Few-shot class-incremental learning (FSCIL) presents a significant challenge in machine learning, requiring models to integrate new classes from limited examples while preserving performance on previously learned classes. Recently, prompt-based CIL approaches leverage ample data to train prompts, effectively mitigating catastrophic forgetting. However, these methods do not account for the semantic features embedded in prompts, exacerbating the plasticity-stability dilemma in few-shot incremental learning. In this paper, we propose a novel and simple framework named SEmantic Complementary Prompt(SEC-Prompt), which learns two sets of semantically complementary prompts based on an adaptive query: discriminative prompts(D-Prompt) and non-discriminative prompts(ND-Prompt). D-Prompt enhances the separation of class-specific feature distributions by strengthening key discriminative features, while ND-Prompt balances non-discriminative information to promote generalization to novel classes. To efficiently learn high-quality knowledge from limited samples, we leverage ND-Prompt for data augmentation to increase sample diversity and introduce Prompt Clustering Loss to prevent noise contamination in D-Prompt, ensuring robust discriminative feature learning and improved generalization. Our experimental results showcase state-of-the-art performance across three benchmark datasets, including CIFAR100, ImageNet-R and CUB datasets.
论文检索
输入标题、作者或关键词，从 3,655 篇学术成果中精准定位
Ges3ViG : Incorporating Pointing Gestures into Language-Based 3D Visual Grounding for Embodied Reference Understanding
PDF ↗3-Dimensional Embodied Reference Understanding (3DERU) combines a language description and an accompanying pointing gesture to identify the most relevant target object in a 3D scene. Although prior work has explored pure language-based 3D grounding, there has been limited exploration of 3D-ERU, which also incorporates human pointing gestures. To address this gap, we introduce a data augmentation framework-Imputer, and use it to curate a new benchmark dataset-ImputeRefer for 3D-ERU, by incorporating human pointing gestures into existing 3D scene datasets that only contain language instructions. We also propose Ges3ViG, a novel model for 3D-ERU that achieves 30% improvement in accuracy as compared to other 3DERU models and 9% compared to other purely language-based 3D grounding models. Our code and dataset are available at https://github.com/AtharvMane/Ges3ViG.
Instance segmentation is essential for augmented reality and virtual reality (AR/VR) as it enables precise object recognition and interaction, enhancing the integration of virtual and real-world elements for an immersive experience. However, the high computational overhead of segmentation limits its application on resource-constrained AR/VR devices, causing large processing latency and degrading user experience. In contrast to conventional scenarios, AR/VR users typically focus on only a few regions within their field of view before shifting perspective, allowing segmentation to be concentrated on gaze-specific areas. This insight drives the need for efficient segmentation methods that prioritize processing instance of interest, reducing computational load and enhancing real-time performance. In this paper, we present a foveated instance segmentation(FovealSeg) framework that leverages real-time user gaze data to perform instance segmentation exclusively on instance of interest, resulting in substantial computational savings. Evaluation results show that FSNet achieves an IoU of 0.56 on ADE20K and 0.54 on LVIS, notably outperforming the baseline. The code is available at https://github.com/SAI-Lab-NYU/Foveated-Instance-Segmentation.
Accurate localization plays a pivotal role in the autonomy of systems operating in unfamiliar environments, particularly when interaction with humans is expected. High-accuracy visual localization systems encompass various components, such as image retrievers, feature extractors, matchers, reconstruction and pose estimation methods. This complexity translates to the necessity of robust evaluation settings and pipelines. However, existing datasets and benchmarks primarily focus on single-agent scenarios, overlooking the critical issue of cross-device localization. Different agents with different sensors will show their own specific strengths and weaknesses, and the data they have available varies substantially. This work addresses this gap by enhancing an existing augmented reality visual localization benchmark with data from legged robots, and evaluating human-robot, cross-device mapping and localization. Our contributions extend beyond device diversity and include high environment variability, spanning ten distinct locations ranging from disaster sites to art exhibitions. Each scene in our dataset features recordings from robot agents, hand-held and head-mounted devices, and high-accuracy ground truth LiDAR scanners, resulting in a comprehensive multi-agent dataset and benchmark. This work represents a significant advancement in the field of visual localization benchmarking, with key insights into the performance of cross-device localization methods across diverse settings.
