Authors: Leif Van Holland, Michael Weinmann, Jan U. M\"uller, Patrick Stotko, Reinhard Klein
Abstract: While neural radiance fields (NeRF) led to a breakthrough in photorealistic novel view synthesis, handling mirroring surfaces still denotes a particular challenge as they introduce severe inconsistencies in the scene representation. Previous attempts either focus on reconstructing single reflective objects or rely on strong supervision guidance in terms of additional user-provided annotations of visible image regions of the mirrors, thereby limiting the practical usability. In contrast, in this paper, we present NeRF-MD, a method which shows that NeRFs can be considered as mirror detectors and which is capable of reconstructing neural radiance fields of scenes containing mirroring surfaces without the need for prior annotations. To this end, we first compute an initial estimate of the scene geometry by training a standard NeRF using a depth reprojection loss. Our key insight lies in the fact that parts of the scene corresponding to a mirroring surface will still exhibit a significant photometric inconsistency, whereas the remaining parts are already reconstructed in a plausible manner. This allows us to detect mirror surfaces by fitting geometric primitives to such inconsistent regions in this initial stage of the training. Using this information, we then jointly optimize the radiance field and mirror geometry in a second training stage to refine their quality. We demonstrate the capability of our method to allow the faithful detection of mirrors in the scene as well as the reconstruction of a single consistent scene representation, and demonstrate its potential in comparison to baseline and mirror-aware approaches.
Authors: Julia Lee Romero, Kyle Min, Subarna Tripathi, Morteza Karimzadeh
Abstract: Egocentric videos capture scenes from a wearer's viewpoint, resulting in dynamic backgrounds, frequent motion, and occlusions, posing challenges to accurate keystep recognition. We propose a flexible graph-learning framework for fine-grained keystep recognition that is able to effectively leverage long-term dependencies in egocentric videos, and leverage alignment between egocentric and exocentric videos during training for improved inference on egocentric videos. Our approach consists of constructing a graph where each video clip of the egocentric video corresponds to a node. During training, we consider each clip of each exocentric video (if available) as additional nodes. We examine several strategies to define connections across these nodes and pose keystep recognition as a node classification task on the constructed graphs. We perform extensive experiments on the Ego-Exo4D dataset and show that our proposed flexible graph-based framework notably outperforms existing methods by more than 12 points in accuracy. Furthermore, the constructed graphs are sparse and compute efficient. We also present a study examining on harnessing several multimodal features, including narrations, depth, and object class labels, on a heterogeneous graph and discuss their corresponding contribution to the keystep recognition performance.
Authors: Kam Woh Ng, Jing Yang, Jia Wei Sii, Jiankang Deng, Chee Seng Chan, Yi-Zhe Song, Tao Xiang, Xiatian Zhu
Abstract: In this paper, we push the boundaries of fine-grained 3D generation into truly creative territory. Current methods either lack intricate details or simply mimic existing objects -- we enable both. By lifting 2D fine-grained understanding into 3D through multi-view diffusion and modeling part latents as continuous distributions, we unlock the ability to generate entirely new, yet plausible parts through interpolation and sampling. A self-supervised feature consistency loss further ensures stable generation of these unseen parts. The result is the first system capable of creating novel 3D objects with species-specific details that transcend existing examples. While we demonstrate our approach on birds, the underlying framework extends beyond things that can chirp! Code will be released at https://github.com/kamwoh/chirpy3d.
Authors: Xuelu Feng, Yunsheng Li, Dongdong Chen, Mei Gao, Mengchen Liu, Junsong Yuan, Chunming Qiao
Abstract: Large multimodal language models (MLLMs) such as GPT-4V and GPT-4o have achieved remarkable advancements in understanding and generating multimodal content, showcasing superior quality and capabilities across diverse tasks. However, their deployment faces significant challenges, including slow inference, high computational cost, and impracticality for on-device applications. In contrast, the emergence of small MLLMs, exemplified by the LLava-series models and Phi-3-Vision, offers promising alternatives with faster inference, reduced deployment costs, and the ability to handle domain-specific scenarios. Despite their growing presence, the capability boundaries between large and small MLLMs remain underexplored. In this work, we conduct a systematic and comprehensive evaluation to benchmark both small and large MLLMs, spanning general capabilities such as object recognition, temporal reasoning, and multimodal comprehension, as well as real-world applications in domains like industry and automotive. Our evaluation reveals that small MLLMs can achieve comparable performance to large models in specific scenarios but lag significantly in complex tasks requiring deeper reasoning or nuanced understanding. Furthermore, we identify common failure cases in both small and large MLLMs, highlighting domains where even state-of-the-art models struggle. We hope our findings will guide the research community in pushing the quality boundaries of MLLMs, advancing their usability and effectiveness across diverse applications.
Authors: Siddharth Joshi, Besmira Nushi, Vidhisha Balachandran, Varun Chandrasekaran, Vibhav Vineet, Neel Joshi, Baharan Mirzasoleiman
Abstract: Vision-language models (VLMs) are highly effective but often underperform on specialized tasks; for example, Llava-1.5 struggles with chart and diagram understanding due to scarce task-specific training data. Existing training data, sourced from general-purpose datasets, fails to capture the nuanced details needed for these tasks. We introduce MM-Gen, a scalable method that generates task-specific, high-quality synthetic text for candidate images by leveraging stronger models. MM-Gen employs a three-stage targeted process: partitioning data into subgroups, generating targeted text based on task descriptions, and filtering out redundant and outlier data. Fine-tuning VLMs with data generated by MM-Gen leads to significant performance gains, including 29% on spatial reasoning and 15% on diagram understanding for Llava-1.5 (7B). Compared to human-curated caption data, MM-Gen achieves up to 1.6x better improvements for the original models, proving its effectiveness in enhancing task-specific VLM performance and bridging the gap between general-purpose datasets and specialized requirements. Code available at https://github.com/sjoshi804/MM-Gen.
Authors: Wisdom O. Ikezogwo, Kevin Zhang, Mehmet Saygin Seyfioglu, Fatemeh Ghezloo, Linda Shapiro, Ranjay Krishna
Abstract: We propose MedicalNarratives, a dataset curated from medical pedagogical videos similar in nature to data collected in Think-Aloud studies and inspired by Localized Narratives, which collects grounded image-text data by curating instructors' speech and mouse cursor movements synchronized in time. MedicalNarratives enables pretraining of both semantic and dense objectives, alleviating the need to train medical semantic and dense tasks disparately due to the lack of reasonably sized datasets. Our dataset contains 4.7M image-text pairs from videos and articles, with 1M samples containing dense annotations in the form of traces and bounding boxes. To evaluate the utility of MedicalNarratives, we train GenMedClip based on the CLIP architecture using our dataset spanning 12 medical domains and demonstrate that it outperforms previous state-of-the-art models on a newly constructed medical imaging benchmark that comprehensively evaluates performance across all modalities. Data, demo, code and models available at https://medical-narratives.github.io
Authors: Longzhen Li, Guang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
Abstract: Dataset distillation is an effective technique for reducing the cost and complexity of model training while maintaining performance by compressing large datasets into smaller, more efficient versions. In this paper, we present a novel generative dataset distillation method that can improve the accuracy of aligning prediction logits. Our approach integrates self-knowledge distillation to achieve more precise distribution matching between the synthetic and original data, thereby capturing the overall structure and relationships within the data. To further improve the accuracy of alignment, we introduce a standardization step on the logits before performing distribution matching, ensuring consistency in the range of logits. Through extensive experiments, we demonstrate that our method outperforms existing state-of-the-art methods, resulting in superior distillation performance.
Authors: Bowen Hao, Dongliang Zhou, Xiaojie Li, Xingyu Zhang, Liang Xie, Jianlong Wu, Erwei Yin
Abstract: Visual speech recognition (VSR), commonly known as lip reading, has garnered significant attention due to its wide-ranging practical applications. The advent of deep learning techniques and advancements in hardware capabilities have significantly enhanced the performance of lip reading models. Despite these advancements, existing datasets predominantly feature stable video recordings with limited variability in lip movements. This limitation results in models that are highly sensitive to variations encountered in real-world scenarios. To address this issue, we propose a novel framework, LipGen, which aims to improve model robustness by leveraging speech-driven synthetic visual data, thereby mitigating the constraints of current datasets. Additionally, we introduce an auxiliary task that incorporates viseme classification alongside attention mechanisms. This approach facilitates the efficient integration of temporal information, directing the model's focus toward the relevant segments of speech, thereby enhancing discriminative capabilities. Our method demonstrates superior performance compared to the current state-of-the-art on the lip reading in the wild (LRW) dataset and exhibits even more pronounced advantages under challenging conditions.
Authors: Seitaro Ono, Yuka Ogino, Takahiro Toizumi, Atsushi Ito, Masato Tsukada
Abstract: In this paper, we propose a novel low-light image enhancement method aimed at improving the performance of recognition models. Despite recent advances in deep learning, the recognition of images under low-light conditions remains a challenge. Although existing low-light image enhancement methods have been developed to improve image visibility for human vision, they do not specifically focus on enhancing recognition model performance. Our proposed low-light image enhancement method consists of two key modules: the Global Enhance Module, which adjusts the overall brightness and color balance of the input image, and the Pixelwise Adjustment Module, which refines image features at the pixel level. These modules are trained to enhance input images to improve downstream recognition model performance effectively. Notably, the proposed method can be applied as a frontend filter to improve low-light recognition performance without requiring retraining of downstream recognition models. Experimental results demonstrate that our method improves the performance of pretrained recognition models under low-light conditions and its effectiveness.
Authors: Abhishek Balasubramaniam, Febin P Sunny, Sudeep Pasricha
Abstract: To enhance perception in autonomous vehicles (AVs), recent efforts are concentrating on 3D object detectors, which deliver more comprehensive predictions than traditional 2D object detectors, at the cost of increased memory footprint and computational resource usage. We present a novel framework called UPAQ, which leverages semi-structured pattern pruning and quantization to improve the efficiency of LiDAR point-cloud and camera-based 3D object detectors on resource-constrained embedded AV platforms. Experimental results on the Jetson Orin Nano embedded platform indicate that UPAQ achieves up to 5.62x and 5.13x model compression rates, up to 1.97x and 1.86x boost in inference speed, and up to 2.07x and 1.87x reduction in energy consumption compared to state-of-the-art model compression frameworks, on the Pointpillar and SMOKE models respectively.
Authors: Ren Tasai, Guang Li, Ren Togo, Minghui Tang, Takaaki Yoshimura, Hiroyuki Sugimori, Kenji Hirata, Takahiro Ogawa, Kohsuke Kudo, Miki Haseyama
Abstract: We propose a novel continual self-supervised learning method (CSSL) considering medical domain knowledge in chest CT images. Our approach addresses the challenge of sequential learning by effectively capturing the relationship between previously learned knowledge and new information at different stages. By incorporating an enhanced DER into CSSL and maintaining both diversity and representativeness within the rehearsal buffer of DER, the risk of data interference during pretraining is reduced, enabling the model to learn more richer and robust feature representations. In addition, we incorporate a mixup strategy and feature distillation to further enhance the model's ability to learn meaningful representations. We validate our method using chest CT images obtained under two different imaging conditions, demonstrating superior performance compared to state-of-the-art methods.
Authors: Yuandi Zhao, Qianxi Xia, Yang Sun, Zhijie Wen, Liyan Ma, Shihui Ying
Abstract: In recent years, the remarkable success of deep neural networks (DNNs) in computer vision is largely due to large-scale, high-quality labeled datasets. Training directly on real-world datasets with label noise may result in overfitting. The traditional method is limited to deal with closed set label noise, where noisy training data has true class labels within the known label space. However, there are some real-world datasets containing open set label noise, which means that some samples belong to an unknown class outside the known label space. To address the open set label noise problem, we introduce a method based on Robust Sample Selection and Margin-Guided Module (RSS-MGM). Firstly, unlike the prior clean sample selection approach, which only select a limited number of clean samples, a robust sample selection module combines small loss selection or high-confidence sample selection to obtain more clean samples. Secondly, to efficiently distinguish open set label noise and closed set ones, margin functions are designed to filter open-set data and closed set data. Thirdly, different processing methods are selected for different types of samples in order to fully utilize the data's prior information and optimize the whole model. Furthermore, extensive experimental results with noisy labeled data from benchmark datasets and real-world datasets, such as CIFAR-100N-C, CIFAR80N-O, WebFG-469, and Food101N, indicate that our approach outperforms many state-of-the-art label noise learning methods. Especially, it can more accurately divide open set label noise samples and closed set ones.
Authors: Yuze Wang, Rong Xiao, Haifeng Li, Mariana Belgiu, Chao Tao
Abstract: In remote sensing scene classification, leveraging the transfer methods with well-trained optical models is an efficient way to overcome label scarcity. However, cloud contamination leads to optical information loss and significant impacts on feature distribution, challenging the reliability and stability of transferred target models. Common solutions include cloud removal for optical data or directly using Synthetic aperture radar (SAR) data in the target domain. However, cloud removal requires substantial auxiliary data for support and pre-training, while directly using SAR disregards the unobstructed portions of optical data. This study presents a scene classification transfer method that synergistically combines multi-modality data, which aims to transfer the source domain model trained on cloudfree optical data to the target domain that includes both cloudy optical and SAR data at low cost. Specifically, the framework incorporates two parts: (1) the collaborative transfer strategy, based on knowledge distillation, enables the efficient prior knowledge transfer across heterogeneous data; (2) the information regulation mechanism (IRM) is proposed to address the modality imbalance issue during transfer. It employs auxiliary models to measure the contribution discrepancy of each modality, and automatically balances the information utilization of modalities during the target model learning process at the sample-level. The transfer experiments were conducted on simulated and real cloud datasets, demonstrating the superior performance of the proposed method compared to other solutions in cloud-covered scenarios. We also verified the importance and limitations of IRM, and further discussed and visualized the modality imbalance problem during the model transfer. Codes are available at https://github.com/wangyuze-csu/ESCCS
Authors: Hyungjin Chung, Dohun Lee, Zihui Wu, Byung-Hoon Kim, Katherine L. Bouman, Jong Chul Ye
Abstract: Compressed sensing MRI seeks to accelerate MRI acquisition processes by sampling fewer k-space measurements and then reconstructing the missing data algorithmically. The success of these approaches often relies on strong priors or learned statistical models. While recent diffusion model-based priors have shown great potential, previous methods typically ignore clinically available metadata (e.g. patient demographics, imaging parameters, slice-specific information). In practice, metadata contains meaningful cues about the anatomy and acquisition protocol, suggesting it could further constrain the reconstruction problem. In this work, we propose ContextMRI, a text-conditioned diffusion model for MRI that integrates granular metadata into the reconstruction process. We train a pixel-space diffusion model directly on minimally processed, complex-valued MRI images. During inference, metadata is converted into a structured text prompt and fed to the model via CLIP text embeddings. By conditioning the prior on metadata, we unlock more accurate reconstructions and show consistent gains across multiple datasets, acceleration factors, and undersampling patterns. Our experiments demonstrate that increasing the fidelity of metadata, ranging from slice location and contrast to patient age, sex, and pathology, systematically boosts reconstruction performance. This work highlights the untapped potential of leveraging clinical context for inverse problems and opens a new direction for metadata-driven MRI reconstruction.
Authors: Seungmin Baek, Soyul Lee, Hayeon Jo, Hyesong Choi, Dongbo Min
Abstract: Transfer learning paradigm has driven substantial advancements in various vision tasks. However, as state-of-the-art models continue to grow, classical full fine-tuning often becomes computationally impractical, particularly in multi-task learning (MTL) setup where training complexity increases proportional to the number of tasks. Consequently, recent studies have explored Parameter-Efficient Fine-Tuning (PEFT) for MTL architectures. Despite some progress, these approaches still exhibit limitations in capturing fine-grained, task-specific features that are crucial to MTL. In this paper, we introduce Task-Adaptive Dynamic transFormer, termed TADFormer, a novel PEFT framework that performs task-aware feature adaptation in the fine-grained manner by dynamically considering task-specific input contexts. TADFormer proposes the parameter-efficient prompting for task adaptation and the Dynamic Task Filter (DTF) to capture task information conditioned on input contexts. Experiments on the PASCAL-Context benchmark demonstrate that the proposed method achieves higher accuracy in dense scene understanding tasks, while reducing the number of trainable parameters by up to 8.4 times when compared to full fine-tuning of MTL models. TADFormer also demonstrates superior parameter efficiency and accuracy compared to recent PEFT methods.
Authors: Siran Chen, Yuxiao Luo, Yue Ma, Yu Qiao, Yali Wang
Abstract: With the prevalence of Multimodal Large Language Models(MLLMs), autonomous driving has encountered new opportunities and challenges. In particular, multi-modal video understanding is critical to interactively analyze what will happen in the procedure of autonomous driving. However, videos in such a dynamical scene that often contains complex spatial-temporal movements, which restricts the generalization capacity of the existing MLLMs in this field. To bridge the gap, we propose a novel Hierarchical Mamba Adaptation (H-MBA) framework to fit the complicated motion changes in autonomous driving videos. Specifically, our H-MBA consists of two distinct modules, including Context Mamba (C-Mamba) and Query Mamba (Q-Mamba). First, C-Mamba contains various types of structure state space models, which can effectively capture multi-granularity video context for different temporal resolutions. Second, Q-Mamba flexibly transforms the current frame as the learnable query, and attentively selects multi-granularity video context into query. Consequently, it can adaptively integrate all the video contexts of multi-scale temporal resolutions to enhance video understanding. Via a plug-and-play paradigm in MLLMs, our H-MBA shows the remarkable performance on multi-modal video tasks in autonomous driving, e.g., for risk object detection, it outperforms the previous SOTA method with 5.5% mIoU improvement.
Authors: Hyogon Ryu, NaHyeon Park, Hyunjung Shim
Abstract: Despite the widespread use of text-to-image diffusion models across various tasks, their computational and memory demands limit practical applications. To mitigate this issue, quantization of diffusion models has been explored. It reduces memory usage and computational costs by compressing weights and activations into lower-bit formats. However, existing methods often struggle to preserve both image quality and text-image alignment, particularly in lower-bit($<$ 8bits) quantization. In this paper, we analyze the challenges associated with quantizing text-to-image diffusion models from a distributional perspective. Our analysis reveals that activation outliers play a crucial role in determining image quality. Additionally, we identify distinctive patterns in cross-attention scores, which significantly affects text-image alignment. To address these challenges, we propose Distribution-aware Group Quantization (DGQ), a method that identifies and adaptively handles pixel-wise and channel-wise outliers to preserve image quality. Furthermore, DGQ applies prompt-specific logarithmic quantization scales to maintain text-image alignment. Our method demonstrates remarkable performance on datasets such as MS-COCO and PartiPrompts. We are the first to successfully achieve low-bit quantization of text-to-image diffusion models without requiring additional fine-tuning of weight quantization parameters.
