Authors: Youcef Ferdi
Abstract: The advances in computer vision made possible by deep learning technology are increasingly being used in precision agriculture to automate the detection and classification of plant diseases. Symptoms of plant diseases are often seen on their leaves. The leaf images in existing datasets have been collected either under controlled conditions or in the field. The majority of previous studies have focused on identifying leaf diseases using images captured in controlled laboratory settings, often achieving high performance. However, methods aimed at detecting and classifying leaf diseases in field images have generally exhibited lower performance. The objective of this study is to evaluate the impact of a data augmentation approach that involves removing complex backgrounds from leaf images on the classification performance of apple leaf diseases in images captured under real world conditions. To achieve this objective, the lightweight pre-trained MobileNetV2 deep learning model was fine-tuned and subsequently used to evaluate the impact of expanding the training dataset with background-removed images on classification performance. Experimental results show that this augmentation strategy enhances classification accuracy. Specifically, using the Adam optimizer, the proposed method achieved a classification accuracy of 98.71% on the Plant Pathology database, representing an approximately 3% improvement and outperforming state-of-the-art methods. This demonstrates the effectiveness of background removal as a data augmentation technique for improving the robustness of disease classification models in real-world conditions.
Authors: Yiyuan Pan, Yunzhe Xu, Zhe Liu, Hesheng Wang
Abstract: Humans navigate unfamiliar environments using the capabilities of episodic simulation and episodic memory. Developing imagination-based memory, analogous to episodic simulation and episodic memory, can enhance embodied agents' comprehension of the complex relationship between environments and objects. However, existing Vision-and-Language Navigation (VLN) agents fail to perform the aforementioned mechanism. We propose a novel architecture to help agents build a recurrent imaginative memory system. Specifically, the agent can maintain a reality-imagination hybrid global memory during navigation and expand the memory map through imaginative mechanisms and navigation actions. Correspondingly, we design a series of pre-training tasks to help the agent acquire fine-grained imaginative abilities. Our agents improve the state-of-the-art (SoTA) success rate (SR) by 7% while simultaneously imagining high-fidelity RGB representations for future scenes.
Authors: Li Jiakun, Wang Qingqing, Dong Hongbin, Li Kexin
Abstract: Current state-of-the-art vision models often utilize feature pyramids to extract multi-scale information, with the Feature Pyramid Network (FPN) being one of the most widely used classic architectures. However, traditional FPNs and their variants (e.g., AUGFPN, PAFPN) fail to fully address spatial misalignment on a global scale, leading to suboptimal performance in high-precision localization of objects. In this paper, we propose a novel Bidirectional Alignment Feature Pyramid Network (BAFPN), which aligns misaligned features globally through a Spatial Feature Alignment Module (SPAM) during the bottom-up information propagation phase. Subsequently, it further mitigates aliasing effects caused by cross-scale feature fusion via a fine-grained Semantic Alignment Module (SEAM) in the top-down phase. On the DOTAv1.5 dataset, BAFPN improves the baseline model's AP75, AP50, and mAP by 1.68%, 1.45%, and 1.34%, respectively. Additionally, BAFPN demonstrates significant performance gains when applied to various other advanced detectors.
Authors: Dylan Waldner, Shyamal Mitra
Abstract: This study takes a preliminary step toward teaching computers to recognize human emotions through Facial Emotion Recognition (FER). Transfer learning is applied using ResNeXt, EfficientNet models, and an ArcFace model originally trained on the facial verification task, leveraging the AffectNet database, a collection of human face images annotated with corresponding emotions. The findings highlight the value of congruent domain transfer learning, the challenges posed by imbalanced datasets in learning facial emotion patterns, and the effectiveness of pairwise learning in addressing class imbalances to enhance model performance on the FER task.
Authors: Boya Zeng, Yida Yin, Zhuang Liu
Abstract: A recent study has shown that large-scale visual datasets are very biased: they can be easily classified by modern neural networks. However, the concrete forms of bias among these datasets remain unclear. In this study, we propose a framework to identify the unique visual attributes distinguishing these datasets. Our approach applies various transformations to extract semantic, structural, boundary, color, and frequency information from datasets, and assess how much each type of information reflects their bias. We further decompose their semantic bias with object-level analysis, and leverage natural language methods to generate detailed, open-ended descriptions of each dataset's characteristics. Our work aims to help researchers understand the bias in existing large-scale pre-training datasets, and build more diverse and representative ones in the future. Our project page and code are available at http://boyazeng.github.io/understand_bias .
Authors: Anirudh S Chakravarthy, Shuai Kyle Zheng, Xin Huang, Sachithra Hemachandra, Xiao Zhang, Yuning Chai, Zhao Chen
Abstract: Fine-tuning pre-trained models has become invaluable in computer vision and robotics. Recent fine-tuning approaches focus on improving efficiency rather than accuracy by using a mixture of smaller learning rates or frozen backbones. To return the spotlight to model accuracy, we present PROFIT, one of the first optimizers specifically designed for incrementally fine-tuning converged models on new tasks or datasets. Unlike traditional optimizers such as SGD or Adam, which make minimal assumptions due to random initialization, PROFIT leverages the structure of a converged model to regularize the optimization process, leading to improved results. By employing a simple temporal gradient orthogonalization process, PROFIT outperforms traditional fine-tuning methods across various tasks: image classification, representation learning, and large-scale motion prediction. Moreover, PROFIT is encapsulated within the optimizer logic, making it easily integrated into any training pipeline with minimal engineering effort. A new class of fine-tuning optimizers like PROFIT can drive advancements as fine-tuning and incremental training become increasingly prevalent, reducing reliance on costly model training from scratch.
Authors: Farhad G. Zanjani, Hong Cai, Hanno Ackermann, Leila Mirvakhabova, Fatih Porikli
Abstract: This paper presents Planar Gaussian Splatting (PGS), a novel neural rendering approach to learn the 3D geometry and parse the 3D planes of a scene, directly from multiple RGB images. The PGS leverages Gaussian primitives to model the scene and employ a hierarchical Gaussian mixture approach to group them. Similar Gaussians are progressively merged probabilistically in the tree-structured Gaussian mixtures to identify distinct 3D plane instances and form the overall 3D scene geometry. In order to enable the grouping, the Gaussian primitives contain additional parameters, such as plane descriptors derived by lifting 2D masks from a general 2D segmentation model and surface normals. Experiments show that the proposed PGS achieves state-of-the-art performance in 3D planar reconstruction without requiring either 3D plane labels or depth supervision. In contrast to existing supervised methods that have limited generalizability and struggle under domain shift, PGS maintains its performance across datasets thanks to its neural rendering and scene-specific optimization mechanism, while also being significantly faster than existing optimization-based approaches.
Authors: Alberto Gonzalo Rodriguez Salgado, Maying Schen, Philipp Harzig, Peter Mayer, Jose M. Alvarez
Abstract: Robustness to out-of-distribution data is crucial for deploying modern neural networks. Recently, Vision Transformers, such as SegFormer for semantic segmentation, have shown impressive robustness to visual corruptions like blur or noise affecting the acquisition device. In this paper, we propose Channel Wise Feature Augmentation (CWFA), a simple yet efficient feature augmentation technique to improve the robustness of Vision Transformers for semantic segmentation. CWFA applies a globally estimated perturbation per encoder with minimal compute overhead during training. Extensive evaluations on Cityscapes and ADE20K, with three state-of-the-art Vision Transformer architectures : SegFormer, Swin Transformer, and Twins demonstrate that CWFA-enhanced models significantly improve robustness without affecting clean data performance. For instance, on Cityscapes, a CWFA-augmented SegFormer-B1 model yields up to 27.7% mIoU robustness gain on impulse noise compared to the non-augmented SegFormer-B1. Furthermore, CWFA-augmented SegFormer-B5 achieves a new state-of-the-art 84.3% retention rate, a 0.7% improvement over the recently published FAN+STL.
Authors: Ignazio Gallo, Mattia Gatti, Nicola Landro, Christian Loschiavo, Mirco Boschetti, Riccardo La Grassa
Abstract: Recent studies have shown that Convolutional Neural Networks (CNNs) achieve impressive results in crop segmentation of Satellite Image Time Series (SITS). However, the emergence of transformer networks in various vision tasks raises the question of whether they can outperform CNNs in this task as well. This paper presents a revised version of the Transformer-based Swin UNETR model, specifically adapted for crop segmentation of SITS. The proposed model demonstrates significant advancements, achieving a validation accuracy of 96.14% and a test accuracy of 95.26% on the Munich dataset, surpassing the previous best results of 93.55% for validation and 92.94% for the test. Additionally, the model's performance on the Lombardia dataset is comparable to UNet3D and superior to FPN and DeepLabV3. Experiments of this study indicate that the model will likely achieve comparable or superior accuracy to CNNs while requiring significantly less training time. These findings highlight the potential of transformer-based architectures for crop segmentation in SITS, opening new avenues for remote sensing applications.
Authors: Said Togru, Youssef Sameh Mostafa, Karim Lotfy
Abstract: This paper evaluates the use of metamorphic relations to enhance the robustness and real-world performance of machine learning models. We propose a Metamorphic Retraining Framework, which applies metamorphic relations to data and utilizes semi-supervised learning algorithms in an iterative and adaptive multi-cycle process. The framework integrates multiple semi-supervised retraining algorithms, including FixMatch, FlexMatch, MixMatch, and FullMatch, to automate the retraining, evaluation, and testing of models with specified configurations. To assess the effectiveness of this approach, we conducted experiments on CIFAR-10, CIFAR-100, and MNIST datasets using a variety of image processing models, both pretrained and non-pretrained. Our results demonstrate the potential of metamorphic retraining to significantly improve model robustness as we show in our results that each model witnessed an increase of an additional flat 17 percent on average in our robustness metric.
Authors: Gustavo P. C. P. da Luz, Gabriel Massuyoshi Sato, Luis Fernando Gomez Gonzalez, Juliana Freitag Borin
Abstract: The increasing urbanization and the growing number of vehicles in cities have underscored the need for efficient parking management systems. Traditional smart parking solutions often rely on sensors or cameras for occupancy detection, each with its limitations. Recent advancements in deep learning have introduced new YOLO models (YOLOv8, YOLOv9, YOLOv10, and YOLOv11), but these models have not been extensively evaluated in the context of smart parking systems, particularly when combined with Region of Interest (ROI) selection for object detection. Existing methods still rely on fixed polygonal ROI selections or simple pixel-based modifications, which limit flexibility and precision. This work introduces a novel approach that integrates Internet of Things, Edge Computing, and Deep Learning concepts, by using the latest YOLO models for vehicle detection. By exploring both edge and cloud computing, it was found that inference times on edge devices ranged from 1 to 92 seconds, depending on the hardware and model version. Additionally, a new pixel-wise post-processing ROI selection method is proposed for accurately identifying regions of interest to count vehicles in parking lot images. The proposed system achieved 99.68% balanced accuracy on a custom dataset of 3,484 images, offering a cost-effective smart parking solution that ensures precise vehicle detection while preserving data privacy
Authors: Armin Shafiee Sarvestani, Sheyang Tang, Zhou Wang
Abstract: Mesh quality assessment (MQA) models play a critical role in the design, optimization, and evaluation of mesh operation systems in a wide variety of applications. Current MQA models, whether model-based methods using topology-aware features or projection-based approaches working on rendered 2D projections, often fail to capture the intricate interactions between texture and 3D geometry. We introduce HybridMQA, a first-of-its-kind hybrid full-reference colored MQA framework that integrates model-based and projection-based approaches, capturing complex interactions between textural information and 3D structures for enriched quality representations. Our method employs graph learning to extract detailed 3D representations, which are then projected to 2D using a novel feature rendering process that precisely aligns them with colored projections. This enables the exploration of geometry-texture interactions via cross-attention, producing comprehensive mesh quality representations. Extensive experiments demonstrate HybridMQA's superior performance across diverse datasets, highlighting its ability to effectively leverage geometry-texture interactions for a thorough understanding of mesh quality. Our implementation will be made publicly available.
Authors: Tom\'a\v{s} Sou\v{c}ek, Prajwal Gatti, Michael Wray, Ivan Laptev, Dima Damen, Josef Sivic
Abstract: The goal of this work is to generate step-by-step visual instructions in the form of a sequence of images, given an input image that provides the scene context and the sequence of textual instructions. This is a challenging problem as it requires generating multi-step image sequences to achieve a complex goal while being grounded in a specific environment. Part of the challenge stems from the lack of large-scale training data for this problem. The contribution of this work is thus three-fold. First, we introduce an automatic approach for collecting large step-by-step visual instruction training data from instructional videos. We apply this approach to one million videos and create a large-scale, high-quality dataset of 0.6M sequences of image-text pairs. Second, we develop and train ShowHowTo, a video diffusion model capable of generating step-by-step visual instructions consistent with the provided input image. Third, we evaluate the generated image sequences across three dimensions of accuracy (step, scene, and task) and show our model achieves state-of-the-art results on all of them. Our code, dataset, and trained models are publicly available.
Authors: David Gimeno-G\'omez, Catarina Botelho, Anna Pompili, Alberto Abad, Carlos-D. Mart\'inez-Hinarejos
Abstract: Recent works in pathological speech analysis have increasingly relied on powerful self-supervised speech representations, leading to promising results. However, the complex, black-box nature of these embeddings and the limited research on their interpretability significantly restrict their adoption for clinical diagnosis. To address this gap, we propose a novel, interpretable framework specifically designed to support Parkinson's Disease (PD) diagnosis. Through the design of simple yet effective cross-attention mechanisms for both embedding- and temporal-level analysis, the proposed framework offers interpretability from two distinct but complementary perspectives. Experimental findings across five well-established speech benchmarks for PD detection demonstrate the framework's capability to identify meaningful speech patterns within self-supervised representations for a wide range of assessment tasks. Fine-grained temporal analyses further underscore its potential to enhance the interpretability of deep-learning pathological speech models, paving the way for the development of more transparent, trustworthy, and clinically applicable computer-assisted diagnosis systems in this domain. Moreover, in terms of classification accuracy, our method achieves results competitive with state-of-the-art approaches, while also demonstrating robustness in cross-lingual scenarios when applied to spontaneous speech production.
Authors: Dar-Yen Chen, Hmrishav Bandyopadhyay, Kai Zou, Yi-Zhe Song
Abstract: We introduce NitroFusion, a fundamentally different approach to single-step diffusion that achieves high-quality generation through a dynamic adversarial framework. While one-step methods offer dramatic speed advantages, they typically suffer from quality degradation compared to their multi-step counterparts. Just as a panel of art critics provides comprehensive feedback by specializing in different aspects like composition, color, and technique, our approach maintains a large pool of specialized discriminator heads that collectively guide the generation process. Each discriminator group develops expertise in specific quality aspects at different noise levels, providing diverse feedback that enables high-fidelity one-step generation. Our framework combines: (i) a dynamic discriminator pool with specialized discriminator groups to improve generation quality, (ii) strategic refresh mechanisms to prevent discriminator overfitting, and (iii) global-local discriminator heads for multi-scale quality assessment, and unconditional/conditional training for balanced generation. Additionally, our framework uniquely supports flexible deployment through bottom-up refinement, allowing users to dynamically choose between 1-4 denoising steps with the same model for direct quality-speed trade-offs. Through comprehensive experiments, we demonstrate that NitroFusion significantly outperforms existing single-step methods across multiple evaluation metrics, particularly excelling in preserving fine details and global consistency.
Authors: Aditya Dutt, Ishikaa Lunawat, Manpreet Kaur
Abstract: Large Foundation Models like Dust3r can produce high quality outputs such as pointmaps, camera intrinsics, and depth estimation, given stereo-image pairs as input. However, the application of these outputs on tasks like Visual Localization requires a large amount of inference time and compute resources. To address these limitations, in this paper, we propose the use of a knowledge distillation pipeline, where we aim to build a student-teacher model with Dust3r as the teacher and explore multiple architectures of student models that are trained using the 3D reconstructed points output by Dust3r. Our goal is to build student models that can learn scene-specific representations and output 3D points with replicable performance such as Dust3r. The data set we used to train our models is 12Scenes. We test two main architectures of models: a CNN-based architecture and a Vision Transformer based architecture. For each architecture, we also compare the use of pre-trained models against models built from scratch. We qualitatively compare the reconstructed 3D points output by the student model against Dust3r's and discuss the various features learned by the student model. We also perform ablation studies on the models through hyperparameter tuning. Overall, we observe that the Vision Transformer presents the best performance visually and quantitatively.
Authors: Lizhen Xu, Shanmin Pang, Wenzhao Qiu, Zehao Wu, Xiuxiu Bai, Kuizhi Mei, Jianru Xue
Abstract: Query-based models are extensively used in 3D object detection tasks, with a wide range of pre-trained checkpoints readily available online. However, despite their popularity, these models often require an excessive number of object queries, far surpassing the actual number of objects to detect. The redundant queries result in unnecessary computational and memory costs. In this paper, we find that not all queries contribute equally -- a significant portion of queries have a much smaller impact compared to others. Based on this observation, we propose an embarrassingly simple approach called \bd{G}radually \bd{P}runing \bd{Q}ueries (GPQ), which prunes queries incrementally based on their classification scores. It is straightforward to implement in any query-based method, as it can be seamlessly integrated as a fine-tuning step using an existing checkpoint after training. With GPQ, users can easily generate multiple models with fewer queries, starting from a checkpoint with an excessive number of queries. Experiments on various advanced 3D detectors show that GPQ effectively reduces redundant queries while maintaining performance. Using our method, model inference on desktop GPUs can be accelerated by up to 1.31x. Moreover, after deployment on edge devices, it achieves up to a 67.86\% reduction in FLOPs and a 76.38\% decrease in inference time. The code will be available at \url{https://github.com/iseri27/Gpq}.
Authors: Ting-Ruen Wei, Haowei Liu, Huei-Chung Hu, Xuyang Wu, Yi Fang, Hsin-Tai Wu
Abstract: We introduce a novel framework for representation learning in head pose estimation (HPE). Previously such a scheme was difficult due to head pose data sparsity, making triplet sampling infeasible. Recent progress in 3D generative adversarial networks (3D-aware GAN) has opened the door for easily sampling triplets (anchor, positive, negative). We perform contrastive learning on extensively augmented data including geometric transformations and demonstrate that contrastive learning allows networks to learn genuine features that contribute to accurate HPE. On the other hand, we observe that existing HPE works struggle to predict head poses as accurately when test image rotation matrices are slightly out of the training dataset distribution. Experiments show that our methodology performs on par with state-of-the-art models on standard test datasets and outperforms them when images are slightly rotated/ flipped or full range head pose. To the best of our knowledge, we are the first to deliver a true full range HPE model capable of accurately predicting any head pose including upside-down pose. Furthermore, we compared with other existing full-yaw range models and demonstrated superior results.
Authors: Zihui Xue, Joungbin An, Xitong Yang, Kristen Grauman
Abstract: While image captioning provides isolated descriptions for individual images, and video captioning offers one single narrative for an entire video clip, our work explores an important middle ground: progress-aware video captioning at the frame level. This novel task aims to generate temporally fine-grained captions that not only accurately describe each frame but also capture the subtle progression of actions throughout a video sequence. Despite the strong capabilities of existing leading vision language models, they often struggle to discern the nuances of frame-wise differences. To address this, we propose ProgressCaptioner, a captioning model designed to capture the fine-grained temporal dynamics within an action sequence. Alongside, we develop the FrameCap dataset to support training and the FrameCapEval benchmark to assess caption quality. The results demonstrate that ProgressCaptioner significantly surpasses leading captioning models, producing precise captions that accurately capture action progression and set a new standard for temporal precision in video captioning. Finally, we showcase practical applications of our approach, specifically in aiding keyframe selection and advancing video understanding, highlighting its broad utility.
Authors: Ismail Ismail Tijjani, Ahmad Abubakar Mustapha, Isma'il Tijjani Idris
Abstract: The Naira is Nigeria's official currency in daily transactions. This study presents the deployment and evaluation of Deep Learning (DL) models to classify Currency Notes (Naira) by denomination. Using a diverse dataset of 1,808 images of Naira notes captured under different conditions, trained the models employing different architectures and got the highest accuracy with MobileNetV2, the model achieved a high accuracy rate of in training of 90.75% and validation accuracy of 87.04% in classification tasks and demonstrated substantial performance across various scenarios. This model holds significant potential for practical applications, including automated cash handling systems, sorting systems, and assistive technology for the visually impaired. The results demonstrate how the model could boost the Nigerian economy's security and efficiency of financial transactions.
Authors: Liu Liu, Xinjie Wang, Jiaxiong Qiu, Tianwei Lin, Xiaolin Zhou, Zhizhong Su
Abstract: 3D scene reconstruction is a foundational problem in computer vision. Despite recent advancements in Neural Implicit Representations (NIR), existing methods often lack editability and compositional flexibility, limiting their use in scenarios requiring high interactivity and object-level manipulation. In this paper, we introduce the Gaussian Object Carver (GOC), a novel, efficient, and scalable framework for object-compositional 3D scene reconstruction. GOC leverages 3D Gaussian Splatting (GS), enriched with monocular geometry priors and multi-view geometry regularization, to achieve high-quality and flexible reconstruction. Furthermore, we propose a zero-shot Object Surface Completion (OSC) model, which uses 3D priors from 3d object data to reconstruct unobserved surfaces, ensuring object completeness even in occluded areas. Experimental results demonstrate that GOC improves reconstruction efficiency and geometric fidelity. It holds promise for advancing the practical application of digital twins in embodied AI, AR/VR, and interactive simulation environments.
Authors: Bo Wen, Haochen Zhang, Dirk-Uwe G. Bartsch, William R. Freeman, Truong Q. Nguyen, Cheolhong An
Abstract: Topological correctness is critical for segmentation of tubular structures. Existing topological segmentation loss functions are primarily based on the persistent homology of the image. They match the persistent features from the segmentation with the persistent features from the ground truth and minimize the difference between them. However, these methods suffer from an ambiguous matching problem since the matching only relies on the information in the topological space. In this work, we propose an effective and efficient Spatial-Aware Topological Loss Function that further leverages the information in the original spatial domain of the image to assist the matching of persistent features. Extensive experiments on images of various types of tubular structures show that the proposed method has superior performance in improving the topological accuracy of the segmentation compared with state-of-the-art methods.
Authors: Zhihang Lin, Mingbao Lin, Wengyi Zhan, Rongrong Ji
Abstract: Diffusion models suffer severe object repetition and local distortion when the inference resolution differs from its pre-trained resolution. We propose AccDiffusion v2, an accurate method for patch-wise higher-resolution diffusion extrapolation without training. Our in-depth analysis in this paper shows that using an identical text prompt for different patches leads to repetitive generation, while the absence of a prompt undermines image details. In response, our AccDiffusion v2 novelly decouples the vanilla image-content-aware prompt into a set of patch-content-aware prompts, each of which serves as a more precise description of a patch. Further analysis reveals that local distortion arises from inaccurate descriptions in prompts about the local structure of higher-resolution images. To address this issue, AccDiffusion v2, for the first time, introduces an auxiliary local structural information through ControlNet during higher-resolution diffusion extrapolation aiming to mitigate the local distortions. Finally, our analysis indicates that global semantic information is conducive to suppressing both repetitive generation and local distortion. Hence, our AccDiffusion v2 further proposes dilated sampling with window interaction for better global semantic information during higher-resolution diffusion extrapolation. We conduct extensive experiments, including both quantitative and qualitative comparisons, to demonstrate the efficacy of our AccDiffusion v2. The quantitative comparison shows that AccDiffusion v2 achieves state-of-the-art performance in image generation extrapolation without training. The qualitative comparison intuitively illustrates that AccDiffusion v2 effectively suppresses the issues of repetitive generation and local distortion in image generation extrapolation. Our code is available at \url{https://github.com/lzhxmu/AccDiffusion_v2}.
Authors: Salman Mohamadi, Gianfranco Doretto, Donald A. Adjeroh
Abstract: The success of self-supervised learning (SSL) has been the focus of multiple recent theoretical and empirical studies, including the role of data augmentation (in feature decoupling) as well as complete and dimensional representation collapse. While complete collapse is well-studied and addressed, dimensional collapse has only gain attention and addressed in recent years mostly using variants of redundancy reduction (aka whitening) techniques. In this paper, we further explore a complementary approach to whitening via feature decoupling for improved representation learning while avoiding representation collapse. In particular, we perform feature decoupling by early promotion of useful features via careful feature coloring. The coloring technique is developed based on a Bayesian prior of the augmented data, which is inherently encoded for feature decoupling. We show that our proposed framework is complementary to the state-of-the-art techniques, while outperforming both contrastive and recent non-contrastive methods. We also study the different effects of coloring approach to formulate it as a general complementary technique along with other baselines.
Authors: Haodong Chen, Lan Wang, Harry Yang, Ser-Nam Lim
Abstract: We introduce OmniCreator, a novel framework that can conduct text-prompted unified (image+video) generation as well as editing all in one place. OmniCreator acquires generative and universal editing capabilities in a self-supervised manner, taking original text-video pairs as conditions while utilizing the same video as a denoising target to learn the semantic correspondence between video and text. During inference, when presented with a text prompt and a video, OmniCreator is capable of generating a target that is faithful to both, achieving a universal editing effect that is unconstrained as opposed to existing editing work that primarily focuses on certain editing types or relies on additional controls (e.g., structural conditions, attention features, or DDIM inversion). On the other hand, when presented with a text prompt only, OmniCreator becomes generative, producing high-quality video as a result of the semantic correspondence learned. Importantly, we found that the same capabilities extend to images as is, making OmniCreator a truly unified framework. Further, due to the lack of existing generative video editing benchmarks, we introduce the OmniBench-99 dataset, designed to evaluate the performance of generative video editing models comprehensively. Extensive experiments demonstrate that OmniCreator exhibits substantial superiority over all other models.
Authors: Zeqing Zhang, Guangze Zheng, Xuebo Ji, Guanqi Chen, Ruixing Jia, Wentao Chen, Guanhua Chen, Liangjun Zhang, Jia Pan
Abstract: Granular materials (GMs) are ubiquitous in daily life. Understanding their properties is also important, especially in agriculture and industry. However, existing works require dedicated measurement equipment and also need large human efforts to handle a large number of particles. In this paper, we introduce a method for estimating the relative values of particle size and density from the video of the interaction with GMs. It is trained on a visuo-haptic learning framework inspired by a contact model, which reveals the strong correlation between GM properties and the visual-haptic data during the probe-dragging in the GMs. After training, the network can map the visual modality well to the haptic signal and implicitly characterize the relative distribution of particle properties in its latent embeddings, as interpreted in that contact model. Therefore, we can analyze GM properties using the trained encoder, and only visual information is needed without extra sensory modalities and human efforts for labeling. The presented GM property estimator has been extensively validated via comparison and ablation experiments. The generalization capability has also been evaluated and a real-world application on the beach is also demonstrated. Experiment videos are available at \url{https://sites.google.com/view/gmwork/vhlearning} .
Authors: Salman Mohamadi, Gianfranco Doretto, Donald A. Adjeroh
Abstract: Self Supervised learning (SSL) has demonstrated its effectiveness in feature learning from unlabeled data. Regarding this success, there have been some arguments on the role that mutual information plays within the SSL framework. Some works argued for increasing mutual information between representation of augmented views. Others suggest decreasing mutual information between them, while increasing task-relevant information. We ponder upon this debate and propose to revisit the core idea of SSL within the framework of partial information decomposition (PID). Thus, with SSL under PID we propose to replace traditional mutual information with the more general concept of joint mutual information to resolve the argument. Our investigation on instantiation of SSL within the PID framework leads to upgrading the existing pipelines by considering the components of the PID in the SSL models for improved representation learning. Accordingly we propose a general pipeline that can be applied to improve existing baselines. Our pipeline focuses on extracting the unique information component under the PID to build upon lower level supervision for generic feature learning and on developing higher-level supervisory signals for task-related feature learning. In essence, this could be interpreted as a joint utilization of local and global clustering. Experiments on four baselines and four datasets show the effectiveness and generality of our approach in improving existing SSL frameworks.
Authors: Gourang Pathak, Abhay Kumar, Sannidhya Rawat, Shikha Gupta
Abstract: This paper addresses the challenge of automated violence detection in video frames captured by surveillance cameras, specifically focusing on classifying scenes as "fight" or "non-fight." This task is critical for enhancing unmanned security systems, online content filtering, and related applications. We propose an approach using a 3D Convolutional Neural Network (3D CNN)-based model named X3D to tackle this problem. Our approach incorporates pre-processing steps such as tube extraction, volume cropping, and frame aggregation, combined with clustering techniques, to accurately localize and classify fight scenes. Extensive experimentation demonstrates the effectiveness of our method in distinguishing violent from non-violent events, providing valuable insights for advancing practical violence detection systems.
Authors: Yifan Jiao, Yunhao Li, Junhua Ding, Qing Yang, Song Fu, Heng Fan, Libo Zhang
Abstract: In this paper, we present a novel benchmark, GSOT3D, that aims at facilitating development of generic 3D single object tracking (SOT) in the wild. Specifically, GSOT3D offers 620 sequences with 123K frames, and covers a wide selection of 54 object categories. Each sequence is offered with multiple modalities, including the point cloud (PC), RGB image, and depth. This allows GSOT3D to support various 3D tracking tasks, such as single-modal 3D SOT on PC and multi-modal 3D SOT on RGB-PC or RGB-D, and thus greatly broadens research directions for 3D object tracking. To provide highquality per-frame 3D annotations, all sequences are labeled manually with multiple rounds of meticulous inspection and refinement. To our best knowledge, GSOT3D is the largest benchmark dedicated to various generic 3D object tracking tasks. To understand how existing 3D trackers perform and to provide comparisons for future research on GSOT3D, we assess eight representative point cloud-based tracking models. Our evaluation results exhibit that these models heavily degrade on GSOT3D, and more efforts are required for robust and generic 3D object tracking. Besides, to encourage future research, we present a simple yet effective generic 3D tracker, named PROT3D, that localizes the target object via a progressive spatial-temporal network and outperforms all current solutions by a large margin. By releasing GSOT3D, we expect to advance further 3D tracking in future research and applications. Our benchmark and model as well as the evaluation results will be publicly released at our webpage https://github.com/ailovejinx/GSOT3D.
