Unknown Object Detection (UOD) aims to identify objects of unseen categories, differing from the traditional detection paradigm limited by the closed-world assumption. A key component of UOD is learning a generalized representation, i.e. objectness for both known and unknown categories to distinguish and localize objects from the background in a class-agnostic manner. However, previous methods obtain supervision signals for learning objectness in isolation from either localization or classification information, leading to poor performance for UOD. To address this issue, we propose a transformer-based UOD framework, UN-DETR. Based on this, we craft Instance Presence Score (IPS) to represent the probability of an object's presence. For the purpose of information complementarity, IPS employs a strategy of joint supervised learning, integrating attributes representing general objectness from the positional and the categorical latent space as supervision signals. To enhance IPS learning, we introduce a one-to-many assignment strategy to incorporate more supervision. Then, we propose Unbiased Query Selection to provide premium initial query vectors for the decoder. Additionally, we propose an IPS-guided post process strategy to filter redundant boxes and correct classification predictions for known and unknown objects. Finally, we pretrain the entire UN-DETR in an unsupervised manner, in order to obtain objectness prior. Our UN-DETR is comprehensively evaluated on multiple UOD and known detection benchmarks, demonstrating its effectiveness and achieving state-of-the-art performance.
论文检索
输入标题、作者或关键词，从 11,272 篇学术成果中精准定位
Multi-Label Few-Shot Image Classification via Pairwise Feature Augmentation and Flexible Prompt Learning
PDF ↗Multi-label few-shot image classification is a crucial and challenging task due to limited annotated data and elusive category specificity. However, research on this topic is still in the rudimentary stage and few methods are available. Existing methods either leverage data augmentation to alleviate data scarcity or utilize label features as auxiliary knowledge to eliminate the negative effect caused by irrelevant categories, but they ignore the utilization of image region features for data augmentation, and overlook to learn appropriate text feature to better match the image features of specific categories. Moreover, these methods only focus on one side and do not effectively tackle the above two issues simultaneously. In this paper, we introduce a novel prototype-based multi-label few-shot learning framework that seamlessly integrates pairwise feature augmentation and flexible prompt learning. Specifically, by pairwise feature augmentation, we leverage the region features of images in the support set to generate more image features and construct image prototypes, thus alleviating the issue of data scarcity. By flexible prompt learning, we adaptively acquire class-specific prompts to build text prototypes that highly match the image features of specific classes, thereby mitigating the impact of irrelevant classes. Finally, with adaptive learnable parameters, we merge image and text prototypes to obtain the final prototypes, achieving a more powerful classifier for multi-label few-shot image classification. Extensive experimental results demonstrate that our proposed method can push the performance to a higher level.
Recent years have witnessed the remarkable success of Text-to-3D generation, particularly with the rise of mainstream conditional diffusion models (DMs). Though achieving substantial progress, existing methods still face a knotty "human preference" dilemma, that is the 3D contents generated by the models often deviate greatly from the desired effects (e.g., perspective, aesthetics, shading, appearance, etc.) due to the lack of attention to human preferences. To mitigate the limitation of data deficiency and enable human preference learning, we first elaborately curate the HP3D, a text-to-3D dataset with expert preference annotations which is initally captioned by the multimodal large model LLava and then refined by human expert. Based on such a brand-new HP3D, we further propose DreamAlign, a reward-free method that does not require designing any complex reward models whereas only by introducing a light-weight lora adapter and then designing a novel direct 3D preference optimization (D-3DPO) algorithm for training. Moreover, in the stage of text-to-3D we design an additional Preference Contrastive Feedback training for score distillation sampling, which enables the generated 3D objects to align the human preferences (e.g., aesthetics, material, etc.). Extensive experiments demonstrate that DreamAlign consistently achieves state-of-the-art performance on generative effects and human preference alignment across various benchmark evaluations.
