In this paper, we address the challenging problem of open-world instance segmentation. Existing works have shown that vanilla visual networks are biased toward learning appearance information, \eg texture, to recognize objects. This implicit bias causes the model to fail in detecting novel objects with unseen textures in the open-world setting. To address this challenge, we propose a learning framework, called view-Consistent LeaRning (v-CLR), which aims to enforce the model to learn appearance-invariant representations for robust instance segmentation. In v-CLR, we first introduce additional views for each image, where the texture undergoes significant alterations while preserving the image's underlying structure. We then encourage the model to learn the appearance-invariant representation by enforcing the consistency between object features across different views, for which we obtain class-agnostic object proposals using off-the-shelf unsupervised models that possess strong object-awareness. These proposals enable cross-view object feature matching, greatly reducing the appearance dependency while enhancing the object-awareness. We thoroughly evaluate our method on public benchmarks under both cross-class and cross-dataset settings, achieving state-of-the-art performance. Project page: https://visual-ai.github.io/vclr
Accurate segmentation of lesions plays a critical role in medical image analysis and diagnosis. Traditional segmentation approaches that rely solely on visual features often struggle with the inherent uncertainty in lesion distribution and size. To address these issues, we propose STPNet, a Scale-aware Text Prompt Network that leverages vision-language modeling to enhance medical image segmentation. Our approach utilizes multi-scale textual descriptions to guide lesion localization and employs retrieval-segmentation joint learning to bridge the semantic gap between visual and linguistic modalities. Crucially, STPNet retrieves relevant textual information from a specialized medical text repository during training, eliminating the need for text input during inference while retaining the benefits of cross-modal learning. We evaluate STPNet on three datasets: COVID-Xray, COVID-CT, and Kvasir-SEG. Experimental results show that our vision-language approach outperforms state-of-the-art segmentation methods, demonstrating the effectiveness of incorporating textual semantic knowledge into medical image analysis. The code has been made publicly on https://github.com/HUANGLIZI/STPNet.
While convolutional neural networks (CNNs) and vision transformers (ViTs) have advanced medical image segmentation, they face inherent limitations such as local receptive fields in CNNs and high computational complexity in ViTs. This paper introduces Deconver, a novel network that integrates traditional deconvolution techniques from image restoration as a core learnable component within a U-shaped architecture. Deconver replaces computationally expensive attention mechanisms with efficient nonnegative deconvolution (NDC) operations, enabling the restoration of high-frequency details while suppressing artifacts. Key innovations include a backpropagation-friendly NDC layer based on a provably monotonic update rule and a parameter-efficient design. Evaluated across four datasets (ISLES'22, BraTS'23, GlaS, FIVES) covering both 2D and 3D segmentation tasks, Deconver achieves state-of-the-art performance in Dice scores and Hausdorff distance while reducing computational costs (FLOPs) by up to 90% compared to leading baselines. By bridging traditional image restoration with deep learning, this work offers a practical solution for high-precision segmentation in resource-constrained clinical workflows. The project is available at https://github.com/pashtari/deconver.
Cell instance segmentation is a fundamental task in digital pathology with broad clinical applications. Recently, vision foundation models, which are predominantly based on Vision Transformers (ViTs), have achieved remarkable success in pathology image analysis. However, their improvements in cell instance segmentation remain limited. A key challenge arises from the tokenization process in ViTs, which substantially reduces the spatial resolution of input images, leading to suboptimal segmentation quality, especially for small and densely packed cells. To address this problem, we propose CellVTA (Cell Vision Transformer with Adapter), a novel method that improves the performance of vision foundation models for cell instance segmentation by incorporating a CNN-based adapter module. This adapter extracts high-resolution spatial information from input images and injects it into the ViT through a cross-attention mechanism. Our method preserves the core architecture of ViT, ensuring seamless integration with pretrained foundation models. Extensive experiments show that CellVTA achieves 0.538 mPQ on the CoNIC dataset and 0.506 mPQ on the PanNuke dataset, which significantly outperforms the state-of-the-art cell segmentation methods. Ablation studies confirm the superiority of our approach over other fine-tuning strategies, including decoder-only fine-tuning and full fine-tuning. Our code and models are publicly available at https://github.com/JieZheng-ShanghaiTech/CellVTA.