Data augmentation (DA) stands out as a powerful technique to enhance the generalization capabilities of deep neural networks across diverse tasks. However, in low-level vision tasks, DA remains rudimentary (i.e., vanilla DA), facing a critical bottleneck due to information loss. In this paper, we introduce a novel Calibrated Attribution Maps (CAM) to generate saliency masks, followed by two saliency-based DA methods-- Attribution-Driven Data augmentation (ADD) and ADD+--designed to address this issue. CAM leverages integrated gradients and incorporates two key innovations: a global feature detector and calibrated integrated gradients. Based on CAM and the proposed methods, we have two new insights for low-level vision tasks: (1) increasing pixel diversity, as seen in vanilla DA, can improve performance, and (2) focusing on salient features while minimizing the impact of irrelevant pixels, as seen in saliency-based DA, more effectively enhances model performance. Additionally, we find and highlight the key guiding principle for designing saliency-based DA: a wider spectrum of degradation patterns. Extensive experiments demonstrate the compatibility and consistency of our method, as well as the significant performance improvement across various SR tasks and networks.
In this paper, we present BWFormer, a novel Transformer-based model for building wireframe reconstruction from airborne LiDAR point cloud. The problem is solved in a ground-up manner here by detecting the building corners in 2D, lifting and connecting them in 3D space afterwards with additional data augmentation.Due to the 2.5D characteristic of the airborne LiDAR point cloud, we simplify the problem by projecting the points on the ground plane to produce a 2D height map. With the height map, a heat map is first generated with pixel-wise corner likelihood to predict the possible 2D corners.Then, 3D corners are predicted by a Transformer-based network with extra height embedding initialization. This 2D-to-3D corner detection strategy reduces the search space significantly. To recover the topological connections among the corners, edges are finally predicted from the height map with the proposed edge attention mechanism, which extracts holistic features and preserves local details simultaneously. In addition, due to the limited datasets in the field and the irregularity of the point clouds, a conditional latent diffusion model for LiDAR scanning simulation is utilized for data augmentation. BWFormer surpasses other state-of-the-art methods, especially in reconstruction completeness. Our code is available at: https://github.com/3dv-casia/BWformer/.
Referring audio-visual segmentation (Ref-AVS) aims to segment objects within audio-visual scenes using multimodal cues embedded in text expressions. While the Segment Anything Model (SAM) has revolutionized visual segmentation, its applicability to Ref-AVS, where multimodal cues act as novel prompts, remains unexplored. SAM's limitation to single-frame segmentation also hinders its ability to capture essential temporal context needed for multi-frame audio-visual segmentation. To address this gap, we propose TSAM, a novel extension of SAM designed to leverage multimodal cues for precise segmentation in dynamic audio-visual scenes. TSAM enhances SAM's image encoder with a temporal modeling branch, enabling spatio-temporal learning and deep multimodal fusion across video frames, while retaining SAM's pre-trained knowledge. Additionally, TSAM replaces SAM's user-interactive prompting mechanism with sparse and dense data-driven prompts, enabling more effective integration of audio-visual inputs and reference text expressions. Extensive experiments on the Ref-AVS dataset demonstrate TSAM's superiority over state-of-the-art methods. The results illustrate its effectiveness in segmenting objects in dynamic audio-visual scenes using text-based multimodal cues and its strong generalization to unseen objects.
SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis
PDF ↗Despite advances in Large Multi-modal Models, applying them to long and untrimmed video content remains challenging due to limitations in context length and substantial memory overhead. These constraints often lead to significant information loss and reduced relevance in the model responses. With the exponential growth of video data across web platforms, understanding long-form video is crucial for advancing generalized intelligence. In this paper, we introduce SALOVA: Segment-Augmented LOng Video Assistant, a novel video-LLM framework designed to enhance the comprehension of lengthy video content through targeted retrieval process. We address two main challenges to achieve it: (i) We present the SceneWalk dataset, a high-quality collection of 87.8K long videos, each densely captioned at the segment level to enable models to capture scene continuity and maintain rich descriptive context. (ii) We develop robust architectural designs integrating dynamic routing mechanism and spatio-temporal projector to efficiently retrieve and process relevant video segments based on user queries. Our framework mitigates the limitations of current video-LMMs by allowing for precise identification and retrieval of relevant video segments in response to queries, thereby improving the contextual relevance of the generated responses. Through extensive experiments, SALOVA demonstrates enhanced capability in processing complex long-form videos, showing significant capability to maintain contextual integrity across extended sequences.