Few-shot classification (FSC) is a fundamental yet challenging task in computer vision that involves recognizing novel classes from limited data. While previous methods have focused on enhancing visual features or incorporating additional modalities, Large Vision Language Models (LVLMs) offer a promising alternative due to their rich knowledge and strong visual perception. However, LVLMs risk learning specific response formats rather than effectively extracting useful information from support data in FSC. In this paper, we investigate LVLMs' performance in FSC and identify key issues such as insufficient learning and the presence of severe position biases. To tackle above challenges, we adopt the meta-learning strategy to teach models ``learn to learn". By constructing a rich set of meta-tasks for instruction fine-tuning, LVLMs enhance the ability to extract information from few-shot support data for classification. Additionally, we further boost LVLM's few-shot learning capabilities through label augmentation (LA) and candidate selection (CS) in the fine-tuning and inference stages, respectively. LA is implemented via a character perturbation strategy to ensure the model focuses on support information. CS leverages attribute descriptions to filter out unreliable candidates and simplify the task. Extensive experiments demonstrate that our approach achieves superior performance on both general and fine-grained datasets. Furthermore, our candidate selection strategy has been proven beneficial for training-free LVLMs.
Acquiring pairwise noisy-clean training data is challenging. Consequently, some self-supervised denoising methods utilize noisy image pairs as both input and target for network training. However, a major issue with these methods is the gap between the clean images of the input and target. In this paper, we achieve high-quality image denoising by reducing or even eliminating this gap. Our method requires no training data or prior knowledge of the noise distribution. It consists of two lightweight networks that can be trained using only a single noisy test image. Specifically, we propose a random mask-based downsampler that generates multiple pairs of downsampled noisy images, which are similar but distinct. These image pairs serve as the input for the first network, with the mean image of each pair used as the target. This initially reduces the gap between the clean images of the input and target. Particularly, in our method, the clean counterpart of the first network's target (i.e., the mean image) can be obtained. We then train a second network using the mean image as input and its clean counterpart as the target. This effectively eliminates the gap and achieves better denoising results. Extensive experiments demonstrate that our method outperforms in both denoising performance and efficiency.
Language-based localization is a crucial task in robotics and computer vision, enabling robots to understand spatial positions through language. Recent methods rely on contrastive learning to establish correspondences between global features of texts and point clouds. However, the inherent ambiguity of textual descriptions makes it difficult to convey geometric information accurately, forcing alignment of them in the feature space may compromise the expressiveness of the point clouds. Unlike previous methods, this paper proposes using language as a filter to distinguish dissimilar locations. To this end, we propose a robust framework of multi-level negative contrastive learning for language-based localization, fully leveraging the descriptive power of language for spatial localization. Our method learns multiple mismatched factors by minimizing the similarity of different locations at different levels, including global-level, instance-level and relationlevel, respectively. Extensive experiments conducted on the KITTI360Pose benchmark demonstrate that our method outperforms better that the state-of-the-art methods. Specifically, we achieve a 56.3% improvement in Top-1 retrieval recall and a 45.9% improvement in 5m localization recall.
Recently, diffusion-based video generation models have achieved significant success. However, existing models often suffer from issues like weak consistency and declining image quality over time. To overcome these challenges, inspired by aesthetic principles, we propose a non-invasive plug-in called Uniform Frame Organizer (UFO), which is compatible with any diffusion-based video generation model. The UFO comprises a series of adaptive adapters with adjustable intensities, which can significantly enhance the consistency between the foreground and background of videos and improve image quality without altering the original model parameters when integrated. The training for UFO is simple, efficient, requires minimal resources, and supports stylized training. Its modular design allows for the combination of multiple UFOs, enabling the customization of personalized video generation models. Furthermore, the UFO also supports direct transferability across different models of the same specification without the need for specific retraining. The experimental results indicate that UFO effectively enhances video generation quality and demonstrates its superiority in public video generation benchmarks.
Due to the successful development of deep image generation technology, forgery detection plays a more important role in social and economic security. Racial bias has not been explored thoroughly in the deep forgery detection field. In the paper, we first contribute a dedicated dataset called the Fair Forgery Detection (FairFD) dataset, where we prove the racial bias of public state-of-the-art (SOTA) methods. Different from existing forgery detection datasets, the self-constructed FairFD dataset contains a balanced racial ratio and diverse forgery generation images with the largest-scale subjects. Additionally, we identify the problems with naive fairness metrics when benchmarking forgery detection models. To comprehensively evaluate fairness, we design novel metrics including Approach Averaged Metric and Utility Regularized Metric, which can avoid deceptive results. We also present an effective and robust post-processing technique, Bias Pruning with Fair Activations (BPFA), which improves fairness without requiring retraining or weight updates. Extensive experiments conducted with 12 representative forgery detection models demonstrate the value of the proposed dataset and the reasonability of the designed fairness metrics. By applying the BPFA to the existing fairest detector, we achieve a new SOTA. Furthermore, we conduct more in-depth analyses to offer more insights to inspire researchers in the community.