Authors: Miao Rang, Zhenni Bi, Chuanjian Liu, Yehui Tang, Kai Han, Yunhe Wang
Abstract: Multimodal vision language models (VLMs) have made significant progress with the support of continuously increasing model sizes and data volumes. Running VLMs on edge devices has become a challenge for their widespread application. There are several efficient VLM efforts, but they often sacrifice linguistic capabilities to enhance multimodal abilities, or require extensive training. To address this quandary,we introduce the innovative framework of Efficient Vision Language Models with Elastic Visual Experts (Eve). By strategically incorporating adaptable visual expertise at multiple stages of training, Eve strikes a balance between preserving linguistic abilities and augmenting multimodal capabilities. This balanced approach results in a versatile model with only 1.8B parameters that delivers significant improvements in both multimodal and linguistic tasks. Notably, in configurations below 3B parameters, Eve distinctly outperforms in language benchmarks and achieves state-of-the-art results 68.87% in VLM Benchmarks. Additionally, its multimodal accuracy outstrips that of the larger 7B LLaVA-1.5 model.
Authors: Zhi-Lin Huang, Yixuan Liu, Chujun Qin, Zhongdao Wang, Dong Zhou, Dong Li, Emad Barsoum
Abstract: Recent advancements in diffusion models have significantly facilitated text-guided video editing. However, there is a relative scarcity of research on image-guided video editing, a method that empowers users to edit videos by merely indicating a target object in the initial frame and providing an RGB image as reference, without relying on the text prompts. In this paper, we propose a novel Image-guided Video Editing Diffusion model, termed IVEDiff for the image-guided video editing. IVEDiff is built on top of image editing models, and is equipped with learnable motion modules to maintain the temporal consistency of edited video. Inspired by self-supervised learning concepts, we introduce a masked motion modeling fine-tuning strategy that empowers the motion module's capabilities for capturing inter-frame motion dynamics, while preserving the capabilities for intra-frame semantic correlations modeling of the base image editing model. Moreover, an optical-flow-guided motion reference network is proposed to ensure the accurate propagation of information between edited video frames, alleviating the misleading effects of invalid information. We also construct a benchmark to facilitate further research. The comprehensive experiments demonstrate that our method is able to generate temporally smooth edited videos while robustly dealing with various editing objects with high quality.
Authors: Lei Liu, Zhenghao Chen, Zhihao Hu, Dong Xu
Abstract: While most existing neural image compression (NIC) and neural video compression (NVC) methodologies have achieved remarkable success, their optimization is primarily focused on human visual perception. However, with the rapid development of artificial intelligence, many images and videos will be used for various machine vision tasks. Consequently, such existing compression methodologies cannot achieve competitive performance in machine vision. In this work, we introduce an efficient adaptive compression (EAC) method tailored for both human perception and multiple machine vision tasks. Our method involves two key modules: 1), an adaptive compression mechanism, that adaptively selects several subsets from latent features to balance the optimizations for multiple machine vision tasks (e.g., segmentation, and detection) and human vision. 2), a task-specific adapter, that uses the parameter-efficient delta-tuning strategy to stimulate the comprehensive downstream analytical networks for specific machine vision tasks. By using the above two modules, we can optimize the bit-rate costs and improve machine vision performance. In general, our proposed EAC can seamlessly integrate with existing NIC (i.e., Ball\'e2018, and Cheng2020) and NVC (i.e., DVC, and FVC) methods. Extensive evaluation on various benchmark datasets (i.e., VOC2007, ILSVRC2012, VOC2012, COCO, UCF101, and DAVIS) shows that our method enhances performance for multiple machine vision tasks while maintaining the quality of human vision.
Authors: Zeyi Huang, Yuyang Ji, Xiaofang Wang, Nikhil Mehta, Tong Xiao, Donghyun Lee, Sigmund Vanvalkenburgh, Shengxin Zha, Bolin Lai, Licheng Yu, Ning Zhang, Yong Jae Lee, Miao Liu
Abstract: Long-form video understanding with Large Vision Language Models is challenged by the need to analyze temporally dispersed yet spatially concentrated key moments within limited context windows. In this work, we introduce VideoMindPalace, a new framework inspired by the "Mind Palace", which organizes critical video moments into a topologically structured semantic graph. VideoMindPalace organizes key information through (i) hand-object tracking and interaction, (ii) clustered activity zones representing specific areas of recurring activities, and (iii) environment layout mapping, allowing natural language parsing by LLMs to provide grounded insights on spatio-temporal and 3D context. In addition, we propose the Video MindPalace Benchmark (VMB), to assess human-like reasoning, including spatial localization, temporal reasoning, and layout-aware sequential understanding. Evaluated on VMB and established video QA datasets, including EgoSchema, NExT-QA, IntentQA, and the Active Memories Benchmark, VideoMindPalace demonstrates notable gains in spatio-temporal coherence and human-aligned reasoning, advancing long-form video analysis capabilities in VLMs.
Authors: Cl\'ement Fuchs, Maxime Zanella, Christophe De Vleeschouwer
Abstract: Online test-time adaptation (OTTA) of vision-language models (VLMs) has recently garnered increased attention to take advantage of data observed along a stream to improve future predictions. Unfortunately, existing methods rely on dataset-specific hyperparameters, significantly limiting their adaptability to unseen tasks. In response, we propose Online Gaussian Adaptation (OGA), a novel method that models the likelihoods of visual features using Gaussian distributions and incorporates zero-shot priors into an interpretable Maximum A Posteriori (MAP) estimation framework with fixed hyper-parameters across all datasets. We demonstrate that OGA outperforms state-of-the-art methods on most datasets and runs. Additionally, we show that combining OTTA with popular few-shot techniques (a practical yet overlooked setting in prior research) is highly beneficial. Furthermore, our experimental study reveals that common OTTA evaluation protocols, which average performance over at most three runs per dataset, are inadequate due to the substantial variability observed across runs for all OTTA methods. Therefore, we advocate for more rigorous evaluation practices, including increasing the number of runs and considering additional quantitative metrics, such as our proposed Expected Tail Accuracy (ETA), calculated as the average accuracy in the worst 10% of runs. We hope these contributions will encourage more rigorous and diverse evaluation practices in the OTTA community. Code is available at https://github.com/cfuchs2023/OGA .
Authors: Xueqiang Ouyang, Jia Wei, Wenjie Huo, Xiaocong Wang, Rui Li, Jianlong Zhou
Abstract: Temporal embryo images and parental fertility table indicators are both valuable for pregnancy prediction in \textbf{in vitro fertilization embryo transfer} (IVF-ET). However, current machine learning models cannot make full use of the complementary information between the two modalities to improve pregnancy prediction performance. In this paper, we propose a Decoupling Fusion Network called DeFusion to effectively integrate the multi-modal information for IVF-ET pregnancy prediction. Specifically, we propose a decoupling fusion module that decouples the information from the different modalities into related and unrelated information, thereby achieving a more delicate fusion. And we fuse temporal embryo images with a spatial-temporal position encoding, and extract fertility table indicator information with a table transformer. To evaluate the effectiveness of our model, we use a new dataset including 4046 cases collected from Southern Medical University. The experiments show that our model outperforms state-of-the-art methods. Meanwhile, the performance on the eye disease prediction dataset reflects the model's good generalization. Our code and dataset are available at https://github.com/Ou-Young-1999/DFNet.
Authors: Guoxin Zhang, Ziying Song, Lin Liu, Zhonghong Ou
Abstract: Multimodal 3D object detection has garnered considerable interest in autonomous driving. However, multimodal detectors suffer from dimension mismatches that derive from fusing 3D points with 2D pixels coarsely, which leads to sub-optimal fusion performance. In this paper, we propose a multimodal framework FGU3R to tackle the issue mentioned above via unified 3D representation and fine-grained fusion, which consists of two important components. First, we propose an efficient feature extractor for raw and pseudo points, termed Pseudo-Raw Convolution (PRConv), which modulates multimodal features synchronously and aggregates the features from different types of points on key points based on multimodal interaction. Second, a Cross-Attention Adaptive Fusion (CAAF) is designed to fuse homogeneous 3D RoI (Region of Interest) features adaptively via a cross-attention variant in a fine-grained manner. Together they make fine-grained fusion on unified 3D representation. The experiments conducted on the KITTI and nuScenes show the effectiveness of our proposed method.
Authors: Kunal Kathare, Ankit Dhiman, K Vikas Gowda, Siddharth Aravindan, Shubham Monga, Basavaraja Shanthappa Vandrotti, Lokesh R Boregowda
Abstract: Transformer based methods have enabled users to create, modify, and comprehend text and image data. Recently proposed Large Reconstruction Models (LRMs) further extend this by providing the ability to generate high-quality 3D models with the help of a single object image. These models, however, lack the ability to manipulate or edit the finer details, such as adding standard design patterns or changing the color and reflectance of the generated objects, thus lacking fine-grained control that may be very helpful in domains such as augmented reality, animation and gaming. Naively training LRMs for this purpose would require generating precisely edited images and 3D object pairs, which is computationally expensive. In this paper, we propose Instructive3D, a novel LRM based model that integrates generation and fine-grained editing, through user text prompts, of 3D objects into a single model. We accomplish this by adding an adapter that performs a diffusion process conditioned on a text prompt specifying edits in the triplane latent space representation of 3D object models. Our method does not require the generation of edited 3D objects. Additionally, Instructive3D allows us to perform geometrically consistent modifications, as the edits done through user-defined text prompts are applied to the triplane latent representation thus enhancing the versatility and precision of 3D objects generated. We compare the objects generated by Instructive3D and a baseline that first generates the 3D object meshes using a standard LRM model and then edits these 3D objects using text prompts when images are provided from the Objaverse LVIS dataset. We find that Instructive3D produces qualitatively superior 3D objects with the properties specified by the edit prompts.
Authors: Xinghe Fu, Zhiyuan Yan, Taiping Yao, Shen Chen, Xi Li
Abstract: The generalization problem is broadly recognized as a critical challenge in detecting deepfakes. Most previous work believes that the generalization gap is caused by the differences among various forgery methods. However, our investigation reveals that the generalization issue can still occur when forgery-irrelevant factors shift. In this work, we identify two biases that detectors may also be prone to overfitting: position bias and content bias, as depicted in Fig. 1. For the position bias, we observe that detectors are prone to lazily depending on the specific positions within an image (e.g., central regions even no forgery). As for content bias, we argue that detectors may potentially and mistakenly utilize forgery-unrelated information for detection (e.g., background, and hair). To intervene these biases, we propose two branches for shuffling and mixing with tokens in the latent space of transformers. For the shuffling branch, we rearrange the tokens and corresponding position embedding for each image while maintaining the local correlation. For the mixing branch, we randomly select and mix the tokens in the latent space between two images with the same label within the mini-batch to recombine the content information. During the learning process, we align the outputs of detectors from different branches in both feature space and logit space. Contrastive losses for features and divergence losses for logits are applied to obtain unbiased feature representation and classifiers. We demonstrate and verify the effectiveness of our method through extensive experiments on widely used evaluation datasets.
Authors: Lin Yuan, Kai Liang, Xiong Li, Tao Wu, Nannan Wang, Xinbo Gao
Abstract: Face anonymization aims to conceal the visual identity of a face to safeguard the individual's privacy. Traditional methods like blurring and pixelation can largely remove identifying features, but these techniques significantly degrade image quality and are vulnerable to deep reconstruction attacks. Generative models have emerged as a promising solution for anonymizing faces while preserving a natural appearance.However, many still face limitations in visual quality and often overlook the potential to recover the original face from the anonymized version, which can be valuable in specific contexts such as image forensics. This paper proposes a novel framework named iFADIT, an acronym for Invertible Face Anonymization via Disentangled Identity Transform.The framework features a disentanglement architecture coupled with a secure flow-based model: the former decouples identity information from non-identifying attributes, while the latter transforms the decoupled identity into an anonymized version in an invertible manner controlled by a secret key. The anonymized face can then be reconstructed based on a pre-trained StyleGAN that ensures high image quality and realistic facial details. Recovery of the original face (aka de-anonymization) is possible upon the availability of the matching secret, by inverting the anonymization process based on the same set of model parameters. Furthermore, a dedicated secret-key mechanism along with a dual-phase training strategy is devised to ensure the desired properties of face anonymization. Qualitative and quantitative experiments demonstrate the superiority of the proposed approach in anonymity, reversibility, security, diversity, and interpretability over competing methods.
Authors: Xin Zhang, Xue Yang, Yuxuan Li, Jian Yang, Ming-Ming Cheng, Xiang Li
Abstract: Rotated object detection has made significant progress in the optical remote sensing. However, advancements in the Synthetic Aperture Radar (SAR) field are laggard behind, primarily due to the absence of a large-scale dataset. Annotating such a dataset is inefficient and costly. A promising solution is to employ a weakly supervised model (e.g., trained with available horizontal boxes only) to generate pseudo-rotated boxes for reference before manual calibration. Unfortunately, the existing weakly supervised models exhibit limited accuracy in predicting the object's angle. Previous works attempt to enhance angle prediction by using angle resolvers that decouple angles into cosine and sine encodings. In this work, we first reevaluate these resolvers from a unified perspective of dimension mapping and expose that they share the same shortcomings: these methods overlook the unit cycle constraint inherent in these encodings, easily leading to prediction biases. To address this issue, we propose the Unit Cycle Resolver, which incorporates a unit circle constraint loss to improve angle prediction accuracy. Our approach can effectively improve the performance of existing state-of-the-art weakly supervised methods and even surpasses fully supervised models on existing optical benchmarks (i.e., DOTA-v1.0 dataset). With the aid of UCR, we further annotate and introduce RSAR, the largest multi-class rotated SAR object detection dataset to date. Extensive experiments on both RSAR and optical datasets demonstrate that our UCR enhances angle prediction accuracy. Our dataset and code can be found at: https://github.com/zhasion/RSAR.
Authors: Dana A Abdullah, Dana Rasul Hamad, Hakem Beitollahi, Ismail Y Maolood, Abdulhady Abas Abdullah, Aso Khaleel Ameen
Abstract: Recognizing the same faces with and without masks is important for ensuring consistent identification in security, access control, and public safety. This capability is crucial in scenarios like law enforcement, healthcare, and surveillance, where accurate recognition must be maintained despite facial occlusion. This research focuses on the challenge of recognizing the same faces with and without masks by employing cosine similarity as the primary technique. With the increased use of masks, traditional facial recognition systems face significant accuracy issues, making it crucial to develop methods that can reliably identify individuals in masked conditions. For that reason, this study proposed Masked-Unmasked Face Matching Model (MUFM). This model employs transfer learning using the Visual Geometry Group (VGG16) model to extract significant facial features, which are subsequently classified utilizing the K-Nearest Neighbors (K-NN) algorithm. The cosine similarity metric is employed to compare masked and unmasked faces of the same individuals. This approach represents a novel contribution, as the task of recognizing the same individual with and without a mask using cosine similarity has not been previously addressed. By integrating these advanced methodologies, the research demonstrates effective identification of individuals despite the presence of masks, addressing a significant limitation in traditional systems. Using data is another essential part of this work, by collecting and preparing an image dataset from three different sources especially some of those data are real provided a comprehensive power of this research. The image dataset used were already collected in three different datasets of masked and unmasked for the same faces.
Authors: Christof A. Bertram, Viktoria Weiss, Taryn A. Donovan, Sweta Banerjee, Thomas Conrad, Jonas Ammeling, Robert Klopfleisch, Christopher Kaltenecker, Marc Aubreville
Abstract: Assessment of the density of mitotic figures (MFs) in histologic tumor sections is an important prognostic marker for many tumor types, including breast cancer. Recently, it has been reported in multiple works that the quantity of MFs with an atypical morphology (atypical MFs, AMFs) might be an independent prognostic criterion for breast cancer. AMFs are an indicator of mutations in the genes regulating the cell cycle and can lead to aberrant chromosome constitution (aneuploidy) of the tumor cells. To facilitate further research on this topic using pattern recognition, we present the first ever publicly available dataset of atypical and normal MFs (AMi-Br). For this, we utilized two of the most popular MF datasets (MIDOG 2021 and TUPAC) and subclassified all MFs using a three expert majority vote. Our final dataset consists of 3,720 MFs, split into 832 AMFs (22.4%) and 2,888 normal MFs (77.6%) across all 223 tumor cases in the combined set. We provide baseline classification experiments to investigate the consistency of the dataset, using a Monte Carlo cross-validation and different strategies to combat class imbalance. We found an averaged balanced accuracy of up to 0.806 when using a patch-level data set split, and up to 0.713 when using a patient-level split.
Authors: Kang Chen, Yajing Zheng, Tiejun Huang, Zhaofei Yu
Abstract: Spike cameras, as innovative neuromorphic devices, generate continuous spike streams to capture high-speed scenes with lower bandwidth and higher dynamic range than traditional RGB cameras. However, reconstructing high-quality images from the spike input under low-light conditions remains challenging. Conventional learning-based methods often rely on the synthetic dataset as the supervision for training. Still, these approaches falter when dealing with noisy spikes fired under the low-light environment, leading to further performance degradation in the real-world dataset. This phenomenon is primarily due to inadequate noise modelling and the domain gap between synthetic and real datasets, resulting in recovered images with unclear textures, excessive noise, and diminished brightness. To address these challenges, we introduce a novel spike-to-image reconstruction framework SpikeCLIP that goes beyond traditional training paradigms. Leveraging the CLIP model's powerful capability to align text and images, we incorporate the textual description of the captured scene and unpaired high-quality datasets as the supervision. Our experiments on real-world low-light datasets U-CALTECH and U-CIFAR demonstrate that SpikeCLIP significantly enhances texture details and the luminance balance of recovered images. Furthermore, the reconstructed images are well-aligned with the broader visual features needed for downstream tasks, ensuring more robust and versatile performance in challenging environments.
Authors: Zhi Jin, Yuwei Qiu, Kaihao Zhang, Hongdong Li, Wenhan Luo
Abstract: Recently, Transformer networks have demonstrated outstanding performance in the field of image restoration due to the global receptive field and adaptability to input. However, the quadratic computational complexity of Softmax-attention poses a significant limitation on its extensive application in image restoration tasks, particularly for high-resolution images. To tackle this challenge, we propose a novel variant of the Transformer. This variant leverages the Taylor expansion to approximate the Softmax-attention and utilizes the concept of norm-preserving mapping to approximate the remainder of the first-order Taylor expansion, resulting in a linear computational complexity. Moreover, we introduce a multi-branch architecture featuring multi-scale patch embedding into the proposed Transformer, which has four distinct advantages: 1) various sizes of the receptive field; 2) multi-level semantic information; 3) flexible shapes of the receptive field; 4) accelerated training and inference speed. Hence, the proposed model, named the second version of Taylor formula expansion-based Transformer (for short MB-TaylorFormer V2) has the capability to concurrently process coarse-to-fine features, capture long-distance pixel interactions with limited computational cost, and improve the approximation of the Taylor expansion remainder. Experimental results across diverse image restoration benchmarks demonstrate that MB-TaylorFormer V2 achieves state-of-the-art performance in multiple image restoration tasks, such as image dehazing, deraining, desnowing, motion deblurring, and denoising, with very little computational overhead. The source code is available at https://github.com/FVL2020/MB-TaylorFormerV2.