Authors: Matthew Ciolino, Willie Maddox
Abstract: This study investigates the impact of ground sample distance (GSD) on the detection performance of various sized aircraft using the proprietary AllPlanes 120 dataset. The data set comprises 120 civilian, military and museum aircraft from multiple satellite/aerial sources collected over two years. Resolutions ranging from 2.4 to 0.3 meters GSD were simulated. Performance metrics were derived from a YOLOv8s model trained on down-sampled versions of zoom level 19 (0.3m GSD) imagery. The results indicate that a GSD of at least 0.86m is required to accurately detect most aircraft, particularly those with wingspans shorter than 20 meters. Due to weight constraints in high-altitude platforms, this GSD specification can inform camera design to minimize weight while maintaining detection accuracy.
Authors: Yuci Liang, Xinheng Lyu, Meidan Ding, Wenting Chen, Jipeng Zhang, Yuexiang Ren, Xiangjian He, Song Wu, Sen Yang, Xiyue Wang, Xiaohan Xing, Linlin Shen
Abstract: Recent advancements in computational pathology have produced patch-level Multi-modal Large Language Models (MLLMs), but these models are limited by their inability to analyze whole slide images (WSIs) comprehensively and their tendency to bypass crucial morphological features that pathologists rely on for diagnosis. To address these challenges, we first introduce WSI-Bench, a large-scale morphology-aware benchmark containing 180k VQA pairs from 9,850 WSIs across 30 cancer types, designed to evaluate MLLMs' understanding of morphological characteristics crucial for accurate diagnosis. Building upon this benchmark, we present WSI-LLaVA, a novel framework for gigapixel WSI understanding that employs a three-stage training approach: WSI-text alignment, feature space alignment, and task-specific instruction tuning. To better assess model performance in pathological contexts, we develop two specialized WSI metrics: WSI-Precision and WSI-Relevance. Experimental results demonstrate that WSI-LLaVA outperforms existing models across all capability dimensions, with a significant improvement in morphological analysis, establishing a clear correlation between morphological understanding and diagnostic accuracy.
Authors: Junda Wu, Hanjia Lyu, Yu Xia, Zhehao Zhang, Joe Barrow, Ishita Kumar, Mehrnoosh Mirtaheri, Hongjie Chen, Ryan A. Rossi, Franck Dernoncourt, Tong Yu, Ruiyi Zhang, Jiuxiang Gu, Nesreen K. Ahmed, Yu Wang, Xiang Chen, Hanieh Deilamsalehy, Namyong Park, Sungchul Kim, Huanrui Yang, Subrata Mitra, Zhengmian Hu, Nedim Lipka, Dang Nguyen, Yue Zhao, Jiebo Luo, Julian McAuley
Abstract: Multimodal Large Language Models (MLLMs) have become increasingly important due to their state-of-the-art performance and ability to integrate multiple data modalities, such as text, images, and audio, to perform complex tasks with high accuracy. This paper presents a comprehensive survey on personalized multimodal large language models, focusing on their architecture, training methods, and applications. We propose an intuitive taxonomy for categorizing the techniques used to personalize MLLMs to individual users, and discuss the techniques accordingly. Furthermore, we discuss how such techniques can be combined or adapted when appropriate, highlighting their advantages and underlying rationale. We also provide a succinct summary of personalization tasks investigated in existing research, along with the evaluation metrics commonly used. Additionally, we summarize the datasets that are useful for benchmarking personalized MLLMs. Finally, we outline critical open challenges. This survey aims to serve as a valuable resource for researchers and practitioners seeking to understand and advance the development of personalized multimodal large language models.
Authors: Liqiong Wang, Teng Jin, Jinyu Yang, Ales Leonardis, Fangyi Wang, Feng Zheng
Abstract: In the general domain, large multimodal models (LMMs) have achieved significant advancements, yet challenges persist in applying them to specific fields, especially agriculture. As the backbone of the global economy, agriculture confronts numerous challenges, with pests and diseases being particularly concerning due to their complexity, variability, rapid spread, and high resistance. This paper specifically addresses these issues. We construct the first multimodal instruction-following dataset in the agricultural domain, covering over 221 types of pests and diseases with approximately 400,000 data entries. This dataset aims to explore and address the unique challenges in pest and disease control. Based on this dataset, we propose a knowledge-infused training method to develop Agri-LLaVA, an agricultural multimodal conversation system. To accelerate progress in this field and inspire more researchers to engage, we design a diverse and challenging evaluation benchmark for agricultural pests and diseases. Experimental results demonstrate that Agri-LLaVA excels in agricultural multimodal conversation and visual understanding, providing new insights and approaches to address agricultural pests and diseases. By open-sourcing our dataset and model, we aim to promote research and development in LMMs within the agricultural domain and make significant contributions to tackle the challenges of agricultural pests and diseases. All resources can be found at https://github.com/Kki2Eve/Agri-LLaVA.
Authors: Yu Yuan, Xijun Wang, Yichen Sheng, Prateek Chennuri, Xingguang Zhang, Stanley Chan
Abstract: Image generation today can produce somewhat realistic images from text prompts. However, if one asks the generator to synthesize a particular camera setting such as creating different fields of view using a 24mm lens versus a 70mm lens, the generator will not be able to interpret and generate scene-consistent images. This limitation not only hinders the adoption of generative tools in photography applications but also exemplifies a broader issue of bridging the gap between the data-driven models and the physical world. In this paper, we introduce the concept of Generative Photography, a framework designed to control camera intrinsic settings during content generation. The core innovation of this work are the concepts of Dimensionality Lifting and Contrastive Camera Learning, which achieve continuous and consistent transitions for different camera settings. Experimental results show that our method produces significantly more scene-consistent photorealistic images than state-of-the-art models such as Stable Diffusion 3 and FLUX.
Authors: Tianyi Wang (Zhejiang University, Hangzhou, China), Zichen Wang (Zhejiang University, Hangzhou, China), Cong Wang (Zhejiang University, Hangzhou, China), Yuanchao Shu (Zhejiang University, Hangzhou, China), Ruilong Deng (Zhejiang University, Hangzhou, China), Peng Cheng (Zhejiang University, Hangzhou, China), Jiming Chen (Zhejiang University, Hangzhou, China)
Abstract: Object detection is a fundamental enabler for many real-time downstream applications such as autonomous driving, augmented reality and supply chain management. However, the algorithmic backbone of neural networks is brittle to imperceptible perturbations in the system inputs, which were generally known as misclassifying attacks. By targeting the real-time processing capability, a new class of latency attacks are reported recently. They exploit new attack surfaces in object detectors by creating a computational bottleneck in the post-processing module, that leads to cascading failure and puts the real-time downstream tasks at risks. In this work, we take an initial attempt to defend against this attack via background-attentive adversarial training that is also cognizant of the underlying hardware capabilities. We first draw system-level connections between latency attack and hardware capacity across heterogeneous GPU devices. Based on the particular adversarial behaviors, we utilize objectness loss as a proxy and build background attention into the adversarial training pipeline, and achieve a reasonable balance between clean and robust accuracy. The extensive experiments demonstrate the defense effectiveness of restoring real-time processing capability from $13$ FPS to $43$ FPS on Jetson Orin NX, with a better trade-off between the clean and robust accuracy.
Authors: Xueqing Wu, Yuheng Ding, Bingxuan Li, Pan Lu, Da Yin, Kai-Wei Chang, Nanyun Peng
Abstract: The ability of large vision-language models (LVLMs) to critique and correct their reasoning is an essential building block towards their self-improvement. However, a systematic analysis of such capabilities in LVLMs is still lacking. We propose VISCO, the first benchmark to extensively analyze the fine-grained critique and correction capabilities of LVLMs. Compared to existing work that uses a single scalar value to critique the entire reasoning [4], VISCO features dense and fine-grained critique, requiring LVLMs to evaluate the correctness of each step in the chain-of-thought and provide natural language explanations to support their judgments. Extensive evaluation of 24 LVLMs demonstrates that human-written critiques significantly enhance the performance after correction, showcasing the potential of the self-improvement strategy. However, the model-generated critiques are less helpful and sometimes detrimental to the performance, suggesting that critique is the crucial bottleneck. We identified three common patterns in critique failures: failure to critique visual perception, reluctance to "say no", and exaggerated assumption of error propagation. To address these issues, we propose an effective LookBack strategy that revisits the image to verify each piece of information in the initial reasoning. LookBack significantly improves critique and correction performance by up to 13.5%.
Authors: R. Mahmood, K. C. L. Wong, D. M. Reyes, N. D'Souza, L. Shi, J. Wu, P. Kaviani, M. Kalra, G. Wang, P. Yan, T. Syeda-Mahmood
Abstract: With the emergence of large-scale vision-language models, realistic radiology reports may be generated using only medical images as input guided by simple prompts. However, their practical utility has been limited due to the factual errors in their description of findings. In this paper, we propose a novel model for explainable fact-checking that identifies errors in findings and their locations indicated through the reports. Specifically, we analyze the types of errors made by automated reporting methods and derive a new synthetic dataset of images paired with real and fake descriptions of findings and their locations from a ground truth dataset. A new multi-label cross-modal contrastive regression network is then trained on this datsaset. We evaluate the resulting fact-checking model and its utility in correcting reports generated by several SOTA automated reporting tools on a variety of benchmark datasets with results pointing to over 40\% improvement in report quality through such error detection and correction.
Authors: Kangsan Kim, Geon Park, Youngwan Lee, Woongyeong Yeo, Sung Ju Hwang
Abstract: Recent advancements in video large multimodal models (LMMs) have significantly improved their video understanding and reasoning capabilities. However, their performance drops on out-of-distribution (OOD) tasks that are underrepresented in training data. Traditional methods like fine-tuning on OOD datasets are impractical due to high computational costs. While In-context learning (ICL) with demonstration examples has shown promising generalization performance in language tasks and image-language tasks without fine-tuning, applying ICL to video-language tasks faces challenges due to the limited context length in Video LMMs, as videos require longer token lengths. To address these issues, we propose VideoICL, a novel video in-context learning framework for OOD tasks that introduces a similarity-based relevant example selection strategy and a confidence-based iterative inference approach. This allows to select the most relevant examples and rank them based on similarity, to be used for inference. If the generated response has low confidence, our framework selects new examples and performs inference again, iteratively refining the results until a high-confidence response is obtained. This approach improves OOD video understanding performance by extending effective context length without incurring high costs. The experimental results on multiple benchmarks demonstrate significant performance gains, especially in domain-specific scenarios, laying the groundwork for broader video comprehension applications. Code will be released at https://github.com/KangsanKim07/VideoICL
Authors: Fan-Yun Sun, Weiyu Liu, Siyi Gu, Dylan Lim, Goutam Bhat, Federico Tombari, Manling Li, Nick Haber, Jiajun Wu
Abstract: Open-universe 3D layout generation arranges unlabeled 3D assets conditioned on language instruction. Large language models (LLMs) struggle with generating physically plausible 3D scenes and adherence to input instructions, particularly in cluttered scenes. We introduce LayoutVLM, a framework and scene layout representation that exploits the semantic knowledge of Vision-Language Models (VLMs) and supports differentiable optimization to ensure physical plausibility. LayoutVLM employs VLMs to generate two mutually reinforcing representations from visually marked images, and a self-consistent decoding process to improve VLMs spatial planning. Our experiments show that LayoutVLM addresses the limitations of existing LLM and constraint-based approaches, producing physically plausible 3D layouts better aligned with the semantic intent of input language instructions. We also demonstrate that fine-tuning VLMs with the proposed scene layout representation extracted from existing scene datasets can improve performance.
Authors: Xiangyong Lu, Masanori Suganuma, Takayuki Okatani
Abstract: In real-world applications of image recognition tasks, such as human pose estimation, cameras often capture objects, like human bodies, at low resolutions. This scenario poses a challenge in extracting and leveraging multi-scale features, which is often essential for precise inference. To address this challenge, we propose a new attention mechanism, named cascaded multi-scale attention (CMSA), tailored for use in CNN-ViT hybrid architectures, to handle low-resolution inputs effectively. The design of CMSA enables the extraction and seamless integration of features across various scales without necessitating the downsampling of the input image or feature maps. This is achieved through a novel combination of grouped multi-head self-attention mechanisms with window-based local attention and cascaded fusion of multi-scale features over different scales. This architecture allows for the effective handling of features across different scales, enhancing the model's ability to perform tasks such as human pose estimation, head pose estimation, and more with low-resolution images. Our experimental results show that the proposed method outperforms existing state-of-the-art methods in these areas with fewer parameters, showcasing its potential for broad application in real-world scenarios where capturing high-resolution images is not feasible. Code is available at https://github.com/xyongLu/CMSA.
Authors: Pritesh Prakash, Ashish Jacob Sam
Abstract: In deep learning, the loss function plays a crucial role in optimizing the network. Many recent innovations in loss techniques have been made, and various margin-based angular loss functions (metric loss) have been designed particularly for face recognition. The concept of transformers is already well-researched and applied in many facets of machine vision. This paper presents a technique for loss evaluation that uses a transformer network as an additive loss in the face recognition domain. The standard metric loss function typically takes the final embedding of the main CNN backbone as its input. Here, we employ a transformer-metric loss, a combined approach that integrates both transformer-loss and metric-loss. This research intends to analyze the transformer behavior on the convolution output when the CNN outcome is arranged in a sequential vector. The transformer encoder takes input from the contextual vectors obtained from the final convolution layer of the network. With this technique, we use transformer loss with various base metric-loss functions to evaluate the effect of the combined loss functions. We observe that such a configuration allows the network to achieve SoTA results on various validation datasets with some limitations. This research expands the role of transformers in the machine vision domain and opens new possibilities for exploring transformers as a loss function.
Authors: Jinzhi Zhang, Feng Xiong, Mu Xu
Abstract: Autoregressive transformers have revolutionized high-fidelity image generation. One crucial ingredient lies in the tokenizer, which compresses high-resolution image patches into manageable discrete tokens with a scanning or hierarchical order suitable for large language models. Extending these tokenizers to 3D generation, however, presents a significant challenge: unlike image patches that naturally exhibit spatial sequence and multi-scale relationships, 3D data lacks an inherent order, making it difficult to compress into fewer tokens while preserving structural details. To address this, we introduce the Variational Tokenizer (VAT), which transforms unordered 3D data into compact latent tokens with an implicit hierarchy, suited for efficient and high-fidelity coarse-to-fine autoregressive modeling. VAT begins with an in-context transformer, which compress numerous unordered 3D features into a reduced token set with minimal information loss. This latent space is then mapped to a Gaussian distribution for residual quantization, with token counts progressively increasing across scales. In this way, tokens at different scales naturally establish the interconnections by allocating themselves into different subspaces within the same Gaussian distribution, facilitating discrete modeling of token relationships across scales. During the decoding phase, a high-resolution triplane is utilized to convert these compact latent tokens into detailed 3D shapes. Extensive experiments demonstrate that VAT enables scalable and efficient 3D generation, outperforming existing methods in quality, efficiency, and generalization. Remarkably, VAT achieves up to a 250x compression, reducing a 1MB mesh to just 3.9KB with a 96% F-score, and can further compress to 256 int8 tokens, achieving a 2000x reduction while maintaining a 92% F-score.
Authors: Zhibo Yang, Jun Tang, Zhaohai Li, Pengfei Wang, Jianqiang Wan, Humen Zhong, Xuejing Liu, Mingkun Yang, Peng Wang, Yuliang Liu, LianWen Jin, Xiang Bai, Shuai Bai, Junyang Lin
Abstract: Large Multimodal Models (LMMs) have demonstrated impressive performance on recognizing document images with natural language instructions. However, it remains unclear to what extent capabilities in literacy with rich structure and fine-grained visual challenges. The current landscape lacks a comprehensive benchmark to effectively measure the literate capabilities of LMMs. Existing benchmarks are often limited by narrow scenarios and specified tasks. To this end, we introduce CC-OCR, a comprehensive benchmark that possess a diverse range of scenarios, tasks, and challenges. CC-OCR comprises four OCR-centric tracks: multi-scene text reading, multilingual text reading, document parsing, and key information extraction. It includes 39 subsets with 7,058 full annotated images, of which 41% are sourced from real applications, being released for the first time. Furthermore, we evaluate nine prominent LMMs and reveal both the strengths and weaknesses of these models, particularly in text grounding, multi-orientation, and hallucination of repetition. CC-OCR aims to comprehensively evaluate the capabilities of LMMs on OCR-centered tasks, driving advancement in LMMs.
Authors: Renan A. Rojas-Gomez, Minh N. Do
Abstract: State-of-the-art Style Transfer methods often leverage pre-trained encoders optimized for discriminative tasks, which may not be ideal for image synthesis. This can result in significant artifacts and loss of photorealism. Motivated by the ability of multiscale geometric image representations to capture fine-grained details and global structure, we propose GIST: Geometric-based Image Style Transfer, a novel Style Transfer technique that exploits the geometric properties of content and style images. GIST replaces the standard Neural Style Transfer autoencoding framework with a multiscale image expansion, preserving scene details without the need for post-processing or training. Our method matches multiresolution and multidirectional representations such as Wavelets and Contourlets by solving an optimal transport problem, leading to an efficient texture transferring. Experiments show that GIST is on-par or outperforms recent photorealistic Style Transfer approaches while significantly reducing the processing time with no model training.
Authors: Zixuan Hu, Yongxian Wei, Li Shen, Chun Yuan, Dacheng Tao
Abstract: Large Language Models (LLMs) such as ChatGPT demonstrate strong few-shot adaptability without requiring fine-tuning, positioning them ideal for data-limited and real-time applications. However, this adaptability has not yet been replicated in current Visual Foundation Models (VFMs), which require explicit fine-tuning with sufficient tuning data. Besides, the pretraining-finetuning paradigm has led to the surge of numerous task-specific modular components, such as Low-Rank Adaptation (LoRA). For the first time, we explore the potential of reusing diverse pre-tuned LoRAs without accessing their original training data, to achieve tuning-free few-shot adaptation in VFMs. Our framework, LoRA Recycle, distills a meta-LoRA from diverse pre-tuned LoRAs with a meta-learning objective, using surrogate data generated inversely from pre-tuned LoRAs themselves. The VFM, once equipped with the meta-LoRA, is empowered to solve new few-shot tasks in a single forward pass, akin to the in-context learning of LLMs. Additionally, we incorporate a double-efficient mechanism tailored to our framework, significantly accelerating the meta-training process while maintaining or even improving performance. Extensive experiments across various few-shot classification benchmarks across both in- and cross-domain scenarios demonstrate the superiority of our framework.
Authors: Qisen Wang, Yifan Zhao, Jiawei Ma, Jia Li
Abstract: Novel view synthesis under sparse views has been a long-term important challenge in 3D reconstruction. Existing works mainly rely on introducing external semantic or depth priors to supervise the optimization of 3D representations. However, the diffusion model, as an external prior that can directly provide visual supervision, has always underperformed in sparse-view 3D reconstruction using Score Distillation Sampling (SDS) due to the low information entropy of sparse views compared to text, leading to optimization challenges caused by mode deviation. To this end, we present a thorough analysis of SDS from the mode-seeking perspective and propose Inline Prior Guided Score Matching (IPSM), which leverages visual inline priors provided by pose relationships between viewpoints to rectify the rendered image distribution and decomposes the original optimization objective of SDS, thereby offering effective diffusion visual guidance without any fine-tuning or pre-training. Furthermore, we propose the IPSM-Gaussian pipeline, which adopts 3D Gaussian Splatting as the backbone and supplements depth and geometry consistency regularization based on IPSM to further improve inline priors and rectified distribution. Experimental results on different public datasets show that our method achieves state-of-the-art reconstruction quality. The code is released at https://github.com/iCVTEAM/IPSM.
Authors: Jikai Wang, Huan Zheng, Jianbing Shen
Abstract: Lightweight image super-resolution (SR) methods aim at increasing the resolution and restoring the details of an image using a lightweight neural network. However, current lightweight SR methods still suffer from inferior performance and unpleasant details. Our analysis reveals that these methods are hindered by constrained feature diversity, which adversely impacts feature representation and detail recovery. To respond this issue, we propose a simple yet effective baseline called CubeFormer, designed to enhance feature richness by completing holistic information aggregation. To be specific, we introduce cube attention, which expands 2D attention to 3D space, facilitating exhaustive information interactions, further encouraging comprehensive information extraction and promoting feature variety. In addition, we inject block and grid sampling strategies to construct intra-cube transformer blocks (Intra-CTB) and inter-cube transformer blocks (Inter-CTB), which perform local and global modeling, respectively. Extensive experiments show that our CubeFormer achieves state-of-the-art performance on commonly used SR benchmarks. Our source code and models will be publicly available.
Authors: Jungwon Park, Jungmin Ko, Dongnam Byun, Jangwon Suh, Wonjong Rhee
Abstract: Recent text-to-image diffusion models leverage cross-attention layers, which have been effectively utilized to enhance a range of visual generative tasks. However, our understanding of cross-attention layers remains somewhat limited. In this study, we present a method for constructing Head Relevance Vectors (HRVs) that align with useful visual concepts. An HRV for a given visual concept is a vector with a length equal to the total number of cross-attention heads, where each element represents the importance of the corresponding head for the given visual concept. We develop and employ an ordered weakening analysis to demonstrate the effectiveness of HRVs as interpretable features. To demonstrate the utility of HRVs, we propose concept strengthening and concept adjusting methods and apply them to enhance three visual generative tasks. We show that misinterpretations of polysemous words in image generation can be corrected in most cases, five challenging attributes in image editing can be successfully modified, and catastrophic neglect in multi-concept generation can be mitigated. Overall, our work provides an advancement in understanding cross-attention layers and introduces new approaches for fine-controlling these layers at the head level.
Authors: Kazuto Nakashima, Xiaowen Liu, Tomoya Miyawaki, Yumi Iwashita, Ryo Kurazume
Abstract: Building LiDAR generative models holds promise as powerful data priors for restoration, scene manipulation, and scalable simulation in autonomous mobile robots. In recent years, approaches using diffusion models have emerged, significantly improving training stability and generation quality. Despite the success of diffusion models, generating high-quality samples requires numerous iterations of running neural networks, and the increasing computational cost can pose a barrier to robotics applications. To address this challenge, this paper presents R2Flow, a fast and high-fidelity generative model for LiDAR data. Our method is based on rectified flows that learn straight trajectories, simulating data generation with much fewer sampling steps against diffusion models. We also propose a efficient Transformer-based model architecture for processing the image representation of LiDAR range and reflectance measurements. Our experiments on the unconditional generation of the KITTI-360 dataset demonstrate the effectiveness of our approach in terms of both efficiency and quality.
Authors: Jun Hu, Zhang Chen, Zhong Li, Yi Xu, Juyong Zhang
Abstract: Recently, several studies have combined Gaussian Splatting to obtain scene representations with language embeddings for open-vocabulary 3D scene understanding. While these methods perform well, they essentially require very dense multi-view inputs, limiting their applicability in real-world scenarios. In this work, we propose SparseLGS to address the challenge of 3D scene understanding with pose-free and sparse view input images. Our method leverages a learning-based dense stereo model to handle pose-free and sparse inputs, and a three-step region matching approach to address the multi-view semantic inconsistency problem, which is especially important for sparse inputs. Different from directly learning high-dimensional CLIP features, we extract low-dimensional information and build bijections to avoid excessive learning and storage costs. We introduce a reconstruction loss during semantic training to improve Gaussian positions and shapes. To the best of our knowledge, we are the first to address the 3D semantic field problem with sparse pose-free inputs. Experimental results show that SparseLGS achieves comparable quality when reconstructing semantic fields with fewer inputs (3-4 views) compared to previous SOTA methods with dense input. Besides, when using the same sparse input, SparseLGS leads significantly in quality and heavily improves the computation speed (5$\times$ speedup). Project page: {\tt\small \url{https://ustc3dv.github.io/SparseLGS}}
Authors: Javier Ure\~na Santiago, Thomas Str\"ohle, Antonio Rodr\'iguez-S\'anchez, Ruth Breu
Abstract: Microorganism enumeration is an essential task in many applications, such as assessing contamination levels or ensuring health standards when evaluating surface cleanliness. However, it's traditionally performed by human-supervised methods that often require manual counting, making it tedious and time-consuming. Previous research suggests automating this task using computer vision and machine learning methods, primarily through instance segmentation or density estimation techniques. This study conducts a comparative analysis of vision transformers (ViTs) for weakly-supervised counting in microorganism enumeration, contrasting them with traditional architectures such as ResNet and investigating ViT-based models such as TransCrowd. We trained different versions of ViTs as the architectural backbone for feature extraction using four microbiology datasets to determine potential new approaches for total microorganism enumeration in images. Results indicate that while ResNets perform better overall, ViTs performance demonstrates competent results across all datasets, opening up promising lines of research in microorganism enumeration. This comparative study contributes to the field of microbial image analysis by presenting innovative approaches to the recurring challenge of microorganism enumeration and by highlighting the capabilities of ViTs in the task of regression counting.
Authors: Miroslav Purkrabek, Jiri Matas
Abstract: Current Human Pose Estimation methods have achieved significant improvements. However, state-of-the-art models ignore out-of-image keypoints and use uncalibrated heatmaps as keypoint location representations. To address these limitations, we propose ProbPose, which predicts for each keypoint: a calibrated probability of keypoint presence at each location in the activation window, the probability of being outside of it, and its predicted visibility. To address the lack of evaluation protocols for out-of-image keypoints, we introduce the CropCOCO dataset and the Extended OKS (Ex-OKS) metric, which extends OKS to out-of-image points. Tested on COCO, CropCOCO, and OCHuman, ProbPose shows significant gains in out-of-image keypoint localization while also improving in-image localization through data augmentation. Additionally, the model improves robustness along the edges of the bounding box and offers better flexibility in keypoint evaluation. The code and models are available on https://mirapurkrabek.github.io/ProbPose/ for research purposes.
Authors: Mingzhe Zheng, Yongqi Xu, Haojian Huang, Xuran Ma, Yexin Liu, Wenjie Shu, Yatian Pang, Feilong Tang, Qifeng Chen, Harry Yang, Ser-Nam Lim
Abstract: Current video generation models excel at generating short clips but still struggle with creating multi-shot, movie-like videos. Existing models trained on large-scale data on the back of rich computational resources are unsurprisingly inadequate for maintaining a logical storyline and visual consistency across multiple shots of a cohesive script since they are often trained with a single-shot objective. To this end, we propose VideoGen-of-Thought (VGoT), a collaborative and training-free architecture designed specifically for multi-shot video generation. VGoT is designed with three goals in mind as follows. Multi-Shot Video Generation: We divide the video generation process into a structured, modular sequence, including (1) Script Generation, which translates a curt story into detailed prompts for each shot; (2) Keyframe Generation, responsible for creating visually consistent keyframes faithful to character portrayals; and (3) Shot-Level Video Generation, which transforms information from scripts and keyframes into shots; (4) Smoothing Mechanism that ensures a consistent multi-shot output. Reasonable Narrative Design: Inspired by cinematic scriptwriting, our prompt generation approach spans five key domains, ensuring logical consistency, character development, and narrative flow across the entire video. Cross-Shot Consistency: We ensure temporal and identity consistency by leveraging identity-preserving (IP) embeddings across shots, which are automatically created from the narrative. Additionally, we incorporate a cross-shot smoothing mechanism, which integrates a reset boundary that effectively combines latent features from adjacent shots, resulting in smooth transitions and maintaining visual coherence throughout the video. Our experiments demonstrate that VGoT surpasses existing video generation methods in producing high-quality, coherent, multi-shot videos.
Authors: Jingyu Gong, Chong Zhang, Fengqi Liu, Ke Fan, Qianyu Zhou, Xin Tan, Zhizhong Zhang, Yuan Xie, Lizhuang Ma
Abstract: Human motion generation is a long-standing problem, and scene-aware motion synthesis has been widely researched recently due to its numerous applications. Prevailing methods rely heavily on paired motion-scene data whose quantity is limited. Meanwhile, it is difficult to generalize to diverse scenes when trained only on a few specific ones. Thus, we propose a unified framework, termed Diffusion Implicit Policy (DIP), for scene-aware motion synthesis, where paired motion-scene data are no longer necessary. In this framework, we disentangle human-scene interaction from motion synthesis during training and then introduce an interaction-based implicit policy into motion diffusion during inference. Synthesized motion can be derived through iterative diffusion denoising and implicit policy optimization, thus motion naturalness and interaction plausibility can be maintained simultaneously. The proposed implicit policy optimizes the intermediate noised motion in a GAN Inversion manner to maintain motion continuity and control keyframe poses though the ControlNet branch and motion inpainting. For long-term motion synthesis, we introduce motion blending for stable transitions between multiple sub-tasks, where motions are fused in rotation power space and translation linear space. The proposed method is evaluated on synthesized scenes with ShapeNet furniture, and real scenes from PROX and Replica. Results show that our framework presents better motion naturalness and interaction plausibility than cutting-edge methods. This also indicates the feasibility of utilizing the DIP for motion synthesis in more general tasks and versatile scenes. https://jingyugong.github.io/DiffusionImplicitPolicy/
Authors: Sepand Dyanatkar, Angran Li, Alexander Dungate
Abstract: Climate change's destruction of marine biodiversity is threatening communities and economies around the world which rely on healthy oceans for their livelihoods. The challenge of applying computer vision to niche, real-world domains such as ocean conservation lies in the dynamic and diverse environments where traditional top-down learning struggle with long-tailed distributions, generalization, and domain transfer. Scalable species identification for ocean monitoring is particularly difficult due to the need to adapt models to new environments and identify rare or unseen species. To overcome these limitations, we propose leveraging bottom-up, open-domain learning frameworks as a resilient, scalable solution for image and video analysis in marine applications. Our preliminary demonstration uses pretrained vision-language models (VLMs) combined with retrieval-augmented generation (RAG) as grounding, leaving the door open for numerous architectural, training and engineering optimizations. We validate this approach through a preliminary application in classifying fish from video onboard fishing vessels, demonstrating impressive emergent retrieval and prediction capabilities without domain-specific training or knowledge of the task itself.