Perturbating, Tuning, and Collaborating: Harnessing Vision Foundation Models for Single Domain Generalization on Medical Imaging
PDF ↗Single Domain Generalization (SDG) is critical in medical imaging applications. Recently, Vision Foundation Models (VFMs) have spearheaded a trend in AI development due to their robust generalizability and versatility. This work aims to fully explore the generalization capabilities of VFMs alongside the domain-specific expertise of specialized models, thoroughly investigating the boundaries of their respective capabilities, thereby collaboratively addressing SDG challenges within medical imaging. We propose a framework for Collaborative reasoning between Specialized and Universal models for Single Domain Generalization (CollaSU-SDG) in medical imaging. Specifically, we first design a model-aware perturbation injection method from the perspective of single-source domain data, enabling differentiated and adaptive perturbation injection for two different scales of models. Then, a domain expansion adapter is designed for the VFM to adapt to the augmented single-source domain medical data. Lastly, we introduce an adaptive hierarchical transfer and dynamic dense prompting method that facilitate collaborative reasoning between the specialized and universal models, eliminating the need for explicit prompts. Through these designs, CollaSU-SDG fully leverages the strengths of both specialized and universal models, achieving robust out-of-distribution generalization capabilities on single-source domain data. Experimental results demonstrate that CollaSU-SDG significantly advances the state-of-the-art performance across a wide range of medical datasets. All the code will be publicly available.
Ophthalmologists typically require multimodal data sources to improve diagnostic accuracy in clinical decisions. However, due to medical device shortages, low-quality data and data privacy concerns, missing data modalities are common in real-world scenarios. Existing deep learning methods tend to address it by learning an implicit latent subspace representation for different modality combinations. We identify two significant limitations of these methods: (1) implicit representation constraints that hinder the model's ability to capture modality-specific information and (2) modality heterogeneity, causing distribution gaps and redundancy in feature representations. To address these, we propose an Incomplete Modality Disentangled Representation (IMDR) strategy, which disentangles features into explicit independent modal-common and modal-specific features by guidance of mutual information, distilling informative knowledge and enabling it to reconstruct valuable missing semantics and produce robust multimodal representations. Furthermore, we introduce a joint proxy learning module that assists IMDR in eliminating intra-modality redundancy by exploiting the extracted proxies from each class. Experiments on four ophthalmology multimodal datasets demonstrate that the proposed IMDR outperforms the state-of-the-art methods significantly.
The paper targets the challenging task of Ship License Plate (SLP) recognition. Existing methods for SLP recognition are hampered by the scarcity of large and publicly available datasets, leading to evaluations on small and non-representative datasets. To alleviate it, we have built a large dataset, called SLP34K, which consists of 34,385 images collected by an intelligent traffic surveillance system. The dataset is carefully manually annotated with text labels and attributes, and presents high data diversity by multiple installation locations and long capturing period of the cameras. Additionally, we propose a simple yet effective SLP recognition baseline method. The baseline is equipped with a strong visual encoder that benefits from initial pre-training via self-supervised learning, followed by further refinement through our devised semantic enhancement module. Extensive experiments on SLP34K verify the effectiveness of our proposed baseline. Moreover, while our baseline is designed for SLP recognition, it can also be used for common scene text recognition and achieve state-of-the-art performance on seven mainstream scene text recognition datasets.
Modeling 3D open-vocabulary language fields is challenging yet highly anticipated. Despite great progress, existing approaches heavily rely on a large number of training views to construct language-embedded 3D scenes, which is unfortunately impractical in real-world scenarios. This paper introduces SOVGaussian, the first method for few-shot novel view open-vocabulary language querying. We introduce a depth-constrained neural language field to mitigate the geometry degradation caused by overfitting training views. Rather than straightforwardly using dense depth maps for loosely accurate supervision, Language-Aware Depth Distillation (LAD) based on open-vocabulary object masks is proposed, ensuring intra-object geometric accuracy within the language field. To further refine the language-geometry consistency of the language field, we propose a novel Language-Guided Outlier Pruning (LOP) strategy, which identifies floating 3D Gaussian primitives overfitting training views based on their language-grouped densities. Our comprehensive experiments demonstrate that SOVGaussian is able to reconstruct a superior scene representation from few-shot images, outperforming existing state-of-the-art methods and achieving significantly better performance on novel view language querying and synthesis.
