monitoring, the routine transfer of patients to the ICU remains the clinical standard, despite its high cost. Predictive Gradient Boosted Trees based on clinical data have attempted to optimize ICU admission by identifying key risk factors pre-operatively; however, these approaches overlook valuable imaging data that could enhance prediction accuracy. In this work, we show that multimodal approaches that combine clinical data with imaging data outperform the current clinical data only baseline from 0.29 [F1] to 0.30 [F1], when only pre-operative clinical data is used and from 0.37 [F1] to 0.41 [F1], for pre- and post-operative data. This study demonstrates that effective ICU admission prediction benefits from multimodal data fusion, especially in contexts of severe class imbalance.
Authors: Xuekai Wei, Junyu Zhang, Qinlin Hu, Mingliang Zhou\\Yong Feng, Weizhi Xian, Huayan Pu, Sam Kwong
Abstract: Current full-reference image quality assessment (FR-IQA) methods often fuse features from reference and distorted images, overlooking that color and luminance distortions occur mainly at low frequencies, whereas edge and texture distortions occur at high frequencies. This work introduces a pioneering training-free FR-IQA method that accurately predicts image quality in alignment with the human visual system (HVS) by leveraging a novel perceptual degradation modelling approach to address this limitation. First, a collaborative feature refinement module employs a carefully designed wavelet transform to extract perceptually relevant features, capturing multiscale perceptual information and mimicking how the HVS analyses visual information at various scales and orientations in the spatial and frequency domains. Second, a Hausdorff distance-based distribution similarity measurement module robustly assesses the discrepancy between the feature distributions of the reference and distorted images, effectively handling outliers and variations while mimicking the ability of HVS to perceive and tolerate certain levels of distortion. The proposed method accurately captures perceptual quality differences without requiring training data or subjective quality scores. Extensive experiments on multiple benchmark datasets demonstrate superior performance compared with existing state-of-the-art approaches, highlighting its ability to correlate strongly with the HVS.\footnote{The code is available at \url{https://anonymous.4open.science/r/CVPR2025-F339}.}
Authors: Sebastian Niehaus, Ingo Roeder, Nico Scherf
Abstract: Decentralised learning enables the training of deep learning algorithms without centralising data sets, resulting in benefits such as improved data privacy, operational efficiency and the fostering of data ownership policies. However, significant data imbalances pose a challenge in this framework. Participants with smaller datasets in distributed learning environments often achieve poorer results than participants with larger datasets. Data imbalances are particularly pronounced in medical fields and are caused by different patient populations, technological inequalities and divergent data collection practices. In this paper, we consider distributed learning as an Stackelberg evolutionary game. We present two algorithms for setting the weights of each node's contribution to the global model in each training round: the Deterministic Stackelberg Weighting Model (DSWM) and the Adaptive Stackelberg Weighting Model (ASWM). We use three medical datasets to highlight the impact of dynamic weighting on underrepresented nodes in distributed learning. Our results show that the ASWM significantly favours underrepresented nodes by improving their performance by 2.713% in AUC. Meanwhile, nodes with larger datasets experience only a modest average performance decrease of 0.441%.
Authors: Jun Ma, Feifei Li, Sumin Kim, Reza Asakereh, Bao-Hiep Le, Dang-Khoa Nguyen-Vu, Alexander Pfefferle, Muxin Wei, Ruochen Gao, Donghang Lyu, Songxiao Yang, Lennart Purucker, Zdravko Marinov, Marius Staring, Haisheng Lu, Thuy Thanh Dao, Xincheng Ye, Zhi Li, Gianluca Brugnara, Philipp Vollmuth, Martha Foltyn-Dumitru, Jaeyoung Cho, Mustafa Ahmed Mahmutoglu, Martin Bendszus, Irada Pfl\"uger, Aditya Rastogi, Dong Ni, Xin Yang, Guang-Quan Zhou, Kaini Wang, Nicholas Heller, Nikolaos Papanikolopoulos, Christopher Weight, Yubing Tong, Jayaram K Udupa, Cahill J. Patrick, Yaqi Wang, Yifan Zhang, Francisco Contijoch, Elliot McVeigh, Xin Ye, Shucheng He, Robert Haase, Thomas Pinetz, Alexander Radbruch, Inga Krause, Erich Kobler, Jian He, Yucheng Tang, Haichun Yang, Yuankai Huo, Gongning Luo, Kaisar Kushibar, Jandos Amankulov, Dias Toleshbayev, Amangeldi Mukhamejan, Jan Egger, Antonio Pepe, Christina Gsaxner, Gijs Luijten, Shohei Fujita, Tomohiro Kikuchi, Benedikt Wiestler, Jan S. Kirschke, Ezequiel de la Rosa, Federico Bolelli, Luca Lumetti, Costantino Grana, Kunpeng Xie, Guomin Wu, Behrus Puladi, Carlos Mart\'in-Isla, Karim Lekadir, Victor M. Campello, Wei Shao, Wayne Brisbane, Hongxu Jiang, Hao Wei, Wu Yuan, Shuangle Li, Yuyin Zhou, Bo Wang
Abstract: Promptable segmentation foundation models have emerged as a transformative approach to addressing the diverse needs in medical images, but most existing models require expensive computing, posing a big barrier to their adoption in clinical practice. In this work, we organized the first international competition dedicated to promptable medical image segmentation, featuring a large-scale dataset spanning nine common imaging modalities from over 20 different institutions. The top teams developed lightweight segmentation foundation models and implemented an efficient inference pipeline that substantially reduced computational requirements while maintaining state-of-the-art segmentation accuracy. Moreover, the post-challenge phase advanced the algorithms through the design of performance booster and reproducibility tasks, resulting in improved algorithms and validated reproducibility of the winning solution. Furthermore, the best-performing algorithms have been incorporated into the open-source software with a user-friendly interface to facilitate clinical adoption. The data and code are publicly available to foster the further development of medical image segmentation foundation models and pave the way for impactful real-world applications.
Authors: Hasan Md Tusfiqur Alam, Devansh Srivastav, Md Abdul Kadir, Daniel Sonntag
Abstract: Deep learning has advanced medical image classification, but interpretability challenges hinder its clinical adoption. This study enhances interpretability in Chest X-ray (CXR) classification by using concept bottleneck models (CBMs) and a multi-agent Retrieval-Augmented Generation (RAG) system for report generation. By modeling relationships between visual features and clinical concepts, we create interpretable concept vectors that guide a multi-agent RAG system to generate radiology reports, enhancing clinical relevance, explainability, and transparency. Evaluation of the generated reports using an LLM-as-a-judge confirmed the interpretability and clinical utility of our model's outputs. On the COVID-QU dataset, our model achieved 81% classification accuracy and demonstrated robust report generation performance, with five key metrics ranging between 84% and 90%. This interpretable multi-agent framework bridges the gap between high-performance AI and the explainability required for reliable AI-driven CXR analysis in clinical settings.
Authors: Muhammad Abdullah Sohail, Salaar Masood, Hamza Iqbal
Abstract: This study investigates the potential of Large Language Models (LLMs), particularly GPT-4o, for Optical Character Recognition (OCR) in low-resource scripts such as Urdu, Albanian, and Tajik, with English serving as a benchmark. Using a meticulously curated dataset of 2,520 images incorporating controlled variations in text length, font size, background color, and blur, the research simulates diverse real-world challenges. Results emphasize the limitations of zero-shot LLM-based OCR, particularly for linguistically complex scripts, highlighting the need for annotated datasets and fine-tuned models. This work underscores the urgency of addressing accessibility gaps in text digitization, paving the way for inclusive and robust OCR solutions for underserved languages.
Authors: Alberta Longhini, Marco Moletta, Alfredo Reichlin, Michael C. Welle, David Held, Zackory Erickson, Danica Kragic
Abstract: We study the problem of learning graph dynamics of deformable objects that generalizes to unknown physical properties. Our key insight is to leverage a latent representation of elastic physical properties of cloth-like deformable objects that can be extracted, for example, from a pulling interaction. In this paper we propose EDO-Net (Elastic Deformable Object - Net), a model of graph dynamics trained on a large variety of samples with different elastic properties that does not rely on ground-truth labels of the properties. EDO-Net jointly learns an adaptation module, and a forward-dynamics module. The former is responsible for extracting a latent representation of the physical properties of the object, while the latter leverages the latent representation to predict future states of cloth-like objects represented as graphs. We evaluate EDO-Net both in simulation and real world, assessing its capabilities of: 1) generalizing to unknown physical properties, 2) transferring the learned representation to new downstream tasks.