Authors: Uri Berger, Omri Abend, Lea Frermann, Gabriel Stanovsky
Abstract: Incorporating automatically predicted human feedback into the process of training generative models has attracted substantial recent interest, while feedback at inference time has received less attention. The typical feedback at training time, i.e., preferences of choice given two samples, does not naturally transfer to the inference phase. We introduce a novel type of feedback -- caption reformulations -- and train models to mimic reformulation feedback based on human annotations. Our method does not require training the image captioning model itself, thereby demanding substantially less computational effort. We experiment with two types of reformulation feedback: first, we collect a dataset of human reformulations that correct errors in the generated captions. We find that incorporating reformulation models trained on this data into the inference phase of existing image captioning models results in improved captions, especially when the original captions are of low quality. We apply our method to non-English image captioning, a domain where robust models are less prevalent, and gain substantial improvement. Second, we apply reformulations to style transfer. Quantitative evaluations reveal state-of-the-art performance on German image captioning and English style transfer, while human validation with a detailed comparative framework exposes the specific axes of improvement.
Authors: Victor Nascimento Ribeiro, Nina S. T. Hirata
Abstract: Video-based vehicle detection and counting play a critical role in managing transport infrastructure. Traditional image-based counting methods usually involve two main steps: initial detection and subsequent tracking, which are applied to all video frames, leading to a significant increase in computational complexity. To address this issue, this work presents an alternative and more efficient method for vehicle detection and counting. The proposed approach eliminates the need for a tracking step and focuses solely on detecting vehicles in key video frames, thereby increasing its efficiency. To achieve this, we developed a system that combines YOLO, for vehicle detection, with Visual Rhythm, a way to create time-spatial images that allows us to focus on frames that contain useful information. Additionally, this method can be used for counting in any application involving unidirectional moving targets to be detected and identified. Experimental analysis using real videos shows that the proposed method achieves mean counting accuracy around 99.15% over a set of videos, with a processing speed three times faster than tracking based approaches.
Authors: Lanlan Feng, Ce Zhu, Yipeng Liu, Saiprasad Ravishankar, Longxiu Huang
Abstract: Robust tensor principal component analysis (RTPCA) aims to separate the low-rank and sparse components from multi-dimensional data, making it an essential technique in the signal processing and computer vision fields. Recently emerging tensor singular value decomposition (t-SVD) has gained considerable attention for its ability to better capture the low-rank structure of tensors compared to traditional matrix SVD. However, existing methods often rely on the computationally expensive tensor nuclear norm (TNN), which limits their scalability for real-world tensors. To address this issue, we explore an efficient scaled gradient descent (SGD) approach within the t-SVD framework for the first time, and propose the RTPCA-SGD method. Theoretically, we rigorously establish the recovery guarantees of RTPCA-SGD under mild assumptions, demonstrating that with appropriate parameter selection, it achieves linear convergence to the true low-rank tensor at a constant rate, independent of the condition number. To enhance its practical applicability, we further propose a learnable self-supervised deep unfolding model, which enables effective parameter learning. Numerical experiments on both synthetic and real-world datasets demonstrate the superior performance of the proposed methods while maintaining competitive computational efficiency, especially consuming less time than RTPCA-TNN.
Authors: Giorgio Giannone, Ruoteng Li, Qianli Feng, Evgeny Perevodchikov, Rui Chen, Aleix Martinez
Abstract: Vision-language models (VLMs) have demonstrated remarkable potential in integrating visual and linguistic information, but their performance is often constrained by the need for extensive, high-quality image-text training data. Curation of these image-text pairs is both time-consuming and computationally expensive. To address this challenge, we introduce SVP (Supervision-free Visual Projection), a novel framework that enhances vision-language alignment without relying on curated data or preference annotation. SVP leverages self-captioning and a pre-trained grounding model as a feedback mechanism to elicit latent information in VLMs. We evaluate our approach across six key areas: captioning, referring, visual question answering, multitasking, hallucination control, and object recall. Results demonstrate significant improvements, including a 14% average improvement in captioning tasks, up to 12% increase in object recall, and substantial reduction in hallucination rates. Notably, a small VLM using SVP achieves hallucination reductions comparable to a model five times larger, while a VLM with initially poor referring capabilities more than doubles its performance, approaching parity with a model twice its size.
Authors: Kangsheng Yin, Quan Liu, Xuelin Shen, Yulin He, Wenhan Yang, Shiqi Wang
Abstract: The image compression model has long struggled with adaptability and generalization, as the decoded bitstream typically serves only human or machine needs and fails to preserve information for unseen visual tasks. Therefore, this paper innovatively introduces supervision obtained from multimodal pre-training models and incorporates adaptive multi-objective optimization tailored to support both human visual perception and machine vision simultaneously with a single bitstream, denoted as Unified and Generalized Image Coding for Machine (UG-ICM). Specifically, to get rid of the reliance between compression models with downstream task supervision, we introduce Contrastive Language-Image Pre-training (CLIP) models into the training constraint for improved generalization. Global-to-instance-wise CLIP supervision is applied to help obtain hierarchical semantics that make models more generalizable for the tasks relying on the information of different granularity. Furthermore, for supporting both human and machine visions with only a unifying bitstream, we incorporate a conditional decoding strategy that takes as conditions human or machine preferences, enabling the bitstream to be decoded into different versions for corresponding preferences. As such, our proposed UG-ICM is fully trained in a self-supervised manner, i.e., without awareness of any specific downstream models and tasks. The extensive experiments have shown that the proposed UG-ICM is capable of achieving remarkable improvements in various unseen machine analytics tasks, while simultaneously providing perceptually satisfying images.
Authors: Miaoyang He, Shuyong Gao, Tsui Qin Mok, Weifeng Ge, Wengqiang Zhang
Abstract: Salient Object Detection (SOD) aims to identify and segment prominent regions within a scene. Traditional models rely on manually annotated pseudo labels with precise pixel-level accuracy, which is time-consuming. We developed a low-cost, high-precision annotation method by leveraging large foundation models to address the challenges. Specifically, we use a weakly supervised approach to guide large models in generating pseudo-labels through textual prompts. Since large models do not effectively focus on the salient regions of images, we manually annotate a subset of text to fine-tune the model. Based on this approach, which enables precise and rapid generation of pseudo-labels, we introduce a new dataset, BDS-TR. Compared to the previous DUTS-TR dataset, BDS-TR is more prominent in scale and encompasses a wider variety of categories and scenes. This expansion will enhance our model's applicability across a broader range of scenarios and provide a more comprehensive foundational dataset for future SOD research. Additionally, we present an edge decoder based on dynamic upsampling, which focuses on object edges while gradually recovering image feature resolution. Comprehensive experiments on five benchmark datasets demonstrate that our method significantly outperforms state-of-the-art approaches and also surpasses several existing fully-supervised SOD methods. The code and results will be made available.
Authors: Runzhen Liu, Qinjie Lin, Yunfei Liu, Lijian Lin, Ye Zhu, Yu Li, Chuhua Xian, Fa-Ting Hong
Abstract: Video dubbing aims to synthesize realistic, lip-synced videos from a reference video and a driving audio signal. Although existing methods can accurately generate mouth shapes driven by audio, they often fail to preserve identity-specific features, largely because they do not effectively capture the nuanced interplay between audio cues and the visual attributes of reference identity . As a result, the generated outputs frequently lack fidelity in reproducing the unique textural and structural details of the reference identity. To address these limitations, we propose IPTalker, a novel and robust framework for video dubbing that achieves seamless alignment between driving audio and reference identity while ensuring both lip-sync accuracy and high-fidelity identity preservation. At the core of IPTalker is a transformer-based alignment mechanism designed to dynamically capture and model the correspondence between audio features and reference images, thereby enabling precise, identity-aware audio-visual integration. Building on this alignment, a motion warping strategy further refines the results by spatially deforming reference images to match the target audio-driven configuration. A dedicated refinement process then mitigates occlusion artifacts and enhances the preservation of fine-grained textures, such as mouth details and skin features. Extensive qualitative and quantitative evaluations demonstrate that IPTalker consistently outperforms existing approaches in terms of realism, lip synchronization, and identity retention, establishing a new state of the art for high-quality, identity-consistent video dubbing.
Authors: Yangfan He, Sida Li, Kun Li, Jianhui Wang, Binxu Li, Tianyu Shi, Jun Yin, Miao Zhang, Xueqian Wang
Abstract: Recent advancements in text-to-image (T2I) generation using diffusion models have enabled cost-effective video-editing applications by leveraging pre-trained models, eliminating the need for resource-intensive training. However, the frame-independence of T2I generation often results in poor temporal consistency. Existing methods address this issue through temporal layer fine-tuning or inference-based temporal propagation, but these approaches suffer from high training costs or limited temporal coherence. To address these challenges, we propose a General and Efficient Adapter (GE-Adapter) that integrates temporal-spatial and semantic consistency with Baliteral DDIM inversion. This framework introduces three key components: (1) Frame-based Temporal Consistency Blocks (FTC Blocks) to capture frame-specific features and enforce smooth inter-frame transitions via temporally-aware loss functions; (2) Channel-dependent Spatial Consistency Blocks (SCD Blocks) employing bilateral filters to enhance spatial coherence by reducing noise and artifacts; and (3) Token-based Semantic Consistency Module (TSC Module) to maintain semantic alignment using shared prompt tokens and frame-specific tokens. Our method significantly improves perceptual quality, text-image alignment, and temporal coherence, as demonstrated on the MSR-VTT dataset. Additionally, it achieves enhanced fidelity and frame-to-frame coherence, offering a practical solution for T2V editing.
Authors: Han Huang, Yulun Wu, Chao Deng, Ge Gao, Ming Gu, Yu-Shen Liu
Abstract: Recently, Gaussian Splatting has sparked a new trend in the field of computer vision. Apart from novel view synthesis, it has also been extended to the area of multi-view reconstruction. The latest methods facilitate complete, detailed surface reconstruction while ensuring fast training speed. However, these methods still require dense input views, and their output quality significantly degrades with sparse views. We observed that the Gaussian primitives tend to overfit the few training views, leading to noisy floaters and incomplete reconstruction surfaces. In this paper, we present an innovative sparse-view reconstruction framework that leverages intra-view depth and multi-view feature consistency to achieve remarkably accurate surface reconstruction. Specifically, we utilize monocular depth ranking information to supervise the consistency of depth distribution within patches and employ a smoothness loss to enhance the continuity of the distribution. To achieve finer surface reconstruction, we optimize the absolute position of depth through multi-view projection features. Extensive experiments on DTU and BlendedMVS demonstrate that our method outperforms state-of-the-art methods with a speedup of 60x to 200x, achieving swift and fine-grained mesh reconstruction without the need for costly pre-training.
Authors: Weitian Zhang, Sijing Wu, Manwen Liao, Yichao Yan
Abstract: Clothed avatar generation has wide applications in virtual and augmented reality, filmmaking, and more. Previous methods have achieved success in generating diverse digital avatars, however, generating avatars with disentangled components (\eg, body, hair, and clothes) has long been a challenge. In this paper, we propose LayerAvatar, the first feed-forward diffusion-based method for generating component-disentangled clothed avatars. To achieve this, we first propose a layered UV feature plane representation, where components are distributed in different layers of the Gaussian-based UV feature plane with corresponding semantic labels. This representation supports high-resolution and real-time rendering, as well as expressive animation including controllable gestures and facial expressions. Based on the well-designed representation, we train a single-stage diffusion model and introduce constrain terms to address the severe occlusion problem of the innermost human body layer. Extensive experiments demonstrate the impressive performances of our method in generating disentangled clothed avatars, and we further explore its applications in component transfer. The project page is available at: https://olivia23333.github.io/LayerAvatar/
Authors: Zhiqiang Gao, Jiaqi Wang, Hangchi Shen, Zhihao Dou, Xiangbo Zhang, Kaizhu Huang
Abstract: Hyperspectral image (HSI) classification is a crucial technique for remote sensing to build large-scale earth monitoring systems. HSI contains much more information than traditional visual images for identifying the categories of land covers. One recent feasible solution for HSI is to leverage CapsNets for capturing spectral-spatial information. However, these methods require high computational requirements due to the full connection architecture between stacked capsule layers. To solve this problem, a DWT-CapsNet is proposed to identify partial but important connections in CapsNet for a effective and efficient HSI classification. Specifically, we integrate a tailored attention mechanism into a Discrete Wavelet Transform (DWT)-based downsampling layer, alleviating the information loss problem of conventional downsampling operation in feature extractors. Moreover, we propose a novel multi-scale routing algorithm that prunes a large proportion of connections in CapsNet. A capsule pyramid fusion mechanism is designed to aggregate the spectral-spatial relationships in multiple levels of granularity, and then a self-attention mechanism is further conducted in a partially and locally connected architecture to emphasize the meaningful relationships. As shown in the experimental results, our method achieves state-of-the-art accuracy while keeping lower computational demand regarding running time, flops, and the number of parameters, rendering it an appealing choice for practical implementation in HSI classification.
Authors: Nannan Li, Kevin J. Shih, Bryan A. Plummer
Abstract: Given an isolated garment image in a canonical product view and a separate image of a person, the virtual try-on task aims to generate a new image of the person wearing the target garment. Prior virtual try-on works face two major challenges in achieving this goal: a) the paired (human, garment) training data has limited availability; b) generating textures on the human that perfectly match that of the prompted garment is difficult, often resulting in distorted text and faded textures. Our work explores ways to tackle these issues through both synthetic data as well as model refinement. We introduce a garment extraction model that generates (human, synthetic garment) pairs from a single image of a clothed individual. The synthetic pairs can then be used to augment the training of virtual try-on. We also propose an Error-Aware Refinement-based Schr\"odinger Bridge (EARSB) that surgically targets localized generation errors for correcting the output of a base virtual try-on model. To identify likely errors, we propose a weakly-supervised error classifier that localizes regions for refinement, subsequently augmenting the Schr\"odinger Bridge's noise schedule with its confidence heatmap. Experiments on VITON-HD and DressCode-Upper demonstrate that our synthetic data augmentation enhances the performance of prior work, while EARSB improves the overall image quality. In user studies, our model is preferred by the users in an average of 59% of cases.
Authors: Yikang Zhou, Tao Zhang, Shilin Xu, Shihao Chen, Qianyu Zhou, Yunhai Tong, Shunping Ji, Jiangning Zhang, Xiangtai Li, Lu Qi
Abstract: Recent advancements in multimodal models have shown a strong ability in visual perception, reasoning abilities, and vision-language understanding. However, studies on visual matching ability are missing, where finding the visual correspondence of objects is essential in vision research. Our research reveals that the matching capabilities in recent multimodal LLMs (MLLMs) still exhibit systematic shortcomings, even with current strong MLLMs models, GPT-4o. In particular, we construct a Multimodal Visual Matching (MMVM) benchmark to fairly benchmark over 30 different MLLMs. The MMVM benchmark is built from 15 open-source datasets and Internet videos with manual annotation. We categorize the data samples of MMVM benchmark into eight aspects based on the required cues and capabilities to more comprehensively evaluate and analyze current MLLMs. In addition, we have designed an automatic annotation pipeline to generate the MMVM SFT dataset, including 220K visual matching data with reasoning annotation. Finally, we present CoLVA, a novel contrastive MLLM with two novel technical designs: fine-grained vision expert with object-level contrastive learning and instruction augmentation strategy. CoLVA achieves 51.06\% overall accuracy (OA) on the MMVM benchmark, surpassing GPT-4o and baseline by 8.41\% and 23.58\% OA, respectively. The results show the effectiveness of our MMVM SFT dataset and our novel technical designs. Code, benchmark, dataset, and models are available at https://github.com/zhouyiks/CoLVA.
Authors: Charles Corbi\`ere, Simon Roburin, Syrielle Montariol, Antoine Bosselut, Alexandre Alahi
Abstract: Large vision-language models (LVLMs) augment language models with visual understanding, enabling multimodal reasoning. However, due to the modality gap between textual and visual data, they often face significant challenges, such as over-reliance on text priors, hallucinations, and limited capacity for complex visual reasoning. Existing benchmarks to evaluate visual reasoning in LVLMs often rely on schematic or synthetic images and on imprecise machine-generated explanations. To bridge the modality gap, we present DrivingVQA, a new benchmark derived from driving theory tests to evaluate visual chain-of-thought reasoning in complex real-world scenarios. It offers 3,931 expert-crafted multiple-choice problems and interleaved explanations grounded with entities relevant to the reasoning process. We leverage this dataset to perform an extensive study of LVLMs' ability to reason about complex visual scenarios. Our experiments reveal that open-source and proprietary LVLMs struggle with visual chain-of-thought reasoning under zero-shot settings. We investigate training strategies that leverage relevant entities to improve visual reasoning. Notably, we observe a performance boost of up to 7\% when reasoning over image tokens of cropped regions tied to these entities.
Authors: Zixuan Huang, Mark Boss, Aaryaman Vasishta, James M. Rehg, Varun Jampani
Abstract: We study the problem of single-image 3D object reconstruction. Recent works have diverged into two directions: regression-based modeling and generative modeling. Regression methods efficiently infer visible surfaces, but struggle with occluded regions. Generative methods handle uncertain regions better by modeling distributions, but are computationally expensive and the generation is often misaligned with visible surfaces. In this paper, we present SPAR3D, a novel two-stage approach aiming to take the best of both directions. The first stage of SPAR3D generates sparse 3D point clouds using a lightweight point diffusion model, which has a fast sampling speed. The second stage uses both the sampled point cloud and the input image to create highly detailed meshes. Our two-stage design enables probabilistic modeling of the ill-posed single-image 3D task while maintaining high computational efficiency and great output fidelity. Using point clouds as an intermediate representation further allows for interactive user edits. Evaluated on diverse datasets, SPAR3D demonstrates superior performance over previous state-of-the-art methods, at an inference speed of 0.7 seconds. Project page with code and model: https://spar3d.github.io
URLs: https://spar3d.github.io
Authors: Ulindu De Silva, Didula Samaraweera, Sasini Wanigathunga, Kavindu Kariyawasam, Kanchana Ranasinghe, Muzammal Naseer, Ranga Rodrigo
Abstract: We present Seg-TTO, a novel framework for zero-shot, open-vocabulary semantic segmentation (OVSS), designed to excel in specialized domain tasks. While current open vocabulary approaches show impressive performance on standard segmentation benchmarks under zero-shot settings, they fall short of supervised counterparts on highly domain-specific datasets. We focus on segmentation-specific test-time optimization to address this gap. Segmentation requires an understanding of multiple concepts within a single image while retaining the locality and spatial structure of representations. We propose a novel self-supervised objective adhering to these requirements and use it to align the model parameters with input images at test time. In the textual modality, we learn multiple embeddings for each category to capture diverse concepts within an image, while in the visual modality, we calculate pixel-level losses followed by embedding aggregation operations specific to preserving spatial structure. Our resulting framework termed Seg-TTO is a plug-in-play module. We integrate Seg-TTO with three state-of-the-art OVSS approaches and evaluate across 22 challenging OVSS tasks covering a range of specialized domains. Our Seg-TTO demonstrates clear performance improvements across these establishing new state-of-the-art. Code: https://github.com/UlinduP/SegTTO.