Authors: Indronil Bhattacharjee, Al-Mahmud, Tareq Mahmud
Abstract: Diabetic Retinopathy is one of the most familiar diseases and is a diabetes complication that affects eyes. Initially, diabetic retinopathy may cause no symptoms or only mild vision problems. Eventually, it can cause blindness. So early detection of symptoms could help to avoid blindness. In this paper, we present some experiments on some features of diabetic retinopathy, like properties of exudates, properties of blood vessels and properties of microaneurysm. Using the features, we can classify healthy, mild non-proliferative, moderate non-proliferative, severe non-proliferative and proliferative stages of DR. Support Vector Machine, Random Forest and Naive Bayes classifiers are used to classify the stages. Finally, Random Forest is found to be the best for higher accuracy, sensitivity and specificity of 76.5%, 77.2% and 93.3% respectively.
Authors: Zhiyuan Chen, Fan Lu, Guo Yu, Bin Li, Sanqing Qu, Yuan Huang, Changhong Fu, Guang Chen
Abstract: Tracking the 6DoF pose of unknown objects in monocular RGB video sequences is crucial for robotic manipulation. However, existing approaches typically rely on accurate depth information, which is non-trivial to obtain in real-world scenarios. Although depth estimation algorithms can be employed, geometric inaccuracy can lead to failures in RGBD-based pose tracking methods. To address this challenge, we introduce GSGTrack, a novel RGB-based pose tracking framework that jointly optimizes geometry and pose. Specifically, we adopt 3D Gaussian Splatting to create an optimizable 3D representation, which is learned simultaneously with a graph-based geometry optimization to capture the object's appearance features and refine its geometry. However, the joint optimization process is susceptible to perturbations from noisy pose and geometry data. Thus, we propose an object silhouette loss to address the issue of pixel-wise loss being overly sensitive to pose noise during tracking. To mitigate the geometric ambiguities caused by inaccurate depth information, we propose a geometry-consistent image pair selection strategy, which filters out low-confidence pairs and ensures robust geometric optimization. Extensive experiments on the OnePose and HO3D datasets demonstrate the effectiveness of GSGTrack in both 6DoF pose tracking and object reconstruction.
Authors: Wenxuan Wang, Chenglei Wang, Huihui Qi, Menghao Ye, Xuelin Qian, Peng Wang, Yanning Zhang
Abstract: With the wide application of deep neural network models in various computer vision tasks, there has been a proliferation of adversarial example generation strategies aimed at deeply exploring model security. However, existing adversarial training defense models, which rely on single or limited types of attacks under a one-time learning process, struggle to adapt to the dynamic and evolving nature of attack methods. Therefore, to achieve defense performance improvements for models in long-term applications, we propose a novel Sustainable Self-Evolution Adversarial Training (SSEAT) framework. Specifically, we introduce a continual adversarial defense pipeline to realize learning from various kinds of adversarial examples across multiple stages. Additionally, to address the issue of model catastrophic forgetting caused by continual learning from ongoing novel attacks, we propose an adversarial data replay module to better select more diverse and key relearning data. Furthermore, we design a consistency regularization strategy to encourage current defense models to learn more from previously trained ones, guiding them to retain more past knowledge and maintain accuracy on clean samples. Extensive experiments have been conducted to verify the efficacy of the proposed SSEAT defense method, which demonstrates superior defense performance and classification accuracy compared to competitors.
Authors: Daniel Siegismund, Mario Wieser, Stephan Heyse, Stephan Steigele
Abstract: Deep Neural Networks (DNNs) have shown remarkable success in various computer vision tasks. However, their black-box nature often leads to difficulty in interpreting their decisions, creating an unfilled need for methods to explain the decisions, and ultimately forming a barrier to their wide acceptance especially in biomedical applications. This work introduces a novel method, Pixel-wise Channel Isolation Mixing (PCIM), to calculate pixel attribution maps, highlighting the image parts most crucial for a classification decision but without the need to extract internal network states or gradients. Unlike existing methods, PCIM treats each pixel as a distinct input channel and trains a blending layer to mix these pixels, reflecting specific classifications. This unique approach allows the generation of pixel attribution maps for each image, but agnostic to the choice of the underlying classification network. Benchmark testing on three application relevant, diverse high content Imaging datasets show state-of-the-art performance, particularly for model fidelity and localization ability in both, fluorescence and bright field High Content Imaging. PCIM contributes as a unique and effective method for creating pixel-level attribution maps from arbitrary DNNs, enabling interpretability and trust.
Authors: Qing Zhang, Zehao Chen, Jinguang Tong, Jing Zhang, Jie Hong, Xuesong Li
Abstract: Despite recent advances in text-to-3D generation techniques, current methods often suffer from geometric inconsistencies, commonly referred to as the Janus Problem. This paper identifies the root cause of the Janus Problem: viewpoint generation bias in diffusion models, which creates a significant gap between the actual generated viewpoint and the expected one required for optimizing the 3D model. To address this issue, we propose a tuning-free approach called the Attention and CLIP Guidance (ACG) mechanism. ACG enhances desired viewpoints by adaptively controlling cross-attention maps, employs CLIP-based view-text similarities to filter out erroneous viewpoints, and uses a coarse-to-fine optimization strategy with staged prompts to progressively refine 3D generation. Extensive experiments demonstrate that our method significantly reduces the Janus Problem without compromising generation speed, establishing ACG as an efficient, plug-and-play component for existing text-to-3D frameworks.
Authors: Thomas Besnier, Emery Pierson, Sylvain Arguillere, Mohamed Daoudi
Abstract: Non-rigid shape deformations pose significant challenges, and most existing methods struggle to handle partial deformations effectively. We present Partial Non-rigid Deformations and interpolations of the human body Surfaces (PaNDAS), a new method to learn local and global deformations of 3D surface meshes by building on recent deep models. Unlike previous approaches, our method enables restricting deformations to specific parts of the shape in a versatile way and allows for mixing and combining various poses from the database, all while not requiring any optimization at inference time. We demonstrate that the proposed framework can be used to generate new shapes, interpolate between parts of shapes, and perform other shape manipulation tasks with state-of-the-art accuracy and greater locality across various types of human surface data. Code and data will be made available soon.
Authors: Leah Bar, Boaz Lerner, Nir Darshan, Rami Ben-Ari
Abstract: Active Learning (AL) is a user-interactive approach aimed at reducing annotation costs by selecting the most crucial examples to label. Although AL has been extensively studied for image classification tasks, the specific scenario of interactive image retrieval has received relatively little attention. This scenario presents unique characteristics, including an open-set and class-imbalanced binary classification, starting with very few labeled samples. We introduce a novel batch-mode Active Learning framework named GAL (Greedy Active Learning) that better copes with this application. It incorporates a new acquisition function for sample selection that measures the impact of each unlabeled sample on the classifier. We further embed this strategy in a greedy selection approach, better exploiting the samples within each batch. We evaluate our framework with both linear (SVM) and non-linear MLP/Gaussian Process classifiers. For the Gaussian Process case, we show a theoretical guarantee on the greedy approximation. Finally, we assess our performance for the interactive content-based image retrieval task on several benchmarks and demonstrate its superiority over existing approaches and common baselines. Code is available at https://github.com/barleah/GreedyAL.
Authors: Lingcong Cai, Yun Li, Xiaomao Fan, Kaixuan Song, Yongcheng Li, Yixuan Yuan, Ruxin Wang, Wenbin Lei
Abstract: The segmentation of endoscopic images plays a vital role in computer-aided diagnosis and treatment. The advancements in deep learning have led to the employment of numerous models for endoscopic tumor segmentation, achieving promising segmentation performance. Despite recent advancements, precise segmentation remains challenging due to limited annotations and the issue of low contrast. To address these issues, we propose a novel semi-supervised segmentation framework termed LoCo via low-contrast-enhanced contrastive learning (LCC). This innovative approach effectively harnesses the vast amounts of unlabeled data available for endoscopic image segmentation, improving both accuracy and robustness in the segmentation process. Specifically, LCC incorporates two advanced strategies to enhance the distinctiveness of low-contrast pixels: inter-class contrast enhancement (ICE) and boundary contrast enhancement (BCE), enabling models to segment low-contrast pixels among malignant tumors, benign tumors, and normal tissues. Additionally, a confidence-based dynamic filter (CDF) is designed for pseudo-label selection, enhancing the utilization of generated pseudo-labels for unlabeled data with a specific focus on minority classes. Extensive experiments conducted on two public datasets, as well as a large proprietary dataset collected over three years, demonstrate that LoCo achieves state-of-the-art results, significantly outperforming previous methods. The source code of LoCo is available at the URL of https://github.com/AnoK3111/LoCo.
Authors: Zedong Chu, Feng Xiong, Meiduo Liu, Jinzhi Zhang, Mingqi Shao, Zhaoxu Sun, Di Wang, Mu Xu
Abstract: With the rapid evolution of 3D generation algorithms, the cost of producing 3D humanoid character models has plummeted, yet the field is impeded by the lack of a comprehensive dataset for automatic rigging, which is a pivotal step in character animation. Addressing this gap, we present HumanRig, the first large-scale dataset specifically designed for 3D humanoid character rigging, encompassing 11,434 meticulously curated T-posed meshes adhered to a uniform skeleton topology. Capitalizing on this dataset, we introduce an innovative, data-driven automatic rigging framework, which overcomes the limitations of GNN-based methods in handling complex AI-generated meshes. Our approach integrates a Prior-Guided Skeleton Estimator (PGSE) module, which uses 2D skeleton joints to provide a preliminary 3D skeleton, and a Mesh-Skeleton Mutual Attention Network (MSMAN) that fuses skeleton features with 3D mesh features extracted by a U-shaped point transformer. This enables a coarse-to-fine 3D skeleton joint regression and a robust skinning estimation, surpassing previous methods in quality and versatility. This work not only remedies the dataset deficiency in rigging research but also propels the animation industry towards more efficient and automated character rigging pipelines.
Authors: Xinjie Li, Yang Zhao, Dong Wang, Yuan Chen, Li Cao, Xiaoping Liu
Abstract: Large-scale generative models have achieved remarkable advancements in various visual tasks, yet their application to shadow removal in images remains challenging. These models often generate diverse, realistic details without adequate focus on fidelity, failing to meet the crucial requirements of shadow removal, which necessitates precise preservation of image content. In contrast to prior approaches that aimed to regenerate shadow-free images from scratch, this paper utilizes diffusion models to generate and refine image residuals. This strategy fully uses the inherent detailed information within shadowed images, resulting in a more efficient and faithful reconstruction of shadow-free content. Additionally, to revent the accumulation of errors during the generation process, a crosstimestep self-enhancement training strategy is proposed. This strategy leverages the network itself to augment the training data, not only increasing the volume of data but also enabling the network to dynamically correct its generation trajectory, ensuring a more accurate and robust output. In addition, to address the loss of original details in the process of image encoding and decoding of large generative models, a content-preserved encoder-decoder structure is designed with a control mechanism and multi-scale skip connections to achieve high-fidelity shadow-free image reconstruction. Experimental results demonstrate that the proposed method can reproduce high-quality results based on a large latent diffusion prior and faithfully preserve the original contents in shadow regions.
Authors: Sabina Martyniak, Joanna Kaleta, Diego Dall'Alba, Micha{\l} Naskr\k{e}t, Szymon P{\l}otka, Przemys{\l}aw Korzeniowski
Abstract: Computer-assisted surgical (CAS) systems enhance surgical execution and outcomes by providing advanced support to surgeons. These systems often rely on deep learning models trained on complex, challenging-to-annotate data. While synthetic data generation can address these challenges, enhancing the realism of such data is crucial. This work introduces a multi-stage pipeline for generating realistic synthetic data, featuring a fully-fledged surgical simulator that automatically produces all necessary annotations for modern CAS systems. This simulator generates a wide set of annotations that surpass those available in public synthetic datasets. Additionally, it offers a more complex and realistic simulation of surgical interactions, including the dynamics between surgical instruments and deformable anatomical environments, outperforming existing approaches. To further bridge the visual gap between synthetic and real data, we propose a lightweight and flexible image-to-image translation method based on Stable Diffusion (SD) and Low-Rank Adaptation (LoRA). This method leverages a limited amount of annotated data, enables efficient training, and maintains the integrity of annotations generated by our simulator. The proposed pipeline is experimentally validated and can translate synthetic images into images with real-world characteristics, which can generalize to real-world context, thereby improving both training and CAS guidance. The code and the dataset are available at https://github.com/SanoScience/SimuScope.
Authors: Zhenyu Li, Mykola Lavreniuk, Jian Shi, Shariq Farooq Bhat, Peter Wonka
Abstract: Amodal depth estimation aims to predict the depth of occluded (invisible) parts of objects in a scene. This task addresses the question of whether models can effectively perceive the geometry of occluded regions based on visible cues. Prior methods primarily rely on synthetic datasets and focus on metric depth estimation, limiting their generalization to real-world settings due to domain shifts and scalability challenges. In this paper, we propose a novel formulation of amodal depth estimation in the wild, focusing on relative depth prediction to improve model generalization across diverse natural images. We introduce a new large-scale dataset, Amodal Depth In the Wild (ADIW), created using a scalable pipeline that leverages segmentation datasets and compositing techniques. Depth maps are generated using large pre-trained depth models, and a scale-and-shift alignment strategy is employed to refine and blend depth predictions, ensuring consistency in ground-truth annotations. To tackle the amodal depth task, we present two complementary frameworks: Amodal-DAV2, a deterministic model based on Depth Anything V2, and Amodal-DepthFM, a generative model that integrates conditional flow matching principles. Our proposed frameworks effectively leverage the capabilities of large pre-trained models with minimal modifications to achieve high-quality amodal depth predictions. Experiments validate our design choices, demonstrating the flexibility of our models in generating diverse, plausible depth structures for occluded regions. Our method achieves a 69.5% improvement in accuracy over the previous SoTA on the ADIW dataset.
Authors: Seul-Ki Yeom, Tae-Ho Kim
Abstract: Transformer-based architectures have demonstrated remarkable success across various domains, but their deployment on edge devices remains challenging due to high memory and computational demands. In this paper, we introduce a novel Reuse Attention mechanism, tailored for efficient memory access and computational optimization, enabling seamless operation on resource-constrained platforms without compromising performance. Unlike traditional multi-head attention (MHA), which redundantly computes separate attention matrices for each head, Reuse Attention consolidates these computations into a shared attention matrix, significantly reducing memory overhead and computational complexity. Comprehensive experiments on ImageNet-1K and downstream tasks show that the proposed UniForm models leveraging Reuse Attention achieve state-of-the-art imagenet classification accuracy while outperforming existing attention mechanisms, such as Linear Attention and Flash Attention, in inference speed and memory scalability. Notably, UniForm-l achieves a 76.7% Top-1 accuracy on ImageNet-1K with 21.8ms inference time on edge devices like the Jetson AGX Orin, representing up to a 5x speedup over competing benchmark methods. These results demonstrate the versatility of Reuse Attention across high-performance GPUs and edge platforms, paving the way for broader real-time applications
Authors: Juhyung Choi, Jinnyeong Kim, Seokjun Choi, Jinwoo Lee, Samuel Brucker, Mario Bijelic, Felix Heide, Seung-Hwan Baek
Abstract: Achieving robust stereo 3D imaging under diverse illumination conditions is an important however challenging task, due to the limited dynamic ranges (DRs) of cameras, which are significantly smaller than real world DR. As a result, the accuracy of existing stereo depth estimation methods is often compromised by under- or over-exposed images. Here, we introduce dual-exposure stereo for extended dynamic range 3D imaging. We develop automatic dual-exposure control method that adjusts the dual exposures, diverging them when the scene DR exceeds the camera DR, thereby providing information about broader DR. From the captured dual-exposure stereo images, we estimate depth using motion-aware dual-exposure stereo network. To validate our method, we develop a robot-vision system, collect stereo video datasets, and generate a synthetic dataset. Our method outperforms other exposure control methods.
Authors: Kailing Wang, Chen Yang, Keyang Zhao, Xiaokang Yang, Wei Shen
Abstract: This paper tackles the challenge of automatically performing realistic surgical simulations from readily available surgical videos. Recent efforts have successfully integrated physically grounded dynamics within 3D Gaussians to perform high-fidelity simulations in well-reconstructed simulation environments from static scenes. However, they struggle with the geometric inconsistency in reconstructing simulation environments and unrealistic physical deformations in simulations of soft tissues when it comes to dynamic and complex surgical processes. In this paper, we propose SurgiSim, a novel automatic simulation system to overcome these limitations. To build a surgical simulation environment, we maintain a canonical 3D scene composed of 3D Gaussians coupled with a deformation field to represent a dynamic surgical scene. This process involves a multi-stage optimization with trajectory and anisotropic regularization, enhancing the geometry consistency of the canonical scene, which serves as the simulation environment. To achieve realistic physical simulations in this environment, we implement a Visco-Elastic deformation model based on the Maxwell model, effectively restoring the complex deformations of tissues. Additionally, we infer the physical parameters of tissues by minimizing the discrepancies between the input video and simulation results guided by estimated tissue motion, ensuring realistic simulation outcomes. Experiments on various surgical scenarios and interactions demonstrate SurgiSim's ability to perform realistic simulation of soft tissues among surgical procedures, showing its enormous potential for enhancing surgical training, planning, and robotic surgery systems. The project page is at https://namaenashibot.github.io/SurgiSim/.
Authors: Khawar Islam, Muhammad Zaigham Zaheer, Arif Mahmood, Karthik Nandakumar, Naveed Akhtar
Abstract: Data augmentation is widely used to enhance generalization in visual classification tasks. However, traditional methods struggle when source and target domains differ, as in domain adaptation, due to their inability to address domain gaps. This paper introduces GenMix, a generalizable prompt-guided generative data augmentation approach that enhances both in-domain and cross-domain image classification. Our technique leverages image editing to generate augmented images based on custom conditional prompts, designed specifically for each problem type. By blending portions of the input image with its edited generative counterpart and incorporating fractal patterns, our approach mitigates unrealistic images and label ambiguity, improving the performance and adversarial robustness of the resulting models. Efficacy of our method is established with extensive experiments on eight public datasets for general and fine-grained classification, in both in-domain and cross-domain settings. Additionally, we demonstrate performance improvements for self-supervised learning, learning with data scarcity, and adversarial robustness. As compared to the existing state-of-the-art methods, our technique achieves stronger performance across the board.
Authors: Eerik Alamikkotervo, Henrik Toikka, Kari Tammi, Risto Ojala
Abstract: Robust road segmentation in all road conditions is required for safe autonomous driving and advanced driver assistance systems. Supervised deep learning methods provide accurate road segmentation in the domain of their training data but cannot be trusted in out-of-distribution scenarios. Including the whole distribution in the trainset is challenging as each sample must be labeled by hand. Trajectory-based self-supervised methods offer a potential solution as they can learn from the traversed route without manual labels. However, existing trajectory-based methods use learning schemes that rely only on the camera or only on the lidar. In this paper, trajectory-based learning is implemented jointly with lidar and camera for increased performance. Our method outperforms recent standalone camera- and lidar-based methods when evaluated with a challenging winter driving dataset including countryside and suburb driving scenes. The source code is available at https://github.com/eerik98/lidar-camera-road-autolabeling.git
URLs: https://github.com/eerik98/lidar-camera-road-autolabeling.git
Authors: Xichen Ye, Yifan Wu, Yiwen Xu, Xiaoqiang Li, Weizhong Zhang, Yifan Chen
Abstract: Deep supervised learning has achieved remarkable success across a wide range of tasks, yet it remains susceptible to overfitting when confronted with noisy labels. To address this issue, noise-robust loss functions offer an effective solution for enhancing learning in the presence of label noise. In this work, we systematically investigate the limitation of the recently proposed Active Passive Loss (APL), which employs Mean Absolute Error (MAE) as its passive loss function. Despite the robustness brought by MAE, one of its key drawbacks is that it pays equal attention to clean and noisy samples; this feature slows down convergence and potentially makes training difficult, particularly in large-scale datasets. To overcome these challenges, we introduce a novel loss function class, termed Normalized Negative Loss Functions (NNLFs), which serve as passive loss functions within the APL framework. NNLFs effectively address the limitations of MAE by concentrating more on memorized clean samples. By replacing MAE in APL with our proposed NNLFs, we enhance APL and present a new framework called Active Negative Loss (ANL). Moreover, in non-symmetric noise scenarios, we propose an entropy-based regularization technique to mitigate the vulnerability to the label imbalance. Extensive experiments demonstrate that the new loss functions adopted by our ANL framework can achieve better or comparable performance to state-of-the-art methods across various label noise types and in image segmentation tasks. The source code is available at: https://github.com/Virusdoll/Active-Negative-Loss.
Authors: Blanca Lasheras-Hernandez, Klaus H. Strobl, Sergio Izquierdo, Tim Bodenm\"uller, Rudolph Triebel, Javier Civera
Abstract: Metric depth estimation from visual sensors is crucial for robots to perceive, navigate, and interact with their environment. Traditional range imaging setups, such as stereo or structured light cameras, face hassles including calibration, occlusions, and hardware demands, with accuracy limited by the baseline between cameras. Single- and multi-view monocular depth offers a more compact alternative, but is constrained by the unobservability of the metric scale. Light field imaging provides a promising solution for estimating metric depth by using a unique lens configuration through a single device. However, its application to single-view dense metric depth is under-addressed mainly due to the technology's high cost, the lack of public benchmarks, and proprietary geometrical models and software. Our work explores the potential of focused plenoptic cameras for dense metric depth. We propose a novel pipeline that predicts metric depth from a single plenoptic camera shot by first generating a sparse metric point cloud using machine learning, which is then used to scale and align a dense relative depth map regressed by a foundation depth model, resulting in dense metric depth. To validate it, we curated the Light Field & Stereo Image Dataset (LFS) of real-world light field images with stereo depth labels, filling a current gap in existing resources. Experimental results show that our pipeline produces accurate metric depth predictions, laying a solid groundwork for future research in this field.
Authors: Ziqian Zou, Conghao Wong, Beihao Xia, Qinmu Peng, Xinge You
Abstract: Understanding and anticipating human movement has become more critical and challenging in diverse applications such as autonomous driving and surveillance. The complex interactions brought by different relations between agents are a crucial reason that poses challenges to this task. Researchers have put much effort into designing a system using rule-based or data-based models to extract and validate the patterns between pedestrian trajectories and these interactions, which has not been adequately addressed yet. Inspired by how humans perceive social interactions with different level of relations to themself, this work proposes the GrouP ConCeption (short for GPCC) model composed of the Group method, which categorizes nearby agents into either group members or non-group members based on a long-term distance kernel function, and the Conception module, which perceives both visual and acoustic information surrounding the target agent. Evaluated across multiple datasets, the GPCC model demonstrates significant improvements in trajectory prediction accuracy, validating its effectiveness in modeling both social and individual dynamics. The qualitative analysis also indicates that the GPCC framework successfully leverages grouping and perception cues human-like intuitively to validate the proposed model's explainability in pedestrian trajectory forecasting.
Authors: Changli Wu, Qi Chen, Jiayi Ji, Haowei Wang, Yiwei Ma, You Huang, Gen Luo, Hao Fei, Xiaoshuai Sun, Rongrong Ji
Abstract: 3D Referring Expression Segmentation (3D-RES) aims to segment 3D objects by correlating referring expressions with point clouds. However, traditional approaches frequently encounter issues like over-segmentation or mis-segmentation, due to insufficient emphasis on spatial information of instances. In this paper, we introduce a Rule-Guided Spatial Awareness Network (RG-SAN) by utilizing solely the spatial information of the target instance for supervision. This approach enables the network to accurately depict the spatial relationships among all entities described in the text, thus enhancing the reasoning capabilities. The RG-SAN consists of the Text-driven Localization Module (TLM) and the Rule-guided Weak Supervision (RWS) strategy. The TLM initially locates all mentioned instances and iteratively refines their positional information. The RWS strategy, acknowledging that only target objects have supervised positional information, employs dependency tree rules to precisely guide the core instance's positioning. Extensive testing on the ScanRefer benchmark has shown that RG-SAN not only establishes new performance benchmarks, with an mIoU increase of 5.1 points, but also exhibits significant improvements in robustness when processing descriptions with spatial ambiguity. All codes are available at https://github.com/sosppxo/RG-SAN.
Authors: Valentin Braeutigam, Vanessa Wirth, Ingrid Ullmann, Christian Sch\"u{\ss}ler, Martin Vossiek, Matthias Berking, Bernhard Egger
Abstract: The 3D reconstruction of faces gains wide attention in computer vision and is used in many fields of application, for example, animation, virtual reality, and even forensics. This work is motivated by monitoring patients in sleep laboratories. Due to their unique characteristics, sensors from the radar domain have advantages compared to optical sensors, namely penetration of electrically non-conductive materials and independence of light. These advantages of radar signals unlock new applications and require adaptation of 3D reconstruction frameworks. We propose a novel model-based method for 3D reconstruction from radar images. We generate a dataset of synthetic radar images with a physics-based but non-differentiable radar renderer. This dataset is used to train a CNN-based encoder to estimate the parameters of a 3D morphable face model. Whilst the encoder alone already leads to strong reconstructions of synthetic data, we extend our reconstruction in an Analysis-by-Synthesis fashion to a model-based autoencoder. This is enabled by learning the rendering process in the decoder, which acts as an object-specific differentiable radar renderer. Subsequently, the combination of both network parts is trained to minimize both, the loss of the parameters and the loss of the resulting reconstructed radar image. This leads to the additional benefit, that at test time the parameters can be further optimized by finetuning the autoencoder unsupervised on the image loss. We evaluated our framework on generated synthetic face images as well as on real radar images with 3D ground truth of four individuals.
Authors: Dongwei Pan, Yang Li, Hongsheng Li, Kwan-Yee Lin
Abstract: We present TimeWalker, a novel framework that models realistic, full-scale 3D head avatars of a person on lifelong scale. Unlike current human head avatar pipelines that capture identity at the momentary level(e.g., instant photography or short videos), TimeWalker constructs a person's comprehensive identity from unstructured data collection over his/her various life stages, offering a paradigm to achieve full reconstruction and animation of that person at different moments of life. At the heart of TimeWalker's success is a novel neural parametric model that learns personalized representation with the disentanglement of shape, expression, and appearance across ages. Central to our methodology are the concepts of two aspects: (1) We track back to the principle of modeling a person's identity in an additive combination of average head representation in the canonical space, and moment-specific head attribute representations driven from a set of neural head basis. To learn the set of head basis that could represent the comprehensive head variations in a compact manner, we propose a Dynamic Neural Basis-Blending Module (Dynamo). It dynamically adjusts the number and blend weights of neural head bases, according to both shared and specific traits of the target person over ages. (2) Dynamic 2D Gaussian Splatting (DNA-2DGS), an extension of Gaussian splatting representation, to model head motion deformations like facial expressions without losing the realism of rendering and reconstruction. DNA-2DGS includes a set of controllable 2D oriented planar Gaussian disks that utilize the priors from parametric model, and move/rotate with the change of expression. Through extensive experimental evaluations, we show TimeWalker's ability to reconstruct and animate avatars across decoupled dimensions with realistic rendering effects, demonstrating a way to achieve personalized 'time traveling' in a breeze.
Authors: Conghao Wong, Ziqian Zou, Beihao Xia, Xinge You
Abstract: Learning to forecast the trajectories of intelligent agents like pedestrians has caught more researchers' attention. Despite researchers' efforts, it remains a challenge to accurately account for social interactions among agents when forecasting, and in particular, to simulate such social modifications to future trajectories in an explainable and decoupled way. Inspired by the resonance phenomenon of vibration systems, we propose the Resonance (short for Re) model to forecast pedestrian trajectories as co-vibrations, and regard that social interactions are associated with spectral properties of agents' trajectories. It forecasts future trajectories as three distinct vibration terms to represent agents' future plans from different perspectives in a decoupled way. Also, agents' social interactions and how they modify scheduled trajectories will be considered in a resonance-like manner by learning the similarities of their trajectory spectrums. Experiments on multiple datasets, whether pedestrian or vehicle, have verified the usefulness of our method both quantitatively and qualitatively.
Authors: Caixin Kang, Yubo Chen, Shouwei Ruan, Shiji Zhao, Ruochen Zhang, Jiayi Wang, Shan Fu, Xingxing Wei
Abstract: With the rise of deep learning, facial recognition technology has seen extensive research and rapid development. Although facial recognition is considered a mature technology, we find that existing open-source models and commercial algorithms lack robustness in certain real-world Out-of-Distribution (OOD) scenarios, raising concerns about the reliability of these systems. In this paper, we introduce OODFace, which explores the OOD challenges faced by facial recognition models from two perspectives: common corruptions and appearance variations. We systematically design 30 OOD scenarios across 9 major categories tailored for facial recognition. By simulating these challenges on public datasets, we establish three robustness benchmarks: LFW-C/V, CFP-FP-C/V, and YTF-C/V. We then conduct extensive experiments on 19 different facial recognition models and 3 commercial APIs, along with extended experiments on face masks, Vision-Language Models (VLMs), and defense strategies to assess their robustness. Based on the results, we draw several key insights, highlighting the vulnerability of facial recognition systems to OOD data and suggesting possible solutions. Additionally, we offer a unified toolkit that includes all corruption and variation types, easily extendable to other datasets. We hope that our benchmarks and findings can provide guidance for future improvements in facial recognition model robustness.