The performance of anomaly inspection in industrial manufacturing is constrained by the scarcity of anomaly data. To overcome this challenge, researchers have started employing anomaly generation approaches to augment the anomaly dataset. However, existing anomaly generation methods suffer from limited diversity in the generated anomalies and struggle to achieve a seamless blending of this anomaly with the original image. Moreover, the generated mask is usually not aligned with the generated anomaly. In this paper, we overcome these challenges from a new perspective, simultaneously generating a pair of the overall image and the corresponding anomaly part. We propose DualAnoDiff, a novel diffusion-based few-shot anomaly image generation model, which can generate diverse and realistic anomaly images by using a dual-interrelated diffusion model, where one of them is employed to generate the whole image while the other one generates the anomaly part. Moreover, we extract background and shape information to mitigate the distortion and blurriness phenomenon in few-shot image generation. Extensive experiments demonstrate the superiority of our proposed model over state-of-the-art methods in terms of diversity, realism and the accuracy of mask. Overall, our approach significantly improves the performance of downstream anomaly inspection tasks, including anomaly detection, anomaly localization, and anomaly classification tasks. Code will be made available.
Deep learning has revolutionized medical image segmentation, yet its full potential remains constrained by the paucity of annotated datasets. While diffusion models have emerged as a promising approach for generating synthetic image-mask pairs to augment these datasets, they paradoxically suffer from the same data scarcity challenges they aim to mitigate. Traditional mask-only models frequently yield low-fidelity images due to their inability to adequately capture morphological intricacies, which can critically compromise the robustness and reliability of segmentation models. To alleviate this limitation, we introduce Siamese-Diffusion, a novel dual-component model comprising Mask-Diffusion and Image-Diffusion. During training, a Noise Consistency Loss is introduced between these components to enhance the morphological fidelity of Mask-Diffusion in the parameter space. During sampling, only Mask-Diffusion is used, ensuring diversity and scalability. Comprehensive experiments demonstrate the superiority of our method. Siamese-Diffusion boosts SANet's mDice and mIoU by 3.6% and 4.4% on the Polyps, while UNet improves by 1.52% and 1.64% on the ISIC2018.
Improving the Training of Data-Efficient GANs via Quality Aware Dynamic Discriminator Rejection Sampling
PDF ↗Data-Efficient Generative Adversarial Nets (DE-GANs) have become more and more popular in recent years. Existing methods apply data augmentation, noise injection and pre-trained models to maximumly increase the number of training samples thus improving the training of DE-GANs. However, none of these methods considers the sample quality during training, which can also significantly influence the training of DE-GANs. Focusing on sample quality during training, in this paper, we are the first to incorporate discriminator rejection sampling (DRS) into the training process and introduce a novel method, called quality aware dynamic discriminator rejection sampling (QADDRS). Specifically, QADDRS consists of two steps: (1) the sample quality aware step, which aims to obtain the sorted critic scores, i.e., the ordered discriminator outputs, on real/fake samples in the current training stage; (2) the dynamic rejection step that obtains dynamic rejection number N, where N is controlled by the overfitting degree of discriminator (D) during training. When updating the parameters of D, the N high critic score real samples and the N low critic score fake samples in the minibatch are rejected dynamically based on the overfitting degree of D. As a result, QADDRS can avoid D becoming overly confident in distinguishing both real and fake samples, thereby alleviating the overfitting of D issue during training. Extensive experiments on several datasets demonstrate that integrating QADDRS into different DE-GANs can achieve better performance and deliver state-of-the-art results. Codes are available at https://github.com/zzhang05/QADDRS.
VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by Video Spatiotemporal Augmentation
PDF ↗Current large multimodal models (LMMs) face significant challenges in processing and comprehending long-duration or high-resolution videos, which is mainly due to the lack of high-quality datasets. To address this issue from a data-centric perspective, we propose VISTA, a simple yet effective video spatiotemporal augmentation framework that synthesizes long-duration and high-resolution video instruction-following pairs from existing video-caption datasets. VISTA spatially and temporally combines videos to create new synthetic videos with extended durations and enhanced resolutions, and subsequently produces question-answer pairs pertaining to these newly synthesized videos. Based on this paradigm, we develop seven video augmentation methods and curate VISTA-400K, a video instruction-following dataset aimed at enhancing long-duration and high-resolution video understanding. Finetuning various video LMMs on our data resulted in an average improvement of 3.3% across four challenging benchmarks for long-video understanding. Furthermore, we introduce the first comprehensive high-resolution video understanding benchmark HRVideoBench, on which our finetuned models achieve a 6.5% performance gain. These results highlight the effectiveness of our framework.