Authors: Yuzhou Huang, Ziyang Yuan, Quande Liu, Qiulin Wang, Xintao Wang, Ruimao Zhang, Pengfei Wan, Di Zhang, Kun Gai
Abstract: Text-to-video generation has made remarkable advancements through diffusion models. However, Multi-Concept Video Customization (MCVC) remains a significant challenge. We identify two key challenges in this task: 1) the identity decoupling problem, where directly adopting existing customization methods inevitably mix attributes when handling multiple concepts simultaneously, and 2) the scarcity of high-quality video-entity pairs, which is crucial for training such a model that represents and decouples various concepts well. To address these challenges, we introduce ConceptMaster, an innovative framework that effectively tackles the critical issues of identity decoupling while maintaining concept fidelity in customized videos. Specifically, we introduce a novel strategy of learning decoupled multi-concept embeddings that are injected into the diffusion models in a standalone manner, which effectively guarantees the quality of customized videos with multiple identities, even for highly similar visual concepts. To further overcome the scarcity of high-quality MCVC data, we carefully establish a data construction pipeline, which enables systematic collection of precise multi-concept video-entity data across diverse concepts. A comprehensive benchmark is designed to validate the effectiveness of our model from three critical dimensions: concept fidelity, identity decoupling ability, and video generation quality across six different concept composition scenarios. Extensive experiments demonstrate that our ConceptMaster significantly outperforms previous approaches for this task, paving the way for generating personalized and semantically accurate videos across multiple concepts.
Authors: Jiteng Mu, Nuno Vasconcelos, Xiaolong Wang
Abstract: Recent progress in controllable image generation and editing is largely driven by diffusion-based methods. Although diffusion models perform exceptionally well in specific tasks with tailored designs, establishing a unified model is still challenging. In contrast, autoregressive models inherently feature a unified tokenized representation, which simplifies the creation of a single foundational model for various tasks. In this work, we propose EditAR, a single unified autoregressive framework for a variety of conditional image generation tasks, e.g., image editing, depth-to-image, edge-to-image, segmentation-to-image. The model takes both images and instructions as inputs, and predicts the edited images tokens in a vanilla next-token paradigm. To enhance the text-to-image alignment, we further propose to distill the knowledge from foundation models into the autoregressive modeling process. We evaluate its effectiveness across diverse tasks on established benchmarks, showing competitive performance to various state-of-the-art task-specific methods. Project page: https://jitengmu.github.io/EditAR/
Authors: Duy M. H. Nguyen, Hasan Md Tusfiqur Alam, Tai Nguyen, Devansh Srivastav, Hans-Juergen Profitlich, Ngan Le, Daniel Sonntag
Abstract: The emergence of artificial intelligence (AI), particularly deep learning (DL), has marked a new era in the realm of ophthalmology, offering transformative potential for the diagnosis and treatment of posterior segment eye diseases. This review explores the cutting-edge applications of DL across a range of ocular conditions, including diabetic retinopathy, glaucoma, age-related macular degeneration, and retinal vessel segmentation. We provide a comprehensive overview of foundational ML techniques and advanced DL architectures, such as CNNs, attention mechanisms, and transformer-based models, highlighting the evolving role of AI in enhancing diagnostic accuracy, optimizing treatment strategies, and improving overall patient care. Additionally, we present key challenges in integrating AI solutions into clinical practice, including ensuring data diversity, improving algorithm transparency, and effectively leveraging multimodal data. This review emphasizes AI's potential to improve disease diagnosis and enhance patient care while stressing the importance of collaborative efforts to overcome these barriers and fully harness AI's impact in advancing eye care.
Authors: Aanish Paruchuri, Carl Thrasher, A. J. Hart, Robert Macfarlane, Arthi Jayaraman
Abstract: Nanoparticle superlattices consisting of ordered arrangements of nanoparticles exhibit unique optical, magnetic, and electronic properties arising from nanoparticle characteristics as well as their collective behaviors. Understanding how processing conditions influence the nanoscale arrangement and microstructure is critical for engineering materials with desired macroscopic properties. Microstructural features such as grain boundaries, lattice defects, and pores significantly affect these properties but are challenging to quantify using traditional manual analyses as they are labor-intensive and prone to errors. In this work, we present a machine learning workflow for automating grain segmentation in scanning electron microscopy (SEM) images of nanoparticle superlattices. This workflow integrates signal processing techniques, such as Radon transforms, with unsupervised learning methods like agglomerative hierarchical clustering to identify and segment grains without requiring manually annotated data. In the workflow we transform the raw pixel data into explainable numerical representation of superlattice orientations for clustering. Benchmarking results demonstrate the workflow's robustness against noisy images and edge cases, with a processing speed of four images per minute on standard computational hardware. This efficiency makes the workflow scalable to large datasets and makes it a valuable tool for integrating data-driven models into decision-making processes for material design and analysis. For example, one can use this workflow to quantify grain size distributions at varying processing conditions like temperature and pressure and using that knowledge adjust processing conditions to achieve desired superlattice orientations and grain sizes.
Authors: Raktim Kumar Mondol, Ewan K. A. Millar, Peter H. Graham, Lois Browne, Arcot Sowmya, Erik Meijering
Abstract: Explainable AI (XAI) in medical histopathology is essential for enhancing the interpretability and clinical trustworthiness of deep learning models in cancer diagnosis. However, the black-box nature of these models often limits their clinical adoption. We introduce GRAPHITE (Graph-based Interpretable Tissue Examination), a post-hoc explainable framework designed for breast cancer tissue microarray (TMA) analysis. GRAPHITE employs a multiscale approach, extracting patches at various magnification levels, constructing an hierarchical graph, and utilising graph attention networks (GAT) with scalewise attention (SAN) to capture scale-dependent features. We trained the model on 140 tumour TMA cores and four benign whole slide images from which 140 benign samples were created, and tested it on 53 pathologist-annotated TMA samples. GRAPHITE outperformed traditional XAI methods, achieving a mean average precision (mAP) of 0.56, an area under the receiver operating characteristic curve (AUROC) of 0.94, and a threshold robustness (ThR) of 0.70, indicating that the model maintains high performance across a wide range of thresholds. In clinical utility, GRAPHITE achieved the highest area under the decision curve (AUDC) of 4.17e+5, indicating reliable decision support across thresholds. These results highlight GRAPHITE's potential as a clinically valuable tool in computational pathology, providing interpretable visualisations that align with the pathologists' diagnostic reasoning and support precision medicine.
Authors: Senwei Xie, Hongyu Wang, Zhanqi Xiao, Ruiping Wang, Xilin Chen
Abstract: Zero-shot generalization across various robots, tasks and environments remains a significant challenge in robotic manipulation. Policy code generation methods use executable code to connect high-level task descriptions and low-level action sequences, leveraging the generalization capabilities of large language models and atomic skill libraries. In this work, we propose Robotic Programmer (RoboPro), a robotic foundation model, enabling the capability of perceiving visual information and following free-form instructions to perform robotic manipulation with policy code in a zero-shot manner. To address low efficiency and high cost in collecting runtime code data for robotic tasks, we devise Video2Code to synthesize executable code from extensive videos in-the-wild with off-the-shelf vision-language model and code-domain large language model. Extensive experiments show that RoboPro achieves the state-of-the-art zero-shot performance on robotic manipulation in both simulators and real-world environments. Specifically, the zero-shot success rate of RoboPro on RLBench surpasses the state-of-the-art model GPT-4o by 11.6%, which is even comparable to a strong supervised training baseline. Furthermore, RoboPro is robust to variations on API formats and skill sets.
Authors: Michal Nohel, Constantin Ulrich, Jonathan Suprijadi, Tassilo Wald, Klaus Maier-Hein
Abstract: This study presents an open-source toolkit to address critical challenges in preprocessing data for self-supervised learning (SSL) for 3D medical imaging, focusing on data privacy and computational efficiency. The toolkit comprises two main components: a segmentation network that delineates foreground regions to optimize data sampling and thus reduce training time, and a segmentation network that identifies anonymized regions, preventing erroneous supervision in reconstruction-based SSL methods. Experimental results demonstrate high robustness, with mean Dice scores exceeding 98.5 across all anonymization methods and surpassing 99.5 for foreground segmentation tasks, highlighting the efficacy of the toolkit in supporting SSL applications in 3D medical imaging for both CT and MRI images. The weights and code is available at https://github.com/MIC-DKFZ/Foreground-and-Anonymization-Area-Segmentation.
URLs: https://github.com/MIC-DKFZ/Foreground-and-Anonymization-Area-Segmentation.
Authors: Yekun Ke, Xiaoyu Li, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song
Abstract: Recently, Visual Autoregressive ($\mathsf{VAR}$) Models introduced a groundbreaking advancement in the field of image generation, offering a scalable approach through a coarse-to-fine "next-scale prediction" paradigm. However, the state-of-the-art algorithm of $\mathsf{VAR}$ models in [Tian, Jiang, Yuan, Peng and Wang, NeurIPS 2024] takes $O(n^4)$ time, which is computationally inefficient. In this work, we analyze the computational limits and efficiency criteria of $\mathsf{VAR}$ Models through a fine-grained complexity lens. Our key contribution is identifying the conditions under which $\mathsf{VAR}$ computations can achieve sub-quadratic time complexity. Specifically, we establish a critical threshold for the norm of input matrices used in $\mathsf{VAR}$ attention mechanisms. Above this threshold, assuming the Strong Exponential Time Hypothesis ($\mathsf{SETH}$) from fine-grained complexity theory, a sub-quartic time algorithm for $\mathsf{VAR}$ models is impossible. To substantiate our theoretical findings, we present efficient constructions leveraging low-rank approximations that align with the derived criteria. This work initiates the study of the computational efficiency of the $\mathsf{VAR}$ model from a theoretical perspective. Our technique will shed light on advancing scalable and efficient image generation in $\mathsf{VAR}$ frameworks.
Authors: Zachary Yahn, Douglas M Trent, Ethan Duncan, Beno\^it Seignovert, John Santerre, Conor Nixon
Abstract: Despite widespread adoption of deep learning models to address a variety of computer vision tasks, planetary science has yet to see extensive utilization of such tools to address its unique problems. On Titan, the largest moon of Saturn, tracking seasonal trends and weather patterns of clouds provides crucial insights into one of the most complex climates in the Solar System, yet much of the available image data are still analyzed in a conventional way. In this work, we apply a Mask R-CNN trained via transfer learning to perform instance segmentation of clouds in Titan images acquired by the Cassini spacecraft - a previously unexplored approach to a big data problem in planetary science. We demonstrate that an automated technique can provide quantitative measures for clouds, such as areas and centroids, that may otherwise be prohibitively time-intensive to produce by human mapping. Furthermore, despite Titan specific challenges, our approach yields accuracy comparable to contemporary cloud identification studies on Earth and other worlds. We compare the efficiencies of human-driven versus algorithmic approaches, showing that transfer learning provides speed-ups that may open new horizons for data investigation for Titan. Moreover, we suggest that such approaches have broad potential for application to similar problems in planetary science where they are currently under-utilized. Future planned missions to the planets and remote sensing initiatives for the Earth promise to provide a deluge of image data in the coming years that will benefit strongly from leveraging machine learning approaches to perform the analysis.
Authors: Khalil Khan, Farhan Ullah, Ikram Syed, Irfan Ullah
Abstract: Congenital heart disease is among the most common fetal abnormalities and birth defects. Despite identifying numerous risk factors influencing its onset, a comprehensive understanding of its genesis and management across diverse populations remains limited. Recent advancements in machine learning have demonstrated the potential for leveraging patient data to enable early congenital heart disease detection. Over the past seven years, researchers have proposed various data-driven and algorithmic solutions to address this challenge. This paper presents a systematic review of congential heart disease recognition using machine learning, conducting a meta-analysis of 432 references from leading journals published between 2018 and 2024. A detailed investigation of 74 scholarly works highlights key factors, including databases, algorithms, applications, and solutions. Additionally, the survey outlines reported datasets used by machine learning experts for congenital heart disease recognition. Using a systematic literature review methodology, this study identifies critical challenges and opportunities in applying machine learning to congenital heart disease.
Authors: Tudor Jianu, Shayan Doust, Mengyun Li, Baoru Huang, Tuong Do, Hoan Nguyen, Karl Bates, Tung D. Ta, Sebastiano Fichera, Pierre Berthet-Rayne, Anh Nguyen
Abstract: Endovascular navigation is a crucial aspect of minimally invasive procedures, where precise control of curvilinear instruments like guidewires is critical for successful interventions. A key challenge in this task is accurately predicting the evolving shape of the guidewire as it navigates through the vasculature, which presents complex deformations due to interactions with the vessel walls. Traditional segmentation methods often fail to provide accurate real-time shape predictions, limiting their effectiveness in highly dynamic environments. To address this, we propose SplineFormer, a new transformer-based architecture, designed specifically to predict the continuous, smooth shape of the guidewire in an explainable way. By leveraging the transformer's ability, our network effectively captures the intricate bending and twisting of the guidewire, representing it as a spline for greater accuracy and smoothness. We integrate our SplineFormer into an end-to-end robot navigation system by leveraging the condensed information. The experimental results demonstrate that our SplineFormer is able to perform endovascular navigation autonomously and achieves a 50% success rate when cannulating the brachiocephalic artery on the real robot.
Authors: Hongxin Zhi, Hongtao Yu, Shaome Li, Xiuming Zhao, Yiteng Wu
Abstract: Adversarial training has proven to be a highly effective method for improving the robustness of deep neural networks against adversarial attacks. Nonetheless, it has been observed to exhibit a limitation in terms of robust fairness, characterized by a significant disparity in robustness across different classes. Recent efforts to mitigate this problem have turned to class-wise reweighted methods. However, these methods suffer from a lack of rigorous theoretical analysis and are limited in their exploration of the weight space, as they mainly rely on existing heuristic algorithms or intuition to compute weights. In addition, these methods fail to guarantee the consistency of the optimization direction due to the decoupled optimization of weights and the model parameters. They potentially lead to suboptimal weight assignments and consequently, a suboptimal model. To address these problems, this paper proposes a novel min-max training framework, Class Optimal Distribution Adversarial Training (CODAT), which employs distributionally robust optimization to fully explore the class-wise weight space, thus enabling the identification of the optimal weight with theoretical guarantees. Furthermore, we derive a closed-form optimal solution to the internal maximization and then get a deterministic equivalent objective function, which provides a theoretical basis for the joint optimization of weights and model parameters. Meanwhile, we propose a fairness elasticity coefficient for the evaluation of the algorithm with regard to both robustness and robust fairness. Experimental results on various datasets show that the proposed method can effectively improve the robust fairness of the model and outperform the state-of-the-art approaches.
Authors: Run Luo, Ting-En Lin, Haonan Zhang, Yuchuan Wu, Xiong Liu, Min Yang, Yongbin Li, Longze Chen, Jiaming Li, Lei Zhang, Yangyi Chen, Hamid Alinejad-Rokny, Fei Huang
Abstract: Recent advancements in omnimodal learning have been achieved in understanding and generation across images, text, and speech, though mainly within proprietary models. Limited omnimodal datasets and the inherent challenges associated with real-time emotional speech generation have hindered open-source progress. To address these issues, we propose openomni, a two-stage training method combining omnimodal alignment and speech generation to develop a state-of-the-art omnimodal large language model. In the alignment phase, a pre-trained speech model is further trained on text-image tasks to generalize from vision to speech in a (near) zero-shot manner, outperforming models trained on tri-modal datasets. In the speech generation phase, a lightweight decoder facilitates real-time emotional speech through training on speech tasks and preference learning. Experiments demonstrate that openomni consistently improves across omnimodal, vision-language, and speech-language evaluations, enabling natural, emotion-rich dialogues and real-time emotional speech generation.
Authors: Boyang Sun, Hanzhi Chen, Stefan Leutenegger, Cesar Cadena, Marc Pollefeys, Hermann Blum
Abstract: Exploration of unknown environments is crucial for autonomous robots; it allows them to actively reason and decide on what new data to acquire for tasks such as mapping, object discovery, and environmental assessment. Existing methods, such as frontier-based methods, rely heavily on 3D map operations, which are limited by map quality and often overlook valuable context from visual cues. This work aims at leveraging 2D visual cues for efficient autonomous exploration, addressing the limitations of extracting goal poses from a 3D map. We propose a image-only frontier-based exploration system, with FrontierNet as a core component developed in this work. FrontierNet is a learning-based model that (i) detects frontiers, and (ii) predicts their information gain, from posed RGB images enhanced by monocular depth priors. Our approach provides an alternative to existing 3D-dependent exploration systems, achieving a 16% improvement in early-stage exploration efficiency, as validated through extensive simulations and real-world experiments.
Authors: Eric Chen, Xi Chen, Arian Maleki, Shirin Jalali
Abstract: Unrolled networks have become prevalent in various computer vision and imaging tasks. Although they have demonstrated remarkable efficacy in solving specific computer vision and computational imaging tasks, their adaptation to other applications presents considerable challenges. This is primarily due to the multitude of design decisions that practitioners working on new applications must navigate, each potentially affecting the network's overall performance. These decisions include selecting the optimization algorithm, defining the loss function, and determining the number of convolutional layers, among others. Compounding the issue, evaluating each design choice requires time-consuming simulations to train, fine-tune the neural network, and optimize for its performance. As a result, the process of exploring multiple options and identifying the optimal configuration becomes time-consuming and computationally demanding. The main objectives of this paper are (1) to unify some ideas and methodologies used in unrolled networks to reduce the number of design choices a user has to make, and (2) to report a comprehensive ablation study to discuss the impact of each of the choices involved in designing unrolled networks and present practical recommendations based on our findings. We anticipate that this study will help scientists and engineers design unrolled networks for their applications and diagnose problems within their networks efficiently.
Authors: Gabrielle Littlefair, Niladri Shekhar Dutt, Niloy J. Mitra
Abstract: Interior design involves the careful selection and arrangement of objects to create an aesthetically pleasing, functional, and harmonized space that aligns with the client's design brief. This task is particularly challenging, as a successful design must not only incorporate all the necessary objects in a cohesive style, but also ensure they are arranged in a way that maximizes accessibility, while adhering to a variety of affordability and usage considerations. Data-driven solutions have been proposed, but these are typically room- or domain-specific and lack explainability in their design design considerations used in producing the final layout. In this paper, we investigate if large language models (LLMs) can be directly utilized for interior design. While we find that LLMs are not yet capable of generating complete layouts, they can be effectively leveraged in a structured manner, inspired by the workflow of interior designers. By systematically probing LLMs, we can reliably generate a list of objects along with relevant constraints that guide their placement. We translate this information into a design layout graph, which is then solved using an off-the-shelf constrained optimization setup to generate the final layouts. We benchmark our algorithm in various design configurations against existing LLM-based methods and human designs, and evaluate the results using a variety of quantitative and qualitative metrics along with user studies. In summary, we demonstrate that LLMs, when used in a structured manner, can effectively generate diverse high-quality layouts, making them a viable solution for creating large-scale virtual scenes. Project webpage at https://flairgpt.github.io/
Authors: Chia-Ming Lee, Yu-Fan Lin, Yu-Hao Ho, Li-Wei Kang, Chih-Chung Hsu
Abstract: Hyperspectral image (HSI) fusion addresses the challenge of reconstructing High-Resolution HSIs (HR-HSIs) from High-Resolution Multispectral images (HR-MSIs) and Low-Resolution HSIs (LR-HSIs), a critical task given the high costs and hardware limitations associated with acquiring high-quality HSIs. While existing methods leverage spatial and spectral relationships, they often suffer from limited receptive fields and insufficient feature utilization, leading to suboptimal performance. Furthermore, the scarcity of high-quality HSI data highlights the importance of efficient data utilization to maximize reconstruction quality. To address these issues, we propose HyFusion, a novel framework designed to enhance the receptive field and enable effective feature map reusing, thereby maximizing data utilization. First, HR-MSI and LR-HSI inputs are concatenated to form a quasi-fused draft, preserving complementary spatial and spectral details. Next, the Enhanced Reception Field Block (ERFB) is introduced, combining shifting-window attention and dense connections to expand the receptive field, effectively capturing long-range dependencies and reusing features to reduce information loss, thereby boosting data efficiency. Finally, the Dual-Coupled Network (DCN) dynamically extracts high-frequency spectral and spatial features from LR-HSI and HR-MSI, ensuring efficient cross-domain fusion. Extensive experiments demonstrate that HyFusion achieves state-of-the-art performance in HR-MSI/LR-HSI fusion, significantly improving reconstruction quality while maintaining a compact model size and computational efficiency. By integrating enhanced receptive fields and feature map reusing, HyFusion provides a practical and effective solution for HSI fusion in resource-constrained scenarios, setting a new benchmark in hyperspectral imaging. Our code will be publicly available.