Authors: Heng Guo, Jianfeng Zhang, Ke Yan, Le Lu, Minfeng Xu
Abstract: Automatic parsing of human anatomies at the instance-level from 3D computed tomography (CT) is a prerequisite step for many clinical applications. The presence of pathologies, broken structures or limited field-of-view (FOV) can all make anatomy parsing algorithms vulnerable. In this work, we explore how to leverage and implement the successful detection-then-segmentation paradigm for 3D medical data, and propose a steerable, robust, and efficient computing framework for detection, identification, and segmentation of anatomies in CT scans. Considering the complicated shapes, sizes, and orientations of anatomies, without loss of generality, we present a nine degrees of freedom (9-DoF) pose estimation solution in full 3D space using a novel single-stage, non-hierarchical representation. Our whole framework is executed in a steerable manner where any anatomy of interest can be directly retrieved to further boost inference efficiency. We have validated our method on three medical imaging parsing tasks: ribs, spine, and abdominal organs. For rib parsing, CT scans have been annotated at the rib instance-level for quantitative evaluation, similarly for spine vertebrae and abdominal organs. Extensive experiments on 9-DoF box detection and rib instance segmentation demonstrate the high efficiency and effectiveness of our framework (with the identification rate of 97.0% and the segmentation Dice score of 90.9%), compared favorably against several strong baselines (e.g., CenterNet, FCOS, and nnU-Net). For spine parsing and abdominal multi-organ segmentation, our method achieves competitive results on par with state-of-the-art methods on the public CTSpine1K dataset and FLARE22 competition, respectively. Our annotations, code, and models are available at: https://github.com/alibaba-damo-academy/Med_Query.
Authors: Riccardo Munaf\`o, Simone Saitta, Giacomo Ingallina, Paolo Denti, Francesco Maisano, Eustachio Agricola, Alberto Redaelli, Emiliano Votta
Abstract: Three-dimensional transesophageal echocardiography (3DTEE) is the recommended imaging technique for the assessment of mitral valve (MV) morphology and lesions in case of mitral regurgitation (MR) requiring surgical or transcatheter repair. Such assessment is key to thorough intervention planning and to intraprocedural guidance. However, it requires segmentation from 3DTEE images, which is timeconsuming, operator-dependent, and often merely qualitative. In the present work, a novel workflow to quantify the patient-specific MV geometry from 3DTEE is proposed. The developed approach relies on a 3D multi-decoder residual convolutional neural network (CNN) with a U-Net architecture for multi-class segmentation of MV annulus and leaflets. The CNN was trained and tested on a dataset comprising 55 3DTEE examinations of MR-affected patients. After training, the CNN is embedded into a fully automatic, and hence fully repeatable, pipeline that refines the predicted segmentation, detects MV anatomical landmarks and quantifies MV morphology. The trained 3D CNN achieves an average Dice score of $0.82 \pm 0.06$, mean surface distance of $0.43 \pm 0.14$ mm and 95% Hausdorff Distance (HD) of $3.57 \pm 1.56$ mm before segmentation refinement, outperforming a state-of-the-art baseline residual U-Net architecture, and provides an unprecedented multi-class segmentation of the annulus, anterior and posterior leaflet. The automatic 3D linear morphological measurements of the annulus and leaflets, specifically diameters and lengths, exhibit differences of less than 1.45 mm when compared to ground truth values. These measurements also demonstrate strong overall agreement with analyses conducted by semi-automated commercial software. The whole process requires minimal user interaction and requires approximately 15 seconds
Authors: Seulki Park, Daeho Um, Hajung Yoon, Sanghyuk Chun, Sangdoo Yun, Jin Young Choi
Abstract: With the extensive use of vision-language models in various downstream tasks, evaluating their robustness is crucial. In this paper, we propose a benchmark for assessing the robustness of vision-language models. We believe that a robust model should properly understand both linguistic and visual semantics and be resilient to explicit variations. In pursuit of this goal, we create new variants of texts and images in the MS-COCO test set and re-evaluate the state-of-the-art (SOTA) models with the new data. Specifically, we alter the meaning of text by replacing a word, and generate visually altered images that maintain some visual context while introducing noticeable pixel changes through image mixing techniques.Our evaluations on the proposed benchmark reveal substantial performance degradation in many SOTA models (e.g., Image-to-Text Recall@1: 81.9\% $\rightarrow$ 48.4\% in BLIP, 66.1\% $\rightarrow$ 37.6\% in VSE$\infty$), with the models often favoring the altered texts/images over the original ones. This indicates the current vision-language models struggle with subtle changes and often fail to understand the overall context of texts and images. Based on these findings, we propose semantic contrastive loss and visual contrastive loss to learn more robust embedding. Datasets and code are available at {\url{https://github.com/pseulki/rococo}}.
Authors: Sagar M. Waghmare, Kimberly Wilber, Dave Hawkey, Xuan Yang, Matthew Wilson, Stephanie Debats, Cattalyya Nuengsigkapian, Astuti Sharma, Lars Pandikow, Huisheng Wang, Hartwig Adam, Mikhail Sirotenko
Abstract: Vision is essential for human navigation. The World Health Organization (WHO) estimates that 43.3 million people were blind in 2020, and this number is projected to reach 61 million by 2050. Modern scene understanding models could empower these people by assisting them with navigation, obstacle avoidance and visual recognition capabilities. The research community needs high quality datasets for both training and evaluation to build these systems. While datasets for autonomous vehicles are abundant, there is a critical gap in datasets tailored for outdoor human navigation. This gap poses a major obstacle to the development of computer vision based Assistive Technologies. To overcome this obstacle, we present SANPO, a large-scale egocentric video dataset designed for dense prediction in outdoor human navigation environments. SANPO contains 701 stereo videos of 30+ seconds captured in diverse real-world outdoor environments across four geographic locations in the USA. Every frame has a high resolution depth map and 112K frames were annotated with temporally consistent dense video panoptic segmentation labels. The dataset also includes 1961 high-quality synthetic videos with pixel accurate depth and panoptic segmentation annotations to balance the noisy real world annotations with the high precision synthetic annotations. SANPO is already publicly available and is being used by mobile applications like Project Guideline to train mobile models that help low-vision users go running outdoors independently. To preserve anonymization during peer review, we will provide a link to our dataset upon acceptance. SANPO is available here: https://google-research-datasets.github.io/sanpo_dataset/
URLs: https://google-research-datasets.github.io/sanpo_dataset/
Authors: Xuan Wang, Guanhong Wang, Wenhao Chai, Jiayu Zhou, Gaoang Wang
Abstract: Image captioning bridges the gap between vision and language by automatically generating natural language descriptions for images. Traditional image captioning methods often overlook the preferences and characteristics of users. Personalized image captioning solves this problem by incorporating user prior knowledge into the model, such as writing styles and preferred vocabularies. Most existing methods emphasize the user context fusion process by memory networks or transformers. However, these methods ignore the distinct domains of each dataset. Therefore, they need to update the entire caption model parameters when meeting new samples, which is time-consuming and calculation-intensive. To address this challenge, we propose a novel personalized image captioning framework that leverages user context to consider personality factors. Additionally, our framework utilizes the prefix-tuning paradigm to extract knowledge from a frozen large language model, reducing the gap between different language domains. Specifically, we employ CLIP to extract the visual features of an image and align the semantic space using a query-guided mapping network. By incorporating the transformer layer, we merge the visual features with the user's contextual prior knowledge to generate informative prefixes. Moreover, we employ GPT-2 as the frozen large language model. With a small number of parameters to be trained, our model performs efficiently and effectively. Our model outperforms existing baseline models on Instagram and YFCC100M datasets across five evaluation metrics, demonstrating its superiority, including twofold improvements in metrics such as BLEU-4 and CIDEr.
Authors: Chuanming Wang, Yuxin Yang, Mengshi Qi, Huadong Ma
Abstract: Object re-identification (ReID) is committed to searching for objects of the same identity across cameras, and its real-world deployment is gradually increasing. Current ReID methods assume that the deployed system follows the centralized processing paradigm, i.e., all computations are conducted in the cloud server and edge devices are only used to capture images. As the number of videos experiences a rapid escalation, this paradigm has become impractical due to the finite computational resources in the cloud server. Therefore, the ReID system should be converted to fit in the cloud-edge collaborative processing paradigm, which is crucial to boost its scalability and practicality. However, current works lack relevant research on this important specific issue, making it difficult to adapt them into a cloud-edge framework effectively. In this paper, we propose a cloud-edge collaborative inference framework for ReID systems, aiming to expedite the return of the desired image captured by the camera to the cloud server by learning the spatial-temporal correlations among objects. In the system, a Distribution-aware Correlation Modeling network (DaCM) is particularly proposed to embed the spatial-temporal correlations of the camera network implicitly into a graph structure, and it can be applied 1) in the cloud to regulate the size of the upload window and 2) on the edge device to adjust the sequence of images, respectively. Notably, the proposed DaCM can be seamlessly combined with traditional ReID methods, enabling their application within our proposed edge-cloud collaborative framework. Extensive experiments demonstrate that our method obviously reduces transmission overhead and significantly improves performance.
Authors: Boyi Li, Junming Chen, Jathushan Rajasegaran, Yossi Gandelsman, Alexei A. Efros, Jitendra Malik
Abstract: In this paper, we present a diffusion model-based framework for animating people from a single image for a given target 3D motion sequence. Our approach has two core components: a) learning priors about invisible parts of the human body and clothing, and b) rendering novel body poses with proper clothing and texture. For the first part, we learn an in-filling diffusion model to hallucinate unseen parts of a person given a single image. We train this model on texture map space, which makes it more sample-efficient since it is invariant to pose and viewpoint. Second, we develop a diffusion-based rendering pipeline, which is controlled by 3D human poses. This produces realistic renderings of novel poses of the person, including clothing, hair, and plausible in-filling of unseen regions. This disentangled approach allows our method to generate a sequence of images that are faithful to the target motion in the 3D pose and, to the input image in terms of visual similarity. In addition to that, the 3D control allows various synthetic camera trajectories to render a person. Our experiments show that our method is resilient in generating prolonged motions and varied challenging and complex poses compared to prior methods. Please check our website for more details: https://boyiliee.github.io/3DHM.github.io/.