Few-Shot Semantic Segmentation (FSS), which focuses on segmenting new classes in images using only a limited number of annotated examples, has recently progressed in data-scarce domains. However, in this work, we show that the existing FSS methods often struggle to generalize to underwater environments. Specifically, the prior features extracted by pre-trained models used as feature extractors are fragile due to the unique challenges of underwater images. To address this, we propose FSSUWNet, a tailored FSS framework for underwater images with feature enhancement. FSSUWNet exploits the integration of complementary features, emphasizing both low-level and high-level image characteristics. In addition to employing a pre-trained model as the primary encoder, we propose an auxiliary encoder called Feature Enhanced Encoder which extracts complementary features to better adapt to underwater scene characteristics. Furthermore, a simple and effective Feature Alignment Module aims to provide global prior knowledge and align low-level features with high-level features in dimensions. Given the scarcity of underwater images, we introduce a cross-validation dataset version based on the Segmentation of Underwater Imagery dataset. Extensive experiments on public underwater segmentation datasets demonstrate that our approach achieves state-of-the-art performance. For example, our method outperforms the previous best method by 2.8% and 2.6% in terms of the mean Intersection over Union metric for 1-shot and 5-shot scenarios in the datasets, respectively. Our implementation is available at https://github.com/lizhh268/FSSUWNet.
Underwater image understanding is crucial for both submarine navigation and seabed exploration. However, the low illumination in underwater environments degrades the imaging quality, which in turn seriously deteriorates the performance of underwater semantic segmentation, particularly for outlining the object region boundaries. To tackle this issue, we present UnderWater SegFormer (UWSegFormer), a transformer-based framework for semantic segmentation of low-quality underwater images. Firstly, we propose the Underwater Image Quality Attention (UIQA) module. This module enhances the representation of highquality semantic information in underwater image feature channels through a channel self-attention mechanism. In order to address the issue of loss of imaging details due to the underwater environment, the Multi-scale Aggregation Attention(MAA) module is proposed. This module aggregates sets of semantic features at different scales by extracting discriminative information from high-level features,thus compensating for the semantic loss of detail in underwater objects. Finally, during training, we introduce Edge Learning Loss (ELL) in order to enhance the model's learning of underwater object edges and improve the model's prediction accuracy. Experiments conducted on the SUIM and DUT-USEG (DUT) datasets have demonstrated that the proposed method has advantages in terms of segmentation completeness, boundary clarity, and subjective perceptual details when compared to SOTA methods. In addition, the proposed method achieves the highest mIoU of 82.12 and 71.41 on the SUIM and DUT datasets, respectively. Code will be available at https://github.com/SAWRJJ/UWSegFormer.
Vision Transformers (ViTs)는 다양한 컴퓨터 비전 작업에서 뛰어난 성능과 확장성을 보여줍니다. 기존의 이미지 분할 방법은 다중 스케일 특징을 생성하는 컨볼루션 어댑터와 피ixel 디코더, 그리고 이를 이용한 트랜스포머 디코더를 포함하는 복잡한 구조를 사용하지만, 본 연구에서는 충분한 크기와 사전 학습이 이루어진 ViT 자체가 이러한 태스크 특화 컴포넌트의 유도 편향을 학습할 수 있음을 보여줍니다. 이를 바탕으로, 단일 구조의 ViT를 활용하는 Encoder-only Mask Transformer (EoMT)를 제안하며, 대규모 사전 학습과 모델 확장으로 기존 최첨단 모델과 유사한 분할 정확도를 달성하면서도 훨씬 빠른 속도를 구현합니다. 이러한 결과는 모델의 크기를 키우는 것에 자원을 집중하는 것이 복잡한 구조를 추가하는 것보다 효율적임을 시사합니다.