Authors: Archita Srivastava, Abhas Kumar, Rajesh Kumar, Prabhakar Srinivasan
Abstract: Chart interpretation is crucial for visual data analysis, but accurately extracting information from charts poses significant challenges for automated models. This study investigates the fine-tuning of DEPLOT, a modality conversion module that translates the image of a plot or chart to a linearized table, on a custom dataset of 50,000 bar charts. The dataset comprises simple, stacked, and grouped bar charts, targeting the unique structural features of these visualizations. The finetuned DEPLOT model is evaluated against its base version using a test set of 1,000 images and two metrics: Relative Mapping Similarity (RMS), which measures categorical mapping accuracy, and Relative Number Set Similarity (RNSS), which evaluates numerical interpretation accuracy. To further explore the reasoning capabilities of large language models (LLMs), we curate an additional set of 100 bar chart images paired with question answer sets. Our findings demonstrate that providing a structured intermediate table alongside the image significantly enhances LLM reasoning performance compared to direct image queries.
Authors: Pedro R. A. S. Bassi, Mehmet Can Yavuz, Kang Wang, Xiaoxi Chen, Wenxuan Li, Sergio Decherchi, Andrea Cavalli, Yang Yang, Alan Yuille, Zongwei Zhou
Abstract: With over 85 million CT scans performed annually in the United States, creating tumor-related reports is a challenging and time-consuming task for radiologists. To address this need, we present RadGPT, an Anatomy-Aware Vision-Language AI Agent for generating detailed reports from CT scans. RadGPT first segments tumors, including benign cysts and malignant tumors, and their surrounding anatomical structures, then transforms this information into both structured reports and narrative reports. These reports provide tumor size, shape, location, attenuation, volume, and interactions with surrounding blood vessels and organs. Extensive evaluation on unseen hospitals shows that RadGPT can produce accurate reports, with high sensitivity/specificity for small tumor (<2 cm) detection: 80/73% for liver tumors, 92/78% for kidney tumors, and 77/77% for pancreatic tumors. For large tumors, sensitivity ranges from 89% to 97%. The results significantly surpass the state-of-the-art in abdominal CT report generation. RadGPT generated reports for 17 public datasets. Through radiologist review and refinement, we have ensured the reports' accuracy, and created the first publicly available image-text 3D medical dataset, comprising over 1.8 million text tokens and 2.7 million images from 9,262 CT scans, including 2,947 tumor scans/reports of 8,562 tumor instances. Our reports can: (1) localize tumors in eight liver sub-segments and three pancreatic sub-segments annotated per-voxel; (2) determine pancreatic tumor stage (T1-T4) in 260 reports; and (3) present individual analyses of multiple tumors--rare in human-made reports. Importantly, 948 of the reports are for early-stage tumors.
Authors: Matin Mortaheb, Mohammad A. Amir Khojastepour, Srimat T. Chakradhar, Sennur Ulukus
Abstract: Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge to generate a response within a context with improved accuracy and reduced hallucinations. However, multi-modal RAG systems face unique challenges: (i) the retrieval process may select irrelevant entries to user query (e.g., images, documents), and (ii) vision-language models or multi-modal language models like GPT-4o may hallucinate when processing these entries to generate RAG output. In this paper, we aim to address the first challenge, i.e, improving the selection of relevant context from the knowledge-base in retrieval phase of the multi-modal RAG. Specifically, we leverage the relevancy score (RS) measure designed in our previous work for evaluating the RAG performance to select more relevant entries in retrieval process. The retrieval based on embeddings, say CLIP-based embedding, and cosine similarity usually perform poorly particularly for multi-modal data. We show that by using a more advanced relevancy measure, one can enhance the retrieval process by selecting more relevant pieces from the knowledge-base and eliminate the irrelevant pieces from the context by adaptively selecting up-to-$k$ entries instead of fixed number of entries. Our evaluation using COCO dataset demonstrates significant enhancement in selecting relevant context and accuracy of the generated response.
Authors: Lucas Prieto, Melih Barsbey, Pedro A. M. Mediano, Tolga Birdal
Abstract: Grokking, the sudden generalization that occurs after prolonged overfitting, is a surprising phenomenon challenging our understanding of deep learning. Although significant progress has been made in understanding grokking, the reasons behind the delayed generalization and its dependence on regularization remain unclear. In this work, we argue that without regularization, grokking tasks push models to the edge of numerical stability, introducing floating point errors in the Softmax function, which we refer to as Softmax Collapse (SC). We demonstrate that SC prevents grokking and that mitigating SC enables grokking without regularization. Investigating the root cause of SC, we find that beyond the point of overfitting, the gradients strongly align with what we call the na\"ive loss minimization (NLM) direction. This component of the gradient does not alter the model's predictions but decreases the loss by scaling the logits, typically by scaling the weights along their current direction. We show that this scaling of the logits explains the delay in generalization characteristic of grokking and eventually leads to SC, halting further learning. To validate our hypotheses, we introduce two key contributions that address the challenges in grokking tasks: StableMax, a new activation function that prevents SC and enables grokking without regularization, and $\perp$Grad, a training algorithm that promotes quick generalization in grokking tasks by preventing NLM altogether. These contributions provide new insights into grokking, elucidating its delayed generalization, reliance on regularization, and the effectiveness of existing grokking-inducing methods. Code for this paper is available at https://github.com/LucasPrietoAl/grokking-at-the-edge-of-numerical-stability.
URLs: https://github.com/LucasPrietoAl/grokking-at-the-edge-of-numerical-stability.
Authors: Ziyuan Huang, Mark Newman, Maria Vaida, Srikar Bellur, Roozbeh Sadeghian, Andrew Siu, Hui Wang, Kevin Huggins
Abstract: This study examined the viability of enhancing the prediction accuracy of artificial neural networks (ANNs) in image classification tasks by developing ANNs with evolution patterns similar to those of biological neural networks. ResNet is a widely used family of neural networks with both deep and wide variants; therefore, it was selected as the base model for our investigation. The aim of this study is to improve the image classification performance of ANNs via a novel approach inspired by the biological nervous system architecture of planarians, which comprises a brain and two nerve cords. We believe that the unique neural architecture of planarians offers valuable insights into the performance enhancement of ANNs. The proposed planarian neural architecture-based neural network was evaluated on the CIFAR-10 and CIFAR-100 datasets. Our results indicate that the proposed method exhibits higher prediction accuracy than the baseline neural network models in image classification tasks. These findings demonstrate the significant potential of biologically inspired neural network architectures in improving the performance of ANNs in a wide range of applications.
Authors: Feixiang Zhou, Xinyu Yang, Fang Chen, Long Chen, Zheheng Jiang, Hui Zhu, Reiko Heckel, Haikuan Wang, Minrui Fei, Huiyu Zhou
Abstract: Automated social behaviour analysis of mice has become an increasingly popular research area in behavioural neuroscience. Recently, pose information (i.e., locations of keypoints or skeleton) has been used to interpret social behaviours of mice. Nevertheless, effective encoding and decoding of social interaction information underlying the keypoints of mice has been rarely investigated in the existing methods. In particular, it is challenging to model complex social interactions between mice due to highly deformable body shapes and ambiguous movement patterns. To deal with the interaction modelling problem, we here propose a Cross-Skeleton Interaction Graph Aggregation Network (CS-IGANet) to learn abundant dynamics of freely interacting mice, where a Cross-Skeleton Node-level Interaction module (CS-NLI) is used to model multi-level interactions (i.e., intra-, inter- and cross-skeleton interactions). Furthermore, we design a novel Interaction-Aware Transformer (IAT) to dynamically learn the graph-level representation of social behaviours and update the node-level representation, guided by our proposed interaction-aware self-attention mechanism. Finally, to enhance the representation ability of our model, an auxiliary self-supervised learning task is proposed for measuring the similarity between cross-skeleton nodes. Experimental results on the standard CRMI13-Skeleton and our PDMB-Skeleton datasets show that our proposed model outperforms several other state-of-the-art approaches.
Authors: Xiangchen Yin, Zhenda Yu, Xin Gao, Xiao Sun
Abstract: Low-light image enhancement restores the colors and details of a single image and improves high-level visual tasks. However, restoring the lost details in the dark area is still a challenge relying only on the RGB domain. In this paper, we delve into frequency as a new clue into the model and propose a DCT-driven enhancement transformer (DEFormer) framework. First, we propose a learnable frequency branch (LFB) for frequency enhancement contains DCT processing and curvature-based frequency enhancement (CFE) to represent frequency features. Additionally, we propose a cross domain fusion (CDF) to reduce the differences between the RGB domain and the frequency domain. Our DEFormer has achieved superior results on the LOL and MIT-Adobe FiveK datasets, improving the dark detection performance.
Authors: Fabricio Breve
Abstract: This paper investigates video game identification through single screenshots, utilizing ten convolutional neural network (CNN) architectures (VGG16, ResNet50, ResNet152, MobileNet, DenseNet169, DenseNet201, EfficientNetB0, EfficientNetB2, EfficientNetB3, and EfficientNetV2S) and three transformers architectures (ViT-B16, ViT-L32, and SwinT) across 22 home console systems, spanning from Atari 2600 to PlayStation 5, totalling 8,796 games and 170,881 screenshots. Except for VGG16, all CNNs outperformed the transformers in this task. Using ImageNet pre-trained weights as initial weights, EfficientNetV2S achieves the highest average accuracy (77.44%) and the highest accuracy in 16 of the 22 systems. DenseNet201 is the best in four systems and EfficientNetB3 is the best in the remaining two systems. Employing alternative initial weights fine-tuned in an arcade screenshots dataset boosts accuracy for EfficientNet architectures, with the EfficientNetV2S reaching a peak accuracy of 77.63% and demonstrating reduced convergence epochs from 26.9 to 24.5 on average. Overall, the combination of optimal architecture and weights attains 78.79% accuracy, primarily led by EfficientNetV2S in 15 systems. These findings underscore the efficacy of CNNs in video game identification through screenshots.
Authors: Andrea Caraffa, Davide Boscaini, Amir Hamza, Fabio Poiesi
Abstract: Estimating the 6D pose of objects unseen during training is highly desirable yet challenging. Zero-shot object 6D pose estimation methods address this challenge by leveraging additional task-specific supervision provided by large-scale, photo-realistic synthetic datasets. However, their performance heavily depends on the quality and diversity of rendered data and they require extensive training. In this work, we show how to tackle the same task but without training on specific data. We propose FreeZe, a novel solution that harnesses the capabilities of pre-trained geometric and vision foundation models. FreeZe leverages 3D geometric descriptors learned from unrelated 3D point clouds and 2D visual features learned from web-scale 2D images to generate discriminative 3D point-level descriptors. We then estimate the 6D pose of unseen objects by 3D registration based on RANSAC. We also introduce a novel algorithm to solve ambiguous cases due to geometrically symmetric objects that is based on visual features. We comprehensively evaluate FreeZe across the seven core datasets of the BOP Benchmark, which include over a hundred 3D objects and 20,000 images captured in various scenarios. FreeZe consistently outperforms all state-of-the-art approaches, including competitors extensively trained on synthetic 6D pose estimation data. Code will be publicly available at https://andreacaraffa.github.io/freeze.
Authors: Han Shu, Wenshuo Li, Yehui Tang, Yiman Zhang, Yihao Chen, Houqiang Li, Yunhe Wang, Xinghao Chen
Abstract: Recently segment anything model (SAM) has shown powerful segmentation capability and has drawn great attention in computer vision fields. Massive following works have developed various applications based on the pre-trained SAM and achieved impressive performance on downstream vision tasks. However, SAM consists of heavy architectures and requires massive computational capacity, which hinders the further application of SAM on computation constrained edge devices. To this end, in this paper we propose a framework to obtain a tiny segment anything model (TinySAM) while maintaining the strong zero-shot performance. We first propose a full-stage knowledge distillation method with hard prompt sampling and hard mask weighting strategy to distill a lightweight student model. We also adapt the post-training quantization to the prompt-based segmentation task and further reduce the computational cost. Moreover, a hierarchical segmenting everything strategy is proposed to accelerate the everything inference by $2\times$ with almost no performance degradation. With all these proposed methods, our TinySAM leads to orders of magnitude computational reduction and pushes the envelope for efficient segment anything task. Extensive experiments on various zero-shot transfer tasks demonstrate the significantly advantageous performance of our TinySAM against counterpart methods. Codes are available at https://github.com/xinghaochen/TinySAM and https://gitee.com/mindspore/models/tree/master/research/cv/TinySAM.
URLs: https://github.com/xinghaochen/TinySAM, https://gitee.com/mindspore/models/tree/master/research/cv/TinySAM.
Authors: Wan Xu, Tianyu Huang, Tianyu Qu, Guanglei Yang, Yiwen Guo, Wangmeng Zuo
Abstract: Few-shot class-incremental learning (FSCIL) aims to mitigate the catastrophic forgetting issue when a model is incrementally trained on limited data. However, many of these works lack effective exploration of prior knowledge, rendering them unable to effectively address the domain gap issue in the context of 3D FSCIL, thereby leading to catastrophic forgetting. The Contrastive Vision-Language Pre-Training (CLIP) model serves as a highly suitable backbone for addressing the challenges of 3D FSCIL due to its abundant shape-related prior knowledge. Unfortunately, its direct application to 3D FSCIL still faces the incompatibility between 3D data representation and the 2D features, primarily manifested as feature space misalignment and significant noise. To address the above challenges, we introduce the FILP-3D framework with two novel components: the Redundant Feature Eliminator (RFE) for feature space misalignment and the Spatial Noise Compensator (SNC) for significant noise. RFE aligns the feature spaces of input point clouds and their embeddings by performing a unique dimensionality reduction on the feature space of pre-trained models (PTMs), effectively eliminating redundant information without compromising semantic integrity. On the other hand, SNC is a graph-based 3D model designed to capture robust geometric information within point clouds, thereby augmenting the knowledge lost due to projection, particularly when processing real-world scanned data. Moreover, traditional accuracy metrics are proven to be biased due to the imbalance in existing 3D datasets. Therefore we propose 3D FSCIL benchmark FSCIL3D-XL and novel evaluation metrics that offer a more nuanced assessment of a 3D FSCIL model. Experimental results on both established and our proposed benchmarks demonstrate that our approach significantly outperforms existing state-of-the-art methods.
Authors: Seitaro Ono, Yuka Ogino, Takahiro Toizumi, Atsushi Ito, Masato Tsukada
Abstract: In recent years, significant progress has been made in image recognition technology based on deep neural networks. However, improving recognition performance under low-light conditions remains a significant challenge. This study addresses the enhancement of recognition model performance in low-light conditions. We propose an image-adaptive learnable module which apply appropriate image processing on input images and a hyperparameter predictor to forecast optimal parameters used in the module. Our proposed approach allows for the enhancement of recognition performance under low-light conditions by easily integrating as a front-end filter without the need to retrain existing recognition models designed for low-light conditions. Through experiments, our proposed method demonstrates its contribution to enhancing image recognition performance under low-light conditions.
Authors: Changgu Chen, Junwei Shu, Gaoqi He, Changbo Wang, Yang Li
Abstract: Recent large-scale pre-trained diffusion models have demonstrated a powerful generative ability to produce high-quality videos from detailed text descriptions. However, exerting control over the motion of objects in videos generated by any video diffusion model is a challenging problem. In this paper, we propose a novel zero-shot moving object trajectory control framework, Motion-Zero, to enable a bounding-box-trajectories-controlled text-to-video diffusion model. To this end, an initial noise prior module is designed to provide a position-based prior to improve the stability of the appearance of the moving object and the accuracy of position. In addition, based on the attention map of the U-net, spatial constraints are directly applied to the denoising process of diffusion models, which further ensures the positional and spatial consistency of moving objects during the inference. Furthermore, temporal consistency is guaranteed with a proposed shift temporal attention mechanism. Our method can be flexibly applied to various state-of-the-art video diffusion models without any training process. Extensive experiments demonstrate our proposed method can control the motion trajectories of objects and generate high-quality videos. Our project page is https://vpx-ecnu.github.io/MotionZero-website/
Authors: Han Zhao, Min Zhang, Wei Zhao, Pengxiang Ding, Siteng Huang, Donglin Wang
Abstract: In recent years, the application of multimodal large language models (MLLM) in various fields has achieved remarkable success. However, as the foundation model for many downstream tasks, current MLLMs are composed of the well-known Transformer network, which has a less efficient quadratic computation complexity. To improve the efficiency of such basic models, we propose Cobra, a linear computational complexity MLLM. Specifically, Cobra integrates the efficient Mamba language model into the visual modality. Moreover, we explore and study various modal fusion schemes to create an effective multi-modal Mamba. Extensive experiments demonstrate that (1) Cobra achieves extremely competitive performance with current computationally efficient state-of-the-art methods, e.g., LLaVA-Phi, TinyLLaVA, and MobileVLM v2, and has faster speed due to Cobra's linear sequential modeling. (2) Interestingly, the results of closed-set challenging prediction benchmarks show that Cobra performs well in overcoming visual illusions and spatial relationship judgments. (3) Notably, Cobra even achieves comparable performance to LLaVA with about 43% of the number of parameters. We will make all codes of Cobra open-source and hope that the proposed method can facilitate future research on complexity problems in MLLM. Our project page is available at: https://sites.google.com/view/cobravlm.
Authors: Taeheon Kim, Sangyun Chung, Damin Yeom, Youngjoon Yu, Hak Gu Kim, Yong Man Ro
Abstract: Multispectral pedestrian detection is attractive for around-the-clock applications due to the complementary information between RGB and thermal modalities. However, current models often fail to detect pedestrians in certain cases (e.g., thermal-obscured pedestrians), particularly due to the modality bias learned from statistically biased datasets. In this paper, we investigate how to mitigate modality bias in multispectral pedestrian detection using Large Language Models (LLMs). Accordingly, we design a Multispectral Chain-of-Thought (MSCoT) prompting strategy, which prompts the LLM to perform multispectral pedestrian detection. Moreover, we propose a novel Multispectral Chain-of-Thought Detection (MSCoTDet) framework that integrates MSCoT prompting into multispectral pedestrian detection. To this end, we design a Language-driven Multi-modal Fusion (LMF) strategy that enables fusing the outputs of MSCoT prompting with the detection results of vision-based multispectral pedestrian detection models. Extensive experiments validate that MSCoTDet effectively mitigates modality biases and improves multispectral pedestrian detection.