Authors: Xiaohan Zhang, Bharat Lal Bhatnagar, Sebastian Starke, Ilya Petrov, Vladimir Guzov, Helisa Dhamo, Eduardo P\'erez-Pellitero, Gerard Pons-Moll
Abstract: Interactions between human and objects are influenced not only by the object's pose and shape, but also by physical attributes such as object mass and surface friction. They introduce important motion nuances that are essential for diversity and realism. Despite advancements in recent human-object interaction methods, this aspect has been overlooked. Generating nuanced human motion presents two challenges. First, it is non-trivial to learn from multi-modal human and object information derived from both the physical and non-physical attributes. Second, there exists no dataset capturing nuanced human interactions with objects of varying physical properties, hampering model development. This work addresses the gap by introducing the FORCE model, an approach for synthesizing diverse, nuanced human-object interactions by modeling physical attributes. Our key insight is that human motion is dictated by the interrelation between the force exerted by the human and the perceived resistance. Guided by a novel intuitive physics encoding, the model captures the interplay between human force and resistance. Experiments also demonstrate incorporating human force facilitates learning multi-class motion. Accompanying our model, we contribute a dataset, which features diverse, different-styled motion through interactions with varying resistances.
Authors: Kartik Narayan, Vibashan VS, Rama Chellappa, Vishal M. Patel
Abstract: In this work, we introduce FaceXFormer, an end-to-end unified transformer model capable of performing nine facial analysis tasks including face parsing, landmark detection, head pose estimation, attribute prediction, and estimation of age, gender, race, expression, and face visibility within a single framework. Conventional methods in face analysis have often relied on task-specific designs and pre-processing techniques, which limit their scalability and integration into a unified architecture. Unlike these conventional methods, FaceXFormer leverages a transformer-based encoder-decoder architecture where each task is treated as a learnable token, enabling the seamless integration and simultaneous processing of multiple tasks within a single framework. Moreover, we propose a novel parameter-efficient decoder, FaceX, which jointly processes face and task tokens, thereby learning generalized and robust face representations across different tasks. We jointly trained FaceXFormer on nine face perception datasets and conducted experiments against specialized and multi-task models in both intra-dataset and cross-dataset evaluations across multiple benchmarks, showcasing state-of-the-art or competitive performance. Further, we performed a comprehensive analysis of different backbones for unified face task processing and evaluated our model "in-the-wild", demonstrating its robustness and generalizability. To the best of our knowledge, this is the first work to propose a single model capable of handling nine facial analysis tasks while maintaining real-time performance at 33.21 FPS.
Authors: Kumara Kahatapitiya, Kanchana Ranasinghe, Jongwoo Park, Michael S. Ryoo
Abstract: Language has become a prominent modality in computer vision with the rise of LLMs. Despite supporting long context-lengths, their effectiveness in handling long-term information gradually declines with input length. This becomes critical, especially in applications such as long-form video understanding. In this paper, we introduce a Language Repository (LangRepo) for LLMs, that maintains concise and structured information as an interpretable (i.e., all-textual) representation. Our repository is updated iteratively based on multi-scale video chunks. We introduce write and read operations that focus on pruning redundancies in text, and extracting information at various temporal scales. The proposed framework is evaluated on zero-shot visual question-answering benchmarks including EgoSchema, NExT-QA, IntentQA and NExT-GQA, showing state-of-the-art performance at its scale. Our code is available at https://github.com/kkahatapitiya/LangRepo.
Authors: Trong-Tung Nguyen, Duc-Anh Nguyen, Anh Tran, Cuong Pham
Abstract: Our work addresses limitations seen in previous approaches for object-centric editing problems, such as unrealistic results due to shape discrepancies and limited control in object replacement or insertion. To this end, we introduce FlexEdit, a flexible and controllable editing framework for objects where we iteratively adjust latents at each denoising step using our FlexEdit block. Initially, we optimize latents at test time to align with specified object constraints. Then, our framework employs an adaptive mask, automatically extracted during denoising, to protect the background while seamlessly blending new content into the target image. We demonstrate the versatility of FlexEdit in various object editing tasks and curate an evaluation test suite with samples from both real and synthetic images, along with novel evaluation metrics designed for object-centric editing. We conduct extensive experiments on different editing scenarios, demonstrating the superiority of our editing framework over recent advanced text-guided image editing methods. Our project page is published at https://flex-edit.github.io/.
Authors: Taha Emre, Arunava Chakravarty, Dmitrii Lachinov, Antoine Rivail, Ursula Schmidt-Erfurth, Hrvoje Bogunovi\'c
Abstract: Contrastive pretraining provides robust representations by ensuring their invariance to different image transformations while simultaneously preventing representational collapse. Equivariant contrastive learning, on the other hand, provides representations sensitive to specific image transformations while remaining invariant to others. By introducing equivariance to time-induced transformations, such as disease-related anatomical changes in longitudinal imaging, the model can effectively capture such changes in the representation space. In this work, we propose a Time-equivariant Contrastive Learning (TC) method. First, an encoder embeds two unlabeled scans from different time points of the same patient into the representation space. Next, a temporal equivariance module is trained to predict the representation of a later visit based on the representation from one of the previous visits and the corresponding time interval with a novel regularization loss term while preserving the invariance property to irrelevant image transformations. On a large longitudinal dataset, our model clearly outperforms existing equivariant contrastive methods in predicting progression from intermediate age-related macular degeneration (AMD) to advanced wet-AMD within a specified time-window.
Authors: Chenyu Yang, Xizhou Zhu, Jinguo Zhu, Weijie Su, Junjie Wang, Xuan Dong, Wenhai Wang, Lewei Lu, Bin Li, Jie Zhou, Yu Qiao, Jifeng Dai
Abstract: Recently, vision model pre-training has evolved from relying on manually annotated datasets to leveraging large-scale, web-crawled image-text data. Despite these advances, there is no pre-training method that effectively exploits the interleaved image-text data, which is very prevalent on the Internet. Inspired by the recent success of compression learning in natural language processing, we propose a novel vision model pre-training method called Latent Compression Learning (LCL) for interleaved image-text data. This method performs latent compression learning by maximizing the mutual information between the inputs and outputs of a causal attention model. The training objective can be decomposed into two basic tasks: 1) contrastive learning between visual representation and preceding context, and 2) generating subsequent text based on visual representation. Our experiments demonstrate that our method not only matches the performance of CLIP on paired pre-training datasets (e.g., LAION), but can also leverage interleaved pre-training data (e.g., MMC4) to learn robust visual representation from scratch, showcasing the potential of vision model pre-training with interleaved image-text data. Code is released at https://github.com/OpenGVLab/LCL.
Authors: Brandon Huang, Chancharik Mitra, Assaf Arbelle, Leonid Karlinsky, Trevor Darrell, Roei Herzig
Abstract: The recent success of interleaved Large Multimodal Models (LMMs) in few-shot learning suggests that in-context learning (ICL) with many examples can be promising for learning new tasks. However, this many-shot multimodal ICL setting has one crucial problem: it is fundamentally limited by the model's context length set at pretraining. The problem is especially prominent in the multimodal domain, which processes both text and images, requiring additional tokens. This motivates the need for a multimodal method to compress many shots into fewer tokens without finetuning. In this work, we enable LMMs to perform multimodal, many-shot in-context learning by leveraging Multimodal Task Vectors (MTV) -- compact implicit representations of in-context examples compressed in the model's attention heads. Specifically, we first demonstrate the existence of such MTV in LMMs and then leverage these extracted MTV to enable many-shot in-context learning for various vision-and-language tasks. Our experiments suggest that MTV can scale in performance with the number of compressed shots and generalize to similar out-of-domain tasks without additional context length for inference. Code: https://github.com/Brandon3964/MultiModal-Task-Vector
Authors: Ali Khaleghi Rahimian, Manish Kumar Govind, Subhajit Maity, Dominick Reilly, Christian K\"ummerle, Srijan Das, Aritra Dutta
Abstract: Transformer architectures such as Vision Transformers (ViT) have proven effective for solving visual perception tasks. However, they suffer from two major limitations; first, the quadratic complexity of self-attention limits the number of tokens that can be processed, and second, Transformers often require large amounts of training data to attain state-of-the-art performance. In this paper, we propose a new multi-head self-attention (MHSA) variant named Fibottention, which can replace MHSA in Transformer architectures. Fibottention is data-efficient and computationally more suitable for processing large numbers of tokens than the standard MHSA. It employs structured sparse attention based on dilated Fibonacci sequences, which, uniquely, differ across attention heads, resulting in inception-like diverse features across heads. The spacing of the Fibonacci sequences follows the Wythoff array, which minimizes the redundancy of token interactions aggregated across different attention heads, while still capturing sufficient complementary information through token pair interactions. These sparse attention patterns are unique among the existing sparse attention and lead to an $O(N \log N)$ complexity, where $N$ is the number of tokens. Leveraging only 2-6% of the elements in the self-attention heads, Fibottention embedded into popular, state-of-the-art Transformer architectures can achieve significantly improved predictive performance for domains with limited data such as image classification, video understanding, and robot learning tasks, and render reduced computational complexity. We further validated the improved diversity of feature representations resulting from different self-attention heads, and our model design against other sparse attention mechanisms.