Neural Architecture Search (NAS) is an automated technique to design optimal neural network architectures for a specific workload. Conventionally, evaluating candidate networks in NAS involves extensive training, which requires significant time and computational resources. To address this, training-free NAS has been proposed to expedite network evaluation with minimal search time. However, state-of-the-art training-free NAS algorithms struggle to precisely distinguish well-performing networks from poorly-performing networks, resulting in inaccurate performance predictions and consequently sub-optimal top-1 network accuracy. Moreover, they are less effective in activation function exploration. To tackle the challenges, this paper proposes RBFleX-NAS, a novel training-free NAS framework that accounts for both activation outputs and input features of the last layer with a Radial Basis Function (RBF) kernel. We also present a detection algorithm to identify optimal hyperparameters using the obtained activation outputs and input feature maps. We verify the efficacy of RBFleX-NAS over a variety of NAS benchmarks. RBFleX-NAS significantly outperforms state-of-the-art training-free NAS methods in terms of top-1 accuracy, achieving this with short search time in NAS-Bench-201 and NAS-Bench-SSS. In addition, it demonstrates higher Kendall correlation compared to layer-based training-free NAS algorithms. Furthermore, we propose NAFBee, a new activation design space that extends the activation type to encompass various commonly used functions. In this extended design space, RBFleX-NAS demonstrates its superiority by accurately identifying the best-performing network during activation function search, providing a significant advantage over other NAS algorithms.
Recent studies have shown that 2D convolution and self-attention exhibit distinct spectral behaviors, and optimizing their spectral properties can enhance vision model performance. However, theoretical analyses remain limited in explaining why 2D convolution is more effective in high-pass filtering than self-attention and why larger kernels favor shape bias, akin to self-attention. In this paper, we employ graph spectral analysis to theoretically simulate and compare the frequency responses of 2D convolution and self-attention within a unified framework. Our results corroborate previous empirical findings and reveal that node connectivity, modulated by window size, is a key factor in shaping spectral functions. Leveraging this insight, we introduce a \textit{spectral-adaptive modulation} (SPAM) mixer, which processes visual features in a spectral-adaptive manner using multi-scale convolutional kernels and a spectral re-scaling mechanism to refine spectral components. Based on SPAM, we develop SPANetV2 as a novel vision backbone. Extensive experiments demonstrate that SPANetV2 outperforms state-of-the-art models across multiple vision tasks, including ImageNet-1K classification, COCO object detection, and ADE20K semantic segmentation.
Referring Video Object Segmentation (RVOS) aims to segment target objects throughout a video based on a text description. This task has attracted increasing attention in the field of computer vision due to its promising applications in video editing and human-agent interaction. Recently, ReferDINO has demonstrated promising performance in this task by adapting object-level vision-language knowledge from pretrained foundational image models. In this report, we further enhance its capabilities by incorporating the advantages of SAM2 in mask quality and object consistency. In addition, to effectively balance performance between single-object and multi-object scenarios, we introduce a conditional mask fusion strategy that adaptively fuses the masks from ReferDINO and SAM2. Our solution, termed ReferDINO-Plus, achieves 60.43 \(\mathcal{J}\&\mathcal{F}\) on MeViS test set, securing 2nd place in the MeViS PVUW challenge at CVPR 2025. The code is available at: https://github.com/iSEE-Laboratory/ReferDINO-Plus.
Medical image segmentation typically relies solely on visual data, overlooking the rich textual information clinicians use for diagnosis. Vision-language models attempt to bridge this gap, but existing approaches often process visual and textual features independently, resulting in weak cross-modal alignment. Simple fusion techniques fail due to the inherent differences between spatial visual features and sequential text embeddings. Additionally, medical terminology deviates from general language, limiting the effectiveness of off-the-shelf text encoders and further hindering vision-language alignment. We propose BiPVL-Seg, an end-to-end framework that integrates vision-language fusion and embedding alignment through architectural and training innovations, where both components reinforce each other to enhance medical image segmentation. BiPVL-Seg introduces bidirectional progressive fusion in the architecture, which facilitates stage-wise information exchange between vision and text encoders. Additionally, it incorporates global-local contrastive alignment, a training objective that enhances the text encoder's comprehension by aligning text and vision embeddings at both class and concept levels. Extensive experiments on diverse medical imaging benchmarks across CT and MR modalities demonstrate BiPVL-Seg's superior performance when compared with state-of-the-art methods in complex multi-class segmentation. Source code is available in this GitHub repository.