Authors: Liping Yang, Joshua Driscol, Ming Gong, Katie Slack, Wenbin Zhang, Shujie Wang, Catherine G. Potts
Abstract: Line detection is a classic and essential problem in image processing, computer vision and machine intelligence. Line detection has many important applications, including image vectorization (e.g., document recognition and art design), indoor mapping, and important societal challenges (e.g., sea ice fracture line extraction from satellite imagery). Many line detection algorithms and methods have been developed, but robust and intuitive methods are still lacking. In this paper, we proposed and implemented a topological graph-guided algorithm, named TGGLinesPlus, for line detection. Our experiments on images from a wide range of domains have demonstrated the flexibility of our TGGLinesPlus algorithm. We benchmarked our algorithm with five classic and state-of-the-art line detection methods and evaluated the benchmark results qualitatively and quantitatively, the results demonstrate the robustness of TGGLinesPlus.
Authors: Yehui Shen, Mingmin Liu, Huimin Lu, Xieyuanli Chen
Abstract: Visual place recognition (VPR) plays a pivotal role in autonomous exploration and navigation of mobile robots within complex outdoor environments. While cost-effective and easily deployed, camera sensors are sensitive to lighting and weather changes, and even slight image alterations can greatly affect VPR efficiency and precision. Existing methods overcome this by exploiting powerful yet large networks, leading to significant consumption of computational resources. In this paper, we propose a high-performance teacher and lightweight student distillation framework called TSCM. It exploits our devised cross-metric knowledge distillation to narrow the performance gap between the teacher and student models, maintaining superior performance while enabling minimal computational load during deployment. We conduct comprehensive evaluations on large-scale datasets, namely Pittsburgh30k and Pittsburgh250k. Experimental results demonstrate the superiority of our method over baseline models in terms of recognition accuracy and model parameter efficiency. Moreover, our ablation studies show that the proposed knowledge distillation technique surpasses other counterparts. The code of our method has been released at https://github.com/nubot-nudt/TSCM.
Authors: Walid Bousselham, Angie Boggust, Sofian Chaybouti, Hendrik Strobelt, Hilde Kuehne
Abstract: Vision Transformers (ViTs), with their ability to model long-range dependencies through self-attention mechanisms, have become a standard architecture in computer vision. However, the interpretability of these models remains a challenge. To address this, we propose LeGrad, an explainability method specifically designed for ViTs. LeGrad computes the gradient with respect to the attention maps of ViT layers, considering the gradient itself as the explainability signal. We aggregate the signal over all layers, combining the activations of the last as well as intermediate tokens to produce the merged explainability map. This makes LeGrad a conceptually simple and an easy-to-implement tool for enhancing the transparency of ViTs. We evaluate LeGrad in challenging segmentation, perturbation, and open-vocabulary settings, showcasing its versatility compared to other SotA explainability methods demonstrating its superior spatial fidelity and robustness to perturbations. A demo and the code is available at https://github.com/WalBouss/LeGrad.
Authors: Yiming Che, Fazle Rafsani, Jay Shah, Md Mahfuzur Rahman Siddiquee, Teresa Wu
Abstract: Weakly-supervised diffusion models (DMs) in anomaly segmentation, leveraging image-level labels, have attracted significant attention for their superior performance compared to unsupervised methods. It eliminates the need for pixel-level labels in training, offering a more cost-effective alternative to supervised methods. However, existing methods are not fully weakly-supervised because they heavily rely on costly pixel-level labels for hyperparameter tuning in inference. To tackle this challenge, we introduce Anomaly Segmentation with Forward Process of Diffusion Models (AnoFPDM), a fully weakly-supervised framework that operates without the need of pixel-level labels. Leveraging the unguided forward process as a reference for the guided forward process, we select hyperparameters such as the noise scale, the threshold for segmentation and the guidance strength. We aggregate anomaly maps from guided forward process, enhancing the signal strength of anomalous regions. Remarkably, our proposed method outperforms recent state-of-the-art weakly-supervised approaches, even without utilizing pixel-level labels.
Authors: Francesco Prinzi, Carmelo Militello, Calogero Zarcaro, Tommaso Vincenzo Bartolotta, Salvatore Gaglio, Salvatore Vitabile
Abstract: In recent years, machine learning-based clinical decision support systems (CDSS) have played a key role in the analysis of several medical conditions. Despite their promising capabilities, the lack of transparency in AI models poses significant challenges, particularly in medical contexts where reliability is a mandatory aspect. However, it appears that explainability is inversely proportional to accuracy. For this reason, achieving transparency without compromising predictive accuracy remains a key challenge. This paper presents a novel method, namely Rad4XCNN, to enhance the predictive power of CNN-derived features with the inherent interpretability of radiomic features. Rad4XCNN diverges from conventional methods based on saliency maps, by associating intelligible meaning to CNN-derived features by means of Radiomics, offering new perspectives on explanation methods beyond visualization maps. Using a breast cancer classification task as a case study, we evaluated Rad4XCNN on ultrasound imaging datasets, including an online dataset and two in-house datasets for internal and external validation. Some key results are: i) CNN-derived features guarantee more robust accuracy when compared against ViT-derived and radiomic features; ii) conventional visualization map methods for explanation present several pitfalls; iii) Rad4XCNN does not sacrifice model accuracy for their explainability; iv) Rad4XCNN provides a global explanation enabling the physician to extract global insights and findings. Our method can mitigate some concerns related to the explainability-accuracy trade-off. This study highlighted the importance of proposing new methods for model explanation without affecting their accuracy.
Authors: Daechul Ahn, Yura Choi, San Kim, Youngjae Yu, Dongyeop Kang, Jonghyun Choi
Abstract: Iterative self-improvement, a concept extending beyond personal growth, has found powerful applications in machine learning, particularly in transforming weak models into strong ones. While recent advances in natural language processing have shown its efficacy through iterative preference optimization, applying this approach to Video Large Multi-modal Models (VLMMs) remains challenging due to modality misalignment. VLMMs struggle with this misalignment during iterative preference modeling, as the self-judge model often prioritizes linguistic knowledge over visual information. Additionally, iterative preference optimization can lead to visually hallucinated verbose responses due to length bias within the self-rewarding cycle. To address these issues, we propose Iterative Self-Retrospective Direct Preference Optimization (ISR-DPO), a method that uses self-retrospection to enhance preference modeling. This approach enhances the self-judge's focus on informative video regions, resulting in more visually grounded preferences. In extensive empirical evaluations across diverse video question answering benchmarks, the ISR-DPO significantly outperforms the state of the art. We are committed to open-sourcing our code, models, and datasets to encourage further investigation.
Authors: Matthew Zheng, Enis Simsar, Hidir Yesiltepe, Federico Tombari, Joel Simon, Pinar Yanardag
Abstract: Text-to-image models are becoming increasingly popular, revolutionizing the landscape of digital art creation by enabling highly detailed and creative visual content generation. These models have been widely employed across various domains, particularly in art generation, where they facilitate a broad spectrum of creative expression and democratize access to artistic creation. In this paper, we introduce \texttt{STYLEBREEDER}, a comprehensive dataset of 6.8M images and 1.8M prompts generated by 95K users on Artbreeder, a platform that has emerged as a significant hub for creative exploration with over 13M users. We introduce a series of tasks with this dataset aimed at identifying diverse artistic styles, generating personalized content, and recommending styles based on user interests. By documenting unique, user-generated styles that transcend conventional categories like 'cyberpunk' or 'Picasso,' we explore the potential for unique, crowd-sourced styles that could provide deep insights into the collective creative psyche of users worldwide. We also evaluate different personalization methods to enhance artistic expression and introduce a style atlas, making these models available in LoRA format for public use. Our research demonstrates the potential of text-to-image diffusion models to uncover and promote unique artistic expressions, further democratizing AI in art and fostering a more diverse and inclusive artistic community. The dataset, code and models are available at https://stylebreeder.github.io under a Public Domain (CC0) license.
Authors: Xu Han, Fangfang Fan, Jingzhao Rong, Zhen Li, Georges El Fakhri, Qingyu Chen, Xiaofeng Liu
Abstract: The text to medical image (T2MedI) with latent diffusion model has great potential to alleviate the scarcity of medical imaging data and explore the underlying appearance distribution of lesions in a specific patient status description. However, as the text to nature image models, we show that the T2MedI model can also bias to some subgroups to overlook the minority ones in the training set. In this work, we first build a T2MedI model based on the pre-trained Imagen model, which has the fixed contrastive language-image pre-training (CLIP) text encoder, while its decoder has been fine-tuned on medical images from the Radiology Objects in COntext (ROCO) dataset. Its gender bias is analyzed qualitatively and quantitatively. Toward this issue, we propose to fine-tune the T2MedI toward the target application dataset to align their sensitive subgroups distribution probability. Specifically, the alignment loss for fine-tuning is guided by an off-the-shelf sensitivity-subgroup classifier to match the classification probability between the generated images and the expected target dataset. In addition, the image quality is maintained by a CLIP-consistency regularization term following a knowledge distillation scheme. For evaluation, we set the target dataset to be enhanced as the BraST18 dataset, and trained a brain magnetic resonance (MR) slice-based gender classifier from it. With our method, the generated MR image can markedly reduce the inconsistency with the gender proportion in the BraTS18 dataset.
Authors: Qiao Yu, Xianzhi Li, Yuan Tang, Xu Han, Jinfeng Xu, Long Hu, Min Chen
Abstract: Reconstructing textured meshes from colored point clouds is an important but challenging task. Most existing methods yield blurry-looking textures or rely on 3D training data that are hard to acquire. Regarding this, we propose PointDreamer, a novel framework for textured mesh reconstruction from colored point cloud via diffusion-based 2D inpainting. Specifically, we first reconstruct an untextured mesh. Next, we project the input point cloud into 2D space to generate sparse multi-view images, and then inpaint empty pixels utilizing a pre-trained 2D diffusion model. After that, we unproject the colors of the inpainted dense images onto the untextured mesh, thus obtaining the final textured mesh. This project-inpaint-unproject pipeline bridges the gap between 3D point clouds and 2D diffusion models for the first time. Thanks to the powerful 2D diffusion model pre-trained on extensive 2D data, PointDreamer reconstructs clear, high-quality textures with high robustness to sparse or noisy input. Also, it's zero-shot requiring no extra training. In addition, we design Non-Border-First unprojection strategy to address the border-area inconsistency issue, which is less explored but commonly-occurred in methods that generate 3D textures from multiview images. Extensive qualitative and quantitative experiments on various synthetic and real-scanned datasets show the SoTA performance of PointDreamer, by significantly outperforming baseline methods with 30% improvement in LPIPS score (from 0.118 to 0.068). Code at: https://github.com/YuQiao0303/PointDreamer.
Authors: Badr-Eddine Marani, Mohamed Hanini, Nihitha Malayarukil, Stergios Christodoulidis, Maria Vakalopoulou, Enzo Ferrante
Abstract: The proliferation of machine learning models in critical decision making processes has underscored the need for bias discovery and mitigation strategies. Identifying the reasons behind a biased system is not straightforward, since in many occasions they are associated with hidden spurious correlations which are not easy to spot. Standard approaches rely on bias audits performed by analyzing model performance in pre-defined subgroups of data samples, usually characterized by common attributes like gender or ethnicity when it comes to people, or other specific attributes defining semantically coherent groups of images. However, it is not always possible to know a-priori the specific attributes defining the failure modes of visual recognition systems. Recent approaches propose to discover these groups by leveraging large vision language models, which enable the extraction of cross-modal embeddings and the generation of textual descriptions to characterize the subgroups where a certain model is underperforming. In this work, we argue that incorporating visual explanations (e.g. heatmaps generated via GradCAM or other approaches) can boost the performance of such bias discovery and mitigation frameworks. To this end, we introduce Visually Grounded Bias Discovery and Mitigation (ViG-Bias), a simple yet effective technique which can be integrated to a variety of existing frameworks to improve both, discovery and mitigation performance. Our comprehensive evaluation shows that incorporating visual explanations enhances existing techniques like DOMINO, FACTS and Bias-to-Text, across several challenging datasets, including CelebA, Waterbirds, and NICO++.
Authors: Xu Han, Linghao Jin, Xuezhe Ma, Xiaofeng Liu
Abstract: Fine-tuning pre-trained Vision-Language Models (VLMs) has shown remarkable capabilities in medical image and textual depiction synergy. Nevertheless, many pre-training datasets are restricted by patient privacy concerns, potentially containing noise that can adversely affect downstream performance. Moreover, the growing reliance on multi-modal generation exacerbates this issue because of its susceptibility to adversarial attacks. To investigate how VLMs trained on adversarial noisy data perform on downstream medical tasks, we first craft noisy upstream datasets using multi-modal adversarial attacks. Through our comprehensive analysis, we unveil that moderate noise enhances model robustness and transferability, but increasing noise levels negatively impact downstream task performance. To mitigate this issue, we propose rectify adversarial noise (RAN) framework, a recipe designed to effectively defend adversarial attacks and rectify the influence of upstream noise during fine-tuning.
Authors: Jingyun Wang, Guoliang Kang
Abstract: Recent works utilize CLIP to perform the challenging unsupervised semantic segmentation task where only images without annotations are available. However, we observe that when adopting CLIP to such a pixel-level understanding task, unexpected bias (including class-preference bias and space-preference bias) occurs. Previous works don't explicitly model the bias, which largely constrains the segmentation performance. In this paper, we propose to explicitly model and rectify the bias existing in CLIP to facilitate the unsupervised semantic segmentation task. Specifically, we design a learnable "Reference" prompt to encode class-preference bias and a projection of the positional embedding in the vision transformer to encode space-preference bias respectively. To avoid interference, two kinds of biases are firstly independently encoded into different features, i.e., the Reference feature and the positional feature. Via a matrix multiplication between the Reference feature and the positional feature, a bias logit map is generated to explicitly represent two kinds of biases. Then we rectify the logits of CLIP via a simple element-wise subtraction. To make the rectified results smoother and more contextual, we design a mask decoder which takes the feature of CLIP and the rectified logits as input and outputs a rectified segmentation mask with the help of Gumbel-Softmax operation. A contrastive loss based on the masked visual features and the text features of different classes is imposed, which makes the bias modeling and rectification process meaningful and effective. Extensive experiments on various benchmarks including PASCAL VOC, PASCAL Context, ADE20K, Cityscapes, and COCO Stuff demonstrate that our method performs favorably against previous state-of-the-arts. The implementation is available at: https://github.com/dogehhh/ReCLIP.
Authors: Tejas Anvekar, Shivanand Venkanna Sheshappanavar
Abstract: In this paper, we discuss Mahalanobis k-NN: A Statistical Lens designed to address the challenges of feature matching in learning-based point cloud registration when confronted with an arbitrary density of point clouds. We tackle this by adopting Mahalanobis k-NN's inherent property to capture the distribution of the local neighborhood and surficial geometry. Our method can be seamlessly integrated into any local-graph-based point cloud analysis method. In this paper, we focus on two distinct methodologies: Deep Closest Point (DCP) and Deep Universal Manifold Embedding (DeepUME). Our extensive benchmarking on the ModelNet40 and FAUST datasets highlights the efficacy of the proposed method in point cloud registration tasks. Moreover, we establish for the first time that the features acquired through point cloud registration inherently can possess discriminative capabilities. This is evident by a substantial improvement of about 20% in the average accuracy observed in the point cloud few-shot classification task, benchmarked on ModelNet40 and ScanObjectNN.
Authors: Omer Regev, Omri Avrahami, Dani Lischinski
Abstract: Recent advancements in generative models have revolutionized image generation and editing, making these tasks accessible to non-experts. This paper focuses on local image editing, particularly the task of adding new content to a loosely specified area. Existing methods often require a precise mask or a detailed description of the location, which can be cumbersome and prone to errors. We propose Click2Mask, a novel approach that simplifies the local editing process by requiring only a single point of reference (in addition to the content description). A mask is dynamically grown around this point during a Blended Latent Diffusion (BLD) process, guided by a masked CLIP-based semantic loss. Click2Mask surpasses the limitations of segmentation-based and fine-tuning dependent methods, offering a more user-friendly and contextually accurate solution. Our experiments demonstrate that Click2Mask not only minimizes user effort but also enables competitive or superior local image manipulations compared to SoTA methods, according to both human judgement and automatic metrics. Key contributions include the simplification of user input, the ability to freely add objects unconstrained by existing segments, and the integration potential of our dynamic mask approach within other editing methods.
Authors: Emanuele Vivoli, Mohamed Ali Souibgui, Andrey Barsky, Artemis LLabr\'es, Marco Bertini, Dimosthenis Karatzas
Abstract: Vision-language models have recently evolved into versatile systems capable of high performance across a range of tasks, such as document understanding, visual question answering, and grounding, often in zero-shot settings. Comics Understanding, a complex and multifaceted field, stands to greatly benefit from these advances. Comics, as a medium, combine rich visual and textual narratives, challenging AI models with tasks that span image classification, object detection, instance segmentation, and deeper narrative comprehension through sequential panels. However, the unique structure of comics -- characterized by creative variations in style, reading order, and non-linear storytelling -- presents a set of challenges distinct from those in other visual-language domains. In this survey, we present a comprehensive review of Comics Understanding from both dataset and task perspectives. Our contributions are fivefold: (1) We analyze the structure of the comics medium, detailing its distinctive compositional elements; (2) We survey the widely used datasets and tasks in comics research, emphasizing their role in advancing the field; (3) We introduce the Layer of Comics Understanding (LoCU) framework, a novel taxonomy that redefines vision-language tasks within comics and lays the foundation for future work; (4) We provide a detailed review and categorization of existing methods following the LoCU framework; (5) Finally, we highlight current research challenges and propose directions for future exploration, particularly in the context of vision-language models applied to comics. This survey is the first to propose a task-oriented framework for comics intelligence and aims to guide future research by addressing critical gaps in data availability and task definition. A project associated with this survey is available at https://github.com/emanuelevivoli/awesome-comics-understanding.
URLs: https://github.com/emanuelevivoli/awesome-comics-understanding.
Authors: Shravan Venkatraman, Jaskaran Singh Walia, Joe Dhanith P R
Abstract: Vision Transformers (ViTs) have redefined image classification by leveraging self-attention to capture complex patterns and long-range dependencies between image patches. However, a key challenge for ViTs is efficiently incorporating multi-scale feature representations, which is inherent in convolutional neural networks (CNNs) through their hierarchical structure. Graph transformers have made strides in addressing this by leveraging graph-based modeling, but they often lose or insufficiently represent spatial hierarchies, especially since redundant or less relevant areas dilute the image's contextual representation. To bridge this gap, we propose SAG-ViT, a Scale-Aware Graph Attention ViT that integrates multi-scale feature capabilities of CNNs, representational power of ViTs, graph-attended patching to enable richer contextual representation. Using EfficientNetV2 as a backbone, the model extracts multi-scale feature maps, dividing them into patches to preserve richer semantic information compared to directly patching the input images. The patches are structured into a graph using spatial and feature similarities, where a Graph Attention Network (GAT) refines the node embeddings. This refined graph representation is then processed by a Transformer encoder, capturing long-range dependencies and complex interactions. We evaluate SAG-ViT on benchmark datasets across various domains, validating its effectiveness in advancing image classification tasks. Our code and weights are available at https://github.com/shravan-18/SAG-ViT.