Authors: Rongzhen Zhao, Vivienne Wang, Juho Kannala, Joni Pajarinen
Abstract: Similar to humans perceiving visual scenes as objects, Object-Centric Learning (OCL) can abstract dense images or videos into sparse object-level features. Transformer-based OCL handles complex textures well due to the decoding guidance of discrete representation, obtained by discretizing noisy features in image or video feature maps using template features from a codebook. However, treating features as minimal units overlooks their composing attributes, thus impeding model generalization; indexing features with natural numbers loses attribute-level commonalities and characteristics, thus diminishing heuristics for model convergence. We propose \textit{Grouped Discrete Representation} (GDR) to address these issues by grouping features into attributes and indexing them with tuple numbers. In extensive experiments across different query initializations, dataset modalities, and model architectures, GDR consistently improves convergence and generalizability. Visualizations show that our method effectively captures attribute-level information in features. The source code will be available upon acceptance.
Authors: Jingchen Sun, Rohan Sharma, Vishnu Suresh Lokhande, Changyou Chen
Abstract: Prompt Tuning has emerged as a prominent research paradigm for adapting vision-language models to various downstream tasks. However, recent research indicates that prompt tuning methods often lead to overfitting due to limited training samples. In this paper, we propose a Cross-modal Aligned Feature Tuning (Craft) method to address this issue. Cross-modal alignment is conducted by first selecting anchors from the alternative domain and deriving relative representations of the embeddings for the selected anchors. Optimizing for a feature alignment loss over anchor-aligned text and image modalities creates a more unified text-image common space. Overfitting in prompt tuning also deteriorates model performance on out-of-distribution samples. To further improve the prompt model's robustness, we propose minimizing Maximum Mean Discrepancy (MMD) over the anchor-aligned feature spaces to mitigate domain shift. The experiment on four different prompt tuning structures consistently shows the improvement of our method, with increases of up to $6.1\%$ in the Base-to-Novel generalization task, $5.8\%$ in the group robustness task, and $2.7\%$ in the out-of-distribution tasks. The code will be available at https://github.com/Jingchensun/Craft
Authors: Chaeyeon Chung, Sunghyun Park, Jeongho Kim, Jaegul Choo
Abstract: Hairstyle transfer is a challenging task in the image editing field that modifies the hairstyle of a given face image while preserving its other appearance and background features. The existing hairstyle transfer approaches heavily rely on StyleGAN, which is pre-trained on cropped and aligned face images. Hence, they struggle to generalize under challenging conditions such as extreme variations of head poses or focal lengths. To address this issue, we propose a one-stage hairstyle transfer diffusion model, HairFusion, that applies to real-world scenarios. Specifically, we carefully design a hair-agnostic representation as the input of the model, where the original hair information is thoroughly eliminated. Next, we introduce a hair align cross-attention (Align-CA) to accurately align the reference hairstyle with the face image while considering the difference in their head poses. To enhance the preservation of the face image's original features, we leverage adaptive hair blending during the inference, where the output's hair regions are estimated by the cross-attention map in Align-CA and blended with non-hair areas of the face image. Our experimental results show that our method achieves state-of-the-art performance compared to the existing methods in preserving the integrity of both the transferred hairstyle and the surrounding features. The codes are available at https://github.com/cychungg/HairFusion
Authors: Rongzhen Zhao, Vivienne Wang, Juho Kannala, Joni Pajarinen
Abstract: Object-Centric Learning (OCL) represents dense image or video pixels as sparse object features. Representative methods utilize discrete representation composed of Variational Autoencoder (VAE) template features to suppress pixel-level information redundancy and guide object-level feature aggregation. The most recent advancement, Grouped Discrete Representation (GDR), further decomposes these template features into attributes. However, its naive channel grouping as decomposition may erroneously group channels belonging to different attributes together and discretize them as sub-optimal template attributes, which losses information and harms expressivity. We propose Organized GDR (OGDR) to organize channels belonging to the same attributes together for correct decomposition from features into attributes. In unsupervised segmentation experiments, OGDR is fully superior to GDR in augmentating classical transformer-based OCL methods; it even improves state-of-the-art diffusion-based ones. Codebook PCA and representation similarity analyses show that compared with GDR, our OGDR eliminates redundancy and preserves information better for guiding object representation learning. The source code is available in the supplementary material.
Authors: Koen Kraaijveld, Yifan Jiang, Kaixin Ma, Filip Ilievski
Abstract: While visual question-answering (VQA) benchmarks have catalyzed the development of reasoning techniques, they have focused on vertical thinking. Effective problem-solving also necessitates lateral thinking, which remains understudied in AI and has not been used to test visual perception systems. To bridge this gap, we formulate visual lateral thinking as a multiple-choice question-answering task and describe a three-step taxonomy-driven methodology for instantiating task examples. Then, we develop COLUMBUS, a synthetic benchmark that applies the task pipeline to create QA sets with text and icon rebus puzzles based on publicly available collections of compounds and common phrases. COLUMBUS comprises over 1,000 puzzles, each with four answer candidates. While the SotA vision-language models (VLMs) achieve decent performance, our evaluation demonstrates a substantial gap between humans and models. VLMs benefit from human-curated descriptions but struggle to self-generate such representations at the right level of abstraction.
Authors: Meng Lou, Yunxiang Fu, Yizhou Yu
Abstract: Due to the capability of dynamic state space models (SSMs) in capturing long-range dependencies with linear-time computational complexity, Mamba has shown notable performance in NLP tasks. This has inspired the rapid development of Mamba-based vision models, resulting in promising results in visual recognition tasks. However, such models are not capable of distilling features across layers through feature aggregation, interaction, and selection. Moreover, existing cross-layer feature aggregation methods designed for CNNs or ViTs are not practical in Mamba-based models due to high computational costs. Therefore, this paper aims to introduce an efficient cross-layer feature aggregation mechanism for vision backbone networks. Inspired by the Retinal Ganglion Cells (RGCs) in the human visual system, we propose a new sparse cross-layer connection mechanism termed SparX to effectively improve cross-layer feature interaction and reuse. Specifically, we build two different types of network layers: ganglion layers and normal layers. The former has higher connectivity and complexity, enabling multi-layer feature aggregation and interaction in an input-dependent manner. In contrast, the latter has lower connectivity and complexity. By interleaving these two types of layers, we design a new family of vision backbone networks with sparsely cross-connected layers, achieving an excellent trade-off among model size, computational cost, memory cost, and accuracy in comparison to its counterparts. For instance, with fewer parameters, SparX-Mamba-T improves the top-1 accuracy of VMamba-T from 82.5\% to 83.5\%, while SparX-Swin-T achieves a 1.3\% increase in top-1 accuracy compared to Swin-T. Extensive experimental results demonstrate that our new connection mechanism possesses both superior performance and generalization capabilities on various vision tasks.
Authors: Hongyi Wang, Xiuju Du, Jing Liu, Shuyi Ouyang, Yen-Wei Chen, Lanfen Lin
Abstract: The advancement of Spatial Transcriptomics (ST) has facilitated the spatially-aware profiling of gene expressions based on histopathology images. Although ST data offers valuable insights into the micro-environment of tumors, its acquisition cost remains expensive. Therefore, directly predicting the ST expressions from digital pathology images is desired. Current methods usually adopt existing regression backbones along with patch-sampling for this task, which ignores the inherent multi-scale information embedded in the pyramidal data structure of digital pathology images, and wastes the inter-spot visual information crucial for accurate gene expression prediction. To address these limitations, we propose M2OST, a many-to-one regression Transformer that can accommodate the hierarchical structure of the pathology images via a decoupled multi-scale feature extractor. Unlike traditional models that are trained with one-to-one image-label pairs, M2OST uses multiple images from different levels of the digital pathology image to jointly predict the gene expressions in their common corresponding spot. Built upon our many-to-one scheme, M2OST can be easily scaled to fit different numbers of inputs, and its network structure inherently incorporates nearby inter-spot features, enhancing regression performance. We have tested M2OST on three public ST datasets and the experimental results show that M2OST can achieve state-of-the-art performance with fewer parameters and floating-point operations (FLOPs).
Authors: Hannah Kerner, Snehal Chaudhari, Aninda Ghosh, Caleb Robinson, Adeel Ahmad, Eddie Choi, Nathan Jacobs, Chris Holmes, Matthias Mohr, Rahul Dodhia, Juan M. Lavista Ferres, Jennifer Marcus
Abstract: Crop field boundaries are foundational datasets for agricultural monitoring and assessments but are expensive to collect manually. Machine learning (ML) methods for automatically extracting field boundaries from remotely sensed images could help realize the demand for these datasets at a global scale. However, current ML methods for field instance segmentation lack sufficient geographic coverage, accuracy, and generalization capabilities. Further, research on improving ML methods is restricted by the lack of labeled datasets representing the diversity of global agricultural fields. We present Fields of The World (FTW) -- a novel ML benchmark dataset for agricultural field instance segmentation spanning 24 countries on four continents (Europe, Africa, Asia, and South America). FTW is an order of magnitude larger than previous datasets with 70,462 samples, each containing instance and semantic segmentation masks paired with multi-date, multi-spectral Sentinel-2 satellite images. We provide results from baseline models for the new FTW benchmark, show that models trained on FTW have better zero-shot and fine-tuning performance in held-out countries than models that aren't pre-trained with diverse datasets, and show positive qualitative zero-shot results of FTW models in a real-world scenario -- running on Sentinel-2 scenes over Ethiopia.