Authors: Qiankun Gao, Yanmin Wu, Chengxiang Wen, Jiarui Meng, Luyang Tang, Jie Chen, Ronggang Wang, Jian Zhang
Abstract: Reconstructing dynamic scenes with large-scale and complex motions remains a significant challenge. Recent techniques like Neural Radiance Fields and 3D Gaussian Splatting (3DGS) have shown promise but still struggle with scenes involving substantial movement. This paper proposes RelayGS, a novel method based on 3DGS, specifically designed to represent and reconstruct highly dynamic scenes. Our RelayGS learns a complete 4D representation with canonical 3D Gaussians and a compact motion field, consisting of three stages. First, we learn a fundamental 3DGS from all frames, ignoring temporal scene variations, and use a learnable mask to separate the highly dynamic foreground from the minimally moving background. Second, we replicate multiple copies of the decoupled foreground Gaussians from the first stage, each corresponding to a temporal segment, and optimize them using pseudo-views constructed from multiple frames within each segment. These Gaussians, termed Relay Gaussians, act as explicit relay nodes, simplifying and breaking down large-scale motion trajectories into smaller, manageable segments. Finally, we jointly learn the scene's temporal motion and refine the canonical Gaussians learned from the first two stages. We conduct thorough experiments on two dynamic scene datasets featuring large and complex motions, where our RelayGS outperforms state-of-the-arts by more than 1 dB in PSNR, and successfully reconstructs real-world basketball game scenes in a much more complete and coherent manner, whereas previous methods usually struggle to capture the complex motion of players. Code will be publicly available at https://github.com/gqk/RelayGS
Authors: Dongya Sun, Yunfei Hu, Xianzhe Zhang, Yingsong Hu
Abstract: Facial expression manipulation aims to change human facial expressions without affecting face recognition. In order to transform the facial expressions to target expressions, previous methods relied on expression labels to guide the manipulation process. However, these methods failed to preserve the details of facial features, which causes the weakening or the loss of identity information in the output image. In our work, we propose WEM-GAN, in short for wavelet-based expression manipulation GAN, which puts more efforts on preserving the details of the original image in the editing process. Firstly, we take advantage of the wavelet transform technique and combine it with our generator with a U-net autoencoder backbone, in order to improve the generator's ability to preserve more details of facial features. Secondly, we also implement the high-frequency component discriminator, and use high-frequency domain adversarial loss to further constrain the optimization of our model, providing the generated face image with more abundant details. Additionally, in order to narrow the gap between generated facial expressions and target expressions, we use residual connections between encoder and decoder, while also using relative action units (AUs) several times. Extensive qualitative and quantitative experiments have demonstrated that our model performs better in preserving identity features, editing capability, and image generation quality on the AffectNet dataset. It also shows superior performance in metrics such as Average Content Distance (ACD) and Expression Distance (ED).
Authors: Jinjin Cai, Kexin Meng, Baijian Yang, Gang Shao
Abstract: Remote sensing scene classification (RSSC) is a critical task with diverse applications in land use and resource management. While unimodal image-based approaches show promise, they often struggle with limitations such as high intra-class variance and inter-class similarity. Incorporating textual information can enhance classification by providing additional context and semantic understanding, but manual text annotation is labor-intensive and costly. In this work, we propose a novel RSSC framework that integrates text descriptions generated by large vision-language models (VLMs) as an auxiliary modality without incurring expensive manual annotation costs. To fully leverage the latent complementarities between visual and textual data, we propose a dual cross-attention-based network to fuse these modalities into a unified representation. Extensive experiments with both quantitative and qualitative evaluation across five RSSC datasets demonstrate that our framework consistently outperforms baseline models. We also verify the effectiveness of VLM-generated text descriptions compared to human-annotated descriptions. Additionally, we design a zero-shot classification scenario to show that the learned multimodal representation can be effectively utilized for unseen class classification. This research opens new opportunities for leveraging textual information in RSSC tasks and provides a promising multimodal fusion structure, offering insights and inspiration for future studies. Code is available at: https://github.com/CJR7/MultiAtt-RSSC
Authors: Quang H. Nguyen, Hoang Phan, Khoa D. Doan
Abstract: Diffusion models have shown remarkable abilities in generating realistic and high-quality images from text prompts. However, a trained model remains black-box; little do we know about the role of its components in exhibiting a concept such as objects or styles. Recent works employ causal tracing to localize layers storing knowledge in generative models without showing how those layers contribute to the target concept. In this work, we approach the model interpretability problem from a more general perspective and pose a question: \textit{``How do model components work jointly to demonstrate knowledge?''}. We adapt component attribution to decompose diffusion models, unveiling how a component contributes to a concept. Our framework allows effective model editing, in particular, we can erase a concept from diffusion models by removing positive components while remaining knowledge of other concepts. Surprisingly, we also show there exist components that contribute negatively to a concept, which has not been discovered in the knowledge localization approach. Experimental results confirm the role of positive and negative components pinpointed by our framework, depicting a complete view of interpreting generative models. Our code is available at \url{https://github.com/mail-research/CAD-attribution4diffusion}
URLs: https://github.com/mail-research/CAD-attribution4diffusion
Authors: Jin Hu, Mingjia Li, Xiaojie Guo
Abstract: Shadows introduce challenges such as reduced brightness, texture deterioration, and color distortion in images, complicating a holistic solution. This study presents \textbf{ShadowHack}, a divide-and-conquer strategy that tackles these complexities by decomposing the original task into luminance recovery and color remedy. To brighten shadow regions and repair the corrupted textures in the luminance space, we customize LRNet, a U-shaped network with a rectified outreach attention module, to enhance information interaction and recalibrate contaminated attention maps. With luminance recovered, CRNet then leverages cross-attention mechanisms to revive vibrant colors, producing visually compelling results. Extensive experiments on multiple datasets are conducted to demonstrate the superiority of ShadowHack over existing state-of-the-art solutions both quantitatively and qualitatively, highlighting the effectiveness of our design. Our code will be made publicly available at https://github.com/lime-j/ShadowHack
Authors: Joongwon Chae, Zhenyu Wang, Peiwu Qin
Abstract: Despite advances in vision-language understanding, implementing image segmentation within multimodal architectures remains a fundamental challenge in modern artificial intelligence systems. Existing vision-language models, which primarily rely on backbone architectures or CLIP-based embedding learning, demonstrate inherent limitations in fine-grained spatial localization and operational capabilities. This paper introduces SJTU: Spatial Judgments in multimodal models - Towards Unified segmentation through coordinate detection, a novel framework that leverages spatial coordinate understanding to bridge vision-language interaction and precise segmentation, enabling accurate target identification through natural language instructions. The framework proposes a novel approach for integrating segmentation techniques with vision-language models based on multimodal spatial inference. By leveraging normalized coordinate detection for bounding boxes and translating it into actionable segmentation outputs, we explore the possibility of integrating multimodal spatial and language representations. Based on the proposed technical approach, the framework demonstrates superior performance on various benchmark datasets as well as accurate object segmentation. Results on the COCO 2017 dataset for general object detection and Pascal VOC datasets for semantic segmentation demonstrate the generalization capabilities of the framework.
Authors: Chenyang Liu, Jiafan Zhang, Keyan Chen, Man Wang, Zhengxia Zou, Zhenwei Shi
Abstract: Temporal image analysis in remote sensing has traditionally centered on change detection, which identifies regions of change between images captured at different times. However, change detection remains limited by its focus on visual-level interpretation, often lacking contextual or descriptive information. The rise of Vision-Language Models (VLMs) has introduced a new dimension to remote sensing temporal image analysis by integrating visual information with natural language, creating an avenue for advanced interpretation of temporal image changes. Remote Sensing Temporal VLMs (RSTVLMs) allow for dynamic interactions, generating descriptive captions, answering questions, and providing a richer semantic understanding of temporal images. This temporal vision-language capability is particularly valuable for complex remote sensing applications, where higher-level insights are crucial. This paper comprehensively reviews the progress of RSTVLM research, with a focus on the latest VLM applications for temporal image analysis. We categorize and discuss core methodologies, datasets, and metrics, highlight recent advances in temporal vision-language tasks, and outline key challenges and future directions for research in this emerging field. This survey fills a critical gap in the literature by providing an integrated overview of RSTVLM, offering a foundation for further advancements in remote sensing temporal image understanding. We will keep tracing related works at \url{https://github.com/Chen-Yang-Liu/Awesome-RS-Temporal-VLM}
URLs: https://github.com/Chen-Yang-Liu/Awesome-RS-Temporal-VLM
Authors: Ze Zhang, Enyuan Zhao, Ziyi Wan, Jie Nie, Xinyue Liang, Lei Huang
Abstract: This paper introduces the task of Remote Sensing Copy-Move Question Answering (RSCMQA). Unlike traditional Remote Sensing Visual Question Answering (RSVQA), RSCMQA focuses on interpreting complex tampering scenarios and inferring relationships between objects. Based on the practical needs of national defense security and land resource monitoring, we have developed an accurate and comprehensive global dataset for remote sensing image copy-move question answering, named RS-CMQA-2.1M. These images were collected from 29 different regions across 14 countries. Additionally, we have refined a balanced dataset, RS-CMQA-B, to address the long-standing issue of long-tail data in the remote sensing field. Furthermore, we propose a region-discriminative guided multimodal CMQA model, which enhances the accuracy of answering questions about tampered images by leveraging prompt about the differences and connections between the source and tampered domains. Extensive experiments demonstrate that our method provides a stronger benchmark for RS-CMQA compared to general VQA and RSVQA models. Our dataset and code are available at https://github.com/shenyedepisa/RSCMQA.
Authors: Yihong Chen, Jiancheng Yang, Deniz Sayin Mercadier, Hieu Le, Pascal Fua
Abstract: We present a novel approach to reconstruction of 3D cardiac motion from sparse intraoperative data. While existing methods can accurately reconstruct 3D organ geometries from full 3D volumetric imaging, they cannot be used during surgical interventions where usually limited observed data, such as a few 2D frames or 1D signals, is available in real-time. We propose a versatile framework for reconstructing 3D motion from such partial data. It discretizes the 3D space into a deformable tetrahedral grid with signed distance values, providing implicit unlimited resolution while maintaining explicit control over motion dynamics. Given an initial 3D model reconstructed from pre-operative full volumetric data, our system, equipped with an universal observation encoder, can reconstruct coherent 3D cardiac motion from full 3D volumes, a few 2D MRI slices or even 1D signals. Extensive experiments on cardiac intervention scenarios demonstrate our ability to generate plausible and anatomically consistent 3D motion reconstructions from various sparse real-time observations, highlighting its potential for multimodal cardiac imaging. Our code and model will be made available at https://github.com/Scalsol/MedTet.
Authors: Junyuan Zhang, Qintong Zhang, Bin Wang, Linke Ouyang, Zichen Wen, Ying Li, Ka-Ho Chow, Conghui He, Wentao Zhang
Abstract: Retrieval-augmented Generation (RAG) enhances Large Language Models (LLMs) by integrating external knowledge to reduce hallucinations and incorporate up-to-date information without retraining. As an essential part of RAG, external knowledge bases are commonly built by extracting structured data from unstructured PDF documents using Optical Character Recognition (OCR). However, given the imperfect prediction of OCR and the inherent non-uniform representation of structured data, knowledge bases inevitably contain various OCR noises. In this paper, we introduce OHRBench, the first benchmark for understanding the cascading impact of OCR on RAG systems. OHRBench includes 350 carefully selected unstructured PDF documents from six real-world RAG application domains, along with Q&As derived from multimodal elements in documents, challenging existing OCR solutions used for RAG To better understand OCR's impact on RAG systems, we identify two primary types of OCR noise: Semantic Noise and Formatting Noise and apply perturbation to generate a set of structured data with varying degrees of each OCR noise. Using OHRBench, we first conduct a comprehensive evaluation of current OCR solutions and reveal that none is competent for constructing high-quality knowledge bases for RAG systems. We then systematically evaluate the impact of these two noise types and demonstrate the vulnerability of RAG systems. Furthermore, we discuss the potential of employing Vision-Language Models (VLMs) without OCR in RAG systems. Code: https://github.com/opendatalab/OHR-Bench
Authors: Aniruddha Ganguly, Debolina Chatterjee, Wentao Huang, Jie Zhang, Alisa Yurovsky, Travis Steele Johnson, Chao Chen
Abstract: Recent advances in Spatial Transcriptomics (ST) pair histology images with spatially resolved gene expression profiles, enabling predictions of gene expression across different tissue locations based on image patches. This opens up new possibilities for enhancing whole slide image (WSI) prediction tasks with localized gene expression. However, existing methods fail to fully leverage the interactions between different tissue locations, which are crucial for accurate joint prediction. To address this, we introduce MERGE (Multi-faceted hiErarchical gRaph for Gene Expressions), which combines a multi-faceted hierarchical graph construction strategy with graph neural networks (GNN) to improve gene expression predictions from WSIs. By clustering tissue image patches based on both spatial and morphological features, and incorporating intra- and inter-cluster edges, our approach fosters interactions between distant tissue locations during GNN learning. As an additional contribution, we evaluate different data smoothing techniques that are necessary to mitigate artifacts in ST data, often caused by technical imperfections. We advocate for adopting gene-aware smoothing methods that are more biologically justified. Experimental results on gene expression prediction show that our GNN method outperforms state-of-the-art techniques across multiple metrics.
Authors: Kaixiong Gong, Kaituo Feng, Bohao Li, Yibing Wang, Mofan Cheng, Shijia Yang, Jiaming Han, Benyou Wang, Yutong Bai, Zhuoran Yang, Xiangyu Yue
Abstract: Recently, multimodal large language models (MLLMs), such as GPT-4o, Gemini 1.5 Pro, and Reka Core, have expanded their capabilities to include vision and audio modalities. While these models demonstrate impressive performance across a wide range of audio-visual applications, our proposed DeafTest reveals that MLLMs often struggle with simple tasks humans find trivial: 1) determining which of two sounds is louder, and 2) determining which of two sounds has a higher pitch. Motivated by these observations, we introduce AV-Odyssey Bench, a comprehensive audio-visual benchmark designed to assess whether those MLLMs can truly understand the audio-visual information. This benchmark encompasses 4,555 carefully crafted problems, each incorporating text, visual, and audio components. To successfully infer answers, models must effectively leverage clues from both visual and audio inputs. To ensure precise and objective evaluation of MLLM responses, we have structured the questions as multiple-choice, eliminating the need for human evaluation or LLM-assisted assessment. We benchmark a series of closed-source and open-source models and summarize the observations. By revealing the limitations of current models, we aim to provide useful insight for future dataset collection and model development.
Authors: Annie N. Wang, Luchao Qi, Roni Sengupta
Abstract: We introduce a novel continual learning problem: how to sequentially update the weights of a personalized 2D and 3D generative face model as new batches of photos in different appearances, styles, poses, and lighting are captured regularly. We observe that naive sequential fine-tuning of the model leads to catastrophic forgetting of past representations of the individual's face. We then demonstrate that a simple random sampling-based experience replay method is effective at mitigating catastrophic forgetting when a relatively large number of images can be stored and replayed. However, for long-term deployment of these models with relatively smaller storage, this simple random sampling-based replay technique also forgets past representations. Thus, we introduce a novel experience replay algorithm that combines random sampling with StyleGAN's latent space to represent the buffer as an optimal convex hull. We observe that our proposed convex hull-based experience replay is more effective in preventing forgetting than a random sampling baseline and the lower bound.
Authors: Yiftach Edelstein, Or Patashnik, Dana Cohen-Bar, Lihi Zelnik-Manor
Abstract: Advancements in text-to-image diffusion models have led to significant progress in fast 3D content creation. One common approach is to generate a set of multi-view images of an object, and then reconstruct it into a 3D model. However, this approach bypasses the use of a native 3D representation of the object and is hence prone to geometric artifacts and limited in controllability and manipulation capabilities. An alternative approach involves native 3D generative models that directly produce 3D representations. These models, however, are typically limited in their resolution, resulting in lower quality 3D objects. In this work, we bridge the quality gap between methods that directly generate 3D representations and ones that reconstruct 3D objects from multi-view images. We introduce a multi-view to multi-view diffusion model called Sharp-It, which takes a 3D consistent set of multi-view images rendered from a low-quality object and enriches its geometric details and texture. The diffusion model operates on the multi-view set in parallel, in the sense that it shares features across the generated views. A high-quality 3D model can then be reconstructed from the enriched multi-view set. By leveraging the advantages of both 2D and 3D approaches, our method offers an efficient and controllable method for high-quality 3D content creation. We demonstrate that Sharp-It enables various 3D applications, such as fast synthesis, editing, and controlled generation, while attaining high-quality assets.
Authors: Jiangtao Wang, Zhen Qin, Yifan Zhang, Vincent Tao Hu, Bj\"orn Ommer, Rania Briq, Stefan Kesselheim
Abstract: Vision tokenizers have gained a lot of attraction due to their scalability and compactness; previous works depend on old-school GAN-based hyperparameters, biased comparisons, and a lack of comprehensive analysis of the scaling behaviours. To tackle those issues, we introduce Grouped Spherical Quantization (GSQ), featuring spherical codebook initialization and lookup regularization to constrain codebook latent to a spherical surface. Our empirical analysis of image tokenizer training strategies demonstrates that GSQ-GAN achieves superior reconstruction quality over state-of-the-art methods with fewer training iterations, providing a solid foundation for scaling studies. Building on this, we systematically examine the scaling behaviours of GSQ, specifically in latent dimensionality, codebook size, and compression ratios, and their impact on model performance. Our findings reveal distinct behaviours at high and low spatial compression levels, underscoring challenges in representing high-dimensional latent spaces. We show that GSQ can restructure high-dimensional latent into compact, low-dimensional spaces, thus enabling efficient scaling with improved quality. As a result, GSQ-GAN achieves a 16x down-sampling with a reconstruction FID (rFID) of 0.50.
Authors: Tianyu Wang, Jianming Zhang, Haitian Zheng, Zhihong Ding, Scott Cohen, Zhe Lin, Wei Xiong, Chi-Wing Fu, Luis Figueroa, Soo Ye Kim
Abstract: Shadows are often under-considered or even ignored in image editing applications, limiting the realism of the edited results. In this paper, we introduce MetaShadow, a three-in-one versatile framework that enables detection, removal, and controllable synthesis of shadows in natural images in an object-centered fashion. MetaShadow combines the strengths of two cooperative components: Shadow Analyzer, for object-centered shadow detection and removal, and Shadow Synthesizer, for reference-based controllable shadow synthesis. Notably, we optimize the learning of the intermediate features from Shadow Analyzer to guide Shadow Synthesizer to generate more realistic shadows that blend seamlessly with the scene. Extensive evaluations on multiple shadow benchmark datasets show significant improvements of MetaShadow over the existing state-of-the-art methods on object-centered shadow detection, removal, and synthesis. MetaShadow excels in image-editing tasks such as object removal, relocation, and insertion, pushing the boundaries of object-centered image editing.
Authors: Jiale Feng, Samuel W. Blair, Timilehin Ayanlade, Aditya Balu, Baskar Ganapathysubramanian, Arti Singh, Soumik Sarkar, Asheesh K Singh
Abstract: We present a novel method for soybean (Glycine max (L.) Merr.) yield estimation leveraging high throughput seed counting via computer vision and deep learning techniques. Traditional methods for collecting yield data are labor-intensive, costly, prone to equipment failures at critical data collection times, and require transportation of equipment across field sites. Computer vision, the field of teaching computers to interpret visual data, allows us to extract detailed yield information directly from images. By treating it as a computer vision task, we report a more efficient alternative, employing a ground robot equipped with fisheye cameras to capture comprehensive videos of soybean plots from which images are extracted in a variety of development programs. These images are processed through the P2PNet-Yield model, a deep learning framework where we combined a Feature Extraction Module (the backbone of the P2PNet-Soy) and a Yield Regression Module to estimate seed yields of soybean plots. Our results are built on three years of yield testing plot data - 8500 in 2021, 2275 in 2022, and 650 in 2023. With these datasets, our approach incorporates several innovations to further improve the accuracy and generalizability of the seed counting and yield estimation architecture, such as the fisheye image correction and data augmentation with random sensor effects. The P2PNet-Yield model achieved a genotype ranking accuracy score of up to 83%. It demonstrates up to a 32% reduction in time to collect yield data as well as costs associated with traditional yield estimation, offering a scalable solution for breeding programs and agricultural productivity enhancement.
Authors: R. R. Samani, A. Nunez, B. De Schutter
Abstract: The growing volume of available infrastructural monitoring data enables the development of powerful datadriven approaches to estimate infrastructure health conditions using direct measurements. This paper proposes a deep learning methodology to estimate infrastructure physical parameters, such as railway track stiffness, using drive-by vibration response signals. The proposed method employs a Long Short-term Memory (LSTM) feature extractor accounting for temporal dependencies in the feature extraction phase, and a bidirectional Long Short-term Memory (BiLSTM) networks to leverage bidirectional temporal dependencies in both the forward and backward paths of the drive-by vibration response in condition estimation phase. Additionally, a framing approach is employed to enhance the resolution of the monitoring task to the beam level by segmenting the vibration signal into frames equal to the distance between individual beams, centering the frames over the beam nodes. The proposed LSTM-BiLSTM model offers a versatile tool for various bridge and railway infrastructure conditions monitoring using direct drive-by vibration response measurements. The results demonstrate the potential of incorporating temporal analysis in the feature extraction phase and emphasize the pivotal role of bidirectional temporal information in infrastructure health condition estimation. The proposed methodology can accurately and automatically estimate railway track stiffness and identify local stiffness reductions in the presence of noise using drive-by measurements. An illustrative case study of vehicle-track interaction simulation is used to demonstrate the performance of the proposed model, achieving a maximum mean absolute percentage error of 1.7% and 0.7% in estimating railpad and ballast stiffness, respectively.
Authors: Lingteng Qiu, Shenhao Zhu, Qi Zuo, Xiaodong Gu, Yuan Dong, Junfei Zhang, Chao Xu, Zhe Li, Weihao Yuan, Liefeng Bo, Guanying Chen, Zilong Dong
Abstract: Generating animatable human avatars from a single image is essential for various digital human modeling applications. Existing 3D reconstruction methods often struggle to capture fine details in animatable models, while generative approaches for controllable animation, though avoiding explicit 3D modeling, suffer from viewpoint inconsistencies in extreme poses and computational inefficiencies. In this paper, we address these challenges by leveraging the power of generative models to produce detailed multi-view canonical pose images, which help resolve ambiguities in animatable human reconstruction. We then propose a robust method for 3D reconstruction of inconsistent images, enabling real-time rendering during inference. Specifically, we adapt a transformer-based video generation model to generate multi-view canonical pose images and normal maps, pretraining on a large-scale video dataset to improve generalization. To handle view inconsistencies, we recast the reconstruction problem as a 4D task and introduce an efficient 3D modeling approach using 4D Gaussian Splatting. Experiments demonstrate that our method achieves photorealistic, real-time animation of 3D human avatars from in-the-wild images, showcasing its effectiveness and generalization capability.
Authors: Viet Nguyen, Anh Aengus Nguyen, Trung Dao, Khoi Nguyen, Cuong Pham, Toan Tran, Anh Tran
Abstract: Recent approaches have yielded promising results in distilling multi-step text-to-image diffusion models into one-step ones. The state-of-the-art efficient distillation technique, i.e., SwiftBrushv2 (SBv2), even surpasses the teacher model's performance with limited resources. However, our study reveals its instability when handling different diffusion model backbones due to using a fixed guidance scale within the Variational Score Distillation (VSD) loss. Another weakness of the existing one-step diffusion models is the missing support for negative prompt guidance, which is crucial in practical image generation. This paper presents SNOOPI, a novel framework designed to address these limitations by enhancing the guidance in one-step diffusion models during both training and inference. First, we effectively enhance training stability through Proper Guidance-SwiftBrush (PG-SB), which employs a random-scale classifier-free guidance approach. By varying the guidance scale of both teacher models, we broaden their output distributions, resulting in a more robust VSD loss that enables SB to perform effectively across diverse backbones while maintaining competitive performance. Second, we propose a training-free method called Negative-Away Steer Attention (NASA), which integrates negative prompts into one-step diffusion models via cross-attention to suppress undesired elements in generated images. Our experimental results show that our proposed methods significantly improve baseline models across various metrics. Remarkably, we achieve an HPSv2 score of 31.08, setting a new state-of-the-art benchmark for one-step diffusion models.
Authors: Kefan Chen, Chaerin Min, Linguang Zhang, Shreyas Hampali, Cem Keskin, Srinath Sridhar
Abstract: Despite remarkable progress in image generation models, generating realistic hands remains a persistent challenge due to their complex articulation, varying viewpoints, and frequent occlusions. We present FoundHand, a large-scale domain-specific diffusion model for synthesizing single and dual hand images. To train our model, we introduce FoundHand-10M, a large-scale hand dataset with 2D keypoints and segmentation mask annotations. Our insight is to use 2D hand keypoints as a universal representation that encodes both hand articulation and camera viewpoint. FoundHand learns from image pairs to capture physically plausible hand articulations, natively enables precise control through 2D keypoints, and supports appearance control. Our model exhibits core capabilities that include the ability to repose hands, transfer hand appearance, and even synthesize novel views. This leads to zero-shot capabilities for fixing malformed hands in previously generated images, or synthesizing hand video sequences. We present extensive experiments and evaluations that demonstrate state-of-the-art performance of our method.
Authors: Fengyuan Shi, Zhuoyan Luo, Yixiao Ge, Yujiu Yang, Ying Shan, Limin Wang
Abstract: Existing vector quantization (VQ) methods struggle with scalability, largely attributed to the instability of the codebook that undergoes partial updates during training. The codebook is prone to collapse as utilization decreases, due to the progressively widening distribution gap between non-activated codes and visual features. To solve the problem, we propose Index Backpropagation Quantization (IBQ), a new VQ method for the joint optimization of all codebook embeddings and the visual encoder. Applying a straight-through estimator on the one-hot categorical distribution between the encoded feature and codebook, all codes are differentiable and maintain a consistent latent space with the visual encoder. IBQ enables scalable training of visual tokenizers and, for the first time, achieves a large-scale codebook ($2^{18}$) with high dimension ($256$) and high utilization. Experiments on the standard ImageNet benchmark demonstrate the scalability and superiority of IBQ, achieving competitive results on both reconstruction ($1.00$ rFID) and autoregressive visual generation ($2.05$ gFID). The code and models are available at https://github.com/TencentARC/SEED-Voken.
Authors: Zhiyuan Xu, Yinhe Chen, Huan-ang Gao, Weiyan Zhao, Guiyu Zhang, Hao Zhao
Abstract: Visual anagrams are images that change appearance upon transformation, like flipping or rotation. With the advent of diffusion models, generating such optical illusions can be achieved by averaging noise across multiple views during the reverse denoising process. However, we observe two critical failure modes in this approach: (i) concept segregation, where concepts in different views are independently generated, which can not be considered a true anagram, and (ii) concept domination, where certain concepts overpower others. In this work, we cast the visual anagram generation problem in a multi-task learning setting, where different viewpoint prompts are analogous to different tasks,and derive denoising trajectories that align well across tasks simultaneously. At the core of our designed framework are two newly introduced techniques, where (i) an anti-segregation optimization strategy that promotes overlap in cross-attention maps between different concepts, and (ii) a noise vector balancing method that adaptively adjusts the influence of different tasks. Additionally, we observe that directly averaging noise predictions yields suboptimal performance because statistical properties may not be preserved, prompting us to derive a noise variance rectification method. Extensive qualitative and quantitative experiments demonstrate our method's superior ability to generate visual anagrams spanning diverse concepts.
Authors: Daniel Geng, Charles Herrmann, Junhwa Hur, Forrester Cole, Serena Zhang, Tobias Pfaff, Tatiana Lopez-Guevara, Carl Doersch, Yusuf Aytar, Michael Rubinstein, Chen Sun, Oliver Wang, Andrew Owens, Deqing Sun
Abstract: Motion control is crucial for generating expressive and compelling video content; however, most existing video generation models rely mainly on text prompts for control, which struggle to capture the nuances of dynamic actions and temporal compositions. To this end, we train a video generation model conditioned on spatio-temporally sparse or dense motion trajectories. In contrast to prior motion conditioning work, this flexible representation can encode any number of trajectories, object-specific or global scene motion, and temporally sparse motion; due to its flexibility we refer to this conditioning as motion prompts. While users may directly specify sparse trajectories, we also show how to translate high-level user requests into detailed, semi-dense motion prompts, a process we term motion prompt expansion. We demonstrate the versatility of our approach through various applications, including camera and object motion control, "interacting" with an image, motion transfer, and image editing. Our results showcase emergent behaviors, such as realistic physics, suggesting the potential of motion prompts for probing video models and interacting with future generative world models. Finally, we evaluate quantitatively, conduct a human study, and demonstrate strong performance. Video results are available on our webpage: https://motion-prompting.github.io/
Authors: Ahsan Mehmood, Asma Sarauji, M. Mahboob Ur Rahman, Tareq Y. Al-Naffouri
Abstract: In the post-covid19 era, every new wave of the pandemic causes an increased concern among the masses to learn more about their state of well-being. Therefore, it is the need of the hour to come up with ubiquitous, low-cost, non-invasive tools for rapid and continuous monitoring of body vitals that reflect the status of one's overall health. In this backdrop, this work proposes a deep learning approach to turn a smartphone-the popular hand-held personal gadget-into a diagnostic tool to measure/monitor the three most important body vitals, i.e., pulse rate (PR), blood oxygen saturation level (aka SpO2), and respiratory rate (RR). Furthermore, we propose another method that could extract a single-lead electrocardiograph (ECG) of the subject. The proposed methods include the following core steps: subject records a small video of his/her fingertip by placing his/her finger on the rear camera of the smartphone, and the recorded video is pre-processed to extract the filtered and/or detrended video-photoplethysmography (vPPG) signal, which is then fed to custom-built convolutional neural networks (CNN), which eventually spit-out the vitals (PR, SpO2, and RR) as well as a single-lead ECG of the subject. To be precise, the contribution of this paper is two-fold: 1) estimation of the three body vitals (PR, SpO2, RR) from the vPPG data using custom-built CNNs, vision transformer, and most importantly by CLIP model; 2) a novel discrete cosine transform+feedforward neural network-based method that translates the recorded video- PPG signal to a single-lead ECG signal. The proposed method is anticipated to find its application in several use-case scenarios, e.g., remote healthcare, mobile health, fitness, sports, etc.