Multimodal large language models (MLLMs) demand considerable computations for inference due to the extensive parameters and the additional input tokens needed for visual information representation. Herein, we introduce Visual Tokens Withdrawal (VTW), a plug-and-play module to boost MLLMs for rapid inference. Our approach is inspired by two intriguing phenomena we have observed: (1) the attention sink phenomenon that is prevalent in LLMs also persists in MLLMs, suggesting that initial tokens and nearest tokens receive the majority of attention, while middle vision tokens garner minimal attention in deep layers; (2) the presence of information migration, which implies that visual information is transferred to subsequent text tokens within the first few layers of MLLMs. As per our findings, we conclude that vision tokens are unnecessary in the deep layers of MLLMs. Thus, we strategically withdraw them at a certain layer, enabling only text tokens to engage in subsequent layers. To pinpoint the ideal layer for VTW, we initially analyze a limited set of tiny datasets and choose the first layer that meets the Kullback-Leibler divergence criterion. Our VTW approach can cut computational overhead by over 40% across diverse multimodal tasks while maintaining performance.
Deep Hierarchies and Invariant Disease-Indicative Feature Learning for Computer Aided Diagnosis of Multiple Fundus Diseases
PDF ↗With the advancement of computer vision, numerous models have been proposed for screening of fundus diseases. However, the recognition of multiple fundus diseases is often hampered by the simultaneous presence of multiple disease types and the confluence of lesion types in fundus images. This paper addresses these challenges by conceptualizing them as multi-level feature fusion and self-supervised disease-indicative feature learning problems. We decode fundus images at various levels of granularity to delineate scenarios wherein multiple diseases and lesions co-occur. To effectively integrate these features, we introduce a hierarchical vision transformer (HVT) that adeptly captures both inter-level and intra-level dependencies. A novel forward-attention module is proposed to enhance the integration of lower-level semantic information into higher semantic layers, thereby enriching the representation of complex features. Additionally, we introduce a novel self-supervised mask-consistent feature learner (MCFL). Unlike traditional mask-autoencoders that reconstruct original images using encoder-decoder structures, MCFL utilizes a teacher-student framework to reconstruct mask-consistent feature maps. In this setup, exponential moving averaging is employed to derive classification-guided features, serving as labels for reconstruction rather than merely reconstructing the original images. This innovative approach facilitates the extraction of disease-indicative features. Extensive experiments demonstrate that our method significantly outperforms existing state-of-the-art models.
Low-light image enhancement (LIE) aims at precisely and efficiently recovering an image degraded in poor illumination environments. Recent advanced LIE techniques are using deep neural networks, which require lots of low-normal light image pairs, network parameters, and computational resources. As a result, their practicality is limited. In this work, we devise a novel unsupervised LIE framework based on diffusion priors and lookup tables (DPLUT) to achieve efficient low-light image recovery. The proposed approach comprises two critical components: a light adjustment lookup table (LLUT) and a noise suppression lookup table (NLUT). LLUT is optimized with a set of unsupervised losses. It aims at predicting pixel-wise curve parameters for the dynamic range adjustment of a specific image. NLUT is designed to remove the amplified noise after the light brightens. As diffusion models are sensitive to noise, diffusion priors are introduced to achieve high-performance noise suppression. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods in terms of visual quality and efficiency.
AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement
PDF ↗Existing low-light image enhancement (LIE) methods have achieved noteworthy success in solving synthetic distortions, yet they often fall short in practical applications. The limitations arise from two inherent challenges in real-world LIE: 1) the collection of distorted/clean image pairs is often impractical and sometimes even unavailable, and 2) accurately modeling complex degradations presents a non-trivial problem. To overcome them, we propose the Attribute Guidance Diffusion framework (AGLLDiff), a training-free method for effective real-world LIE. Instead of specifically defining the degradation process, AGLLDiff shifts the paradigm and models the desired attributes, such as image exposure, structure and color of normal-light images. These attributes are readily available and impose no assumptions about the degradation process, which guides the diffusion sampling process to a reliable high-quality solution space. Extensive experiments demonstrate that our approach outperforms the current leading unsupervised LIE methods across benchmarks in terms of distortion-based and perceptual-based metrics, and it performs well even in sophisticated wild degradation.