Authors: Chong-Yang Xiang, Jun-Yan He, Zhi-Qi Cheng, Xiao Wu, Xian-Sheng Hua
Abstract: Achieving a balance between accuracy and efficiency is a critical challenge in facial landmark detection (FLD). This paper introduces Parallel Optimal Position Search (POPoS), a high-precision encoding-decoding framework designed to address the limitations of traditional FLD methods. POPoS employs three key contributions: (1) Pseudo-range multilateration is utilized to correct heatmap errors, improving landmark localization accuracy. By integrating multiple anchor points, it reduces the impact of individual heatmap inaccuracies, leading to robust overall positioning. (2) To enhance the pseudo-range accuracy of selected anchor points, a new loss function, named multilateration anchor loss, is proposed. This loss function enhances the accuracy of the distance map, mitigates the risk of local optima, and ensures optimal solutions. (3) A single-step parallel computation algorithm is introduced, boosting computational efficiency and reducing processing time. Extensive evaluations across five benchmark datasets demonstrate that POPoS consistently outperforms existing methods, particularly excelling in low-resolution heatmaps scenarios with minimal computational overhead. These advantages make POPoS a highly efficient and accurate tool for FLD, with broad applicability in real-world scenarios.
Authors: Daniel Bermuth, Alexander Poeppel, Wolfgang Reif
Abstract: In the rapidly evolving field of computer vision, the task of accurately estimating the poses of multiple individuals from various viewpoints presents a formidable challenge, especially if the estimations should be reliable as well. This work presents an extensive evaluation of the generalization capabilities of multi-view multi-person pose estimators to unseen datasets and presents a new algorithm with strong performance in this task. It also studies the improvements by additionally using depth information. Since the new approach can not only generalize well to unseen datasets, but also to different keypoints, the first multi-view multi-person whole-body estimator is presented. To support further research on those topics, all of the work is publicly accessible.
Authors: Haomeng Zhang, Chiao-An Yang, Raymond A. Yeh
Abstract: Multi-object 3D Grounding involves locating 3D boxes based on a given query phrase from a point cloud. It is a challenging and significant task with numerous applications in visual understanding, human-computer interaction, and robotics. To tackle this challenge, we introduce D-LISA, a two-stage approach incorporating three innovations. First, a dynamic vision module that enables a variable and learnable number of box proposals. Second, a dynamic camera positioning that extracts features for each proposal. Third, a language-informed spatial attention module that better reasons over the proposals to output the final prediction. Empirically, experiments show that our method outperforms the state-of-the-art methods on multi-object 3D grounding by 12.8% (absolute) and is competitive in single-object 3D grounding.
Authors: Chengpeng Wang, Li Chen, Lili Wang, Zhaofan Li, Xuebin Lv
Abstract: Facial expression recognition faces challenges where labeled significant features in datasets are mixed with unlabeled redundant ones. In this paper, we introduce Cross Similarity Attention (CSA) to mine richer intrinsic information from image pairs, overcoming a limitation when the Scaled Dot-Product Attention of ViT is directly applied to calculate the similarity between two different images. Based on CSA, we simultaneously minimize intra-class differences and maximize inter-class differences at the fine-grained feature level through interactions among multiple branches. Contrastive residual distillation is utilized to transfer the information learned in the cross module back to the base network. We ingeniously design a four-branch centrally symmetric network, named Quadruplet Cross Similarity (QCS), which alleviates gradient conflicts arising from the cross module and achieves balanced and stable training. It can adaptively extract discriminative features while isolating redundant ones. The cross-attention modules exist during training, and only one base branch is retained during inference, resulting in no increase in inference time. Extensive experiments show that our proposed method achieves state-of-the-art performance on several FER datasets.
Authors: Tim Kaiser, Nikolas Adaloglou, Markus Kollmann
Abstract: Guidance is an error-correcting technique used to improve the perceptual quality of images generated by diffusion models. Typically, the correction is achieved by linear extrapolation, using an auxiliary diffusion model that has lower performance than the primary model. Using a 2D toy example, we show that it is highly beneficial when the auxiliary model exhibits similar errors as the primary one but stronger. We verify this finding in higher dimensions, where we show that competitive generative performance to state-of-the-art guidance methods can be achieved when the auxiliary model differs from the primary one only by having stronger weight regularization. As an independent contribution, we investigate whether upweighting long-range spatial dependencies improves visual fidelity. The result is a novel guidance method, which we call sliding window guidance (SWG), that guides the primary model with itself by constraining its receptive field. Intriguingly, SWG aligns better with human preferences than state-of-the-art guidance methods while requiring neither training, architectural modifications, nor class conditioning. The code will be released.
Authors: Yongdong Luo, Xiawu Zheng, Xiao Yang, Guilin Li, Haojia Lin, Jinfa Huang, Jiayi Ji, Fei Chao, Jiebo Luo, Rongrong Ji
Abstract: Existing large video-language models (LVLMs) struggle to comprehend long videos correctly due to limited context. To address this problem, fine-tuning long-context LVLMs and employing GPT-based agents have emerged as promising solutions. However, fine-tuning LVLMs would require extensive high-quality data and substantial GPU resources, while GPT-based agents would rely on proprietary models (e.g., GPT-4o). In this paper, we propose Video Retrieval-Augmented Generation (Video-RAG), a training-free and cost-effective pipeline that employs visually-aligned auxiliary texts to help facilitate cross-modality alignment while providing additional information beyond the visual content. Specifically, we leverage open-source external tools to extract visually-aligned information from pure video data (e.g., audio, optical character, and object detection), and incorporate the extracted information into an existing LVLM as auxiliary texts, alongside video frames and queries, in a plug-and-play manner. Our Video-RAG offers several key advantages: (i) lightweight with low computing overhead due to single-turn retrieval; (ii) easy implementation and compatibility with any LVLM; and (iii) significant, consistent performance gains across long video understanding benchmarks, including Video-MME, MLVU, and LongVideoBench. Notably, our model demonstrates superior performance over proprietary models like Gemini-1.5-Pro and GPT-4o when utilized with a 72B model.
Authors: Anthony Nguyen
Abstract: Graphical User Interface (GUI) grounding plays a crucial role in enhancing the capabilities of Vision-Language Model (VLM) agents. While general VLMs, such as GPT-4V, demonstrate strong performance across various tasks, their proficiency in GUI grounding remains suboptimal. Recent studies have focused on fine-tuning these models specifically for zero-shot GUI grounding, yielding significant improvements over baseline performance. We introduce a visual prompting framework that employs an iterative narrowing mechanism to further improve the performance of both general and fine-tuned models in GUI grounding. For evaluation, we tested our method on a comprehensive benchmark comprising various UI platforms and provided the code to reproduce our results.
Authors: Anjali Nambiyar Rajkumar Kannan
Abstract: Edge detection has been one of the most difficult challenges in computer vision because of the difficulty in identifying the borders and edges from the real-world images including objects of varying kinds and sizes. Methods based on ensemble learning, which use a combination of backbones and attention modules, outperformed more conventional approaches, such as Sobel and Canny edge detection. Nevertheless, these algorithms are still challenged when faced with complicated scene photos. In addition, the identified edges utilizing the current methods are not refined and often include incorrect edges. In this work, we used a Cascaded Ensemble Canny operator to solve these problems and detect the object edges. The most difficult Fresh and Rotten and Berkeley datasets are used to test the suggested approach in Python. In terms of performance metrics and output picture quality, the acquired results outperform the specified edge detection networks
Authors: Baixin Xu, Jiangbei Hu, Jiaze Li, Ying He
Abstract: Surface reconstruction from multi-view images is a core challenge in 3D vision. Recent studies have explored signed distance fields (SDF) within Neural Radiance Fields (NeRF) to achieve high-fidelity surface reconstructions. However, these approaches often suffer from slow training and rendering speeds compared to 3D Gaussian splatting (3DGS). Current state-of-the-art techniques attempt to fuse depth information to extract geometry from 3DGS, but frequently result in incomplete reconstructions and fragmented surfaces. In this paper, we introduce GSurf, a novel end-to-end method for learning a signed distance field directly from Gaussian primitives. The continuous and smooth nature of SDF addresses common issues in the 3DGS family, such as holes resulting from noisy or missing depth data. By using Gaussian splatting for rendering, GSurf avoids the redundant volume rendering typically required in other GS and SDF integrations. Consequently, GSurf achieves faster training and rendering speeds while delivering 3D reconstruction quality comparable to neural implicit surface methods, such as VolSDF and NeuS. Experimental results across various benchmark datasets demonstrate the effectiveness of our method in producing high-fidelity 3D reconstructions.