Authors: Xinran Wang, Haiwen Zhang, Baoteng Li, Kongming Liang, Hao Sun, Zhongjiang He, Zhanyu Ma, Jun Guo
Abstract: Object description plays an important role for visually impaired individuals to understand and compare the differences between objects. Recent multimodal large language models(MLLMs) exhibit powerful perceptual abilities and demonstrate impressive potential for generating object-centric descriptions. However, the descriptions generated by such models may still usually contain a lot of content that is not relevant to the user intent or miss some important object dimension details. Under special scenarios, users may only need the details of certain dimensions of an object. In this paper, we propose a training-free object description refinement pipeline, Dimension Tailor, designed to enhance user-specified details in object descriptions. This pipeline includes three steps: dimension extracting, erasing, and supplementing, which decompose the description into user-specified dimensions. Dimension Tailor can not only improve the quality of object details but also offer flexibility in including or excluding specific dimensions based on user preferences. We conducted extensive experiments to demonstrate the effectiveness of Dimension Tailor on controllable object descriptions. Notably, the proposed pipeline can consistently improve the performance of the recent MLLMs. The code is currently accessible at https://github.com/xin-ran-w/ControllableObjectDescription.
URLs: https://github.com/xin-ran-w/ControllableObjectDescription.
Authors: Tianshuo Xu, Zhifei Chen, Leyi Wu, Hao Lu, Yuying Chen, Lihui Jiang, Bingbing Liu, Yingcong Chen
Abstract: Recent numerous video generation models, also known as world models, have demonstrated the ability to generate plausible real-world videos. However, many studies have shown that these models often produce motion results lacking logical or physical coherence. In this paper, we revisit video generation models and find that single-stage approaches struggle to produce high-quality results while maintaining coherent motion reasoning. To address this issue, we propose \textbf{Motion Dreamer}, a two-stage video generation framework. In Stage I, the model generates an intermediate motion representation-such as a segmentation map or depth map-based on the input image and motion conditions, focusing solely on the motion itself. In Stage II, the model uses this intermediate motion representation as a condition to generate a high-detail video. By decoupling motion reasoning from high-fidelity video synthesis, our approach allows for more accurate and physically plausible motion generation. We validate the effectiveness of our approach on the Physion dataset and in autonomous driving scenarios. For example, given a single push, our model can synthesize the sequential toppling of a set of dominoes. Similarly, by varying the movements of ego-cars, our model can produce different effects on other vehicles. Our work opens new avenues in creating models that can reason about physical interactions in a more coherent and realistic manner. Our webpage is available: https://envision-research.github.io/MotionDreamer/.
Authors: Marco Garosi, Riccardo Tedoldi, Davide Boscaini, Massimiliano Mancini, Nicu Sebe, Fabio Poiesi
Abstract: Supervised 3D part segmentation models are tailored for a fixed set of objects and parts, limiting their transferability to open-set, real-world scenarios. Recent works have explored vision-language models (VLMs) as a promising alternative, using multi-view rendering and textual prompting to identify object parts. However, naively applying VLMs in this context introduces several drawbacks, such as the need for meticulous prompt engineering, and fails to leverage the 3D geometric structure of objects. To address these limitations, we propose COPS, a COmprehensive model for Parts Segmentation that blends the semantics extracted from visual concepts and 3D geometry to effectively identify object parts. COPS renders a point cloud from multiple viewpoints, extracts 2D features, projects them back to 3D, and uses a novel geometric-aware feature aggregation procedure to ensure spatial and semantic consistency. Finally, it clusters points into parts and labels them. We demonstrate that COPS is efficient, scalable, and achieves zero-shot state-of-the-art performance across five datasets, covering synthetic and real-world data, texture-less and coloured objects, as well as rigid and non-rigid shapes. The code is available at https://3d-cops.github.io.
Authors: Sindhu Boddu, Arindam Mukherjee
Abstract: This paper presents a robust approach for object detection in aerial imagery using the YOLOv5 model. We focus on identifying critical objects such as ambulances, car crashes, police vehicles, tow trucks, fire engines, overturned cars, and vehicles on fire. By leveraging a custom dataset, we outline the complete pipeline from data collection and annotation to model training and evaluation. Our results demonstrate that YOLOv5 effectively balances speed and accuracy, making it suitable for real-time emergency response applications. This work addresses key challenges in aerial imagery, including small object detection and complex backgrounds, and provides insights for future research in automated emergency response systems.
Authors: Jingxu Ng, Cheng Lv, Pu Zhao, Wei Niu, Juyi Lin, Minzhou Pan, Yun Liang, Yanzhi Wang
Abstract: Stable diffusion plays a crucial role in generating high-quality images. However, image generation is time-consuming and memory-intensive. To address this, stable-diffusion.cpp (Sdcpp) emerges as an efficient inference framework to accelerate the diffusion models. Although it is lightweight, the current implementation of ggml_conv_2d operator in Sdcpp is suboptimal, exhibiting both high inference latency and massive memory usage. To address this, in this work, we present an optimized version of Sdcpp leveraging the Winograd algorithm to accelerate 2D convolution operations, which is the primary bottleneck in the pipeline. By analyzing both dependent and independent computation graphs, we exploit the device's locality and parallelism to achieve substantial performance improvements. Our framework delivers correct end-to-end results across various stable diffusion models, including SDv1.4, v1.5, v2.1, SDXL, and SDXL-Turbo. Our evaluation results demonstrate a speedup up to 2.76x for individual convolutional layers and an inference speedup up to 4.79x for the overall image generation process, compared with the original Sdcpp on M1 pro. Homepage: https://github.com/SealAILab/stable-diffusion-cpp
Authors: Shanlin Sun, Gabriel De Araujo, Jiaqi Xu, Shenghan Zhou, Hanwen Zhang, Ziheng Huang, Chenyu You, Xiaohui Xie
Abstract: 3D human motion generation has seen substantial advancement in recent years. While state-of-the-art approaches have improved performance significantly, they still struggle with complex and detailed motions unseen in training data, largely due to the scarcity of motion datasets and the prohibitive cost of generating new training examples. To address these challenges, we introduce CoMA, an agent-based solution for complex human motion generation, editing, and comprehension. CoMA leverages multiple collaborative agents powered by large language and vision models, alongside a mask transformer-based motion generator featuring body part-specific encoders and codebooks for fine-grained control. Our framework enables generation of both short and long motion sequences with detailed instructions, text-guided motion editing, and self-correction for improved quality. Evaluations on the HumanML3D dataset demonstrate competitive performance against state-of-the-art methods. Additionally, we create a set of context-rich, compositional, and long text prompts, where user studies show our method significantly outperforms existing approaches.
Authors: Ximing Xing, Juncheng Hu, Guotao Liang, Jing Zhang, Dong Xu, Qian Yu
Abstract: The unprecedented advancements in Large Language Models (LLMs) have profoundly impacted natural language processing but have yet to fully embrace the realm of scalable vector graphics (SVG) generation. While LLMs encode partial knowledge of SVG data from web pages during training, recent findings suggest that semantically ambiguous and tokenized representations within LLMs may result in hallucinations in vector primitive predictions. Additionally, LLM training typically lacks modeling and understanding of the rendering sequence of vector paths, which can lead to occlusion between output vector primitives. In this paper, we present LLM4SVG, an initial yet substantial step toward bridging this gap by enabling LLMs to better understand and generate vector graphics. LLM4SVG facilitates a deeper understanding of SVG components through learnable semantic tokens, which precisely encode these tokens and their corresponding properties to generate semantically aligned SVG outputs. Using a series of learnable semantic tokens, a structured dataset for instruction following is developed to support comprehension and generation across two primary tasks. Our method introduces a modular architecture to existing large language models, integrating semantic tags, vector instruction encoders, fine-tuned commands, and powerful LLMs to tightly combine geometric, appearance, and language information. To overcome the scarcity of SVG-text instruction data, we developed an automated data generation pipeline that collected a massive dataset of more than 250k SVG data and 580k SVG-text instructions, which facilitated the adoption of the two-stage training strategy popular in LLM development. By exploring various training strategies, we developed LLM4SVG, which significantly moves beyond optimized rendering-based approaches and language-model-based baselines to achieve remarkable results in human evaluation tasks.
Authors: Maham Tanveer, Yang Zhou, Simon Niklaus, Ali Mahdavi Amiri, Hao Zhang, Krishna Kumar Singh, Nanxuan Zhao
Abstract: By generating plausible and smooth transitions between two image frames, video inbetweening is an essential tool for video editing and long video synthesis. Traditional works lack the capability to generate complex large motions. While recent video generation techniques are powerful in creating high-quality results, they often lack fine control over the details of intermediate frames, which can lead to results that do not align with the creative mind. We introduce MotionBridge, a unified video inbetweening framework that allows flexible controls, including trajectory strokes, keyframes, masks, guide pixels, and text. However, learning such multi-modal controls in a unified framework is a challenging task. We thus design two generators to extract the control signal faithfully and encode feature through dual-branch embedders to resolve ambiguities. We further introduce a curriculum training strategy to smoothly learn various controls. Extensive qualitative and quantitative experiments have demonstrated that such multi-modal controls enable a more dynamic, customizable, and contextually accurate visual narrative.
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: Luoxu Jin, Hiroshi Watanabe
Abstract: With the development of video generation models has advanced significantly in recent years, we adopt large-scale image-to-video diffusion models for video frame interpolation. We present a conditional encoder designed to adapt an image-to-video model for large-motion frame interpolation. To enhance performance, we integrate a dual-branch feature extractor and propose a cross-frame attention mechanism that effectively captures both spatial and temporal information, enabling accurate interpolations of intermediate frames. Our approach demonstrates superior performance on the Fr\'echet Video Distance (FVD) metric when evaluated against other state-of-the-art approaches, particularly in handling large motion scenarios, highlighting advancements in generative-based methodologies.
Authors: Hao Gui, Lin Hu, Rui Chen, Mingxiao Huang, Yuxin Yin, Jin Yang, Yong Wu, Chen Liu, Zhongxu Sun, Xueyang Zhang, Kun Zhan
Abstract: 3D Gaussian Splatting (3DGS) is increasingly attracting attention in both academia and industry owing to its superior visual quality and rendering speed. However, training a 3DGS model remains a time-intensive task, especially in load imbalance scenarios where workload diversity among pixels and Gaussian spheres causes poor renderCUDA kernel performance. We introduce Balanced 3DGS, a Gaussian-wise parallelism rendering with fine-grained tiling approach in 3DGS training process, perfectly solving load-imbalance issues. First, we innovatively introduce the inter-block dynamic workload distribution technique to map workloads to Streaming Multiprocessor(SM) resources within a single GPU dynamically, which constitutes the foundation of load balancing. Second, we are the first to propose the Gaussian-wise parallel rendering technique to significantly reduce workload divergence inside a warp, which serves as a critical component in addressing load imbalance. Based on the above two methods, we further creatively put forward the fine-grained combined load balancing technique to uniformly distribute workload across all SMs, which boosts the forward renderCUDA kernel performance by up to 7.52x. Besides, we present a self-adaptive render kernel selection strategy during the 3DGS training process based on different load-balance situations, which effectively improves training efficiency.
Authors: W. He, Z. Huang, X. Meng, X. Qi, R. Xiao, C. -G. Li
Abstract: In the era of pre-trained models, image clustering task is usually addressed by two relevant stages: a) to produce features from pre-trained vision models; and b) to find clusters from the pre-trained features. However, these two stages are often considered separately or learned by different paradigms, leading to suboptimal clustering performance. In this paper, we propose a unified framework, termed graph Cut-guided Maximal Coding Rate Reduction (CgMCR$^2$), for jointly learning the structured embeddings and the clustering. To be specific, we attempt to integrate an efficient clustering module into the principled framework for learning structured representation, in which the clustering module is used to provide partition information to guide the cluster-wise compression and the learned embeddings is aligned to desired geometric structures in turn to help for yielding more accurate partitions. We conduct extensive experiments on both standard and out-of-domain image datasets and experimental results validate the effectiveness of our approach.
Authors: Yuqian Yuan, Hang Zhang, Wentong Li, Zesen Cheng, Boqiang Zhang, Long Li, Xin Li, Deli Zhao, Wenqiao Zhang, Yueting Zhuang, Jianke Zhu, Lidong Bing
Abstract: Video Large Language Models (Video LLMs) have recently exhibited remarkable capabilities in general video understanding. However, they mainly focus on holistic comprehension and struggle with capturing fine-grained spatial and temporal details. Besides, the lack of high-quality object-level video instruction data and a comprehensive benchmark further hinders their advancements. To tackle these challenges, we introduce the VideoRefer Suite to empower Video LLM for finer-level spatial-temporal video understanding, i.e., enabling perception and reasoning on any objects throughout the video. Specially, we thoroughly develop VideoRefer Suite across three essential aspects: dataset, model, and benchmark. Firstly, we introduce a multi-agent data engine to meticulously curate a large-scale, high-quality object-level video instruction dataset, termed VideoRefer-700K. Next, we present the VideoRefer model, which equips a versatile spatial-temporal object encoder to capture precise regional and sequential representations. Finally, we meticulously create a VideoRefer-Bench to comprehensively assess the spatial-temporal understanding capability of a Video LLM, evaluating it across various aspects. Extensive experiments and analyses demonstrate that our VideoRefer model not only achieves promising performance on video referring benchmarks but also facilitates general video understanding capabilities.
Authors: Er Jin, Qihui Feng, Yongli Mou, Stefan Decker, Gerhard Lakemeyer, Oliver Simons, Johannes Stegmaier
Abstract: Logical image understanding involves interpreting and reasoning about the relationships and consistency within an image's visual content. This capability is essential in applications such as industrial inspection, where logical anomaly detection is critical for maintaining high-quality standards and minimizing costly recalls. Previous research in anomaly detection (AD) has relied on prior knowledge for designing algorithms, which often requires extensive manual annotations, significant computing power, and large amounts of data for training. Autoregressive, multimodal Vision Language Models (AVLMs) offer a promising alternative due to their exceptional performance in visual reasoning across various domains. Despite this, their application to logical AD remains unexplored. In this work, we investigate using AVLMs for logical AD and demonstrate that they are well-suited to the task. Combining AVLMs with format embedding and a logic reasoner, we achieve SOTA performance on public benchmarks, MVTec LOCO AD, with an AUROC of 86.0% and F1-max of 83.7%, along with explanations of anomalies. This significantly outperforms the existing SOTA method by a large margin.
Authors: Victor Nascimento Ribeiro, Nina S. T. Hirata
Abstract: Automatic License Plate Recognition (ALPR) involves extracting vehicle license plate information from image or a video capture. These systems have gained popularity due to the wide availability of low-cost surveillance cameras and advances in Deep Learning. Typically, video-based ALPR systems rely on multiple frames to detect the vehicle and recognize the license plates. Therefore, we propose a system capable of extracting exactly one frame per vehicle and recognizing its license plate characters from this singular image using an Optical Character Recognition (OCR) model. Early experiments show that this methodology is viable.
Authors: Niloufar Eghbali, Hassan Bagher-Ebadian, Tuka Alhanai, Mohammad M. Ghassemi
Abstract: Vision Transformers (ViTs) have shown promise in medical image semantic segmentation (MISS) by capturing long-range correlations. However, ViTs often struggle to model local spatial information effectively, which is essential for accurately segmenting fine anatomical details, particularly when applied to small datasets without extensive pre-training. We introduce Gabor and Laplacian of Gaussian Convolutional Swin Network (GLoG-CSUnet), a novel architecture enhancing Transformer-based models by incorporating learnable radiomic features. This approach integrates dynamically adaptive Gabor and Laplacian of Gaussian (LoG) filters to capture texture, edge, and boundary information, enhancing the feature representation processed by the Transformer model. Our method uniquely combines the long-range dependency modeling of Transformers with the texture analysis capabilities of Gabor and LoG features. Evaluated on the Synapse multi-organ and ACDC cardiac segmentation datasets, GLoG-CSUnet demonstrates significant improvements over state-of-the-art models, achieving a 1.14% increase in Dice score for Synapse and 0.99% for ACDC, with minimal computational overhead (only 15 and 30 additional parameters, respectively). GLoG-CSUnet's flexible design allows integration with various base models, offering a promising approach for incorporating radiomics-inspired feature extraction in Transformer architectures for medical image analysis. The code implementation is available on GitHub at: https://github.com/HAAIL/GLoG-CSUnet.
Authors: Tianyu Cui, Jinbin Bai, Guo-Hua Wang, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, Ye Shi
Abstract: Evaluating image captions typically relies on reference captions, which are costly to obtain and exhibit significant diversity and subjectivity. While reference-free evaluation metrics have been proposed, most focus on cross-modal evaluation between captions and images. Recent research has revealed that the modality gap generally exists in the representation of contrastive learning-based multi-modal systems, undermining the reliability of cross-modality metrics like CLIPScore. In this paper, we propose CAMScore, a cyclic reference-free automatic evaluation metric for image captioning models. To circumvent the aforementioned modality gap, CAMScore utilizes a text-to-image model to generate images from captions and subsequently evaluates these generated images against the original images. Furthermore, to provide fine-grained information for a more comprehensive evaluation, we design a three-level evaluation framework for CAMScore that encompasses pixel-level, semantic-level, and objective-level perspectives. Extensive experiment results across multiple benchmark datasets show that CAMScore achieves a superior correlation with human judgments compared to existing reference-based and reference-free metrics, demonstrating the effectiveness of the framework.
Authors: Xinbin Yuan, ZhaoHui Zheng, Yuxuan Li, Xialei Liu, Li Liu, Xiang Li, Qibin Hou, Ming-Ming Cheng
Abstract: While witnessed with rapid development, remote sensing object detection remains challenging for detecting high aspect ratio objects. This paper shows that large strip convolutions are good feature representation learners for remote sensing object detection and can detect objects of various aspect ratios well. Based on large strip convolutions, we build a new network architecture called Strip R-CNN, which is simple, efficient, and powerful. Unlike recent remote sensing object detectors that leverage large-kernel convolutions with square shapes, our Strip R-CNN takes advantage of sequential orthogonal large strip convolutions to capture spatial information. In addition, we enhance the localization capability of remote-sensing object detectors by decoupling the detection heads and equipping the localization head with strip convolutions to better localize the target objects. Extensive experiments on several benchmarks, e.g., DOTA, FAIR1M, HRSC2016, and DIOR, show that our Strip R-CNN can largely improve previous works. Notably, our 30M model achieves 82.75% mAP on DOTA-v1.0, setting a new state-of-the-art record.Code is available at https://github.com/YXB-NKU/Strip-R-CNN.