Authors: Rose Alaslani, Levina Perzhilla, Muhammad Mahboob Ur Rahman, Taous-Meriem Laleg-Kirati, Tareq Y. Al-Naffouri
Abstract: This work proposes for the first time to utilize the regular smartphone -- a popular assistive gadget -- to design a novel, non-invasive method for self-monitoring of one's hydration level on a scale of 1 to 4. The proposed method involves recording a small video of a fingertip using the smartphone camera. Subsequently, a photoplethysmography (PPG) signal is extracted from the video data, capturing the fluctuations in peripheral blood volume as a reflection of a person's hydration level changes over time. To train and evaluate the artificial intelligence models, a custom multi-session labeled dataset was constructed by collecting video-PPG data from 25 fasting subjects during the month of Ramadan in 2023. With this, we solve two distinct problems: 1) binary classification (whether a person is hydrated or not), 2) four-class classification (whether a person is fully hydrated, mildly dehydrated, moderately dehydrated, or extremely dehydrated). For both classification problems, we feed the pre-processed and augmented PPG data to a number of machine learning, deep learning and transformer models which models provide a very high accuracy, i.e., in the range of 95% to 99%. We also propose an alternate method where we feed high-dimensional PPG time-series data to a DL model for feature extraction, followed by t-SNE method for feature selection and dimensionality reduction, followed by a number of ML classifiers that do dehydration level classification. Finally, we interpret the decisions by the developed deep learning model under the SHAP-based explainable artificial intelligence framework. The proposed method allows rapid, do-it-yourself, at-home testing of one's hydration level, is cost-effective and thus inline with the sustainable development goals 3 & 10 of the United Nations, and a step-forward to patient-centric healthcare systems, smart homes, and smart cities of future.
Authors: Qiyang Sun, Alican Akman, Bj\"orn W. Schuller
Abstract: The continuous development of artificial intelligence (AI) theory has propelled this field to unprecedented heights, owing to the relentless efforts of scholars and researchers. In the medical realm, AI takes a pivotal role, leveraging robust machine learning (ML) algorithms. AI technology in medical imaging aids physicians in X-ray, computed tomography (CT) scans, and magnetic resonance imaging (MRI) diagnoses, conducts pattern recognition and disease prediction based on acoustic data, delivers prognoses on disease types and developmental trends for patients, and employs intelligent health management wearable devices with human-computer interaction technology to name but a few. While these well-established applications have significantly assisted in medical field diagnoses, clinical decision-making, and management, collaboration between the medical and AI sectors faces an urgent challenge: How to substantiate the reliability of decision-making? The underlying issue stems from the conflict between the demand for accountability and result transparency in medical scenarios and the black-box model traits of AI. This article reviews recent research grounded in explainable artificial intelligence (XAI), with an emphasis on medical practices within the visual, audio, and multimodal perspectives. We endeavour to categorise and synthesise these practices, aiming to provide support and guidance for future researchers and healthcare professionals.
Authors: Tom Bisson, Isil Dogan O, Iris Piwonski, Tim-Rasmus Kiehl, Georg Lukas Baumg\"artner, Rita Carvalho, Peter Hufnagl, Tobias Penzkofer, Norman Zerbe, Sefer Elezkurtaj
Abstract: Surgical treatment for prostate cancer often involves organ removal, i.e., prostatectomy. Pathology reports on these specimens convey treatment-relevant information. Beyond these reports, the diagnostic process generates extensive and complex information that is difficult to represent in reports, although it is of significant interest to the other medical specialties involved. 3D tissue reconstruction would allow for better spatial visualization, as well as combinations with other imaging modalities. Existing approaches in this area have proven labor-intensive and challenging to integrate into clinical workflows. 3D-SLIVER provides a simplified solution, implemented as an open-source 3DSlicer extension. We outline three specific real-world scenarios to illustrate its potential to improve transparency in diagnostic workflows and contribute to multi-modal research endeavors. Implementing the 3D reconstruction process involved four sub-modules of 3D-SLIVER: digitization of slicing protocol, virtual slicing of arbitrary 3D models based on that protocol, registration of slides with virtual slices using the Coherent Point Drift algorithm, and 3D reconstruction of registered information using convex hulls, Gaussian splatter and linear extrusion. Three use cases to employ 3D-SLIVER are presented: a low-effort approach to pathology workflow integration and two research-related use cases illustrating how to perform retrospective evaluations of PI-RADS predictions and statistically model 3D distributions of morphological patterns. 3D-SLIVER allows for improved interdisciplinary communication among specialties. It is designed for simplicity in application, allowing for flexible integration into various workflows and use cases. Here we focused on the clinical care of prostate cancer patients, but future possibilities are extensive with other neoplasms and in education and research.
Authors: Xueyang Li, Han Xiao, Weixiang Weng, Xiaowei Xu, Yiyu Shi
Abstract: Colorectal cancer is a prevalent form of cancer, and many patients develop colorectal cancer liver metastasis (CRLM) as a result. Early detection of CRLM is critical for improving survival rates. Radiologists usually rely on a series of multi-phase contrast-enhanced computed tomography (CECT) scans done during follow-up visits to perform early detection of the potential CRLM. These scans form unique five-dimensional data (time, phase, and axial, sagittal, and coronal planes in 3D CT). Most of the existing deep learning models can readily handle four-dimensional data (e.g., time-series 3D CT images) and it is not clear how well they can be extended to handle the additional dimension of phase. In this paper, we build a dataset of time-series CECT scans to aid in the early diagnosis of CRLM, and build upon state-of-the-art deep learning techniques to evaluate how to best predict CRLM. Our experimental results show that a multi-plane architecture based on 3D bi-directional LSTM, which we call MPBD-LSTM, works best, achieving an area under curve (AUC) of 0.79. On the other hand, analysis of the results shows that there is still great room for further improvement.
Authors: Wenbo Zhang, Junyu Chen, Christopher Kanan
Abstract: Due to their large sizes, volumetric scans and whole-slide pathology images (WSIs) are often processed by extracting embeddings from local regions and then an aggregator makes predictions from this set. However, current methods require post-hoc visualization techniques (e.g., Grad-CAM) and often fail to localize small yet clinically crucial details. To address these limitations, we introduce INSIGHT, a novel weakly-supervised aggregator that integrates heatmap generation as an inductive bias. Starting from pre-trained feature maps, INSIGHT employs a detection module with small convolutional kernels to capture fine details and a context module with a broader receptive field to suppress local false positives. The resulting internal heatmap highlights diagnostically relevant regions. On CT and WSI benchmarks, INSIGHT achieves state-of-the-art classification results and high weakly-labeled semantic segmentation performance. Project website and code are available at: https://zhangdylan83.github.io/ewsmia/
Authors: Ihab Tabbara, Hussein Sibai
Abstract: Safety filters in control systems correct nominal controls that violate safety constraints. Designing such filters as functions of visual observations in uncertain and complex environments is challenging. Several deep learning-based approaches to tackle this challenge have been proposed recently. However, formally verifying that the learned filters satisfy critical properties that enable them to guarantee the safety of the system is currently beyond reach. Instead, in this work, motivated by the success of ensemble methods in reinforcement learning, we empirically investigate the efficacy of ensembles in enhancing the accuracy and the out-of-distribution generalization of such filters, as a step towards more reliable ones. We experiment with diverse pre-trained vision representation models as filter backbones, training approaches, and output aggregation techniques. We compare the performance of ensembles with different configurations against each other, their individual member models, and large single-model baselines in distinguishing between safe and unsafe states and controls in the DeepAccident dataset. Our results show that diverse ensembles have better state and control classification accuracies compared to individual models.
Authors: Pan Zhang, Baochai Peng, Chaoran Lu, Quanjin Huang
Abstract: Synthetic Aperture Radar (SAR) images have proven to be a valuable cue for multimodal Land Cover Classification (LCC) when combined with RGB images. Most existing studies on cross-modal fusion assume that consistent feature information is necessary between the two modalities, and as a result, they construct networks without adequately addressing the unique characteristics of each modality. In this paper, we propose a novel architecture, named the Asymmetric Semantic Aligning Network (ASANet), which introduces asymmetry at the feature level to address the issue that multi-modal architectures frequently fail to fully utilize complementary features. The core of this network is the Semantic Focusing Module (SFM), which explicitly calculates differential weights for each modality to account for the modality-specific features. Furthermore, ASANet incorporates a Cascade Fusion Module (CFM), which delves deeper into channel and spatial representations to efficiently select features from the two modalities for fusion. Through the collaborative effort of these two modules, the proposed ASANet effectively learns feature correlations between the two modalities and eliminates noise caused by feature differences. Comprehensive experiments demonstrate that ASANet achieves excellent performance on three multimodal datasets. Additionally, we have established a new RGB-SAR multimodal dataset, on which our ASANet outperforms other mainstream methods with improvements ranging from 1.21% to 17.69%. The ASANet runs at 48.7 frames per second (FPS) when the input image is 256x256 pixels. The source code are available at https://github.com/whu-pzhang/ASANet
Authors: Justin Folden, Atul Ingle, Sanjeev J. Koppal
Abstract: Fast, efficient, and accurate depth-sensing is important for safety-critical applications such as autonomous vehicles. Direct time-of-flight LiDAR has the potential to fulfill these demands, thanks to its ability to provide high-precision depth measurements at long standoff distances. While conventional LiDAR relies on avalanche photodiodes (APDs), single-photon avalanche diodes (SPADs) are an emerging image-sensing technology that offer many advantages such as extreme sensitivity and time resolution. In this paper, we remove the key challenges to widespread adoption of SPAD-based LiDARs: their susceptibility to ambient light and the large amount of raw photon data that must be processed to obtain in-pixel depth estimates. We propose new algorithms and sensing policies that improve signal-to-noise ratio (SNR) and increase computing and memory efficiency for SPAD-based LiDARs. During capture, we use external signals to \emph{foveate}, i.e., guide how the SPAD system estimates scene depths. This foveated approach allows our method to ``zoom into'' the signal of interest, reducing the amount of raw photon data that needs to be stored and transferred from the SPAD sensor, while also improving resilience to ambient light. We show results both in simulation and also with real hardware emulation, with specific implementations achieving a 1548-fold reduction in memory usage, and our algorithms can be applied to newly available and future SPAD arrays.
Authors: Ao Liu, Cuihong Wen, Jieci Wang
Abstract: Deep Learning has shown remarkable capabilities in pattern recognition, feature extraction, and classification decision-making. With the rise of quantum computing, the potential of quantum neural networks (QNNs) in Artificial Intelligence is emerging. However, the intrinsic mechanisms and decision transparency of QNNs remain unclear. In this paper, we propose a classic-quantum hybrid network framework (CQH-Net), which uses traditional machine learning methods for feature extraction and quantizes neural networks for classification tasks. We apply CQH-Net to image classification on public datasets. Experimentally, CQH-Net achieves an average convergence rate improvement of 72.8% compared to classical convolutional networks (CNNs) with identical parameters. On the Fashion MNIST dataset, it reaches a final accuracy of 99.02%, representing a significant increase of 5.07% over CNNs. Furthermore, we explore visual explanations for CQH-Net's decision-making process. Results show that the model effectively captures key data features during training and establishes associations between these features and their corresponding categories. This study demonstrates that quantization enhances the models ability to tackle complex classification problems while providing transparency in its decision-making process further supporting quantum advantages in machine learning.
Authors: Md Hafizur Rahman, Md Mashfiq Rizvee, Sumaiya Shomaji, Prabuddha Chakraborty
Abstract: Artificial intelligence (AI) is widely used in various fields including healthcare, autonomous vehicles, robotics, traffic monitoring, and agriculture. Many modern AI applications in these fields are multi-tasking in nature (i.e. perform multiple analysis on same data) and are deployed on resource-constrained edge devices requiring the AI models to be efficient across different metrics such as power, frame rate, and size. For these specific use-cases, in this work, we propose a new paradigm of neural network architecture (ILASH) that leverages a layer sharing concept for minimizing power utilization, increasing frame rate, and reducing model size. Additionally, we propose a novel neural network architecture search framework (ILASH-NAS) for efficient construction of these neural network models for a given set of tasks and device constraints. The proposed NAS framework utilizes a data-driven intelligent approach to make the search efficient in terms of energy, time, and CO2 emission. We perform extensive evaluations of the proposed layer shared architecture paradigm (ILASH) and the ILASH-NAS framework using four open-source datasets (UTKFace, MTFL, CelebA, and Taskonomy). We compare ILASH-NAS with AutoKeras and observe significant improvement in terms of both the generated model performance and neural search efficiency with up to 16x less energy utilization, CO2 emission, and training/search time.
Authors: Junqiu Yu, Xinlin Ren, Yongchong Gu, Haitao Lin, Tianyu Wang, Yi Zhu, Hang Xu, Yu-Gang Jiang, Xiangyang Xue, Yanwei Fu
Abstract: Language-guided robotic grasping is a rapidly advancing field where robots are instructed using human language to grasp specific objects. However, existing methods often depend on dense camera views and struggle to quickly update scenes, limiting their effectiveness in changeable environments. In contrast, we propose SparseGrasp, a novel open-vocabulary robotic grasping system that operates efficiently with sparse-view RGB images and handles scene updates fastly. Our system builds upon and significantly enhances existing computer vision modules in robotic learning. Specifically, SparseGrasp utilizes DUSt3R to generate a dense point cloud as the initialization for 3D Gaussian Splatting (3DGS), maintaining high fidelity even under sparse supervision. Importantly, SparseGrasp incorporates semantic awareness from recent vision foundation models. To further improve processing efficiency, we repurpose Principal Component Analysis (PCA) to compress features from 2D models. Additionally, we introduce a novel render-and-compare strategy that ensures rapid scene updates, enabling multi-turn grasping in changeable environments. Experimental results show that SparseGrasp significantly outperforms state-of-the-art methods in terms of both speed and adaptability, providing a robust solution for multi-turn grasping in changeable environment.
Authors: Fnu Neha, Deepshikha Bhati, Deepak Kumar Shukla, Sonavi Makarand Dalvi, Nikolaos Mantzou, Safa Shubbar
Abstract: Medical imaging is essential in healthcare to provide key insights into patient anatomy and pathology, aiding in diagnosis and treatment. Non-invasive techniques such as X-ray, Magnetic Resonance Imaging (MRI), Computed Tomography (CT), and Ultrasound (US), capture detailed images of organs, tissues, and abnormalities. Effective analysis of these images requires precise segmentation to delineate regions of interest (ROI), such as organs or lesions. Traditional segmentation methods, relying on manual feature-extraction, are labor-intensive and vary across experts. Recent advancements in Artificial Intelligence (AI) and Deep Learning (DL), particularly convolutional models such as U-Net and its variants (U-Net++ and U-Net 3+), have transformed medical image segmentation (MIS) by automating the process and enhancing accuracy. These models enable efficient, precise pixel-wise classification across various imaging modalities, overcoming the limitations of manual segmentation. This review explores various medical imaging techniques, examines the U-Net architectures and their adaptations, and discusses their application across different modalities. It also identifies common challenges in MIS and proposes potential solutions.
Authors: Jing Zeng, Qi Ye, Tianle Liu, Yang Xu, Jin Li, Jinming Xu, Liang Li, Jiming Chen
Abstract: Implicit neural representations and 3D Gaussian splatting (3DGS) have shown great potential for scene reconstruction. Recent studies have expanded their applications in autonomous reconstruction through task assignment methods. However, these methods are mainly limited to single robot, and rapid reconstruction of large-scale scenes remains challenging. Additionally, task-driven planning based on surface uncertainty is prone to being trapped in local optima. To this end, we propose the first 3DGS-based centralized multi-robot autonomous 3D reconstruction framework. To further reduce time cost of task generation and improve reconstruction quality, we integrate online open-vocabulary semantic segmentation with surface uncertainty of 3DGS, focusing view sampling on regions with high instance uncertainty. Finally, we develop a multi-robot collaboration strategy with mode and task assignments improving reconstruction quality while ensuring planning efficiency. Our method demonstrates the highest reconstruction quality among all planning methods and superior planning efficiency compared to existing multi-robot methods. We deploy our method on multiple robots, and results show that it can effectively plan view paths and reconstruct scenes with high quality.
Authors: Jaehyun Choi, Junwon Ko, Dong-Jae Lee, Junmo Kim
Abstract: Open compound domain adaptation (OCDA) is a practical domain adaptation problem that consists of a source domain, target compound domain, and unseen open domain. In this problem, the absence of domain labels and pixel-level segmentation labels for both compound and open domains poses challenges to the direct application of existing domain adaptation and generalization methods. To address this issue, we propose Amplitude-based curriculum learning and a Hopfield segmentation model for Open Compound Domain Adaptation (AH-OCDA). Our method comprises two complementary components: 1) amplitude-based curriculum learning and 2) Hopfield segmentation model. Without prior knowledge of target domains within the compound domains, amplitude-based curriculum learning gradually induces the semantic segmentation model to adapt from the near-source compound domain to the far-source compound domain by ranking unlabeled compound domain images through Fast Fourier Transform (FFT). Additionally, the Hopfield segmentation model maps segmentation feature distributions from arbitrary domains to the feature distributions of the source domain. AH-OCDA achieves state-of-the-art performance on two OCDA benchmarks and extended open domains, demonstrating its adaptability to continuously changing compound domains and unseen open domains.
Authors: Maximilian E. Tschuchnig, Philipp Steininger, Michael Gadermayr
Abstract: Computer-Assisted Interventions enable clinicians to perform precise, minimally invasive procedures, often relying on advanced imaging methods. Cone-beam computed tomography (CBCT) can be used to facilitate computer-assisted interventions, despite often suffering from artifacts that pose challenges for accurate interpretation. While the degraded image quality can affect image analysis, the availability of high quality, preoperative scans offers potential for improvements. Here we consider a setting where preoperative CT and intraoperative CBCT scans are available, however, the alignment (registration) between the scans is imperfect to simulate a real world scenario. We propose a multimodal learning method that fuses roughly aligned CBCT and CT scans and investigate the effect on segmentation performance. For this experiment we use synthetically generated data containing real CT and synthetic CBCT volumes with corresponding voxel annotations. We show that this fusion setup improves segmentation performance in $18$ out of $20$ investigated setups.
Authors: Jiamian Hu, Yuanyuan Hong, Yihua Chen, He Wang, Moriaki Yasuhara
Abstract: We present the Noisy Ostracods, a noisy dataset for genus and species classification of crustacean ostracods with specialists' annotations. Over the 71466 specimens collected, 5.58% of them are estimated to be noisy (possibly problematic) at genus level. The dataset is created to addressing a real-world challenge: creating a clean fine-grained taxonomy dataset. The Noisy Ostracods dataset has diverse noises from multiple sources. Firstly, the noise is open-set, including new classes discovered during curation that were not part of the original annotation. The dataset has pseudo-classes, where annotators misclassified samples that should belong to an existing class into a new pseudo-class. The Noisy Ostracods dataset is highly imbalanced with a imbalance factor $\rho$ = 22429. This presents a unique challenge for robust machine learning methods, as existing approaches have not been extensively evaluated on fine-grained classification tasks with such diverse real-world noise. Initial experiments using current robust learning techniques have not yielded significant performance improvements on the Noisy Ostracods dataset compared to cross-entropy training on the raw, noisy data. On the other hand, noise detection methods have underperformed in error hit rate compared to naive cross-validation ensembling for identifying problematic labels. These findings suggest that the fine-grained, imbalanced nature, and complex noise characteristics of the dataset present considerable challenges for existing noise-robust algorithms. By openly releasing the Noisy Ostracods dataset, our goal is to encourage further research into the development of noise-resilient machine learning methods capable of effectively handling diverse, real-world noise in fine-grained classification tasks. The dataset, along with its evaluation protocols, can be accessed at https://github.com/H-Jamieu/Noisy_ostracods.
Authors: Leixin Zhang, Steffen Eger, Yinjie Cheng, Weihe Zhai, Jonas Belouadi, Christoph Leiter, Simone Paolo Ponzetto, Fahimeh Moafian, Zhixue Zhao
Abstract: Multimodal large language models (LLMs) have demonstrated impressive capabilities in generating high-quality images from textual instructions. However, their performance in generating scientific images--a critical application for accelerating scientific progress--remains underexplored. In this work, we address this gap by introducing ScImage, a benchmark designed to evaluate the multimodal capabilities of LLMs in generating scientific images from textual descriptions. ScImage assesses three key dimensions of understanding: spatial, numeric, and attribute comprehension, as well as their combinations, focusing on the relationships between scientific objects (e.g., squares, circles). We evaluate five models, GPT-4o, Llama, AutomaTikZ, Dall-E, and StableDiffusion, using two modes of output generation: code-based outputs (Python, TikZ) and direct raster image generation. Additionally, we examine four different input languages: English, German, Farsi, and Chinese. Our evaluation, conducted with 11 scientists across three criteria (correctness, relevance, and scientific accuracy), reveals that while GPT-4o produces outputs of decent quality for simpler prompts involving individual dimensions such as spatial, numeric, or attribute understanding in isolation, all models face challenges in this task, especially for more complex prompts.
Authors: Martin K\v{r}\'i\v{z}ek, Matou\v{s} Vrba, Antonella Bari\v{s}i\'c Kula\v{s}, Stjepan Bogdan, Martin Saska
Abstract: We propose a new approach to visual perception for relative localization of agents within large-scale swarms of UAVs. Inspired by biological perception utilized by schools of sardines, swarms of bees, and other large groups of animals capable of moving in a decentralized yet coherent manner, our method does not rely on detecting individual neighbors by each agent and estimating their relative position, but rather we propose to regress a neighbor density over distance. This allows for a more accurate distance estimation as well as better scalability with respect to the number of neighbors. Additionally, a novel swarm control algorithm is proposed to make it compatible with the new relative localization method. We provide a thorough evaluation of the presented methods and demonstrate that the regressing approach to distance estimation is more robust to varying relative pose of the targets and that it is suitable to be used as the main source of relative localization for swarm stabilization.
Authors: Adam Wr\'obel, Miko{\l}aj Janusz, Bartosz Zieli\'nski, Dawid Rymarczyk
Abstract: Deep Learning (DL) models are often black boxes, making their decision-making processes difficult to interpret. This lack of transparency has driven advancements in eXplainable Artificial Intelligence (XAI), a field dedicated to clarifying the reasoning behind DL model predictions. Among these, attribution-based methods such as LRP and GradCAM are widely used, though they rely on approximations that can be imprecise. To address these limitations, we introduce One Matrix to Explain Neural Networks (OMENN), a novel post-hoc method that represents a neural network as a single, interpretable matrix for each specific input. This matrix is constructed through a series of linear transformations that represent the processing of the input by each successive layer in the neural network. As a result, OMENN provides locally precise, attribution-based explanations of the input across various modern models, including ViTs and CNNs. We present a theoretical analysis of OMENN based on dynamic linearity property and validate its effectiveness with extensive tests on two XAI benchmarks, demonstrating that OMENN is competitive with state-of-the-art methods.
Authors: Tom White
Abstract: We present VISTA (Visualization of Internal States and Their Associations), a novel pipeline for visually exploring and interpreting neural network representations. VISTA addresses the challenge of analyzing vast multidimensional spaces in modern machine learning models by mapping representations into a semantic 2D space. The resulting collages visually reveal patterns and relationships within internal representations. We demonstrate VISTA's utility by applying it to sparse autoencoder latents uncovering new properties and interpretations. We review the VISTA methodology, present findings from our case study ( https://got.drib.net/latents/ ), and discuss implications for neural network interpretability across various domains of machine learning.
Authors: Mingyi Shi, Dafei Qin, Leo Ho, Zhouyingcheng Liao, Yinghao Huang, Junichi Yamagishi, Taku Komura
Abstract: Conversational scenarios are very common in real-world settings, yet existing co-speech motion synthesis approaches often fall short in these contexts, where one person's audio and gestures will influence the other's responses. Additionally, most existing methods rely on offline sequence-to-sequence frameworks, which are unsuitable for online applications. In this work, we introduce an audio-driven, auto-regressive system designed to synthesize dynamic movements for two characters during a conversation. At the core of our approach is a diffusion-based full-body motion synthesis model, which is conditioned on the past states of both characters, speech audio, and a task-oriented motion trajectory input, allowing for flexible spatial control. To enhance the model's ability to learn diverse interactions, we have enriched existing two-person conversational motion datasets with more dynamic and interactive motions. We evaluate our system through multiple experiments to show it outperforms across a variety of tasks, including single and two-person co-speech motion generation, as well as interactive motion generation. To the best of our knowledge, this is the first system capable of generating interactive full-body motions for two characters from speech in an online manner.
Authors: Malik Abdul Manan, Feng Jinchao, Muhammad Yaqub, Shahzad Ahmed, Syed Muhammad Ali Imran, Imran Shabir Chuhan, Haroon Ahmed Khan
Abstract: Colorectal polyps are structural abnormalities of the gastrointestinal tract that can potentially become cancerous in some cases. The study introduces a novel framework for colorectal polyp segmentation named the Multi-Scale and Multi-Path Cascaded Convolution Network (MMCC-Net), aimed at addressing the limitations of existing models, such as inadequate spatial dependence representation and the absence of multi-level feature integration during the decoding stage by integrating multi-scale and multi-path cascaded convolutional techniques and enhances feature aggregation through dual attention modules, skip connections, and a feature enhancer. MMCC-Net achieves superior performance in identifying polyp areas at the pixel level. The Proposed MMCC-Net was tested across six public datasets and compared against eight SOTA models to demonstrate its efficiency in polyp segmentation. The MMCC-Net's performance shows Dice scores with confidence intervals ranging between (77.08, 77.56) and (94.19, 94.71) and Mean Intersection over Union (MIoU) scores with confidence intervals ranging from (72.20, 73.00) to (89.69, 90.53) on the six databases. These results highlight the model's potential as a powerful tool for accurate and efficient polyp segmentation, contributing to early detection and prevention strategies in colorectal cancer.
Authors: Chenguang Huang, Shengchao Yan, Wolfram Burgard
Abstract: Dynamic scene understanding remains a persistent challenge in robotic applications. Early dynamic mapping methods focused on mitigating the negative influence of short-term dynamic objects on camera motion estimation by masking or tracking specific categories, which often fall short in adapting to long-term scene changes. Recent efforts address object association in long-term dynamic environments using neural networks trained on synthetic datasets, but they still rely on predefined object shapes and categories. Other methods incorporate visual, geometric, or semantic heuristics for the association but often lack robustness. In this work, we introduce BYE, a class-agnostic, per-scene point cloud encoder that removes the need for predefined categories, shape priors, or extensive association datasets. Trained on only a single sequence of exploration data, BYE can efficiently perform object association in dynamically changing scenes. We further propose an ensembling scheme combining the semantic strengths of Vision Language Models (VLMs) with the scene-specific expertise of BYE, achieving a 7% improvement and a 95% success rate in object association tasks. Code and dataset are available at https://byencoder.github.io.
Authors: Fabian Schmidt, Constantin Blessing, Markus Enzweiler, Abhinav Valada
Abstract: Robust Simultaneous Localization and Mapping (SLAM) is a crucial enabler for autonomous navigation in natural, unstructured environments such as parks and gardens. However, these environments present unique challenges for SLAM due to frequent seasonal changes, varying light conditions, and dense vegetation. These factors often degrade the performance of visual SLAM algorithms originally developed for structured urban environments. To address this gap, we present ROVER, a comprehensive benchmark dataset tailored for evaluating visual SLAM algorithms under diverse environmental conditions and spatial configurations. We captured the dataset with a robotic platform equipped with monocular, stereo, and RGB-D cameras, as well as inertial sensors. It covers 39 recordings across five outdoor locations, collected through all seasons and various lighting scenarios, i.e., day, dusk, and night with and without external lighting. With this novel dataset, we evaluate several traditional and deep learning-based SLAM methods and study their performance in diverse challenging conditions. The results demonstrate that while stereo-inertial and RGB-D configurations generally perform better under favorable lighting and moderate vegetation, most SLAM systems perform poorly in low-light and high-vegetation scenarios, particularly during summer and autumn. Our analysis highlights the need for improved adaptability in visual SLAM algorithms for outdoor applications, as current systems struggle with dynamic environmental factors affecting scale, feature extraction, and trajectory consistency. This dataset provides a solid foundation for advancing visual SLAM research in real-world, natural environments, fostering the development of more resilient SLAM systems for long-term outdoor localization and mapping. The dataset and the code of the benchmark are available under https://iis-esslingen.github.io/rover.