Authors: Nikita Gabdullin
Abstract: This paper studies a combined person reidentification (re-id) method that uses human parsing, analytical feature extraction and similarity estimation schemes. One of its prominent features is its low computational requirements so it can be implemented on edge devices. The method allows direct comparison of specific image regions using interpretable features which consist of color and texture channels. It is proposed to analyze and compare colors in CIE-Lab color space using histogram smoothing for noise reduction. A novel pre-configured latent space (LS) supervised autoencoder (SAE) is proposed for texture analysis which encodes input textures as LS points. This allows to obtain more accurate similarity measures compared to simplistic label comparison. The proposed method also does not rely upon photos or other re-id data for training, which makes it completely re-id dataset-agnostic. The viability of the proposed method is verified by computing rank-1, rank-10, and mAP re-id metrics on Market1501 dataset. The results are comparable to those of conventional deep learning methods and the potential ways to further improve the method are discussed.
Authors: Shahran Rahman Alve
Abstract: This project aims to develop a robust video surveillance system, which can segment videos into smaller clips based on the detection of activities. It uses CCTV footage, for example, to record only major events-like the appearance of a person or a thief-so that storage is optimized and digital searches are easier. It utilizes the latest techniques in object detection and tracking, including Convolutional Neural Networks (CNNs) like YOLO, SSD, and Faster R-CNN, as well as Recurrent Neural Networks (RNNs) and Long Short-Term Memory networks (LSTMs), to achieve high accuracy in detection and capture temporal dependencies. The approach incorporates adaptive background modeling through Gaussian Mixture Models (GMM) and optical flow methods like Lucas-Kanade to detect motions. Multi-scale and contextual analysis are used to improve detection across different object sizes and environments. A hybrid motion segmentation strategy combines statistical and deep learning models to manage complex movements, while optimizations for real-time processing ensure efficient computation. Tracking methods, such as Kalman Filters and Siamese networks, are employed to maintain smooth tracking even in cases of occlusion. Detection is improved on various-sized objects for multiple scenarios by multi-scale and contextual analysis. Results demonstrate high precision and recall in detecting and tracking objects, with significant improvements in processing times and accuracy due to real-time optimizations and illumination-invariant features. The impact of this research lies in its potential to transform video surveillance, reducing storage requirements and enhancing security through reliable and efficient object detection and tracking.
Authors: Wenbo Huang, Jinghui Zhang, Guang Li, Lei Zhang, Shuoyuan Wang, Fang Dong, Jiahui Jin, Takahiro Ogawa, Miki Haseyama
Abstract: In few-shot action recognition (FSAR), long sub-sequences of video naturally express entire actions more effectively. However, the high computational complexity of mainstream Transformer-based methods limits their application. Recent Mamba demonstrates efficiency in modeling long sequences, but directly applying Mamba to FSAR overlooks the importance of local feature modeling and alignment. Moreover, long sub-sequences within the same class accumulate intra-class variance, which adversely impacts FSAR performance. To solve these challenges, we propose a Matryoshka MAmba and CoNtrasTive LeArning framework (Manta). Firstly, the Matryoshka Mamba introduces multiple Inner Modules to enhance local feature representation, rather than directly modeling global features. An Outer Module captures dependencies of timeline between these local features for implicit temporal alignment. Secondly, a hybrid contrastive learning paradigm, combining both supervised and unsupervised methods, is designed to mitigate the negative effects of intra-class variance accumulation. The Matryoshka Mamba and the hybrid contrastive learning paradigm operate in two parallel branches within Manta, enhancing Mamba for FSAR of long sub-sequence. Manta achieves new state-of-the-art performance on prominent benchmarks, including SSv2, Kinetics, UCF101, and HMDB51. Extensive empirical studies prove that Manta significantly improves FSAR of long sub-sequence from multiple perspectives.
Authors: Akram Zaytar, Girmaw Abebe Tadesse, Caleb Robinson, Eduardo G. Bendito, Medha Devare, Meklit Chernet, Gilles Q. Hacheme, Rahul Dodhia, Juan M. Lavista Ferres
Abstract: Acquiring, processing, and visualizing geospatial data requires significant computing resources, especially for large spatio-temporal domains. This challenge hinders the rapid discovery of predictive features, which is essential for advancing geospatial modeling. To address this, we developed Similarity Search (Sims), a no-code web tool that allows users to perform clustering and similarity search over defined regions of interest using Google Earth Engine as a backend. Sims is designed to complement existing modeling tools by focusing on feature exploration rather than model creation. We demonstrate the utility of Sims through a case study analyzing simulated maize yield data in Rwanda, where we evaluate how different combinations of soil, weather, and agronomic features affect the clustering of yield response zones. Sims is open source and available at https://github.com/microsoft/Sims
Authors: Zhengcong Fei, Di Qiu, Changqian Yu, Debang Li, Mingyuan Fan, Xiang Wen
Abstract: This paper investigates a solution for enabling in-context capabilities of video diffusion transformers, with minimal tuning required for activation. Specifically, we propose a simple pipeline to leverage in-context generation: ($\textbf{i}$) concatenate videos along spacial or time dimension, ($\textbf{ii}$) jointly caption multi-scene video clips from one source, and ($\textbf{iii}$) apply task-specific fine-tuning using carefully curated small datasets. Through a series of diverse controllable tasks, we demonstrate qualitatively that existing advanced text-to-video models can effectively perform in-context generation. Notably, it allows for the creation of consistent multi-scene videos exceeding 30 seconds in duration, without additional computational overhead. Importantly, this method requires no modifications to the original models, results in high-fidelity video outputs that better align with prompt specifications and maintain role consistency. Our framework presents a valuable tool for the research community and offers critical insights for advancing product-level controllable video generation systems. The data, code, and model weights are publicly available at: \url{https://github.com/feizc/Video-In-Context}.
Authors: Hao Chen, Ze Wang, Xiang Li, Ximeng Sun, Fangyi Chen, Jiang Liu, Jindong Wang, Bhiksha Raj, Zicheng Liu, Emad Barsoum
Abstract: Efficient image tokenization with high compression ratios remains a critical challenge for training generative models. We present SoftVQ-VAE, a continuous image tokenizer that leverages soft categorical posteriors to aggregate multiple codewords into each latent token, substantially increasing the representation capacity of the latent space. When applied to Transformer-based architectures, our approach compresses 256x256 and 512x512 images using as few as 32 or 64 1-dimensional tokens. Not only does SoftVQ-VAE show consistent and high-quality reconstruction, more importantly, it also achieves state-of-the-art and significantly faster image generation results across different denoising-based generative models. Remarkably, SoftVQ-VAE improves inference throughput by up to 18x for generating 256x256 images and 55x for 512x512 images while achieving competitive FID scores of 1.78 and 2.21 for SiT-XL. It also improves the training efficiency of the generative models by reducing the number of training iterations by 2.3x while maintaining comparable performance. With its fully-differentiable design and semantic-rich latent space, our experiment demonstrates that SoftVQ-VAE achieves efficient tokenization without compromising generation quality, paving the way for more efficient generative models. Code and model are released.
Authors: Yuanmin Tang, Xiaoting Qin, Jue Zhang, Jing Yu, Gaopeng Gou, Gang Xiong, Qingwei Ling, Saravan Rajmohan, Dongmei Zhang, Qi Wu
Abstract: Composed Image Retrieval (CIR) aims to retrieve target images that closely resemble a reference image while integrating user-specified textual modifications, thereby capturing user intent more precisely. Existing training-free zero-shot CIR (ZS-CIR) methods often employ a two-stage process: they first generate a caption for the reference image and then use Large Language Models for reasoning to obtain a target description. However, these methods suffer from missing critical visual details and limited reasoning capabilities, leading to suboptimal retrieval performance. To address these challenges, we propose a novel, training-free one-stage method, One-Stage Reflective Chain-of-Thought Reasoning for ZS-CIR (OSrCIR), which employs Multimodal Large Language Models to retain essential visual information in a single-stage reasoning process, eliminating the information loss seen in two-stage methods. Our Reflective Chain-of-Thought framework further improves interpretative accuracy by aligning manipulation intent with contextual cues from reference images. OSrCIR achieves performance gains of 1.80% to 6.44% over existing training-free methods across multiple tasks, setting new state-of-the-art results in ZS-CIR and enhancing its utility in vision-language applications. Our code will be available at https://github.com/Pter61/osrcir2024/.
Authors: Antonios Gasteratos, Stavros N. Moutsis, Konstantinos A. Tsintotas, Yiannis Aloimonos
Abstract: Visual-based human action recognition can be found in various application fields, e.g., surveillance systems, sports analytics, medical assistive technologies, or human-robot interaction frameworks, and it concerns the identification and classification of individuals' activities within a video. Since actions typically occur over a sequence of consecutive images, it is particularly challenging due to the inclusion of temporal analysis, which introduces an extra layer of complexity. However, although multiple approaches try to handle temporal analysis, there are still difficulties because of their computational cost and lack of adaptability. Therefore, different types of vision data, containing transition information between consecutive images, provided by next-generation hardware sensors will guide the robotics community in tackling the problem of human action recognition. On the other hand, while there is a plethora of still-image datasets, that researchers can adopt to train new artificial intelligence models, videos representing human activities are of limited capabilities, e.g., small and unbalanced datasets or selected without control from multiple sources. To this end, generating new and realistic synthetic videos is possible since labeling is performed throughout the data creation process, while reinforcement learning techniques can permit the avoidance of considerable dataset dependence. At the same time, human factors' involvement raises ethical issues for the research community, as doubts and concerns about new technologies already exist.