Semi-supervised crowd counting is crucial for addressing the high annotation costs of densely populated scenes. Although several methods based on pseudo-labeling have been proposed, it remains challenging to effectively and accurately utilize unlabeled data. In this paper, we propose a novel framework called Taste More Taste Better (TMTB), which emphasizes both data and model aspects. Firstly, we explore a data augmentation technique well-suited for the crowd counting task. By inpainting the background regions, this technique can effectively enhance data diversity while preserving the fidelity of the entire scenes. Secondly, we introduce the Visual State Space Model as backbone to capture the global context information from crowd scenes, which is crucial for extremely crowded, low-light, and adverse weather scenarios. In addition to the traditional regression head for exact prediction, we employ an Anti-Noise classification head to provide less exact but more accurate supervision, since the regression head is sensitive to noise in manual annotations. We conduct extensive experiments on four benchmark datasets and show that our method outperforms state-of-the-art methods by a large margin. Code is publicly available on https://github.com/syhien/taste_more_taste_better.
BADGR: Bundle Adjustment Diffusion Conditioned by Gradients for Wide-Baseline Floor Plan Reconstruction
PDF ↗Reconstructing precise camera poses and floor plan layouts from wide-baseline RGB panoramas is a difficult and unsolved problem. We introduce BADGR, a novel diffusion model that jointly performs reconstruction and bundle adjustment (BA) to refine poses and layouts from a coarse state, using 1D floor boundary predictions from dozens of sparsely captured images. Unlike guided diffusion models, BADGR is conditioned on dense per-column outputs from a single-step Levenberg Marquardt (LM) optimizer and is trained to predict camera and wall positions, while minimizing reprojection errors for view consistency. The objective of layout generation from denoising diffusion process complements BA optimization by providing additional learned layout-structural constraints on top of the co-visible features across images. These constraints help BADGR make plausible guesses about spatial relationships, which constrain the pose graph, such as wall adjacency and collinearity, while also learning to mitigate errors from dense boundary observations using global context. BADGR trains exclusively on 2D floor plans, simplifying data acquisition, enabling robust augmentation, and supporting a variety of input densities. Our experiments validate our method, which significantly outperforms the state-of-the-art pose and floor plan layout reconstruction with different input densities.
Gain from Neighbors: Boosting Model Robustness in the Wild via Adversarial Perturbations Toward Neighboring Classes
PDF ↗Recent approaches, such as data augmentation, adversarial training, and transfer learning, have shown potential in addressing the issue of performance degradation caused by distributional shifts. However, they typically demand careful design in terms of data or models and lack awareness of the impact of distributional shifts. In this paper, we observe that classification errors arising from distribution shifts tend to cluster near the true values, suggesting that misclassifications commonly occur in semantically similar, neighboring categories. Furthermore, robust advanced vision foundation models maintain larger inter-class distances while preserving semantic consistency, making them less vulnerable to such shifts. Building on these findings, we propose a new method called GFN (Gain From Neighbors), which uses gradient priors from neighboring classes to perturb input images and incorporates an inter-class distance-weighted loss to improve class separation. This approach encourages the model to learn more resilient features from data prone to errors, enhancing its robustness against shifts in diverse settings. In extensive experiments across various model architectures and benchmark datasets, GFN consistently demonstrated superior performance. For instance, compared to the current state-of-the-art TAPADL method, our approach achieved a higher corruption robustness of 41.4% on ImageNet-C (+2.3%), without requiring additional parameters and using only minimal data.
Successful forensic detectors can produce excellent results in supervised learning benchmarks but struggle to transfer to real-world applications. We believe this limitation is largely due to inadequate training data quality. While most research focuses on developing new algorithms, less attention is given to training data selection, despite evidence that performance can be strongly impacted by spurious correlations such as content, format, or resolution. A well-designed forensic detector should detect generator specific artifacts rather than reflect data biases. To this end, we propose B-Free, a bias-free training paradigm, where fake images are generated from real ones using the conditioning procedure of stable diffusion models. This ensures semantic alignment between real and fake images, allowing any differences to stem solely from the subtle artifacts introduced by AI generation. Through content-based augmentation, we show significant improvements in both generalization and robustness over state-of-the-art detectors and more calibrated results across 27 different generative models, including recent releases, like FLUX and Stable Diffusion 3.5. Our findings emphasize the importance of a careful dataset design, highlighting the need for further research on this topic. Code and data are publicly available at https://grip-unina.github.io/B-Free/.