Authors: Haidong Xu, Meishan Zhang, Hao Ju, Zhedong Zheng, Hongyuan Zhu, Erik Cambria, Min Zhang, Hao Fei
Abstract: Producing emotionally dynamic 3D facial avatars with text derived from spoken words (Emo3D) has been a pivotal research topic in 3D avatar generation. While progress has been made in general-purpose 3D avatar generation, the exploration of generating emotional 3D avatars remains scarce, primarily due to the complexities of identifying and rendering rich emotions from spoken words. This paper reexamines Emo3D generation and draws inspiration from human processes, breaking down Emo3D into two cascading steps: Text-to-3D Expression Mapping (T3DEM) and 3D Avatar Rendering (3DAR). T3DEM is the most crucial step in determining the quality of Emo3D generation and encompasses three key challenges: Expression Diversity, Emotion-Content Consistency, and Expression Fluidity. To address these challenges, we introduce a novel benchmark to advance research in Emo3D generation. First, we present EmoAva, a large-scale, high-quality dataset for T3DEM, comprising 15,000 text-to-3D expression mappings that characterize the aforementioned three challenges in Emo3D generation. Furthermore, we develop various metrics to effectively evaluate models against these identified challenges. Next, to effectively model the consistency, diversity, and fluidity of human expressions in the T3DEM step, we propose the Continuous Text-to-Expression Generator, which employs an autoregressive Conditional Variational Autoencoder for expression code generation, enhanced with Latent Temporal Attention and Expression-wise Attention mechanisms. Finally, to further enhance the 3DAR step on rendering higher-quality subtle expressions, we present the Globally-informed Gaussian Avatar (GiGA) model. GiGA incorporates a global information mechanism into 3D Gaussian representations, enabling the capture of subtle micro-expressions and seamless transitions between emotional states.
Authors: Jan Quenzel, Linus T. Mallwitz, Benedikt T. Arnold, Sven Behnke
Abstract: Modern unmanned aerial vehicles (UAVs) are irreplaceable in search and rescue (SAR) missions to obtain a situational overview or provide closeups without endangering personnel. However, UAVs heavily rely on global navigation satellite system (GNSS) for localization which works well in open spaces, but the precision drastically degrades in the vicinity of buildings. These inaccuracies hinder aggregation of diverse data from multiple sources in a unified georeferenced frame for SAR operators. In contrast, CityGML models provide approximate building shapes with accurate georeferenced poses. Besides, LiDAR works best in the vicinity of 3D structures. Hence, we refine coarse GNSS measurements by registering LiDAR maps against CityGML and digital elevation map (DEM) models as a prior for allocentric mapping. An intuitive plausibility score selects the best hypothesis based on occupancy using a 2D height map. Afterwards, we integrate the registration results in a continuous-time spline-based pose graph optimizer with LiDAR odometry and further sensing modalities to obtain globally consistent, georeferenced trajectories and maps. We evaluate the viability of our approach on multiple flights captured at two distinct testing sites. Our method successfully reduced GNSS offset errors from up-to 16 m to below 0.5 m on multiple flights. Furthermore, we obtain globally consistent maps w.r.t. prior 3D geospatial models.
Authors: Ali Rostami, Fatemeh Fouladi, Hedieh Sajedi
Abstract: Coronary artery disease stands as one of the primary contributors to global mortality rates. The automated identification of coronary artery stenosis from X-ray images plays a critical role in the diagnostic process for coronary heart disease. This task is challenging due to the complex structure of coronary arteries, intrinsic noise in X-ray images, and the fact that stenotic coronary arteries appear narrow and blurred in X-ray angiographies. This study employs five different variants of the Mamba-based model and one variant of the Swin Transformer-based model, primarily based on the U-Net architecture, for the localization of stenosis in Coronary artery disease. Our best results showed an F1 score of 68.79% for the U-Mamba BOT model, representing an 11.8% improvement over the semi-supervised approach.
Authors: Jacob Marks, Brent A. Griffin, Jason J. Corso
Abstract: We introduce a new framework for analyzing classification datasets based on the ratios of reconstruction errors between autoencoders trained on individual classes. This analysis framework enables efficient characterization of datasets on the sample, class, and entire dataset levels. We define reconstruction error ratios (RERs) that probe classification difficulty and allow its decomposition into (1) finite sample size and (2) Bayes error and decision-boundary complexity. Through systematic study across 19 popular visual datasets, we find that our RER-based dataset difficulty probe strongly correlates with error rate for state-of-the-art (SOTA) classification models. By interpreting sample-level classification difficulty as a label mistakenness score, we further find that RERs achieve SOTA performance on mislabel detection tasks on hard datasets under symmetric and asymmetric label noise. Our code is publicly available at https://github.com/voxel51/reconstruction-error-ratios.
URLs: https://github.com/voxel51/reconstruction-error-ratios.
Authors: Hiroki Furuta, Heiga Zen, Dale Schuurmans, Aleksandra Faust, Yutaka Matsuo, Percy Liang, Sherry Yang
Abstract: Large text-to-video models hold immense potential for a wide range of downstream applications. However, these models struggle to accurately depict dynamic object interactions, often resulting in unrealistic movements and frequent violations of real-world physics. One solution inspired by large language models is to align generated outputs with desired outcomes using external feedback. This enables the model to refine its responses autonomously, eliminating extensive manual data collection. In this work, we investigate the use of feedback to enhance the object dynamics in text-to-video models. We aim to answer a critical question: what types of feedback, paired with which specific self-improvement algorithms, can most effectively improve text-video alignment and realistic object interactions? We begin by deriving a unified probabilistic objective for offline RL finetuning of text-to-video models. This perspective highlights how design elements in existing algorithms like KL regularization and policy projection emerge as specific choices within a unified framework. We then use derived methods to optimize a set of text-video alignment metrics (e.g., CLIP scores, optical flow), but notice that they often fail to align with human perceptions of generation quality. To address this limitation, we propose leveraging vision-language models to provide more nuanced feedback specifically tailored to object dynamics in videos. Our experiments demonstrate that our method can effectively optimize a wide variety of rewards, with binary AI feedback driving the most significant improvements in video quality for dynamic interactions, as confirmed by both AI and human evaluations. Notably, we observe substantial gains when using reward signals derived from AI feedback, particularly in scenarios involving complex interactions between multiple objects and realistic depictions of objects falling.
Authors: Xuanlin Li, Tong Zhao, Xinghao Zhu, Jiuguang Wang, Tao Pang, Kuan Fang
Abstract: Contact-rich bimanual manipulation involves precise coordination of two arms to change object states through strategically selected contacts and motions. Due to the inherent complexity of these tasks, acquiring sufficient demonstration data and training policies that generalize to unseen scenarios remain a largely unresolved challenge. Building on recent advances in planning through contacts, we introduce Generalizable Planning-Guided Diffusion Policy Learning (GLIDE), an approach that effectively learns to solve contact-rich bimanual manipulation tasks by leveraging model-based motion planners to generate demonstration data in high-fidelity physics simulation. Through efficient planning in randomized environments, our approach generates large-scale and high-quality synthetic motion trajectories for tasks involving diverse objects and transformations. We then train a task-conditioned diffusion policy via behavior cloning using these demonstrations. To tackle the sim-to-real gap, we propose a set of essential design options in feature extraction, task representation, action prediction, and data augmentation that enable learning robust prediction of smooth action sequences and generalization to unseen scenarios. Through experiments in both simulation and the real world, we demonstrate that our approach can enable a bimanual robotic system to effectively manipulate objects of diverse geometries, dimensions, and physical properties. Website: https://glide-manip.github.io/
Authors: Beihao Xia, Conghao Wong, Duanquan Xu, Qinmu Peng, Xinge You
Abstract: With the fast development of AI-related techniques, the applications of trajectory prediction are no longer limited to easier scenes and trajectories. More and more trajectories with different forms, such as coordinates, bounding boxes, and even high-dimensional human skeletons, need to be analyzed and forecasted. Among these heterogeneous trajectories, interactions between different elements within a frame of trajectory, which we call ``Dimension-wise Interactions'', would be more complex and challenging. However, most previous approaches focus mainly on a specific form of trajectories, and potential dimension-wise interactions are less concerned. In this work, we expand the trajectory prediction task by introducing the trajectory dimensionality $M$, thus extending its application scenarios to heterogeneous trajectories. We first introduce the Haar transform as an alternative to Fourier transform to better capture the time-frequency properties of each trajectory-dimension. Then, we adopt the bilinear structure to model and fuse two factors simultaneously, including the time-frequency response and the dimension-wise interaction, to forecast heterogeneous trajectories via trajectory spectrums hierarchically in a generic way. Experiments show that the proposed model outperforms most state-of-the-art methods on ETH-UCY, SDD, nuScenes, and Human3.6M with heterogeneous trajectories, including 2D coordinates, 2D/3D bounding boxes, and 3D human skeletons.
Authors: Ao Li, Le Zhang, Yun Liu, Ce Zhu
Abstract: Transformer-based methods have exhibited remarkable potential in single image super-resolution (SISR) by effectively extracting long-range dependencies. However, most of the current research in this area has prioritized the design of transformer blocks to capture global information, while overlooking the importance of incorporating high-frequency priors, which we believe could be beneficial. In our study, we conducted a series of experiments and found that transformer structures are more adept at capturing low-frequency information, but have limited capacity in constructing high-frequency representations when compared to their convolutional counterparts. Our proposed solution, the cross-refinement adaptive feature modulation transformer (CRAFT), integrates the strengths of both convolutional and transformer structures. It comprises three key components: the high-frequency enhancement residual block (HFERB) for extracting high-frequency information, the shift rectangle window attention block (SRWAB) for capturing global information, and the hybrid fusion block (HFB) for refining the global representation. To tackle the inherent intricacies of transformer structures, we introduce a frequency-guided post-training quantization (PTQ) method aimed at enhancing CRAFT's efficiency. These strategies incorporate adaptive dual clipping and boundary refinement. To further amplify the versatility of our proposed approach, we extend our PTQ strategy to function as a general quantization method for transformer-based SISR techniques. Our experimental findings showcase CRAFT's superiority over current state-of-the-art methods, both in full-precision and quantization scenarios. These results underscore the efficacy and universality of our PTQ strategy. The source code is available at: https://github.com/AVC2-UESTC/Frequency-Inspired-Optimization-for-EfficientSR.git.
URLs: https://github.com/AVC2-UESTC/Frequency-Inspired-Optimization-for-EfficientSR.git.
Authors: Minh-Quan Le, Minh-Triet Tran, Trung-Nghia Le, Tam V. Nguyen, Thanh-Toan Do
Abstract: Camouflaged object detection (COD) and camouflaged instance segmentation (CIS) aim to recognize and segment objects that are blended into their surroundings, respectively. While several deep neural network models have been proposed to tackle those tasks, augmentation methods for COD and CIS have not been thoroughly explored. Augmentation strategies can help improve models' performance by increasing the size and diversity of the training data and exposing the model to a wider range of variations in the data. Besides, we aim to automatically learn transformations that help to reveal the underlying structure of camouflaged objects and allow the model to learn to better identify and segment camouflaged objects. To achieve this, we propose a learnable augmentation method in the frequency domain for COD and CIS via the Fourier transform approach, dubbed CamoFA. Our method leverages a conditional generative adversarial network and cross-attention mechanism to generate a reference image and an adaptive hybrid swapping with parameters to mix the low-frequency component of the reference image and the high-frequency component of the input image. This approach aims to make camouflaged objects more visible for detection and segmentation models. Without bells and whistles, our proposed augmentation method boosts the performance of camouflaged object detectors and instance segmenters by large margins.
Authors: Rohit Lal, Saketh Bachu, Yash Garg, Arindam Dutta, Calvin-Khang Ta, Dripta S. Raychaudhuri, Hannah Dela Cruz, M. Salman Asif, Amit K. Roy-Chowdhury
Abstract: The capability to accurately estimate 3D human poses is crucial for diverse fields such as action recognition, gait recognition, and virtual/augmented reality. However, a persistent and significant challenge within this field is the accurate prediction of human poses under conditions of severe occlusion. Traditional image-based estimators struggle with heavy occlusions due to a lack of temporal context, resulting in inconsistent predictions. While video-based models benefit from processing temporal data, they encounter limitations when faced with prolonged occlusions that extend over multiple frames. This challenge arises because these models struggle to generalize beyond their training datasets, and the variety of occlusions is hard to capture in the training data. Addressing these challenges, we propose STRIDE (Single-video based TempoRally contInuous occlusion Robust 3D Pose Estimation), a novel Test-Time Training (TTT) approach to fit a human motion prior for each video. This approach specifically handles occlusions that were not encountered during the model's training. By employing STRIDE, we can refine a sequence of noisy initial pose estimates into accurate, temporally coherent poses during test time, effectively overcoming the limitations of prior methods. Our framework demonstrates flexibility by being model-agnostic, allowing us to use any off-the-shelf 3D pose estimation method for improving robustness and temporal consistency. We validate STRIDE's efficacy through comprehensive experiments on challenging datasets like Occluded Human3.6M, Human3.6M, and OCMotion, where it not only outperforms existing single-image and video-based pose estimation models but also showcases superior handling of substantial occlusions, achieving fast, robust, accurate, and temporally consistent 3D pose estimates. Code is made publicly available at https://github.com/take2rohit/stride
Authors: Joanna Waczy\'nska, Piotr Borycki, S{\l}awomir Tadeja, Jacek Tabor, Przemys{\l}aw Spurek
Abstract: Gaussian Splatting (GS) is a novel, state-of-the-art technique for rendering points in a 3D scene by approximating their contribution to image pixels through Gaussian distributions, warranting fast training and real-time rendering. The main drawback of GS is the absence of a well-defined approach for its conditioning due to the necessity of conditioning several hundred thousand Gaussian components. To solve this, we introduce the Gaussian Mesh Splatting (GaMeS) model, which allows modification of Gaussian components in a similar way as meshes. We parameterize each Gaussian component by the vertices of the mesh face. Furthermore, our model needs mesh initialization on input or estimated mesh during training. We also define Gaussian splats solely based on their location on the mesh, allowing for automatic adjustments in position, scale, and rotation during animation. As a result, we obtain a real-time rendering of editable GS.
Authors: Minsoo Kim, Min-Cheol Sagong, Gi Pyo Nam, Junghyun Cho, Ig-Jae Kim
Abstract: Deep learning-based face recognition continues to face challenges due to its reliance on huge datasets obtained from web crawling, which can be costly to gather and raise significant real-world privacy concerns. To address this issue, we propose VIGFace, a novel framework capable of generating synthetic facial images. Our idea originates from pre-assigning virtual identities in the feature space. Initially, we train the face recognition model using a real face dataset and create a feature space for both real and virtual identities, where virtual prototypes are orthogonal to other prototypes. Subsequently, we generate synthetic images by using the diffusion model based on the feature space. The diffusion model is capable of reconstructing authentic human facial representations from established real prototypes, while synthesizing virtual entities from devised virtual prototypes. Our proposed framework provides two significant benefits. Firstly, it allows one to create virtual facial images without concerns about privacy and portrait rights, guaranteeing that the generated virtual face images are clearly differentiated from existing individuals. Secondly, it serves as an effective augmentation method by incorporating real existing images. Further experiments demonstrate the superiority of our virtual face dataset and framework, outperforming the previous state-of-the-art on various face recognition benchmarks.
Authors: Ruida Zhang, Chenyangguang Zhang, Yan Di, Fabian Manhardt, Xingyu Liu, Federico Tombari, Xiangyang Ji
Abstract: In this paper, we present KP-RED, a unified KeyPoint-driven REtrieval and Deformation framework that takes object scans as input and jointly retrieves and deforms the most geometrically similar CAD models from a pre-processed database to tightly match the target. Unlike existing dense matching based methods that typically struggle with noisy partial scans, we propose to leverage category-consistent sparse keypoints to naturally handle both full and partial object scans. Specifically, we first employ a lightweight retrieval module to establish a keypoint-based embedding space, measuring the similarity among objects by dynamically aggregating deformation-aware local-global features around extracted keypoints. Objects that are close in the embedding space are considered similar in geometry. Then we introduce the neural cage-based deformation module that estimates the influence vector of each keypoint upon cage vertices inside its local support region to control the deformation of the retrieved shape. Extensive experiments on the synthetic dataset PartNet and the real-world dataset Scan2CAD demonstrate that KP-RED surpasses existing state-of-the-art approaches by a large margin. Codes and trained models are released on https://github.com/lolrudy/KP-RED.
Authors: Minkyu Choi, Harsh Goel, Mohammad Omama, Yunhao Yang, Sahil Shah, Sandeep Chinchali
Abstract: The unprecedented surge in video data production in recent years necessitates efficient tools to extract meaningful frames from videos for downstream tasks. Long-term temporal reasoning is a key desideratum for frame retrieval systems. While state-of-the-art foundation models, like VideoLLaMA and ViCLIP, are proficient in short-term semantic understanding, they surprisingly fail at long-term reasoning across frames. A key reason for this failure is that they intertwine per-frame perception and temporal reasoning into a single deep network. Hence, decoupling but co-designing semantic understanding and temporal reasoning is essential for efficient scene identification. We propose a system that leverages vision-language models for semantic understanding of individual frames but effectively reasons about the long-term evolution of events using state machines and temporal logic (TL) formulae that inherently capture memory. Our TL-based reasoning improves the F1 score of complex event identification by 9-15% compared to benchmarks that use GPT4 for reasoning on state-of-the-art self-driving datasets such as Waymo and NuScenes.
Authors: Pin-Hung Kuo, Jinshan Pan, Shao-Yi Chien, Ming-Hsuan Yang
Abstract: The Transformer architecture has achieved remarkable success in natural language processing and high-level vision tasks over the past few years. However, the inherent complexity of self-attention is quadratic to the size of the image, leading to unaffordable computational costs for high-resolution vision tasks. In this paper, we introduce Concertormer, featuring a novel Concerto Self-Attention (CSA) mechanism designed for image deblurring. The proposed CSA divides self-attention into two distinct components: one emphasizes generally global and another concentrates on specifically local correspondence. By retaining partial information in additional dimensions independent from the self-attention calculations, our method effectively captures global contextual representations with complexity linear to the image size. To effectively leverage the additional dimensions, we present a Cross-Dimensional Communication module, which linearly combines attention maps and thus enhances expressiveness. Moreover, we amalgamate the two-staged Transformer design into a single stage using the proposed gated-dconv MLP architecture. While our primary objective is single-image motion deblurring, extensive quantitative and qualitative evaluations demonstrate that our approach performs favorably against the state-of-the-art methods in other tasks, such as deraining and deblurring with JPEG artifacts. The source codes and trained models will be made available to the public.
Authors: Tianyi Liang, Jiangqi Liu, Sicheng Song, Shiqi Jiang, Yifei Huang, Xinzhuo Zhang, Changbo Wang, Chenhui Li
Abstract: Recent advancements in Text-to-image (T2I) generation have witnessed a shift from adapting text to fixed backgrounds to creating images around text. Traditional approaches are often limited to generate layouts within static images for effective text placement. Our proposed approach, TextCenGen, introduces a dynamic adaptation of the blank region for text-friendly image generation, emphasizing text-centric design and visual harmony generation. Our method employs force-directed attention guidance in T2I models to generate images that strategically reserve whitespace for pre-defined text areas, even for text or icons at the golden ratio. Observing how cross-attention maps affect object placement, we detect and repel conflicting objects using a force-directed graph approach, combined with a Spatial Excluding Cross-Attention Constraint for smooth attention in whitespace areas. As a novel task in graphic design, experiments indicate that TextCenGen outperforms existing methods with more harmonious compositions. Furthermore, our method significantly enhances T2I model outcomes on our specially collected prompt datasets, catering to varied text positions. These results demonstrate the efficacy of TextCenGen in creating more harmonious and integrated text-image compositions.
Authors: Nupur Kumari, Grace Su, Richard Zhang, Taesung Park, Eli Shechtman, Jun-Yan Zhu
Abstract: Model customization introduces new concepts to existing text-to-image models, enabling the generation of these new concepts/objects in novel contexts. However, such methods lack accurate camera view control with respect to the new object, and users must resort to prompt engineering (e.g., adding ``top-view'') to achieve coarse view control. In this work, we introduce a new task -- enabling explicit control of the object viewpoint in the customization of text-to-image diffusion models. This allows us to modify the custom object's properties and generate it in various background scenes via text prompts, all while incorporating the object viewpoint as an additional control. This new task presents significant challenges, as one must harmoniously merge a 3D representation from the multi-view images with the 2D pre-trained model. To bridge this gap, we propose to condition the diffusion process on the 3D object features rendered from the target viewpoint. During training, we fine-tune the 3D feature prediction modules to reconstruct the object's appearance and geometry, while reducing overfitting to the input multi-view images. Our method outperforms existing image editing and model customization baselines in preserving the custom object's identity while following the target object viewpoint and the text prompt.
Authors: Joanna Waczy\'nska, Piotr Borycki, Joanna Kaleta, S{\l}awomir Tadeja, Przemys{\l}aw Spurek
Abstract: Over the past years, we have observed an abundance of approaches for modeling dynamic 3D scenes using Gaussian Splatting (GS). Such solutions use GS to represent the scene's structure and the neural network to model dynamics. Such approaches allow fast rendering and extracting each element of such a dynamic scene. However, modifying such objects over time is challenging. SC-GS (Sparse Controlled Gaussian Splatting) enhanced with Deformed Control Points partially solves this issue. However, this approach necessitates selecting elements that need to be kept fixed, as well as centroids that should be adjusted throughout editing. Moreover, this task poses additional difficulties regarding the re-productivity of such editing. To address this, we propose Dynamic Multi-Gaussian Soup (D-MiSo), which allows us to model the mesh-inspired representation of dynamic GS. Additionally, we propose a strategy of linking parameterized Gaussian splats, forming a Triangle Soup with the estimated mesh. Consequently, we can separately construct new trajectories for the 3D objects composing the scene. Thus, we can make the scene's dynamic editable over time or while maintaining partial dynamics.
Authors: Yangxiao Lu, Jishnu Jaykumar P, Yunhui Guo, Nicholas Ruozzi, Yu Xiang
Abstract: Novel Instance Detection and Segmentation (NIDS) aims at detecting and segmenting novel object instances given a few examples of each instance. We propose a unified, simple yet effective framework (NIDS-Net) comprising object proposal generation, embedding creation for both instance templates and proposal regions, and embedding matching for instance label assignment. Leveraging recent advancements in large vision methods, we utilize Grounding DINO and Segment Anything Model (SAM) to obtain object proposals with accurate bounding boxes and masks. Central to our approach is the generation of high-quality instance embeddings. We utilize foreground feature averages of patch embeddings from the DINOv2 ViT backbone, followed by refinement through a weight adapter mechanism that we introduce. We show experimentally that our weight adapter can adjust the embeddings locally within their feature space and effectively limit overfitting in the few-shot setting. This methodology enables a straightforward matching strategy, resulting in significant performance gains. Our framework surpasses current state-of-the-art methods, demonstrating notable improvements of 22.3, 46.2, 10.3, and 24.0 in average precision (AP) across four detection datasets. In instance segmentation tasks on seven core datasets of the BOP challenge, our method is around 4.5 times faster than the leading published RGB method and surpasses it by 3.6 AP. NIDS-Net is about 5.7 times faster than the top RGB-D method while maintaining competitive performance. Project Page: https://irvlutd.github.io/NIDSNet/
Authors: Hui Li, Haolong Ma, Chunyang Cheng, Zhongwei Shen, Xiaoning Song, Xiao-Jun Wu
Abstract: For better explore the relations of inter-modal and inner-modal, even in deep learning fusion framework, the concept of decomposition plays a crucial role. However, the previous decomposition strategies (base \& detail or low-frequency \& high-frequency) are too rough to present the common features and the unique features of source modalities, which leads to a decline in the quality of the fused images. The existing strategies treat these relations as a binary system, which may not be suitable for the complex generation task (e.g. image fusion). To address this issue, a continuous decomposition-based fusion framework (Conti-Fuse) is proposed. Conti-Fuse treats the decomposition results as few samples along the feature variation trajectory of the source images, extending this concept to a more general state to achieve continuous decomposition. This novel continuous decomposition strategy enhances the representation of complementary information of inter-modal by increasing the number of decomposition samples, thus reducing the loss of critical information. To facilitate this process, the continuous decomposition module (CDM) is introduced to decompose the input into a series continuous components. The core module of CDM, State Transformer (ST), is utilized to efficiently capture the complementary information from source modalities. Furthermore, a novel decomposition loss function is also designed which ensures the smooth progression of the decomposition process while maintaining linear growth in time complexity with respect to the number of decomposition samples. Extensive experiments demonstrate that our proposed Conti-Fuse achieves superior performance compared to the state-of-the-art fusion methods.
Authors: Neng Wang, Ruibin Guo, Chenghao Shi, Ziyue Wang, Hui Zhang, Huimin Lu, Zhiqiang Zheng, Xieyuanli Chen
Abstract: 4D LiDAR semantic segmentation, also referred to as multi-scan semantic segmentation, plays a crucial role in enhancing the environmental understanding capabilities of autonomous vehicles or robots. It classifies the semantic category of each LiDAR measurement point and detects whether it is dynamic, a critical ability for tasks like obstacle avoidance and autonomous navigation. Existing approaches often rely on computationally heavy 4D convolutions or recursive networks, which result in poor real-time performance, making them unsuitable for online robotics and autonomous driving applications. In this paper, we introduce SegNet4D, a novel real-time 4D semantic segmentation network offering both efficiency and strong semantic understanding. SegNet4D addresses 4D segmentation as two tasks: single-scan semantic segmentation and moving object segmentation, each tackled by a separate network head. Both results are combined in a motion-semantic fusion module to achieve comprehensive 4D segmentation. Additionally, instance information is extracted from the current scan and exploited for instance-wise segmentation consistency. Our approach surpasses state-of-the-art in both multi-scan semantic segmentation and moving object segmentation while offering greater efficiency, enabling real-time operation. Besides, its effectiveness and efficiency have also been validated on a real-world unmanned ground platform. Our code will be released at https://github.com/nubot-nudt/SegNet4D.
Authors: Yuchen Zhou, Jiayuan Gu, Tung Yen Chiang, Fanbo Xiang, Hao Su
Abstract: The development of 2D foundation models for image segmentation has been significantly advanced by the Segment Anything Model (SAM). However, achieving similar success in 3D models remains a challenge due to issues such as non-unified data formats, poor model scalability, and the scarcity of labeled data with diverse masks. To this end, we propose a 3D promptable segmentation model Point-SAM, focusing on point clouds. We employ an efficient transformer-based architecture tailored for point clouds, extending SAM to the 3D domain. We then distill the rich knowledge from 2D SAM for Point-SAM training by introducing a data engine to generate part-level and object-level pseudo-labels at scale from 2D SAM. Our model outperforms state-of-the-art 3D segmentation models on several indoor and outdoor benchmarks and demonstrates a variety of applications, such as interactive 3D annotation and zero-shot 3D instance proposal. Codes and demo can be found at https://github.com/zyc00/Point-SAM.
Authors: Wenqiang Zu, Shenghao Xie, Qing Zhao, Guoqi Li, Lei Ma
Abstract: Foundation models pre-trained on large-scale data have been widely witnessed to achieve success in various natural imaging downstream tasks. Parameter-efficient fine-tuning (PEFT) methods aim to adapt foundation models to new domains by updating only a small portion of parameters in order to reduce computational overhead. However, the effectiveness of these PEFT methods, especially in cross-domain few-shot scenarios, e.g., medical image analysis, has not been fully explored. In this work, we facilitate the study of the performance of PEFT when adapting foundation models to medical image classification tasks. Furthermore, to alleviate the limitations of prompt introducing ways and approximation capabilities on Transformer architectures of mainstream prompt tuning methods, we propose the Embedded Prompt Tuning (EPT) method by embedding prompt tokens into the expanded channels. We also find that there are anomalies in the feature space distribution of foundation models during pre-training process, and prompt tuning can help mitigate this negative impact. To explain this phenomenon, we also introduce a novel perspective to understand prompt tuning: Prompt tuning is a distribution calibrator. And we support it by analyzing patch-wise scaling and feature separation operations contained in EPT. Our experiments show that EPT outperforms several state-of-the-art fine-tuning methods by a significant margin on few-shot medical image classification tasks, and completes the fine-tuning process within highly competitive time, indicating EPT is an effective PEFT method. The source code is available at github.com/zuwenqiang/EPT.
Authors: Laiyan Ding, Hualie Jiang, Jie Li, Yongquan Chen, Rui Huang
Abstract: Depth estimation is a cornerstone for autonomous driving, yet acquiring per-pixel depth ground truth for supervised learning is challenging. Self-Supervised Surround Depth Estimation (SSSDE) from consecutive images offers an economical alternative. While previous SSSDE methods have proposed different mechanisms to fuse information across images, few of them explicitly consider the cross-view constraints, leading to inferior performance, particularly in overlapping regions. This paper proposes an efficient and consistent pose estimation design and two loss functions to enhance cross-view consistency for SSSDE. For pose estimation, we propose to use only front-view images to reduce training memory and sustain pose estimation consistency. The first loss function is the dense depth consistency loss, which penalizes the difference between predicted depths in overlapping regions. The second one is the multi-view reconstruction consistency loss, which aims to maintain consistency between reconstruction from spatial and spatial-temporal contexts. Additionally, we introduce a novel flipping augmentation to improve the performance further. Our techniques enable a simple neural model to achieve state-of-the-art performance on the DDAD and nuScenes datasets. Last but not least, our proposed techniques can be easily applied to other methods. The code is available at https://github.com/denyingmxd/CVCDepth.
Authors: Jinhua Zhang, Hualian Sheng, Sijia Cai, Bing Deng, Qiao Liang, Wen Li, Ying Fu, Jieping Ye, Shuhang Gu
Abstract: Controllable generation is considered a potentially vital approach to address the challenge of annotating 3D data, and the precision of such controllable generation becomes particularly imperative in the context of data production for autonomous driving. Existing methods focus on the integration of diverse generative information into controlling inputs, utilizing frameworks such as GLIGEN or ControlNet, to produce commendable outcomes in controllable generation. However, such approaches intrinsically restrict generation performance to the learning capacities of predefined network architectures. In this paper, we explore the integration of controlling information and introduce PerLDiff (\textbf{Per}spective-\textbf{L}ayout \textbf{Diff}usion Models), a method for effective street view image generation that fully leverages perspective 3D geometric information. Our PerLDiff employs 3D geometric priors to guide the generation of street view images with precise object-level control within the network learning process, resulting in a more robust and controllable output. Moreover, it demonstrates superior controllability compared to alternative layout control methods. Empirical results justify that our PerLDiff markedly enhances the precision of generation on the NuScenes and KITTI datasets.