Authors: Zhuoran Du, Shaodi You, Cheng Cheng, Shikui Wei
Abstract: Hyperspectral image (HSI) densely samples the world in both the space and frequency domain and therefore is more distinctive than RGB images. Usually, HSI needs to be calibrated to minimize the impact of various illumination conditions. The traditional way to calibrate HSI utilizes a physical reference, which involves manual operations, occlusions, and/or limits camera mobility. These limitations inspire this paper to automatically calibrate HSIs using a learning-based method. Towards this goal, a large-scale HSI calibration dataset is created, which has 765 high-quality HSI pairs covering diversified natural scenes and illuminations. The dataset is further expanded to 7650 pairs by combining with 10 different physically measured illuminations. A spectral illumination transformer (SIT) together with an illumination attention module is proposed. Extensive benchmarks demonstrate the SoTA performance of the proposed SIT. The benchmarks also indicate that low-light conditions are more challenging than normal conditions. The dataset and codes are available online:https://github.com/duranze/Automatic-spectral-calibration-of-HSI
URLs: https://github.com/duranze/Automatic-spectral-calibration-of-HSI
Authors: Zesong Yang, Ru Zhang, Jiale Shi, Zixiang Ai, Boming Zhao, Hujun Bao, Luwei Yang, Zhaopeng Cui
Abstract: Neural surface representation has demonstrated remarkable success in the areas of novel view synthesis and 3D reconstruction. However, assessing the geometric quality of 3D reconstructions in the absence of ground truth mesh remains a significant challenge, due to its rendering-based optimization process and entangled learning of appearance and geometry with photometric losses. In this paper, we present a novel framework, i.e, GURecon, which establishes a geometric uncertainty field for the neural surface based on geometric consistency. Different from existing methods that rely on rendering-based measurement, GURecon models a continuous 3D uncertainty field for the reconstructed surface, and is learned by an online distillation approach without introducing real geometric information for supervision. Moreover, in order to mitigate the interference of illumination on geometric consistency, a decoupled field is learned and exploited to finetune the uncertainty field. Experiments on various datasets demonstrate the superiority of GURecon in modeling 3D geometric uncertainty, as well as its plug-and-play extension to various neural surface representations and improvement on downstream tasks such as incremental reconstruction. The code and supplementary material are available on the project website: https://zju3dv.github.io/GURecon/.
Authors: Chuanxing Geng, Aiyang Han, Songcan Chen
Abstract: Consistency and complementarity are two key ingredients for boosting multi-view clustering (MVC). Recently with the introduction of popular contrastive learning, the consistency learning of views has been further enhanced in MVC, leading to promising performance. However, by contrast, the complementarity has not received sufficient attention except just in the feature facet, where the Hilbert Schmidt Independence Criterion term or the independent encoder-decoder network is usually adopted to capture view-specific information. This motivates us to reconsider the complementarity learning of views comprehensively from multiple facets including the feature-, view-label- and contrast- facets, while maintaining the view consistency. We empirically find that all the facets contribute to the complementarity learning, especially the view-label facet, which is usually neglected by existing methods. Based on this, a simple yet effective \underline{M}ultifacet \underline{C}omplementarity learning framework for \underline{M}ulti-\underline{V}iew \underline{C}lustering (MCMVC) is naturally developed, which fuses multifacet complementarity information, especially explicitly embedding the view-label information. To our best knowledge, it is the first time to use view-labels explicitly to guide the complementarity learning of views. Compared with the SOTA baselines, MCMVC achieves remarkable improvements, e.g., by average margins over $5.00\%$ and $7.00\%$ respectively in complete and incomplete MVC settings on Caltech101-20 in terms of three evaluation metrics.
Authors: Kihyuk Yoon, Chiehyeon Lim
Abstract: In this work, we propose a novel activation mechanism called LayerAct for CNNs. This approach is motivated by our theoretical and experimental analyses, which demonstrate that Layer Normalization (LN) can mitigate a limitation of existing activation functions regarding noise robustness. However, LN is known to be disadvantageous in CNNs due to its tendency to make activation outputs homogeneous. The proposed method is designed to be more robust than existing activation functions by reducing the upper bound of influence caused by input shifts without inheriting LN's limitation. We provide analyses and experiments showing that LayerAct functions exhibit superior robustness compared to ElementAct functions. Experimental results on three clean and noisy benchmark datasets for image classification tasks indicate that LayerAct functions outperform other activation functions in handling noisy datasets while achieving superior performance on clean datasets in most cases.
Authors: P\'eter P\'osfay, Marcell T. Kurbucz, P\'eter Kov\'acs, Antal Jakov\'ac
Abstract: This paper introduces LLT-ECG, a novel method for electrocardiogram (ECG) signal classification that leverages concepts from theoretical physics to automatically generate features from time series data. Unlike traditional deep learning approaches, LLT-ECG operates in a forward manner, eliminating the need for backpropagation and hyperparameter tuning. By identifying linear laws that capture shared patterns within specific classes, the proposed method constructs a compact and verifiable representation, enhancing the effectiveness of downstream classifiers. We demonstrate LLT-ECG's state-of-the-art performance on real-world ECG datasets from PhysioNet, underscoring its potential for medical applications where speed and verifiability are crucial.
Authors: George Yiasemis, Nikita Moriakov, Clara I. S\'anchez, Jan-Jakob Sonke, Jonas Teuwen
Abstract: Magnetic Resonance Imaging (MRI) represents an important diagnostic modality; however, its inherently slow acquisition process poses challenges in obtaining fully-sampled $k$-space data under motion. In the absence of fully-sampled acquisitions, serving as ground truths, training deep learning algorithms in a supervised manner to predict the underlying ground truth image becomes challenging. To address this limitation, self-supervised methods have emerged as a viable alternative, leveraging available subsampled $k$-space data to train deep neural networks for MRI reconstruction. Nevertheless, these approaches often fall short when compared to supervised methods. We propose Joint Supervised and Self-supervised Learning (JSSL), a novel training approach for deep learning-based MRI reconstruction algorithms aimed at enhancing reconstruction quality in cases where target datasets containing fully-sampled $k$-space measurements are unavailable. JSSL operates by simultaneously training a model in a self-supervised learning setting, using subsampled data from the target dataset(s), and in a supervised learning manner, utilizing datasets with fully-sampled $k$-space data, referred to as proxy datasets. We demonstrate JSSL's efficacy using subsampled prostate or cardiac MRI data as the target datasets, with fully-sampled brain and knee, or brain, knee and prostate $k$-space acquisitions, respectively, as proxy datasets. Our results showcase substantial improvements over conventional self-supervised methods, validated using common image quality metrics. Furthermore, we provide theoretical motivations for JSSL and establish "rule-of-thumb" guidelines for training MRI reconstruction models. JSSL effectively enhances MRI reconstruction quality in scenarios where fully-sampled $k$-space data is not available, leveraging the strengths of supervised learning by incorporating proxy datasets.
Authors: Eric Xue, Yijiang Li, Haoyang Liu, Peiran Wang, Yifan Shen, Haohan Wang
Abstract: Dataset distillation (DD) allows datasets to be distilled to fractions of their original size while preserving the rich distributional information so that models trained on the distilled datasets can achieve a comparable accuracy while saving significant computational loads. Recent research in this area has been focusing on improving the accuracy of models trained on distilled datasets. In this paper, we aim to explore a new perspective of DD. We study how to embed adversarial robustness in distilled datasets, so that models trained on these datasets maintain the high accuracy and meanwhile acquire better adversarial robustness. We propose a new method that achieves this goal by incorporating curvature regularization into the distillation process with much less computational overhead than standard adversarial training. Extensive empirical experiments suggest that our method not only outperforms standard adversarial training on both accuracy and robustness with less computation overhead but is also capable of generating robust distilled datasets that can withstand various adversarial attacks.
Authors: Yongliang Wu, Shiji Zhou, Mingzhuo Yang, Lianzhe Wang, Heng Chang, Wenbo Zhu, Xinting Hu, Xiao Zhou, Xu Yang
Abstract: Text-to-image diffusion models have achieved remarkable success in generating photorealistic images. However, the inclusion of sensitive information during pre-training poses significant risks. Machine Unlearning (MU) offers a promising solution to eliminate sensitive concepts from these models. Despite its potential, existing MU methods face two main challenges: 1) limited generalization, where concept erasure is effective only within the unlearned set, failing to prevent sensitive concept generation from out-of-set prompts; and 2) utility degradation, where removing target concepts significantly impacts the model's overall performance. To address these issues, we propose a novel concept domain correction framework named \textbf{DoCo} (\textbf{Do}main \textbf{Co}rrection). By aligning the output domains of sensitive and anchor concepts through adversarial training, our approach ensures comprehensive unlearning of target concepts. Additionally, we introduce a concept-preserving gradient surgery technique that mitigates conflicting gradient components, thereby preserving the model's utility while unlearning specific concepts. Extensive experiments across various instances, styles, and offensive concepts demonstrate the effectiveness of our method in unlearning targeted concepts with minimal impact on related concepts, outperforming previous approaches even for out-of-distribution prompts.