Transformer-based models have recently achieved outstanding performance in image matting. However, their application to high-resolution images remains challenging due to the quadratic complexity of global self-attention. To address this issue, we propose MEMatte, a memory-efficient matting framework for processing high-resolution images. MEMatte incorporates a router before each global attention block, directing informative tokens to the global attention while routing other tokens to a Lightweight Token Refinement Module (LTRM). Specifically, the router employs a local-global strategy to predict the routing probability of each token, and the LTRM utilizes efficient modules to simulate global attention. Additionally, we introduce a Batch-constrained Adaptive Token Routing (BATR) mechanism, which allows each router to dynamically route tokens based on image content and the stages of attention block in the network. Furthermore, we construct an ultra high-resolution image matting dataset, UHR-395, comprising 35,500 training images and 1,000 test images, with an average resolution of 4872 × 6017. This dataset is created by compositing 395 different alpha mattes across 11 categories onto various backgrounds, all with high-quality manual annotation. Extensive experiments demonstrate that MEMatte outperforms existing methods on both high-resolution and real-world datasets, significantly reducing memory usage by approximately 88% and latency by 50% on the Composition-1K benchmark.
In recent years, there has been a growing demand to stylize a given 3D scene to align with the artistic style of reference images for creative purposes. While 3D Gaussian Splatting (GS) has emerged as a promising and efficient method for realistic 3D scene modeling, there remains a challenge in adapting it to stylize 3D GS to match with multiple styles through automatic local style transfer or manual designation, while maintaining memory efficiency for stylization training. In this paper, we introduce a novel 3D GS stylization solution termed Multi-StyleGS to tackle these challenges. In particular, we employ a bipartite matching mechanism to automatically identify correspondences between the style images and the local regions of the rendered images. To facilitate local style transfer, we introduce a novel semantic style loss function that employs a segmentation network to apply distinct styles to various objects of the scene and propose a local-global feature matching to enhance the multi-view consistency. Furthermore, this technique can achieve memory-efficient training, more texture details and better color match. To better assign a robust semantic label to each Gaussian, we propose several techniques to regularize the segmentation network. As demonstrated by our comprehensive experiments, our approach outperforms existing ones in producing plausible stylization results and offering flexible editing.
Existing hands datasets are largely short-range and the interaction is weak due to the self-occlusion and self-similarity of hands, which can not yet fit the need for interacting hands motion generation. To rescue the data scarcity, we propose HandDiffuse12.5M, a novel and real dataset that consists of temporal sequences with strong two-hand interactions. HandDiffuse12.5M has the largest scale and richest interactions among the existing two-hand datasets. We further present a strong baseline method HandDiffuse for the controllable motion generation of interacting hands using various controllers. Specifically, we apply the diffusion model as the backbone and design two motion representations for different controllers. To reduce artifacts, we also propose Interaction Loss which explicitly quantifies the dynamic interaction process. Our HandDiffuse enables various applications, i.e., motion in-betweening and trajectory controled generation. Experiments show that our method outperforms the state-of-the-art techniques in motion generation. The vivid two-hand motions generated by our method can also construct synthetic datasets and enhances the accuracy of existing hand motion capture algorithms.
Scene flow methods based on deep learning have achieved impressive performance. However, current top-performing methods still struggle with ill-posed regions, such as extensive flat regions or occlusions, due to insufficient local evidence. In this paper, we propose a novel global-aware scene flow estimation network with global motion propagation, named FlowMamba. The core idea of FlowMamba is a novel Iterative Unit based on the State Space Model (ISU), which first propagates global motion patterns and then adaptively integrates the global motion information with previously hidden states. As the irregular nature of point clouds limits the performance of ISU in global motion propagation, we propose a feature-induced ordering strategy (FIO). The FIO leverages semantic-related and motion-related features to order points into a sequence characterized by spatial continuity. Extensive experiments demonstrate the effectiveness of FlowMamba, with 21.9% and 20.5% EPE3D reduction from the best published results on FlyingThings3D and KITTI datasets. Specifically, our FlowMamba is the first method to achieve millimeter-level prediction accuracy in FlyingThings3D and KITTI. Furthermore, the proposed ISU can be seamlessly embedded into existing iterative networks as a plug-and-play module, improving their estimation accuracy significantly.