Authors: Xiao Wang, Weizhe Kong, Jiandong Jin, Shiao Wang, Ruichong Gao, Qingchuan Ma, Chenglong Li, Jin Tang
Abstract: Current strong pedestrian attribute recognition models are developed based on Transformer networks, which are computationally heavy. Recently proposed models with linear complexity (e.g., Mamba) have garnered significant attention and have achieved a good balance between accuracy and computational cost across a variety of visual tasks. Relevant review articles also suggest that while these models can perform well on some pedestrian attribute recognition datasets, they are generally weaker than the corresponding Transformer models. To further tap into the potential of the novel Mamba architecture for PAR tasks, this paper designs and adapts Mamba into two typical PAR frameworks, i.e., the text-image fusion approach and pure vision Mamba multi-label recognition framework. It is found that interacting with attribute tags as additional input does not always lead to an improvement, specifically, Vim can be enhanced, but VMamba cannot. This paper further designs various hybrid Mamba-Transformer variants and conducts thorough experimental validations. These experimental results indicate that simply enhancing Mamba with a Transformer does not always lead to performance improvements but yields better results under certain settings. We hope this empirical study can further inspire research in Mamba for PAR, and even extend into the domain of multi-label recognition, through the design of these network structures and comprehensive experimentation. The source code of this work will be released at \url{https://github.com/Event-AHU/OpenPAR}
Authors: Zichen Yu, Quanli Liu, Wei Wang, Liyong Zhang, Xiaoguang Zhao
Abstract: Recently, LSS-based multi-view 3D object detection provides an economical and deployment-friendly solution for autonomous driving. However, all the existing LSS-based methods transform multi-view image features into a Cartesian Bird's-Eye-View(BEV) representation, which does not take into account the non-uniform image information distribution and hardly exploits the view symmetry. In this paper, in order to adapt the image information distribution and preserve the view symmetry by regular convolution, we propose to employ the polar BEV representation to substitute the Cartesian BEV representation. To achieve this, we elaborately tailor three modules: a polar view transformer to generate the polar BEV representation, a polar temporal fusion module for fusing historical polar BEV features and a polar detection head to predict the polar-parameterized representation of the object. In addition, we design a 2D auxiliary detection head and a spatial attention enhancement module to improve the quality of feature extraction in perspective view and BEV, respectively. Finally, we integrate the above improvements into a novel multi-view 3D object detector, PolarBEVDet. Experiments on nuScenes show that PolarBEVDet achieves the superior performance. The code is available at https://github.com/Yzichen/PolarBEVDet.git.
Authors: Tavis Shore, Oscar Mendez, Simon Hadfield
Abstract: Cross-View Geo-Localisation within urban regions is challenging in part due to the lack of geo-spatial structuring within current datasets and techniques. We propose utilising graph representations to model sequences of local observations and the connectivity of the target location. Modelling as a graph enables generating previously unseen sequences by sampling with new parameter configurations. To leverage this newly available information, we propose a GNN-based architecture, producing spatially strong embeddings and improving discriminability over isolated image embeddings. We outline SpaGBOL, introducing three novel contributions. 1) The first graph-structured dataset for Cross-View Geo-Localisation, containing multiple streetview images per node to improve generalisation. 2) Introducing GNNs to the problem, we develop the first system that exploits the correlation between node proximity and feature similarity. 3) Leveraging the unique properties of the graph representation - we demonstrate a novel retrieval filtering approach based on neighbourhood bearings. SpaGBOL achieves state-of-the-art accuracies on the unseen test graph - with relative Top-1 retrieval improvements on previous techniques of 11%, and 50% when filtering with Bearing Vector Matching on the SpaGBOL dataset.
Authors: Sandika Biswas, Qianyi Wu, Biplab Banerjee, Hamid Rezatofighi
Abstract: Despite advancements in Neural Implicit models for 3D surface reconstruction, handling dynamic environments with interactions between arbitrary rigid, non-rigid, or deformable entities remains challenging. The generic reconstruction methods adaptable to such dynamic scenes often require additional inputs like depth or optical flow or rely on pre-trained image features for reasonable outcomes. These methods typically use latent codes to capture frame-by-frame deformations. Another set of dynamic scene reconstruction methods, are entity-specific, mostly focusing on humans, and relies on template models. In contrast, some template-free methods bypass these requirements and adopt traditional LBS (Linear Blend Skinning) weights for a detailed representation of deformable object motions, although they involve complex optimizations leading to lengthy training times. To this end, as a remedy, this paper introduces TFS-NeRF, a template-free 3D semantic NeRF for dynamic scenes captured from sparse or single-view RGB videos, featuring interactions among two entities and more time-efficient than other LBS-based approaches. Our framework uses an Invertible Neural Network (INN) for LBS prediction, simplifying the training process. By disentangling the motions of interacting entities and optimizing per-entity skinning weights, our method efficiently generates accurate, semantically separable geometries. Extensive experiments demonstrate that our approach produces high-quality reconstructions of both deformable and non-deformable objects in complex interactions, with improved training efficiency compared to existing methods.
Authors: Heqing Zou (Xiao Jie), Tianze Luo (Xiao Jie), Guiyang Xie (Xiao Jie), Victor (Xiao Jie), Zhang, Fengmao Lv, Guangcong Wang, Junyang Chen, Zhuochen Wang, Hansheng Zhang, Huaijian Zhang
Abstract: The integration of Large Language Models (LLMs) with visual encoders has recently shown promising performance in visual understanding tasks, leveraging their inherent capability to comprehend and generate human-like text for visual reasoning. Given the diverse nature of visual data, MultiModal Large Language Models (MM-LLMs) exhibit variations in model designing and training for understanding images, short videos, and long videos. Our paper focuses on the substantial differences and unique challenges posed by long video understanding compared to static image and short video understanding. Unlike static images, short videos encompass sequential frames with both spatial and within-event temporal information, while long videos consist of multiple events with between-event and long-term temporal information. In this survey, we aim to trace and summarize the advancements of MM-LLMs from image understanding to long video understanding. We review the differences among various visual understanding tasks and highlight the challenges in long video understanding, including more fine-grained spatiotemporal details, dynamic events, and long-term dependencies. We then provide a detailed summary of the advancements in MM-LLMs in terms of model design and training methodologies for understanding long videos. Finally, we compare the performance of existing MM-LLMs on video understanding benchmarks of various lengths and discuss potential future directions for MM-LLMs in long video understanding.
Authors: Weixing Zhang, Zongrui Li, De Ma, Huajin Tang, Xudong Jiang, Qian Zheng, Gang Pan
Abstract: 3D Gaussian Splatting is capable of reconstructing 3D scenes in minutes. Despite recent advances in improving surface reconstruction accuracy, the reconstructed results still exhibit bias and suffer from inefficiency in storage and training. This paper provides a different observation on the cause of the inefficiency and the reconstruction bias, which is attributed to the integration of the low-opacity parts (LOPs) of the generated Gaussians. We show that LOPs consist of Gaussians with overall low-opacity (LOGs) and the low-opacity tails (LOTs) of Gaussians. We propose Spiking GS to reduce such two types of LOPs by integrating spiking neurons into the Gaussian Splatting pipeline. Specifically, we introduce global and local full-precision integrate-and-fire spiking neurons to the opacity and representation function of flattened 3D Gaussians, respectively. Furthermore, we enhance the density control strategy with spiking neurons' thresholds and a new criterion on the scale of Gaussians. Our method can represent more accurate reconstructed surfaces at a lower cost. The supplementary material and code are available at https://github.com/zju-bmi-lab/SpikingGS.
Authors: DuoSheng Chen, Binghui Chen, Yifeng Geng, Liefeng Bo
Abstract: Recently, several point-based image editing methods (e.g., DragDiffusion, FreeDrag, DragNoise) have emerged, yielding precise and high-quality results based on user instructions. However, these methods often make insufficient use of semantic information, leading to less desirable results. In this paper, we proposed a novel mask-free point-based image editing method, AdaptiveDrag, which provides a more flexible editing approach and generates images that better align with user intent. Specifically, we design an auto mask generation module using super-pixel division for user-friendliness. Next, we leverage a pre-trained diffusion model to optimize the latent, enabling the dragging of features from handle points to target points. To ensure a comprehensive connection between the input image and the drag process, we have developed a semantic-driven optimization. We design adaptive steps that are supervised by the positions of the points and the semantic regions derived from super-pixel segmentation. This refined optimization process also leads to more realistic and accurate drag results. Furthermore, to address the limitations in the generative consistency of the diffusion model, we introduce an innovative corresponding loss during the sampling process. Building on these effective designs, our method delivers superior generation results using only the single input image and the handle-target point pairs. Extensive experiments have been conducted and demonstrate that the proposed method outperforms others in handling various drag instructions (e.g., resize, movement, extension) across different domains (e.g., animals, human face, land space, clothing).
Authors: Laiyan Ding, Hualie Jiang, Rui Xu, Rui Huang
Abstract: Depth completion using lightweight time-of-flight (ToF) depth sensors is attractive due to their low cost. However, lightweight ToF sensors usually have a limited field of view (FOV) compared with cameras. Thus, only pixels in the zone area of the image can be associated with depth signals. Previous methods fail to propagate depth features from the zone area to the outside-zone area effectively, thus suffering from degraded depth completion performance outside the zone. To this end, this paper proposes the CFPNet to achieve cross-zone feature propagation from the zone area to the outside-zone area with two novel modules. The first is a direct-attention-based propagation module (DAPM), which enforces direct cross-zone feature acquisition. The second is a large-kernel-based propagation module (LKPM), which realizes cross-zone feature propagation by utilizing convolution layers with kernel sizes up to 31. CFPNet achieves state-of-the-art (SOTA) depth completion performance by combining these two modules properly, as verified by extensive experimental results on the ZJU-L5 dataset. The code is available at https://github.com/denyingmxd/CFPNet.
Authors: Yongyu Wang
Abstract: DBSCAN is one of the most important non-parametric unsupervised data analysis tools. By applying DBSCAN to a dataset, two key analytical results can be obtained: (1) clustering data points based on density distribution and (2) identifying outliers in the dataset. However, the time complexity of the DBSCAN algorithm is $O(n^2 \beta)$, where $n$ is the number of data points and $\beta = O(D)$, with $D$ representing the dimensionality of the data space. As a result, DBSCAN becomes computationally infeasible when both $n$ and $D$ are large. In this paper, we propose a DBSCAN method based on spectral data compression, capable of efficiently processing datasets with a large number of data points ($n$) and high dimensionality ($D$). By preserving only the most critical structural information during the compression process, our method effectively removes substantial redundancy and noise. Consequently, the solution quality of DBSCAN is significantly improved, enabling more accurate and reliable results.
Authors: Xinhao Zhong, Siyu Jiao, Yao Zhao, Yunchao Wei
Abstract: Current Semi-Supervised Object Detection (SSOD) methods enhance detector performance by leveraging large amounts of unlabeled data, assuming that both labeled and unlabeled data share the same label space. However, in open-set scenarios, the unlabeled dataset contains both in-distribution (ID) classes and out-of-distribution (OOD) classes. Applying semi-supervised detectors in such settings can lead to misclassifying OOD class as ID classes. To alleviate this issue, we propose a simple yet effective method, termed Collaborative Feature-Logits Detector (CFL-Detector). Specifically, we introduce a feature-level clustering method using contrastive loss to clarify vector boundaries in the feature space and highlight class differences. Additionally, by optimizing the logits-level uncertainty classification loss, the model enhances its ability to effectively distinguish between ID and OOD classes. Extensive experiments demonstrate that our method achieves state-of-the-art performance compared to existing methods.
Authors: Nitish Shukla, Arun Ross
Abstract: A facial morph is an image created by combining two face images pertaining to two distinct identities. Face demorphing inverts the process and tries to recover the original images constituting a facial morph. While morph attack detection (MAD) techniques can be used to flag morph images, they do not divulge any visual information about the faces used to create them. Demorphing helps address this problem. Existing demorphing techniques are either very restrictive (assume identities during testing) or produce feeble outputs (both outputs look very similar). In this paper, we overcome these issues by proposing dc-GAN, a novel GAN-based demorphing method conditioned on the morph images. Our method overcomes morph-replication and produces high quality reconstructions of the bonafide images used to create the morphs. Moreover, our method is highly generalizable across demorphing paradigms (differential/reference-free). We conduct experiments on AMSL, FRLL-Morphs and MorDiff datasets to showcase the efficacy of our method.
Authors: Xin He, Haiyun Guo, Kuan Zhu, Bingke Zhu, Xu Zhao, Jianwu Fang, Jinqiao Wang
Abstract: Lane detection plays an important role in autonomous driving perception systems. As deep learning algorithms gain popularity, monocular lane detection methods based on them have demonstrated superior performance and emerged as a key research direction in autonomous driving perception. The core designs of these algorithmic frameworks can be summarized as follows: (1) Task paradigm, focusing on lane instance-level discrimination; (2) Lane modeling, representing lanes as a set of learnable parameters in the neural network; (3) Global context supplementation, enhancing inference on the obscure lanes; (4) Perspective effect elimination, providing accurate 3D lanes for downstream applications. From these perspectives, this paper presents a comprehensive overview of existing methods, encompassing both the increasingly mature 2D lane detection approaches and the developing 3D lane detection works. Besides, this paper compares the performance of mainstream methods on different benchmarks and investigates their inference speed under a unified setting for fair comparison. Moreover, we present some extended works on lane detection, including multi-task perception, video lane detection, online high-definition map construction, and lane topology reasoning, to offer readers a comprehensive roadmap for the evolution of lane detection. Finally, we point out some potential future research directions in this field. We exhaustively collect the papers and codes of existing works at https://github.com/Core9724/Awesome-Lane-Detection and will keep tracing the research.
Authors: S. P. Sharan, Minkyu Choi, Sahil Shah, Harsh Goel, Mohammad Omama, Sandeep Chinchali
Abstract: Recent advancements in text-to-video models such as Sora, Gen-3, MovieGen, and CogVideoX are pushing the boundaries of synthetic video generation, with adoption seen in fields like robotics, autonomous driving, and entertainment. As these models become prevalent, various metrics and benchmarks have emerged to evaluate the quality of the generated videos. However, these metrics emphasize visual quality and smoothness, neglecting temporal fidelity and text-to-video alignment, which are crucial for safety-critical applications. To address this gap, we introduce NeuS-V, a novel synthetic video evaluation metric that rigorously assesses text-to-video alignment using neuro-symbolic formal verification techniques. Our approach first converts the prompt into a formally defined Temporal Logic (TL) specification and translates the generated video into an automaton representation. Then, it evaluates the text-to-video alignment by formally checking the video automaton against the TL specification. Furthermore, we present a dataset of temporally extended prompts to evaluate state-of-the-art video generation models against our benchmark. We find that NeuS-V demonstrates a higher correlation by over 5x with human evaluations when compared to existing metrics. Our evaluation further reveals that current video generation models perform poorly on these temporally complex prompts, highlighting the need for future work in improving text-to-video generation capabilities.
Authors: Bhuvan Sachdeva, Naren Akash, Tajamul Ashraf, Simon Mueller, Thomas Schultz, Maximilian W. M. Wintergerst, Niharika Singri Prasad, Kaushik Murali, Mohit Jain
Abstract: Cataract surgery is the most common surgical procedure globally, with a disproportionately higher burden in developing countries. While automated surgical video analysis has been explored in general surgery, its application to ophthalmic procedures remains limited. Existing works primarily focus on Phaco cataract surgery, an expensive technique not accessible in regions where cataract treatment is most needed. In contrast, Manual Small-Incision Cataract Surgery (MSICS) is the preferred low-cost, faster alternative in high-volume settings and for challenging cases. However, no dataset exists for MSICS. To address this gap, we introduce Sankara-MSICS, the first comprehensive dataset containing 53 surgical videos annotated for 18 surgical phases and 3,527 frames with 13 surgical tools at the pixel level. We benchmark this dataset on state-of-the-art models and present ToolSeg, a novel framework that enhances tool segmentation by introducing a phase-conditional decoder and a simple yet effective semi-supervised setup leveraging pseudo-labels from foundation models. Our approach significantly improves segmentation performance, achieving a $23.77\%$ to $38.10\%$ increase in mean Dice scores, with a notable boost for tools that are less prevalent and small. Furthermore, we demonstrate that ToolSeg generalizes to other surgical settings, showcasing its effectiveness on the CaDIS dataset.
Authors: Libo Zhu, Jianze Li, Haotong Qin, Wenbo Li, Yulun Zhang, Yong Guo, Xiaokang Yang
Abstract: Diffusion-based image super-resolution (SR) models have shown superior performance at the cost of multiple denoising steps. However, even though the denoising step has been reduced to one, they require high computational costs and storage requirements, making it difficult for deployment on hardware devices. To address these issues, we propose a novel post-training quantization approach with adaptive scale in one-step diffusion (OSD) image SR, PassionSR. First, we simplify OSD model to two core components, UNet and Variational Autoencoder (VAE) by removing the CLIPEncoder. Secondly, we propose Learnable Boundary Quantizer (LBQ) and Learnable Equivalent Transformation (LET) to optimize the quantization process and manipulate activation distributions for better quantization. Finally, we design a Distributed Quantization Calibration (DQC) strategy that stabilizes the training of quantized parameters for rapid convergence. Comprehensive experiments demonstrate that PassionSR with 8-bit and 6-bit obtains comparable visual results with full-precision model. Moreover, our PassionSR achieves significant advantages over recent leading low-bit quantization methods for image SR. Our code will be at https://github.com/libozhu03/PassionSR.
Authors: Joongwon Chae, Zhenyu Wang, Lian Zhang, Dongmei Yu, Peiwu Qin
Abstract: Recent advances in multimodal models have demonstrated impressive capabilities in object recognition and scene understanding. However, these models often struggle with precise spatial localization - a critical capability for real-world applications. Inspired by how humans use grid-based references like chess boards and maps, we propose introducing explicit visual position encoding through a simple grid overlay approach. By adding a 9x9 black grid pattern onto input images, our method provides visual spatial guidance analogous to how positional encoding works in transformers, but in an explicit, visual form. Experiments on the COCO 2017 dataset demonstrate that our grid-based approach achieves significant improvements in localization accuracy, with a 107.4% increase in IoU (from 0.27 to 0.56) and a 194.4% improvement in GIoU (from 0.18 to 0.53) compared to baseline performance. Through attention visualization analysis, we show how this visual position encoding helps models better ground spatial relationships. Our method's simplicity and effectiveness make it particularly valuable for applications requiring accurate spatial reasoning, such as robotic manipulation, medical imaging, and autonomous navigation.
Authors: Hui Li, Mingwang Xu, Yun Zhan, Shan Mu, Jiaye Li, Kaihui Cheng, Yuxuan Chen, Tan Chen, Mao Ye, Jingdong Wang, Siyu Zhu
Abstract: Recent advancements in visual generation technologies have markedly increased the scale and availability of video datasets, which are crucial for training effective video generation models. However, a significant lack of high-quality, human-centric video datasets presents a challenge to progress in this field. To bridge this gap, we introduce OpenHumanVid, a large-scale and high-quality human-centric video dataset characterized by precise and detailed captions that encompass both human appearance and motion states, along with supplementary human motion conditions, including skeleton sequences and speech audio. To validate the efficacy of this dataset and the associated training strategies, we propose an extension of existing classical diffusion transformer architectures and conduct further pretraining of our models on the proposed dataset. Our findings yield two critical insights: First, the incorporation of a large-scale, high-quality dataset substantially enhances evaluation metrics for generated human videos while preserving performance in general video generation tasks. Second, the effective alignment of text with human appearance, human motion, and facial motion is essential for producing high-quality video outputs. Based on these insights and corresponding methodologies, the straightforward extended network trained on the proposed dataset demonstrates an obvious improvement in the generation of human-centric videos. Project page https://fudan-generative-vision.github.io/OpenHumanVid
URLs: https://fudan-generative-vision.github.io/OpenHumanVid
Authors: Taesung Kwon, Jong Chul Ye
Abstract: In this paper, we propose a novel framework for solving high-definition video inverse problems using latent image diffusion models. Building on recent advancements in spatio-temporal optimization for video inverse problems using image diffusion models, our approach leverages latent-space diffusion models to achieve enhanced video quality and resolution. To address the high computational demands of processing high-resolution frames, we introduce a pseudo-batch consistent sampling strategy, allowing efficient operation on a single GPU. Additionally, to improve temporal consistency, we present batch-consistent inversion, an initialization technique that incorporates informative latents from the measurement frame. By integrating with SDXL, our framework achieves state-of-the-art video reconstruction across a wide range of spatio-temporal inverse problems, including complex combinations of frame averaging and various spatial degradations, such as deblurring, super-resolution, and inpainting. Unlike previous methods, our approach supports multiple aspect ratios (landscape, vertical, and square) and delivers HD-resolution reconstructions (exceeding 1280x720) in under 2.5 minutes on a single NVIDIA 4090 GPU.
Authors: Xiaoyan Xing, Konrad Groh, Sezer Karaoglu, Theo Gevers, Anand Bhattad
Abstract: We introduce LumiNet, a novel architecture that leverages generative models and latent intrinsic representations for effective lighting transfer. Given a source image and a target lighting image, LumiNet synthesizes a relit version of the source scene that captures the target's lighting. Our approach makes two key contributions: a data curation strategy from the StyleGAN-based relighting model for our training, and a modified diffusion-based ControlNet that processes both latent intrinsic properties from the source image and latent extrinsic properties from the target image. We further improve lighting transfer through a learned adaptor (MLP) that injects the target's latent extrinsic properties via cross-attention and fine-tuning. Unlike traditional ControlNet, which generates images with conditional maps from a single scene, LumiNet processes latent representations from two different images - preserving geometry and albedo from the source while transferring lighting characteristics from the target. Experiments demonstrate that our method successfully transfers complex lighting phenomena including specular highlights and indirect illumination across scenes with varying spatial layouts and materials, outperforming existing approaches on challenging indoor scenes using only images as input.
Authors: Feng Xu, David Ahmedt-Aristizabal, Lars Petersson, Dadong Wang, Xun Li
Abstract: Facial expression recognition (FER) systems raise significant privacy concerns due to the potential exposure of sensitive identity information. This paper presents a study on removing identity information while preserving FER capabilities. Drawing on the observation that low-frequency components predominantly contain identity information and high-frequency components capture expression, we propose a novel two-stream framework that applies privacy enhancement to each component separately. We introduce a controlled privacy enhancement mechanism to optimize performance and a feature compensator to enhance task-relevant features without compromising privacy. Furthermore, we propose a novel privacy-utility trade-off, providing a quantifiable measure of privacy preservation efficacy in closed-set FER tasks. Extensive experiments on the benchmark CREMA-D dataset demonstrate that our framework achieves 78.84% recognition accuracy with a privacy (facial identity) leakage ratio of only 2.01%, highlighting its potential for secure and reliable video-based FER applications.
Authors: Judy X Yang, Jing Wang, Zekun Long, Chenhong Sui, Jun Zhou
Abstract: Classifying hyperspectral images (HSIs) is a complex task in remote sensing due to the high-dimensional nature and volume of data involved. To address these challenges, we propose the Spectral-Spatial non-Linear Model, a novel framework that significantly reduces data volume while enhancing classification accuracy. Our model employs a bidirectional reversed convolutional neural network (CNN) to efficiently extract spectral features, complemented by a specialized block for spatial feature analysis. This hybrid approach leverages the operational efficiency of CNNs and incorporates dynamic feature extraction inspired by attention mechanisms, optimizing performance without the high computational demands typically associated with transformer-based models. The SS non-Linear Model is designed to process hyperspectral data bidirectionally, achieving notable classification and efficiency improvements by fusing spectral and spatial features effectively. This approach yields superior classification accuracy compared to existing benchmarks while maintaining computational efficiency, making it suitable for resource-constrained environments. We validate the SS non-Linear Model on three widely recognized datasets, Houston 2013, Indian Pines, and Pavia University, demonstrating its ability to outperform current state-of-the-art models in HSI classification and efficiency. This work highlights the innovative methodology of the SS non-Linear Model and its practical benefits for remote sensing applications, where both data efficiency and classification accuracy are critical. For further details, please refer to our code repository on GitHub: HSILinearModel.
Authors: Judy X Yang, Jing Wang, Chen Hong Sui, Zekun Long, Jun Zhou
Abstract: The integration of hyperspectral imaging (HSI) and LiDAR data within new linear feature spaces offers a promising solution to the challenges posed by the high-dimensionality and redundancy inherent in HSIs. This study introduces a dual linear fused space framework that capitalizes on bidirectional reversed convolutional neural network (CNN) pathways, coupled with a specialized spatial analysis block. This approach combines the computational efficiency of CNNs with the adaptability of attention mechanisms, facilitating the effective fusion of spectral and spatial information. The proposed method not only enhances data processing and classification accuracy, but also mitigates the computational burden typically associated with advanced models such as Transformers. Evaluations of the Houston 2013 dataset demonstrate that our approach surpasses existing state-of-the-art models. This advancement underscores the potential of the framework in resource-constrained environments and its significant contributions to the field of remote sensing.
Authors: Yu Wang, Xiaofei Zhou, Yichen Wang, Geyuan Zhang, Tianxing He
Abstract: With the significant advancement of Large Vision-Language Models (VLMs), concerns about their potential misuse and abuse have grown rapidly. Previous studies have highlighted VLMs' vulnerability to jailbreak attacks, where carefully crafted inputs can lead the model to produce content that violates ethical and legal standards. However, existing methods struggle against state-of-the-art VLMs like GPT-4o, due to the over-exposure of harmful content and lack of stealthy malicious guidance. In this work, we propose a novel jailbreak attack framework: Multi-Modal Linkage (MML) Attack. Drawing inspiration from cryptography, MML utilizes an encryption-decryption process across text and image modalities to mitigate over-exposure of malicious information. To align the model's output with malicious intent covertly, MML employs a technique called "evil alignment", framing the attack within a video game production scenario. Comprehensive experiments demonstrate MML's effectiveness. Specifically, MML jailbreaks GPT-4o with attack success rates of 97.80% on SafeBench, 98.81% on MM-SafeBench and 99.07% on HADES-Dataset. Our code is available at https://github.com/wangyu-ovo/MML
Authors: Xin Xie, Dong Gong
Abstract: Text-to-image diffusion model alignment is critical for improving the alignment between the generated images and human preferences. While training-based methods are constrained by high computational costs and dataset requirements, training-free alignment methods remain underexplored and are often limited by inaccurate guidance. We propose a plug-and-play training-free alignment method, DyMO, for aligning the generated images and human preferences during inference. Apart from text-aware human preference scores, we introduce a semantic alignment objective for enhancing the semantic alignment in the early stages of diffusion, relying on the fact that the attention maps are effective reflections of the semantics in noisy images. We propose dynamic scheduling of multiple objectives and intermediate recurrent steps to reflect the requirements at different steps. Experiments with diverse pre-trained diffusion models and metrics demonstrate the effectiveness and robustness of the proposed method.
Authors: Wenxuan Huang, Zijie Zhai, Yunhang Shen, Shaoshen Cao, Fei Zhao, Xiangfeng Xu, Zheyu Ye, Shaohui Lin
Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable success in vision understanding, reasoning, and interaction. However, the inference computation and memory increase progressively with the generation of output tokens during decoding, directly affecting the efficacy of MLLMs. Existing methods attempt to reduce the vision context redundancy to achieve efficient MLLMs. Unfortunately, the efficiency benefits of the vision context reduction in the prefill stage gradually diminish during the decoding stage. To address this problem, we proposed a dynamic vision-language context sparsification framework Dynamic-LLaVA, which dynamically reduces the redundancy of vision context in the prefill stage and decreases the memory and computation overhead of the generated language context during decoding. Dynamic-LLaVA designs a tailored sparsification inference scheme for different inference modes, i.e., prefill, decoding with and without KV cache, to achieve efficient inference of MLLMs. In practice, Dynamic-LLaVA can reduce computation consumption by $\sim$75\% in the prefill stage. Meanwhile, throughout the entire generation process of MLLMs, Dynamic-LLaVA reduces the $\sim$50\% computation consumption under decoding without KV cache, while saving $\sim$50\% GPU memory overhead when decoding with KV cache, due to the vision-language context sparsification. Extensive experiments also demonstrate that Dynamic-LLaVA achieves efficient inference for MLLMs with negligible understanding and generation ability degradation or even performance gains compared to the full-context inference baselines. Code is available at https://github.com/Osilly/dynamic_llava .
Authors: Grace Colverd, Jumpei Takami, Laura Schade, Karol Bot, Joseph A. Gallego-Mejia
Abstract: Tree height estimation serves as an important proxy for biomass estimation in ecological and forestry applications. While traditional methods such as photogrammetry and Light Detection and Ranging (LiDAR) offer accurate height measurements, their application on a global scale is often cost-prohibitive and logistically challenging. In contrast, remote sensing techniques, particularly 3D tomographic reconstruction from Synthetic Aperture Radar (SAR) imagery, provide a scalable solution for global height estimation. SAR images have been used in earth observation contexts due to their ability to work in all weathers, unobscured by clouds. In this study, we use deep learning to estimate forest canopy height directly from 2D Single Look Complex (SLC) images, a derivative of SAR. Our method attempts to bypass traditional tomographic signal processing, potentially reducing latency from SAR capture to end product. We also quantify the impact of varying numbers of SLC images on height estimation accuracy, aiming to inform future satellite operations and optimize data collection strategies. Compared to full tomographic processing combined with deep learning, our minimal method (partial processing + deep learning) falls short, with an error 16-21\% higher, highlighting the continuing relevance of geometric signal processing.