In this work, we focus on continual semantic segmentation (CSS), where segmentation networks are required to continuously learn new classes without erasing knowledge of previously learned ones. Although storing images of old classes and directly incorporating them into the training of new models has proven effective in mitigating catastrophic forgetting in classification tasks, this strategy presents notable limitations in CSS. Specifically, the stored and new images with partial category annotations leads to confusion between unannotated categories and the background, complicating model fitting. To tackle this issue, this paper proposes a novel Enhanced Instance Replay (EIR) method, which not only preserves knowledge of old classes while simultaneously eliminating background confusion by instance storage of old classes, but also mitigates background shifts in the new images by integrating stored instances with new images. By effectively resolving background shifts in both stored and new images, EIR alleviates catastrophic forgetting in the CSS task, thereby enhancing the model's capacity for CSS. Experimental results validate the efficacy of our approach, which significantly outperforms state-of-the-art CSS methods.
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-
Weakly Supervised Semantic Segmentation (WSSS) with image-level labels aims to achieve pixel-level predictions using Class Activation Maps (CAMs). Recently, Contrastive Language-Image Pre-training (CLIP) has been introduced in WSSS. However, recent methods primarily focus on image-text alignment for CAM generation, while CLIP's potential in patch-text alignment remains unexplored. In this work, we propose ExCEL to explore CLIP's dense knowledge via a novel patch-text alignment paradigm for WSSS. Specifically, we propose Text Semantic Enrichment (TSE) and Visual Calibration (VC) modules to improve the dense alignment across both text and vision modalities. To make text embeddings semantically informative, our TSE module applies Large Language Models (LLMs) to build a dataset-wide knowledge base and enriches the text representations with an implicit attribute-hunting process. To mine fine-grained knowledge from visual features, our VC module first proposes Static Visual Calibration (SVC) to propagate fine-grained knowledge in a non-parametric manner. Then Learnable Visual Calibration (LVC) is further proposed to dynamically shift the frozen features towards distributions with diverse semantics. With these enhancements, ExCEL not only retains CLIP's training-free advantages but also significantly outperforms other state-of-the-art methods with much less training cost on PASCAL VOC and MS COCO.
Semantic scene understanding is crucial for robotics and computer vision applications. In autonomous driving, 3D semantic segmentation plays an important role for enabling safe navigation. Despite significant advances in the field, the complexity of collecting and annotating 3D data is a bottleneck in this developments. To overcome that data annotation limitation, synthetic simulated data has been used to generate annotated data on demand. There is still however a domain gap between real and simulated data. More recently, diffusion models have been in the spotlight, enabling close-to-real data synthesis. Those generative models have been recently applied to the 3D data domain for generating scene-scale data with semantic annotations. Still, those methods either rely on image projection or decoupled models trained with different resolutions in a coarse-to-fine manner. Such intermediary representations impact the generated data quality due to errors added in those transformations. In this work, we propose a novel approach able to generate 3D semantic scene-scale data without relying on any projection or decoupled trained multi-resolution models, achieving more realistic semantic scene data generation compared to previous state-of-the-art methods. Besides improving 3D semantic scene-scale data synthesis, we thoroughly evaluate the use of the synthetic scene samples as labeled data to train a semantic segmentation network. In our experiments, we show that using the synthetic annotated data generated by our method as training data together with the real semantic segmentation labels, leads to an improvement in the semantic segmentation model performance. Our results show the potential of generated scene-scale point clouds to generate more training data to extend existing datasets, reducing the data annotation effort. Our code is available at https://github.com/PRBonn/3DiSS.