Authors: Anna Breger, Clemens Karner, Ian Selby, Janek Gr\"ohl, S\"oren Dittmer, Edward Lilley, Judith Babar, Jake Beckford, Thomas R Else, Timothy J Sadler, Shahab Shahipasand, Arthikkaa Thavakumar, Michael Roberts, Carola-Bibiane Sch\"onlieb
Abstract: Image quality assessment (IQA) is standard practice in the development stage of novel machine learning algorithms that operate on images. The most commonly used IQA measures have been developed and tested for natural images, but not in the medical setting. Reported inconsistencies arising in medical images are not surprising, as they have different properties than natural images. In this study, we test the applicability of common IQA measures for medical image data by comparing their assessment to manually rated chest X-ray (5 experts) and photoacoustic image data (2 experts). Moreover, we include supplementary studies on grayscale natural images and accelerated brain MRI data. The results of all experiments show a similar outcome in line with previous findings for medical images: PSNR and SSIM in the default setting are in the lower range of the result list and HaarPSI outperforms the other tested measures in the overall performance. Also among the top performers in our experiments are the full reference measures FSIM, LPIPS and MS-SSIM. Generally, the results on natural images yield considerably higher correlations, suggesting that additional employment of tailored IQA measures for medical imaging algorithms is needed.
Authors: Yiping Wang, Yifang Chen, Wendan Yan, Alex Fang, Wenjing Zhou, Kevin Jamieson, Simon Shaolei Du
Abstract: Data selection has emerged as a core issue for large-scale visual-language model pretaining (e.g., CLIP), particularly with noisy web-curated datasets. Three main data selection approaches are: (1) leveraging external non-CLIP models to aid data selection, (2) training new CLIP-style embedding models that are more effective at selecting high-quality data than the original OpenAI CLIP model, and (3) designing better metrics or strategies universally applicable to any CLIP embedding without requiring specific model properties (e.g., CLIPScore is one popular metric). While the first two approaches have been extensively studied, the third remains under-explored. In this paper, we advance the third approach by proposing two new methods. Firstly, instead of classical CLIP scores that only consider the alignment between two modalities from a single sample, we introduce surrogate-CLIPLoss (s-CLIPLoss), a CLIP loss-inspired method that adds the alignment between one sample and its contrastive pairs as an extra normalization term for better quality measurement. Secondly, when downstream tasks are known, we propose a new norm-based metric, NormSim, to measure the similarity between pretraining data and target data. We test our methods on the data selection benchmark, DataComp~\cite{gadre2023datacomp}. Compared to the best baseline using only OpenAI's CLIP-L/14, our methods achieve a 5.3\% improvement on ImageNet-1k and a 2.8\% improvement on 38 downstream evaluation tasks. Moreover, both s-CLIPLoss and NormSim are compatible with existing techniques. By combining our methods with the current best methods DFN and HYPE, we can boost average performance on downstream tasks by 0.9\%, achieving a new state-of-the-art on the DataComp-medium benchmark.
Authors: Jinning Li, Jiachen Li, Sangjae Bae, David Isele
Abstract: Deep learning-based trajectory prediction models for autonomous driving often struggle with generalization to out-of-distribution (OOD) scenarios, sometimes performing worse than simple rule-based models. To address this limitation, we propose a novel framework, Adaptive Prediction Ensemble (APE), which integrates deep learning and rule-based prediction experts. A learned routing function, trained concurrently with the deep learning model, dynamically selects the most reliable prediction based on the input scenario. Our experiments on large-scale datasets, including Waymo Open Motion Dataset (WOMD) and Argoverse, demonstrate improvement in zero-shot generalization across datasets. We show that our method outperforms individual prediction models and other variants, particularly in long-horizon prediction and scenarios with a high proportion of OOD data. This work highlights the potential of hybrid approaches for robust and generalizable motion prediction in autonomous driving. More details can be found on the project page: https://sites.google.com/view/ape-generalization.
Authors: Zhengcong Fei, Mingyuan Fan, Changqian Yu, Junshi Huang
Abstract: This paper explores a simple extension of diffusion-based rectified flow Transformers for text-to-music generation, termed as FluxMusic. Generally, along with design in advanced Flux\footnote{https://github.com/black-forest-labs/flux} model, we transfers it into a latent VAE space of mel-spectrum. It involves first applying a sequence of independent attention to the double text-music stream, followed by a stacked single music stream for denoised patch prediction. We employ multiple pre-trained text encoders to sufficiently capture caption semantic information as well as inference flexibility. In between, coarse textual information, in conjunction with time step embeddings, is utilized in a modulation mechanism, while fine-grained textual details are concatenated with the music patch sequence as inputs. Through an in-depth study, we demonstrate that rectified flow training with an optimized architecture significantly outperforms established diffusion methods for the text-to-music task, as evidenced by various automatic metrics and human preference evaluations. Our experimental data, code, and model weights are made publicly available at: \url{https://github.com/feizc/FluxMusic}.
URLs: https://github.com/black-forest-labs/flux, https://github.com/feizc/FluxMusic
Authors: Paolo Rabino, Tatiana Tommasi
Abstract: Interacting with real-world cluttered scenes pose several challenges to robotic agents that need to understand complex spatial dependencies among the observed objects to determine optimal pick sequences or efficient object retrieval strategies. Existing solutions typically manage simplified scenarios and focus on predicting pairwise object relationships following an initial object detection phase, but often overlook the global context or struggle with handling redundant and missing object relations. In this work, we present a modern take on visual relational reasoning for grasp planning. We introduce D3GD, a novel testbed that includes bin picking scenes with up to 35 objects from 97 distinct categories. Additionally, we propose D3G, a new end-to-end transformer-based dependency graph generation model that simultaneously detects objects and produces an adjacency matrix representing their spatial relationships. Recognizing the limitations of standard metrics, we employ the Average Precision of Relationships for the first time to evaluate model performance, conducting an extensive experimental benchmark. The obtained results establish our approach as the new state-of-the-art for this task, laying the foundation for future research in robotic manipulation. We publicly release the code and dataset at https://paolotron.github.io/d3g.github.io.
Authors: Yucheng Zhou, Zhi Rao, Jun Wan, Jianbing Shen
Abstract: Large Vision-Language Models (LVLMs) excel in cross-model tasks but experience performance declines in long-context reasoning due to overreliance on textual information and reduced visual dependency. In this study, we empirically analyze LVLMs in long-context reasoning, revealing that increased context length leads to a higher dependence on language at the expense of visual dependency. To address this issue, we propose a novel training-free context pruning method that selectively removes less critical textual information. Our approach enhances visual dependency and reduces textual noise, thereby improving LVLM performance in long-context reasoning. We validate our method by constructing a long-context dataset, demonstrating its effectiveness across various LVLMs. Moreover, further analysis confirms the robustness of different token pruning strategies and preliminary explores scaling laws between pruning rates and context length.
Authors: Tyler J. Kovach, Daniel Schug, M. A. Wolfe, E. R. MacQuarrie, Patrick J. Walsh, Jared Benson, Mark Friesen, M. A. Eriksson, Justyna P. Zwolak
Abstract: Semiconductor quantum dot (QD) devices have become central to advancements in spin-based quantum computing. As the complexity of QD devices grows, manual tuning becomes increasingly infeasible, necessitating robust and scalable autotuning solutions. Tuning large arrays of QD qubits depends on efficient choices of automated protocols. Here, we introduce a bootstrapping, autonomous testing, and initialization system (BATIS) designed to streamline QD device evaluation and calibration. BATIS navigates high-dimensional gate voltage spaces, automating essential steps such as leakage testing and gate characterization. For forming the current channels, BATIS follows a non-standard approach that requires a single measurement regardless of the number of channels. Demonstrated at 1.3 K on a quad-QD Si/Si$_x$Ge$_{1-x}$ device, BATIS eliminates the need for deep cryogenic environments during initial device diagnostics, significantly enhancing scalability and reducing setup times. By requiring only minimal prior knowledge of the device architecture, BATIS represents a platform-agnostic solution, adaptable to various QD systems, which bridges a critical gap in QD autotuning.
Authors: Arth Shukla, Stone Tao, Hao Su
Abstract: High-quality benchmarks are the foundation for embodied AI research, enabling significant advancements in long-horizon navigation, manipulation and rearrangement tasks. However, as frontier tasks in robotics get more advanced, they require faster simulation speed, more intricate test environments, and larger demonstration datasets. To this end, we present MS-HAB, a holistic benchmark for low-level manipulation and in-home object rearrangement. First, we provide a GPU-accelerated implementation of the Home Assistant Benchmark (HAB). We support realistic low-level control and achieve over 3x the speed of previous magical grasp implementations at similar GPU memory usage. Second, we train extensive reinforcement learning (RL) and imitation learning (IL) baselines for future work to compare against. Finally, we develop a rule-based trajectory filtering system to sample specific demonstrations from our RL policies which match predefined criteria for robot behavior and safety. Combining demonstration filtering with our fast environments enables efficient, controlled data generation at scale.