Authors: Haodong Lu, Chongyang Zhao, Jason Xue, Lina Yao, Kristen Moore, Dong Gong
Abstract: We investigate whether the pre-trained knowledge of vision-language models (VLMs), such as CLIP, can be retained or even enhanced during continual learning (CL) while absorbing knowledge from a data stream. Existing methods often rely on additional reference data, isolated components for distribution or domain predictions, leading to high training costs, increased inference complexity, and limited improvement potential for pre-trained models. To address these challenges, we first comprehensively analyze the effects of parameter update locations and ranks on downstream adaptation and knowledge retention. Based on these insights, we propose Dynamic Rank-Selective Low Rank Adaptation (LoRA), a universal and efficient CL approach that adaptively assigns ranks to LoRA modules based on their relevance to the current data. Unlike prior methods, our approach continually enhances the pre-trained VLM by retaining both the pre-trained knowledge and the knowledge acquired during CL. Our approach eliminates the need for explicit domain or distribution prediction and additional reference data, enabling seamless integration of new tasks while preserving pre-trained capabilities. It also maintains the original architecture and deployment pipeline of the pre-trained model without incurring any additional inference overhead. Extensive experiments and analyses demonstrate that our method outperforms state-of-the-art approaches in continually absorbing knowledge of downstream tasks while retaining pre-trained knowledge.
Authors: Bolin Lai, Felix Juefei-Xu, Miao Liu, Xiaoliang Dai, Nikhil Mehta, Chenguang Zhu, Zeyi Huang, James M. Rehg, Sangmin Lee, Ning Zhang, Tong Xiao
Abstract: Text-guided image manipulation has experienced notable advancement in recent years. In order to mitigate linguistic ambiguity, few-shot learning with visual examples has been applied for instructions that are underrepresented in the training set, or difficult to describe purely in language. However, learning from visual prompts requires strong reasoning capability, which diffusion models are struggling with. To address this issue, we introduce a novel multi-modal autoregressive model, dubbed $\textbf{InstaManip}$, that can $\textbf{insta}$ntly learn a new image $\textbf{manip}$ulation operation from textual and visual guidance via in-context learning, and apply it to new query images. Specifically, we propose an innovative group self-attention mechanism to break down the in-context learning process into two separate stages -- learning and applying, which simplifies the complex problem into two easier tasks. We also introduce a relation regularization method to further disentangle image transformation features from irrelevant contents in exemplar images. Extensive experiments suggest that our method surpasses previous few-shot image manipulation models by a notable margin ($\geq$19% in human evaluation). We also find our model can be further boosted by increasing the number or diversity of exemplar images.
Authors: Penghui Wen, Lei Bai, Mengwei He, Patrick Filippi, Feng Zhang, Thomas Francis Bishop, Zhiyong Wang, Kun Hu
Abstract: Recently, extended short-term precipitation nowcasting struggles with decreasing precision because of insufficient consideration of meteorological knowledge, such as weather fronts which significantly influence precipitation intensity, duration, and spatial distribution. Therefore, in this paper, we present DuoCast, a novel dual-probabilistic meteorology-aware model designed to address both broad weather evolution and micro-scale fluctuations using two diffusion models, PrecipFlow and MicroDynamic, respectively. Our PrecipFlow model captures evolution trends through an Extreme Precipitation-Aware Encoder (EPA-Encoder), which includes AirConvolution and FrontAttention blocks to process two levels of precipitation data: general and extreme. The output conditions a UNet-based diffusion to produce prediction maps enriched with weather front information. The MicroDynamic model further refines the results to capture micro-scale variability. Extensive experiments on four public benchmarks demonstrate the effectiveness of our DuoCast, achieving superior performance over state-of-the-art methods. Our code is available at https://github.com/ph-w2000/DuoCast.
Authors: Chenyang Zhu, Kai Li, Yue Ma, Longxiang Tang, Chengyu Fang, Chubin Chen, Qifeng Chen, Xiu Li
Abstract: Recent advances in Customized Concept Swapping (CCS) enable a text-to-image model to swap a concept in the source image with a customized target concept. However, the existing methods still face the challenges of inconsistency and inefficiency. They struggle to maintain consistency in both the foreground and background during concept swapping, especially when the shape difference is large between objects. Additionally, they either require time-consuming training processes or involve redundant calculations during inference. To tackle these issues, we introduce InstantSwap, a new CCS method that aims to handle sharp shape disparity at speed. Specifically, we first extract the bbox of the object in the source image automatically based on attention map analysis and leverage the bbox to achieve both foreground and background consistency. For background consistency, we remove the gradient outside the bbox during the swapping process so that the background is free from being modified. For foreground consistency, we employ a cross-attention mechanism to inject semantic information into both source and target concepts inside the box. This helps learn semantic-enhanced representations that encourage the swapping process to focus on the foreground objects. To improve swapping speed, we avoid computing gradients at each timestep but instead calculate them periodically to reduce the number of forward passes, which improves efficiency a lot with a little sacrifice on performance. Finally, we establish a benchmark dataset to facilitate comprehensive evaluation. Extensive evaluations demonstrate the superiority and versatility of InstantSwap. Project Page: https://instantswap.github.io/
Authors: Lingyun Zhang, Yu Xie, Yanwei Fu, Ping Chen
Abstract: As large-scale diffusion models continue to advance, they excel at producing high-quality images but often generate unwanted content, such as sexually explicit or violent content. Existing methods for concept removal generally guide the image generation process but can unintentionally modify unrelated regions, leading to inconsistencies with the original model. We propose a novel approach for targeted concept replacing in diffusion models, enabling specific concepts to be removed without affecting non-target areas. Our method introduces a dedicated concept localizer for precisely identifying the target concept during the denoising process, trained with few-shot learning to require minimal labeled data. Within the identified region, we introduce a training-free Dual Prompts Cross-Attention (DPCA) module to substitute the target concept, ensuring minimal disruption to surrounding content. We evaluate our method on concept localization precision and replacement efficiency. Experimental results demonstrate that our method achieves superior precision in localizing target concepts and performs coherent concept replacement with minimal impact on non-target areas, outperforming existing approaches.
Authors: Zehuan Wu, Jingcheng Ni, Xiaodong Wang, Yuxin Guo, Rui Chen, Lewei Lu, Jifeng Dai, Yuwen Xiong
Abstract: Generative models have significantly improved the generation and prediction quality on either camera images or LiDAR point clouds for autonomous driving. However, a real-world autonomous driving system uses multiple kinds of input modality, usually cameras and LiDARs, where they contain complementary information for generation, while existing generation methods ignore this crucial feature, resulting in the generated results only covering separate 2D or 3D information. In order to fill the gap in 2D-3D multi-modal joint generation for autonomous driving, in this paper, we propose our framework, \emph{HoloDrive}, to jointly generate the camera images and LiDAR point clouds. We employ BEV-to-Camera and Camera-to-BEV transform modules between heterogeneous generative models, and introduce a depth prediction branch in the 2D generative model to disambiguate the un-projecting from image space to BEV space, then extend the method to predict the future by adding temporal structure and carefully designed progressive training. Further, we conduct experiments on single frame generation and world model benchmarks, and demonstrate our method leads to significant performance gains over SOTA methods in terms of generation metrics.
Authors: Sangbeom Lim, Seongchan Kim, Seungjun An, Seokju Cho, Paul Hongsuck Seo, Seungryong Kim
Abstract: Current benchmarks for video segmentation are limited to annotating only salient objects (i.e., foreground instances). Despite their impressive architectural designs, previous works trained on these benchmarks have struggled to adapt to real-world scenarios. Thus, developing a new video segmentation dataset aimed at tracking multi-granularity segmentation target in the video scene is necessary. In this work, we aim to generate multi-granularity video segmentation dataset that is annotated for both salient and non-salient masks. To achieve this, we propose a large-scale, densely annotated multi-granularity video object segmentation (MUG-VOS) dataset that includes various types and granularities of mask annotations. We automatically collected a training set that assists in tracking both salient and non-salient objects, and we also curated a human-annotated test set for reliable evaluation. In addition, we present memory-based mask propagation model (MMPM), trained and evaluated on MUG-VOS dataset, which leads to the best performance among the existing video object segmentation methods and Segment SAM-based video segmentation methods. Project page is available at https://cvlab-kaist.github.io/MUG-VOS.
Authors: Xingyu Liu, Yingyue Li, Chengxi Li, Gu Wang, Chenyangguang Zhang, Ziqin Huang, Xiangyang Ji
Abstract: In this report, we provide the technical details of the submitted method GFreeDet, which exploits Gaussian splatting and vision Foundation models for the model-free unseen object Detection track in the BOP 2024 Challenge.
Authors: Jacob Fein-Ashley, Benjamin Fein-Ashley
Abstract: Image inpainting is a fundamental task in computer vision, aiming to restore missing or corrupted regions in images realistically. While recent deep learning approaches have significantly advanced the state-of-the-art, challenges remain in maintaining structural continuity and generating coherent textures, particularly in large missing areas. Diffusion models have shown promise in generating high-fidelity images but often lack the structural guidance necessary for realistic inpainting. We propose a novel inpainting method that combines diffusion models with anisotropic Gaussian splatting to capture both local structures and global context effectively. By modeling missing regions using anisotropic Gaussian functions that adapt to local image gradients, our approach provides structural guidance to the diffusion-based inpainting network. The Gaussian splat maps are integrated into the diffusion process, enhancing the model's ability to generate high-fidelity and structurally coherent inpainting results. Extensive experiments demonstrate that our method outperforms state-of-the-art techniques, producing visually plausible results with enhanced structural integrity and texture realism.
Authors: Alexey Bokhovkin, Quan Meng, Shubham Tulsiani, Angela Dai
Abstract: We present SceneFactor, a diffusion-based approach for large-scale 3D scene generation that enables controllable generation and effortless editing. SceneFactor enables text-guided 3D scene synthesis through our factored diffusion formulation, leveraging latent semantic and geometric manifolds for generation of arbitrary-sized 3D scenes. While text input enables easy, controllable generation, text guidance remains imprecise for intuitive, localized editing and manipulation of the generated 3D scenes. Our factored semantic diffusion generates a proxy semantic space composed of semantic 3D boxes that enables controllable editing of generated scenes by adding, removing, changing the size of the semantic 3D proxy boxes that guides high-fidelity, consistent 3D geometric editing. Extensive experiments demonstrate that our approach enables high-fidelity 3D scene synthesis with effective controllable editing through our factored diffusion approach.
Authors: Anton Voronov, Denis Kuznedelev, Mikhail Khoroshikh, Valentin Khrulkov, Dmitry Baranchuk
Abstract: This work presents Switti, a scale-wise transformer for text-to-image generation. Starting from existing next-scale prediction AR models, we first explore them for T2I generation and propose architectural modifications to improve their convergence and overall performance. We then observe that self-attention maps of our pretrained scale-wise AR model exhibit weak dependence on preceding scales. Based on this insight, we propose a non-AR counterpart facilitating ~11% faster sampling and lower memory usage while also achieving slightly better generation quality. Furthermore, we reveal that classifier-free guidance at high-resolution scales is often unnecessary and can even degrade performance. By disabling guidance at these scales, we achieve an additional sampling acceleration of ~20% and improve the generation of fine-grained details. Extensive human preference studies and automated evaluations show that Switti outperforms existing T2I AR models and competes with state-of-the-art T2I diffusion models while being up to 7 times faster.
Authors: Amirhosein Chahe, Chenan Wang, Abhishek Jeyapratap, Kaidi Xu, Lifeng Zhou
Abstract: This paper introduces an attacking mechanism to challenge the resilience of autonomous driving systems. Specifically, we manipulate the decision-making processes of an autonomous vehicle by dynamically displaying adversarial patches on a screen mounted on another moving vehicle. These patches are optimized to deceive the object detection models into misclassifying targeted objects, e.g., traffic signs. Such manipulation has significant implications for critical multi-vehicle interactions such as intersection crossing and lane changing, which are vital for safe and efficient autonomous driving systems. Particularly, we make four major contributions. First, we introduce a novel adversarial attack approach where the patch is not co-located with its target, enabling more versatile and stealthy attacks. Moreover, our method utilizes dynamic patches displayed on a screen, allowing for adaptive changes and movement, enhancing the flexibility and performance of the attack. To do so, we design a Screen Image Transformation Network (SIT-Net), which simulates environmental effects on the displayed images, narrowing the gap between simulated and real-world scenarios. Further, we integrate a positional loss term into the adversarial training process to increase the success rate of the dynamic attack. Finally, we shift the focus from merely attacking perceptual systems to influencing the decision-making algorithms of self-driving systems. Our experiments demonstrate the first successful implementation of such dynamic adversarial attacks in real-world autonomous driving scenarios, paving the way for advancements in the field of robust and secure autonomous driving.
Authors: Chengting Yu, Fengzhao Zhang, Hanzhi Ma, Aili Wang, Erping Li
Abstract: Traditional end-to-end (E2E) training of deep networks necessitates storing intermediate activations for back-propagation, resulting in a large memory footprint on GPUs and restricted model parallelization. As an alternative, greedy local learning partitions the network into gradient-isolated modules and trains supervisely based on local preliminary losses, thereby providing asynchronous and parallel training methods that substantially reduce memory cost. However, empirical experiments reveal that as the number of segmentations of the gradient-isolated module increases, the performance of the local learning scheme degrades substantially, severely limiting its expansibility. To avoid this issue, we theoretically analyze the greedy local learning from the standpoint of information theory and propose a ContSup scheme, which incorporates context supply between isolated modules to compensate for information loss. Experiments on benchmark datasets (i.e. CIFAR, SVHN, STL-10) achieve SOTA results and indicate that our proposed method can significantly improve the performance of greedy local learning with minimal memory and computational overhead, allowing for the boost of the number of isolated modules. Our codes are available at https://github.com/Tab-ct/ContSup.
Authors: Meng Wei, Zhongnian Li, Yong Zhou, Xinzheng Xu
Abstract: Long-tailed data is prevalent in real-world classification tasks and heavily relies on supervised information, which makes the annotation process exceptionally labor-intensive and time-consuming. Unfortunately, despite being a common approach to mitigate labeling costs, existing weakly supervised learning methods struggle to adequately preserve supervised information for tail samples, resulting in a decline in accuracy for the tail classes. To alleviate this problem, we introduce a novel weakly supervised labeling setting called Reduced Label. The proposed labeling setting not only avoids the decline of supervised information for the tail samples, but also decreases the labeling costs associated with long-tailed data. Additionally, we propose an straightforward and highly efficient unbiased framework with strong theoretical guarantees to learn from these Reduced Labels. Extensive experiments conducted on benchmark datasets including ImageNet validate the effectiveness of our approach, surpassing the performance of state-of-the-art weakly supervised methods.
Authors: Zirui Qiu, Hassan Rivaz, Yiming Xiao
Abstract: Purpose: As visual inspection is an inherent process during radiological screening, the associated eye gaze data can provide valuable insights into relevant clinical decisions. As deep learning has become the state-of-the-art for computer-assisted diagnosis, integrating human behavior, such as eye gaze data, into these systems is instrumental to help align machine predictions with clinical diagnostic criteria, thus enhancing the quality of automatic radiological diagnosis. Methods: We propose a novel deep learning framework for joint disease diagnosis and prediction of corresponding clinical visual attention maps for chest X-ray scans. Specifically, we introduce a new dual-encoder multi-task UNet, which leverages both a DenseNet201 backbone and a Residual and Squeeze-and-Excitation block-based encoder to extract diverse features for visual attention map prediction, and a multi-scale feature-fusion classifier to perform disease classification. To tackle the issue of asynchronous training schedules of individual tasks in multi-task learning, we proposed a multi-stage cooperative learning strategy, with contrastive learning for feature encoder pretraining to boost performance. Results: Our proposed method is shown to significantly outperform existing techniques for chest X-ray diagnosis (AUC=0.93) and the quality of visual attention map prediction (Correlation coefficient=0.58). Conclusion: Benefiting from the proposed multi-task multi-stage cooperative learning, our technique demonstrates the benefit of integrating clinicians' eye gaze into clinical AI systems to boost performance and potentially explainability.
Authors: Niclas V\"odisch, K\"ursat Petek, Markus K\"appeler, Abhinav Valada, Wolfram Burgard
Abstract: A key challenge for the widespread application of learning-based models for robotic perception is to significantly reduce the required amount of annotated training data while achieving accurate predictions. This is essential not only to decrease operating costs but also to speed up deployment time. In this work, we address this challenge for PAnoptic SegmenTation with fEw Labels (PASTEL) by exploiting the groundwork paved by visual foundation models. We leverage descriptive image features from such a model to train two lightweight network heads for semantic segmentation and object boundary detection, using very few annotated training samples. We then merge their predictions via a novel fusion module that yields panoptic maps based on normalized cut. To further enhance the performance, we utilize self-training on unlabeled images selected by a feature-driven similarity scheme. We underline the relevance of our approach by employing PASTEL to important robot perception use cases from autonomous driving and agricultural robotics. In extensive experiments, we demonstrate that PASTEL significantly outperforms previous methods for label-efficient segmentation even when using fewer annotations. The code of our work is publicly available at http://pastel.cs.uni-freiburg.de.
Authors: Peyman Milanfar, Mauricio Delbracio
Abstract: Denoising, the process of reducing random fluctuations in a signal to emphasize essential patterns, has been a fundamental problem of interest since the dawn of modern scientific inquiry. Recent denoising techniques, particularly in imaging, have achieved remarkable success, nearing theoretical limits by some measures. Yet, despite tens of thousands of research papers, the wide-ranging applications of denoising beyond noise removal have not been fully recognized. This is partly due to the vast and diverse literature, making a clear overview challenging. This paper aims to address this gap. We present a clarifying perspective on denoisers, their structure, and desired properties. We emphasize the increasing importance of denoising and showcase its evolution into an essential building block for complex tasks in imaging, inverse problems, and machine learning. Despite its long history, the community continues to uncover unexpected and groundbreaking uses for denoising, further solidifying its place as a cornerstone of scientific and engineering practice.
Authors: Christofel Rio Goenawan
Abstract: In the modern world, the development of Artificial Intelligence (AI) has contributed to improvements in various areas, including automation, computer vision, fraud detection, and more. AI can be leveraged to enhance the efficiency of Autonomous Smart Traffic Management (ASTM) systems and reduce traffic congestion rates. This paper presents an Autonomous Smart Traffic Management (STM) system that uses AI to improve traffic flow rates. The system employs the YOLO V5 Convolutional Neural Network to detect vehicles in traffic management images. Additionally, it predicts the number of vehicles for the next 12 hours using a Recurrent Neural Network with Long Short-Term Memory (RNN-LSTM). The Smart Traffic Management Cycle Length Analysis manages the traffic cycle length based on these vehicle predictions, aided by AI. From the results of the RNN-LSTM model for predicting vehicle numbers over the next 12 hours, we observe that the model predicts traffic with a Mean Squared Error (MSE) of 4.521 vehicles and a Root Mean Squared Error (RMSE) of 2.232 vehicles. After simulating the STM system in the CARLA simulation environment, we found that the Traffic Management Congestion Flow Rate with ASTM (21 vehicles per minute) is 50\% higher than the rate without STM (around 15 vehicles per minute). Additionally, the Traffic Management Vehicle Pass Delay with STM (5 seconds per vehicle) is 70\% lower than without STM (around 12 seconds per vehicle). These results demonstrate that the STM system using AI can increase traffic flow by 50\% and reduce vehicle pass delays by 70\%.
Authors: Dev Rishi Verma, Vibhor Saxena, Dhruv Sharma, Arpan Gupta
Abstract: In this work for Capsule Vision Challenge 2024, we addressed the challenge of multiclass anomaly classification in video capsule Endoscopy (VCE)[1] with a variety of deep learning models, ranging from custom CNNs to advanced transformer architectures. The purpose is to correctly classify diverse gastrointestinal disorders, which is critical for increasing diagnostic efficiency in clinical settings. We started with a baseline CNN model and improved performance with ResNet[2] for better feature extraction, followed by Vision Transformer (ViT)[3] to capture global dependencies. We further improve the results by using Multiscale Vision Transformer (MViT)[4] for improved hierarchical feature extraction, while Dual Attention Vision Transformer (DaViT) [5] delivered best results by combining spatial and channel attention methods. Our best balanced accuracy on validation set [6] was 0.8592 and Mean AUC was 0.9932. This methodology enabled us to improve model accuracy across a wide range of criteria, greatly surpassing all other methods.Additionally, our team capsule commandos achieved 7th place ranking with a test set[7] performance of Mean AUC: 0.7314 and balanced accuracy: 0.3235
Authors: Yanke Song, Jonathan Lorraine, Weili Nie, Karsten Kreis, James Lucas
Abstract: Diffusion models achieve high-quality sample generation at the cost of a lengthy multistep inference procedure. To overcome this, diffusion distillation techniques produce student generators capable of matching or surpassing the teacher in a single step. However, the student model's inference speed is limited by the size of the teacher architecture, preventing real-time generation for computationally heavy applications. In this work, we introduce Multi-Student Distillation (MSD), a framework to distill a conditional teacher diffusion model into multiple single-step generators. Each student generator is responsible for a subset of the conditioning data, thereby obtaining higher generation quality for the same capacity. MSD trains multiple distilled students, allowing smaller sizes and, therefore, faster inference. Also, MSD offers a lightweight quality boost over single-student distillation with the same architecture. We demonstrate MSD is effective by training multiple same-sized or smaller students on single-step distillation using distribution matching and adversarial distillation techniques. With smaller students, MSD gets competitive results with faster inference for single-step generation. Using 4 same-sized students, MSD significantly outperforms single-student baseline counterparts and achieves remarkable FID scores for one-step image generation: 1.20 on ImageNet-64x64 and 8.20 on zero-shot COCO2014.
Authors: Chengting Yu, Fengzhao Zhang, Ruizhe Chen, Aili Wang, Zuozhu Liu, Shurun Tan, Er-Ping Li
Abstract: Knowledge Distillation (KD), a learning manner with a larger teacher network guiding a smaller student network, transfers dark knowledge from the teacher to the student via logits or intermediate features, with the aim of producing a well-performed lightweight model. Notably, many subsequent feature-based KD methods outperformed the earliest logit-based KD method and iteratively generated numerous state-of-the-art distillation methods. Nevertheless, recent work has uncovered the potential of the logit-based method, bringing the simple KD form based on logits back into the limelight. Features or logits? They partially implement the KD with entirely distinct perspectives; therefore, choosing between logits and features is not straightforward. This paper provides a unified perspective of feature alignment in order to obtain a better comprehension of their fundamental distinction. Inheriting the design philosophy and insights of feature-based and logit-based methods, we introduce a block-wise logit distillation framework to apply implicit logit-based feature alignment by gradually replacing teacher's blocks as intermediate stepping-stone models to bridge the gap between the student and the teacher. Our method obtains comparable or superior results to state-of-the-art distillation methods. This paper demonstrates the great potential of combining logit and features, and we hope it will inspire future research to revisit KD from a higher vantage point.
Authors: Md Ashik Khan, Rafath Bin Zafar Auvee
Abstract: Accurate brain tumor classification in MRI images is critical for timely diagnosis and treatment planning. While deep learning models like ResNet-18, VGG-16 have shown high accuracy, they often come with increased complexity and computational demands. This study presents a comparative analysis of effective yet simple Convolutional Neural Network (CNN) architecture and pre-trained ResNet18, and VGG16 model for brain tumor classification using two publicly available datasets: Br35H:: Brain Tumor Detection 2020 and Brain Tumor MRI Dataset. The custom CNN architecture, despite its lower complexity, demonstrates competitive performance with the pre-trained ResNet18 and VGG16 models. In binary classification tasks, the custom CNN achieved an accuracy of 98.67% on the Br35H dataset and 99.62% on the Brain Tumor MRI Dataset. For multi-class classification, the custom CNN, with a slight architectural modification, achieved an accuracy of 98.09%, on the Brain Tumor MRI Dataset. Comparatively, ResNet18 and VGG16 maintained high performance levels, but the custom CNNs provided a more computationally efficient alternative. Additionally,the custom CNNs were evaluated using few-shot learning (0, 5, 10, 15, 20, 40, and 80 shots) to assess their robustness, achieving notable accuracy improvements with increased shots. This study highlights the potential of well-designed, less complex CNN architectures as effective and computationally efficient alternatives to deeper, pre-trained models for medical imaging tasks, including brain tumor classification. This study underscores the potential of custom CNNs in medical imaging tasks and encourages further exploration in this direction.
Authors: Kaizhao Liang, Lizhang Chen, Bo Liu, Qiang Liu
Abstract: AdamW has been the default optimizer for transformer pretraining. For many years, our community searches for faster and more stable optimizers with only constraint positive outcomes. In this work, we propose a \textbf{single-line modification in Pytorch} to any momentum-based optimizer, which we rename Cautious Optimizer, e.g. C-AdamW and C-Lion. Our theoretical result shows that this modification preserves Adam's Hamiltonian function and it does not break the convergence guarantee under the Lyapunov analysis. In addition, a whole new family of optimizers is revealed by our theoretical insight. Among them, we pick the simplest one for empirical experiments, showing speed-up on Llama and MAE pretraining up to $1.47\times$. Code is available at https://github.com/kyleliang919/C-Optim
Authors: Nati Daniel, May Nathan, Eden Azeroual, Yael Fisher, Yonatan Savir
Abstract: Incorporating artificial intelligence (AI) into digital pathology offers promising prospects for automating and enhancing tasks such as image analysis and diagnostic processes. However, the diversity of tissue samples and the necessity for meticulous image labeling often result in biased datasets, constraining the applicability of algorithms trained on them. To harness synthetic histopathological images to cope with this challenge, it is essential not only to produce photorealistic images but also to be able to exert control over the cellular characteristics they depict. Previous studies used methods to generate, from random noise, semantic masks that captured the spatial distribution of the tissue. These masks were then used as a prior for conditional generative approaches to produce photorealistic histopathological images. However, as with many other generative models, this solution exhibits mode collapse as the model fails to capture the full diversity of the underlying data distribution. In this work, we present a pipeline, coined PriorPath, that generates detailed, realistic, semantic masks derived from coarse-grained images delineating tissue regions. This approach enables control over the spatial arrangement of the generated masks and, consequently, the resulting synthetic images. We demonstrated the efficacy of our method across three cancer types, skin, prostate, and lung, showcasing PriorPath's capability to cover the semantic mask space and to provide better similarity to real masks compared to previous methods. Our approach allows for specifying desired tissue distributions and obtaining both photorealistic masks and images within a single platform, thus providing a state-of-the-art, controllable solution for generating histopathological images to facilitate AI for computational pathology.
Authors: Leila Gheisi, Henry Chu, Raju Gottumukkala, Yan Luo, Xingquan Zhu, Mengyu Wang, Min Shi
Abstract: The use of artificial intelligence (AI) in automated disease classification significantly reduces healthcare costs and improves the accessibility of services. However, this transformation has given rise to concerns about the fairness of AI, which disproportionately affects certain groups, particularly patients from underprivileged populations. Recently, a number of methods and large-scale datasets have been proposed to address group performance disparities. Although these methods have shown effectiveness in disease classification tasks, they may fall short in ensuring fair prediction of disease progression, mainly because of limited longitudinal data with diverse demographics available for training a robust and equitable prediction model. In this paper, we introduce TransFair to enhance demographic fairness in progression prediction for ocular diseases. TransFair aims to transfer a fairness-enhanced disease classification model to the task of progression prediction with fairness preserved. Specifically, we train a fair EfficientNet, termed FairEN, equipped with a fairness-aware attention mechanism using extensive data for ocular disease classification. Subsequently, this fair classification model is adapted to a fair progression prediction model through knowledge distillation, which aims to minimize the latent feature distances between the classification and progression prediction models. We evaluate FairEN and TransFair for fairness-enhanced ocular disease classification and progression prediction using both two-dimensional (2D) and 3D retinal images. Extensive experiments and comparisons with models with and without considering fairness learning show that TransFair effectively enhances demographic equity in predicting ocular disease progression.
Authors: Malik Abdul Manan, Feng Jinchao, Shahzad Ahmed, Abdul Raheem
Abstract: In medical imaging, efficient segmentation of colon polyps plays a pivotal role in minimally invasive solutions for colorectal cancer. This study introduces a novel approach employing two parallel encoder branches within a network for polyp segmentation. One branch of the encoder incorporates the dual convolution blocks that have the capability to maintain feature information over increased depths, and the other block embraces the single convolution block with the addition of the previous layer's feature, offering diversity in feature extraction within the encoder, combining them before transpose layers with a depth-wise concatenation operation. Our model demonstrated superior performance, surpassing several established deep-learning architectures on the Kvasir and CVC-ClinicDB datasets, achieved a Dice score of 0.919, a mIoU of 0.866 for the Kvasir dataset, and a Dice score of 0.931 and a mIoU of 0.891 for the CVC-ClinicDB. The visual and quantitative results highlight the efficacy of our model, potentially setting a new model in medical image segmentation.
Authors: Qian Shao, Kai Zhang, Bang Du, Zepeng Li, Yixuan Wu, Qiyuan Chen, Jian Wu, Jintai Chen, Honghao Gao, Hongxia Xu
Abstract: Deep learning models are widely used to process Computed Tomography (CT) data in the automated screening of pulmonary diseases, significantly reducing the workload of physicians. However, the three-dimensional nature of CT volumes involves an excessive number of voxels, which significantly increases the complexity of model processing. Previous screening approaches often overlook this issue, which undoubtedly reduces screening efficiency. Towards efficient and effective screening, we design a hierarchical approach to reduce the computational cost of pulmonary disease screening. The new approach re-organizes the screening workflows into three steps. First, we propose a Computed Tomography Volume Compression (CTVC) method to select a small slice subset that comprehensively represents the whole CT volume. Second, the selected CT slices are used to detect pulmonary diseases coarsely via a lightweight classification model. Third, an uncertainty measurement strategy is applied to identify samples with low diagnostic confidence, which are re-detected by radiologists. Experiments on two public pulmonary disease datasets demonstrate that our approach achieves comparable accuracy and recall while reducing the time by 50%-70% compared with the counterparts using full CT volumes. Besides, we also found that our approach outperforms previous cutting-edge CTVC methods in retaining important indications after compression.