Vision-Language Models (VLMs) excel in integrating visual and textual information for vision-centric tasks, but their handling of inconsistencies between modalities is underexplored. We investigate VLMs' modality preferences when faced with visual data and varied textual inputs in vision-centered settings.By introducing textual variations to four vision-centric tasks and evaluating ten Vision-Language Models (VLMs), we discover a "blind faith in text" phenomenon: VLMs disproportionately trust textual data over visual data when inconsistencies arise, leading to significant performance drops under corrupted text and raising safety concerns.We analyze factors influencing this text bias, including instruction prompts, language model size, text relevance, token order, and the interplay between visual and textual certainty. While certain factors, such as scaling up the language model size, slightly mitigate text bias, others like token order can exacerbate it due to positional biases inherited from language models. To address this issue, we explore supervised fine-tuning with text augmentation and demonstrate its effectiveness in reducing text bias. Additionally, we provide a theoretical analysis suggesting that the blind faith in text phenomenon may stem from an imbalance of pure text and multi-modal data during training.Our findings highlight the need for balanced training and careful consideration of modality interactions in VLMs to enhance their robustness and reliability in handling multi-modal data inconsistencies.
Robotic manipulation in embodied AI critically depends on large-scale, high-quality datasets that reflect realistic object interactions and physical dynamics. However, existing data collection pipelines are often slow, expensive, and heavily reliant on manual efforts. We present DynScene, a diffusion-based framework for generating dynamic robotic manipulation scenes directly from textual instructions. Unlike prior methods that focus solely on static environments or isolated robot actions, DynScene decomposes the generation into two phases static scene synthesis and action trajectory generation allowing fine-grained control and diversity. Our model enhances realism and physical feasibility through scene refinement (layout sampling, quaternion quantization) and leverages residual action representation to enable action augmentation, generating multiple diverse trajectories from a single static configuration. Experiments show DynScene achieves 26.8x faster generation, 1.84x higher accuracy, and 28% greater action diversity than human-crafted data. Furthermore, agents trained with DynScene exhibit up to 19.4% higher success rates across complex manipulation tasks. Our approach paves the way for scalable, automated dataset generation in robot learning.
We propose KAHAN, a knowledge-augmented hierarchical framework that systematically extracts insights from raw tabular data at entity, pairwise, group, and system levels. KAHAN uniquely leverages LLMs as domain experts to drive the analysis. On DataTales financial reporting benchmark, KAHAN outperforms existing approaches by over 20% on narrative quality (GPT-4o), maintains 98.2% factuality, and demonstrates practical utility in human evaluation. Our results reveal that knowledge quality drives model performance through distillation, hierarchical analysis benefits vary with market complexity, and the framework transfers effectively to healthcare domains. The data and code are available at https://github.com/yajingyang/kahan.
AMANDA: Agentic Medical Knowledge Augmentation for Data-Efficient Medical Visual Question Answering
PDF ↗Medical Multimodal Large Language Models (Med-MLLMs) have shown great promise in medical visual question answering (Med-VQA). However, when deployed in low-resource settings where abundant labeled data are unavailable, existing Med-MLLMs commonly fail due to their medical reasoning capability bottlenecks: (i) the intrinsic reasoning bottleneck that ignores the details from the medical image; (ii) the extrinsic reasoning bottleneck that fails to incorporate specialized medical knowledge. To address those limitations, we propose AMANDA, a training-free agentic framework that performs medical knowledge augmentation via LLM agents. Specifically, our intrinsic medical knowledge augmentation focuses on coarse-to-fine question decomposition for comprehensive diagnosis, while extrinsic medical knowledge augmentation grounds the reasoning process via biomedical knowledge graph retrieval. Extensive experiments across eight Med-VQA benchmarks demonstrate substantial improvements in both zero-shot and few-shot Med-VQA settings. The code is available at https://github.com/REAL-Lab-NU/AMANDA.