Authors: Eduarda Caldeira, Guray Ozgur, Tahar Chettaoui, Marija Ivanovska, Peter Peer, Fadi Boutros, Vitomir Struc, Naser Damer
Abstract: Despite the considerable performance improvements of face recognition algorithms in recent years, the same scientific advances responsible for this progress can also be used to create efficient ways to attack them, posing a threat to their secure deployment. Morphing attack detection (MAD) systems aim to detect a specific type of threat, morphing attacks, at an early stage, preventing them from being considered for verification in critical processes. Foundation models (FM) learn from extensive amounts of unlabeled data, achieving remarkable zero-shot generalization to unseen domains. Although this generalization capacity might be weak when dealing with domain-specific downstream tasks such as MAD, FMs can easily adapt to these settings while retaining the built-in knowledge acquired during pre-training. In this work, we recognize the potential of FMs to perform well in the MAD task when properly adapted to its specificities. To this end, we adapt FM CLIP architectures with LoRA weights while simultaneously training a classification header. The proposed framework, MADation surpasses our alternative FM and transformer-based frameworks and constitutes the first adaption of FMs to the MAD task. MADation presents competitive results with current MAD solutions in the literature and even surpasses them in several evaluation scenarios. To encourage reproducibility and facilitate further research in MAD, we publicly release the implementation of MADation at https: //github.com/gurayozgur/MADation
Authors: Jinyung Hong, Theodore P. Pavlic
Abstract: Fruit flies are established model systems for studying olfactory learning as they will readily learn to associate odors with both electric shock or sugar rewards. The mechanisms of the insect brain apparently responsible for odor learning form a relatively shallow neuronal architecture. Olfactory inputs are received by the antennal lobe (AL) of the brain, which produces an encoding of each odor mixture across ~50 sub-units known as glomeruli. Each of these glomeruli then projects its component of this feature vector to several of ~2000 so-called Kenyon Cells (KCs) in a region of the brain known as the mushroom body (MB). Fly responses to odors are generated by small downstream neutrophils that decode the higher-order representation from the MB. Research has shown that there is no recognizable pattern in the glomeruli--KC connections (and thus the particular higher-order representations); they are akin to fingerprints--even isogenic flies have different projections. Leveraging insights from this architecture, we propose KCNet, a single-hidden-layer neural network that contains sparse, randomized, binary weights between the input layer and the hidden layer and analytically learned weights between the hidden layer and the output layer. Furthermore, we also propose a dynamic optimization algorithm that enables the KCNet to increase performance beyond its structural limits by searching for a more efficient set of inputs. For odorant-perception tasks that predict the perceptual properties of an odorant, we show that KCNet outperforms existing data-driven approaches, such as XGBoost. For image classification tasks, KCNet achieves reasonable performance on benchmark datasets (MNIST, Fashion-MNIST, and EMNIST) without any data-augmentation methods or convolutional layers and shows a particularly fast running time.
Authors: \"Ozg\"un Turgut, Philip M\"uller, Paul Hager, Suprosanna Shit, Sophie Starck, Martin J. Menten, Eimo Martens, Daniel Rueckert
Abstract: Cardiovascular diseases (CVD) can be diagnosed using various diagnostic modalities. The electrocardiogram (ECG) is a cost-effective and widely available diagnostic aid that provides functional information of the heart. However, its ability to classify and spatially localise CVD is limited. In contrast, cardiac magnetic resonance (CMR) imaging provides detailed structural information of the heart and thus enables evidence-based diagnosis of CVD, but long scan times and high costs limit its use in clinical routine. In this work, we present a deep learning strategy for cost-effective and comprehensive cardiac screening solely from ECG. Our approach combines multimodal contrastive learning with masked data modelling to transfer domain-specific information from CMR imaging to ECG representations. In extensive experiments using data from 40,044 UK Biobank subjects, we demonstrate the utility and generalisability of our method for subject-specific risk prediction of CVD and the prediction of cardiac phenotypes using only ECG data. Specifically, our novel multimodal pre-training paradigm improves performance by up to 12.19 % for risk prediction and 27.59 % for phenotype prediction. In a qualitative analysis, we demonstrate that our learned ECG representations incorporate information from CMR image regions of interest. Our entire pipeline is publicly available at https://github.com/oetu/MMCL-ECG-CMR.
Authors: Mingyuan Meng, Michael Fulham, Dagan Feng, Lei Bi, Jinman Kim
Abstract: Deformable image registration aims to find a dense non-linear spatial correspondence between a pair of images, which is a crucial step for many medical tasks such as tumor growth monitoring and population analysis. Recently, Deep Neural Networks (DNNs) have been widely recognized for their ability to perform fast end-to-end registration. However, DNN-based registration needs to explore the spatial information of each image and fuse this information to characterize spatial correspondence. This raises an essential question: what is the optimal fusion strategy to characterize spatial correspondence? Existing fusion strategies (e.g., early fusion, late fusion) were empirically designed to fuse information by manually defined prior knowledge, which inevitably constrains the registration performance within the limits of empirical designs. In this study, we depart from existing empirically-designed fusion strategies and develop a data-driven fusion strategy for deformable image registration. To achieve this, we propose an Automatic Fusion network (AutoFuse) that provides flexibility to fuse information at many potential locations within the network. A Fusion Gate (FG) module is also proposed to control how to fuse information at each potential network location based on training data. Our AutoFuse can automatically optimize its fusion strategy during training and can be generalizable to both unsupervised registration (without any labels) and semi-supervised registration (with weak labels provided for partial training data). Extensive experiments on two well-benchmarked medical registration tasks (inter- and intra-patient registration) with eight public datasets show that our AutoFuse outperforms state-of-the-art unsupervised and semi-supervised registration methods.
Authors: Shezheng Song, Xiaopeng Li, Shasha Li, Shan Zhao, Jie Yu, Jun Ma, Xiaoguang Mao, Weimin Zhang
Abstract: We explore Multimodal Large Language Models (MLLMs), which integrate LLMs like GPT-4 to handle multimodal data, including text, images, audio, and more. MLLMs demonstrate capabilities such as generating image captions and answering image-based questions, bridging the gap towards real-world human-computer interactions and hinting at a potential pathway to artificial general intelligence. However, MLLMs still face challenges in addressing the semantic gap in multimodal data, which may lead to erroneous outputs, posing potential risks to society. Selecting the appropriate modality alignment method is crucial, as improper methods might require more parameters without significant performance improvements. This paper aims to explore modality alignment methods for LLMs and their current capabilities. Implementing effective modality alignment can help LLMs address environmental issues and enhance accessibility. The study surveys existing modality alignment methods for MLLMs, categorizing them into four groups: (1) Multimodal Converter, which transforms data into a format that LLMs can understand; (2) Multimodal Perceiver, which improves how LLMs percieve different types of data; (3) Tool Learning, which leverages external tools to convert data into a common format, usually text; and (4) Data-Driven Method, which teaches LLMs to understand specific data types within datasets.
Authors: Hong Nguyen, Cuong V. Nguyen, Shrikanth Narayanan, Benjamin Y. Xu, Michael Pazzani
Abstract: Primary open-angle glaucoma (POAG) is a chronic and progressive optic nerve condition that results in an acquired loss of optic nerve fibers and potential blindness. The gradual onset of glaucoma results in patients progressively losing their vision without being consciously aware of the changes. To diagnose POAG and determine its severity, patients must undergo a comprehensive dilated eye examination. In this work, we build a framework to rank, compare, and interpret the severity of glaucoma using fundus images. We introduce a siamese-based severity ranking using pairwise n-hidden comparisons. We additionally have a novel approach to explaining why a specific image is deemed more severe than others. Our findings indicate that the proposed severity ranking model surpasses traditional ones in terms of diagnostic accuracy and delivers improved saliency explanations.
Authors: Hao Zhang, Qi Wang, Jun Shi, Shihui Ying, Zhijie Wen
Abstract: Multi-modal Magnetic Resonance Imaging (MRI) offers complementary diagnostic information, but some modalities are limited by the long scanning time. To accelerate the whole acquisition process, MRI reconstruction of one modality from highly undersampled k-space data with another fully-sampled reference modality is an efficient solution. However, the misalignment between modalities, which is common in clinic practice, can negatively affect reconstruction quality. Existing deep learning-based methods that account for inter-modality misalignment perform better, but still share two main common limitations: (1) The spatial alignment task is not adaptively integrated with the reconstruction process, resulting in insufficient complementarity between the two tasks; (2) the entire framework has weak interpretability. In this paper, we construct a novel Deep Unfolding Network with Spatial Alignment, termed DUN-SA, to appropriately embed the spatial alignment task into the reconstruction process. Concretely, we derive a novel joint alignment-reconstruction model with a specially designed cross-modal spatial alignment term. By relaxing the model into cross-modal spatial alignment and multi-modal reconstruction tasks, we propose an effective algorithm to solve this model alternatively. Then, we unfold the iterative steps of the proposed algorithm and design corresponding network modules to build DUN-SA with interpretability. Through end-to-end training, we effectively compensate for spatial misalignment using only reconstruction loss, and utilize the progressively aligned reference modality to provide inter-modality prior to improve the reconstruction of the target modality. Comprehensive experiments on three real datasets demonstrate that our method exhibits superior reconstruction performance compared to state-of-the-art methods.
Authors: Salman Ul Hassan Dar, Marvin Seyfarth, Isabelle Ayx, Theano Papavassiliu, Stefan O. Schoenberg, Robert Malte Siepmann, Fabian Christopher Laqua, Jannik Kahmann, Norbert Frey, Bettina Bae{\ss}ler, Sebastian Foersch, Daniel Truhn, Jakob Nikolas Kather, Sandy Engelhardt
Abstract: AI models present a wide range of applications in the field of medicine. However, achieving optimal performance requires access to extensive healthcare data, which is often not readily available. Furthermore, the imperative to preserve patient privacy restricts patient data sharing with third parties and even within institutes. Recently, generative AI models have been gaining traction for facilitating open-data sharing by proposing synthetic data as surrogates of real patient data. Despite the promise, some of these models are susceptible to patient data memorization, where models generate patient data copies instead of novel synthetic samples. Considering the importance of the problem, surprisingly it has received relatively little attention in the medical imaging community. To this end, we assess memorization in unconditional latent diffusion models. We train latent diffusion models on CT, MR, and X-ray datasets for synthetic data generation. We then detect the amount of training data memorized utilizing our novel self-supervised copy detection approach and further investigate various factors that can influence memorization. Our findings show a surprisingly high degree of patient data memorization across all datasets. Comparison with non-diffusion generative models, such as autoencoders and generative adversarial networks, indicates that while latent diffusion models are more susceptible to memorization, overall they outperform non-diffusion models in synthesis quality. Further analyses reveal that using augmentation strategies, small architecture, and increasing dataset can reduce memorization while over-training the models can enhance it. Collectively, our results emphasize the importance of carefully training generative models on private medical imaging datasets, and examining the synthetic data to ensure patient privacy before sharing it for medical research and applications.
Authors: Haoyu Li, Hao Wu, Badong Chen
Abstract: Reconstructing visual stimuli from functional Magnetic Resonance Imaging fMRI enables fine-grained retrieval of brain activity. However, the accurate reconstruction of diverse details, including structure, background, texture, color, and more, remains challenging. The stable diffusion models inevitably result in the variability of reconstructed images, even under identical conditions. To address this challenge, we first uncover the neuroscientific perspective of diffusion methods, which primarily involve top-down creation using pre-trained knowledge from extensive image datasets, but tend to lack detail-driven bottom-up perception, leading to a loss of faithful details. In this paper, we propose NeuralDiffuser, which incorporates primary visual feature guidance to provide detailed cues in the form of gradients. This extension of the bottom-up process for diffusion models achieves both semantic coherence and detail fidelity when reconstructing visual stimuli. Furthermore, we have developed a novel guidance strategy for reconstruction tasks that ensures the consistency of repeated outputs with original images rather than with various outputs. Extensive experimental results on the Natural Senses Dataset (NSD) qualitatively and quantitatively demonstrate the advancement of NeuralDiffuser by comparing it against baseline and state-of-the-art methods horizontally, as well as conducting longitudinal ablation studies.
Authors: Stanley H. Chan
Abstract: The astonishing growth of generative tools in recent years has empowered many exciting applications in text-to-image generation and text-to-video generation. The underlying principle behind these generative tools is the concept of diffusion, a particular sampling mechanism that has overcome some shortcomings that were deemed difficult in the previous approaches. The goal of this tutorial is to discuss the essential ideas underlying the diffusion models. The target audience of this tutorial includes undergraduate and graduate students who are interested in doing research on diffusion models or applying these models to solve other problems.
Authors: Jiawu Tian, Liwei Xu, Xiaowei Zhang, Yongqi Li
Abstract: Training deep neural networks is a challenging task. In order to speed up training and enhance the performance of deep neural networks, we rectify the vanilla conjugate gradient as conjugate-gradient-like and incorporate it into the generic Adam, and thus propose a new optimization algorithm named CG-like-Adam for deep learning. Specifically, both the first-order and the second-order moment estimation of generic Adam are replaced by the conjugate-gradient-like. Convergence analysis handles the cases where the exponential moving average coefficient of the first-order moment estimation is constant and the first-order moment estimation is unbiased. Numerical experiments show the superiority of the proposed algorithm based on the CIFAR10/100 dataset.
Authors: Claus Hofmann, Simon Schmid, Bernhard Lehner, Daniel Klotz, Sepp Hochreiter
Abstract: Out-of-distribution (OOD) detection is critical when deploying machine learning models in the real world. Outlier exposure methods, which incorporate auxiliary outlier data in the training process, can drastically improve OOD detection performance compared to approaches without advanced training strategies. We introduce Hopfield Boosting, a boosting approach, which leverages modern Hopfield energy (MHE) to sharpen the decision boundary between the in-distribution and OOD data. Hopfield Boosting encourages the model to concentrate on hard-to-distinguish auxiliary outlier examples that lie close to the decision boundary between in-distribution and auxiliary outlier data. Our method achieves a new state-of-the-art in OOD detection with outlier exposure, improving the FPR95 metric from 2.28 to 0.92 on CIFAR-10 and from 11.76 to 7.94 on CIFAR-100.
Authors: Markus Wei{\ss}flog, Stefan Schubert, Peter Protzel, Peer Neubert
Abstract: Visual SLAM is a key technology for many autonomous systems. However, tracking loss can lead to the creation of disjoint submaps in multimap SLAM systems like ORB-SLAM3. Because of that, these systems employ submap merging strategies. As we show, these strategies are not always successful. In this paper, we investigate the impact of using modern VPR approaches for submap merging in visual SLAM. We argue that classical evaluation metrics are not sufficient to estimate the impact of a modern VPR component on the overall system. We show that naively replacing the VPR component does not leverage its full potential without requiring substantial interference in the original system. Because of that, we present a post-processing pipeline along with a set of metrics that allow us to estimate the impact of modern VPR components. We evaluate our approach on the NCLT and Newer College datasets using ORB-SLAM3 with NetVLAD and HDC-DELF as VPR components. Additionally, we present a simple approach for combining VPR with temporal consistency for map merging. We show that the map merging performance of ORB-SLAM3 can be improved. Building on these results, researchers in VPR can assess the potential of their approaches for SLAM systems.
Authors: Changchang Sun, Ren Wang, Yihua Zhang, Jinghan Jia, Jiancheng Liu, Gaowen Liu, Sijia Liu, Yan Yan
Abstract: Machine unlearning (MU), which seeks to erase the influence of specific unwanted data from already-trained models, is becoming increasingly vital in model editing, particularly to comply with evolving data regulations like the ``right to be forgotten''. Conventional approaches are predominantly model-based, typically requiring retraining or fine-tuning the model's weights to meet unlearning requirements. In this work, we approach the MU problem from a novel input perturbation-based perspective, where the model weights remain intact throughout the unlearning process. We demonstrate the existence of a proactive input-based unlearning strategy, referred to forget vector, which can be generated as an input-agnostic data perturbation and remains as effective as model-based approximate unlearning approaches. We also explore forget vector arithmetic, whereby multiple class-specific forget vectors are combined through simple operations (e.g., linear combinations) to generate new forget vectors for unseen unlearning tasks, such as forgetting arbitrary subsets across classes. Extensive experiments validate the effectiveness and adaptability of the forget vector, showcasing its competitive performance relative to state-of-the-art model-based methods. Codes are available at https://github.com/Changchangsun/Forget-Vector.
Authors: Motonari Kambara, Komei Sugiura
Abstract: This study addresses a task designed to predict the future success or failure of open-vocabulary object manipulation. In this task, the model is required to make predictions based on natural language instructions, egocentric view images before manipulation, and the given end-effector trajectories. Conventional methods typically perform success prediction only after the manipulation is executed, limiting their efficiency in executing the entire task sequence. We propose a novel approach that enables the prediction of success or failure by aligning the given trajectories and images with natural language instructions. We introduce Trajectory Encoder to apply learnable weighting to the input trajectories, allowing the model to consider temporal dynamics and interactions between objects and the end effector, improving the model's ability to predict manipulation outcomes accurately. We constructed a dataset based on the RT-1 dataset, a large-scale benchmark for open-vocabulary object manipulation tasks, to evaluate our method. The experimental results show that our method achieved a higher prediction accuracy than baseline approaches.
Authors: Syed Tahir Hussain Rizvi, Neel Kanwal, Muddasar Naeem, Alfredo Cuzzocrea, Antonio Coronato
Abstract: Time Series Forecasting (TSF) is an important application across many fields. There is a debate about whether Transformers, despite being good at understanding long sequences, struggle with preserving temporal relationships in time series data. Recent research suggests that simpler linear models might outperform or at least provide competitive performance compared to complex Transformer-based models for TSF tasks. In this paper, we propose a novel data-efficient architecture, GLinear, for multivariate TSF that exploits periodic patterns to provide better accuracy. It also provides better prediction accuracy by using a smaller amount of historical data compared to other state-of-the-art linear predictors. Four different datasets (ETTh1, Electricity, Traffic, and Weather) are used to evaluate the performance of the proposed predictor. A performance comparison with state-of-the-art linear architectures (such as NLinear, DLinear, and RLinear) and transformer-based time series predictor (Autoformer) shows that the GLinear, despite being parametrically efficient, significantly outperforms the existing architectures in most cases of multivariate TSF. We hope that the proposed GLinear opens new fronts of research and development of simpler and more sophisticated architectures for data and computationally efficient time-series analysis.
Authors: Abderrezzaq Sendjasni, Mohamed-Chaker Larabi
Abstract: Super-resolution (SR) techniques play a pivotal role in enhancing the quality of low-resolution images, particularly for applications such as security and surveillance, where accurate license plate recognition is crucial. This study proposes a novel framework that combines pixel-based loss with embedding similarity learning to address the unique challenges of license plate super-resolution (LPSR). The introduced pixel and embedding consistency loss (PECL) integrates a Siamese network and applies contrastive loss to force embedding similarities to improve perceptual and structural fidelity. By effectively balancing pixel-wise accuracy with embedding-level consistency, the framework achieves superior alignment of fine-grained features between high-resolution (HR) and super-resolved (SR) license plates. Extensive experiments on the CCPD dataset validate the efficacy of the proposed framework, demonstrating consistent improvements over state-of-the-art methods in terms of PSNR_RGB, PSNR_Y and optical character recognition (OCR) accuracy. These results highlight the potential of embedding similarity learning to advance both perceptual quality and task-specific performance in extreme super-resolution scenarios.