Despite the significant advancements in general image segmentation achieved by large-scale pre-trained foundation models (such as Meta's Segment Any-thing Model (SAM) series and DINOv2), their performance in specialized fields remains limited by two critical issues: the excessive training costs due to large model parameters, and the insufficient ability to represent specific domain characteristics. This paper proposes a multi-scale feature collabora-tion framework guided by DINOv2 for SAM2, with core innovations in three aspects: (1) Establishing a feature collaboration mechanism between DINOv2 and SAM2 backbones, where high-dimensional semantic features extracted by the self-supervised model guide multi-scale feature fusion; (2) Designing lightweight adapter modules and cross-modal, cross-layer feature fusion units to inject cross-domain knowledge while freezing the base model parameters; (3) Constructing a U-shaped network structure based on U-net, which utilizes attention mechanisms to achieve adaptive aggregation decoding of multi-granularity features. This framework surpasses existing state-of-the-art meth-ods in downstream tasks such as camouflage target detection and salient ob-ject detection, without requiring costly training processes. It provides a tech-nical pathway for efficient deployment of visual image segmentation, demon-strating significant application value in a wide range of downstream tasks and specialized fields within image segmentation.Project page: https://github.com/CheneyXuYiMin/SAM2DINO-Seg
Open-vocabulary semantic segmentation models associate vision and text to label pixels from an undefined set of classes using textual queries, providing versatile performance on novel datasets. However, large shifts between training and test domains degrade their performance, requiring fine-tuning for effective real-world applications. We introduce Semantic Library Adaptation (SemLA), a novel framework for training-free, test-time domain adaptation. SemLA leverages a library of LoRA-based adapters indexed with CLIP embeddings, dynamically merging the most relevant adapters based on proximity to the target domain in the embedding space. This approach constructs an ad-hoc model tailored to each specific input without additional training. Our method scales efficiently, enhances explainability by tracking adapter contributions, and inherently protects data privacy, making it ideal for sensitive applications. Comprehensive experiments on a 20-domain benchmark built over 10 standard datasets demonstrate SemLA's superior adaptability and performance across diverse settings, establishing a new standard in domain adaptation for open-vocabulary semantic segmentation.
Underwater dense prediction, especially depth estimation and semantic segmentation, is crucial for gaining a comprehensive understanding of underwater scenes. Nevertheless, high-quality and large-scale underwater datasets with dense annotations remain scarce because of the complex environment and the exorbitant data collection costs. This paper proposes a unified Text-to-Image and DEnse annotation generation method (TIDE) for underwater scenes. It relies solely on text as input to simultaneously generate realistic underwater images and multiple highly consistent dense annotations. Specifically, we unify the generation of text-to-image and text-to-dense annotations within a single model. The Implicit Layout Sharing mechanism (ILS) and cross-modal interaction method called Time Adaptive Normalization (TAN) are introduced to jointly optimize the consistency between image and dense annotations. We synthesize a large-scale underwater dataset using TIDE to validate the effectiveness of our method in underwater dense prediction tasks. The results demonstrate that our method effectively improves the performance of existing underwater dense prediction models and mitigates the scarcity of underwater data with dense annotations. We hope our method can offer new perspectives on alleviating data scarcity issues in other fields. The code is available at https: //github.com/HongkLin/TIDE.
Video semantic segmentation (VSS) plays a vital role in understanding the temporal evolution of scenes. Traditional methods often segment videos frame-by-frame or in a short temporal window, leading to limited temporal context, redundant computations, and heavy memory requirements. To this end, we introduce a Temporal Video State Space Sharing (TV3S) architecture to leverage Mamba state space models for temporal feature sharing. Our model features a selective gating mechanism that efficiently propagates relevant information across video frames, eliminating the need for a memory-heavy feature pool. By processing spatial patches independently and incorporating shifted operation, TV3S supports highly parallel computation in both training and inference stages, which reduces the delay in sequential state space processing and improves the scalability for long video sequences. Moreover, TV3S incorporates information from prior frames during inference, achieving long-range temporal coherence and superior adaptability to extended sequences. Evaluations on the VSPW and Cityscapes datasets reveal that our approach outperforms current state-of-the-art methods, establishing a new standard for VSS with consistent results across long video sequences. By achieving a good balance between accuracy and efficiency, TV3S shows a significant advancement in spatiotemporal modeling, paving the way for efficient video analysis. The code is publicly available at https://github.com/Ashesham/TV3S.git.
We propose a training-free method for open-vocabulary semantic segmentation using Vision-and-Language Models (VLMs). Our approach enhances the initial per-patch predictions of VLMs through label propagation, which jointly optimizes predictions by incorporating patch-to-patch relationships. Since VLMs are primarily optimized for cross-modal alignment and not for intra-modal similarity, we use a Vision Model (VM) that is observed to better capture these relationships. We address resolution limitations inherent to patch-based encoders by applying label propagation at the pixel level as a refinement step, significantly improving segmentation accuracy near class boundaries. Our method, called LPOSS+, performs inference over the entire image, avoiding window-based processing and thereby capturing contextual interactions across the full image. LPOSS+ achieves state-of-the-art performance among training-free methods, across a diverse set of datasets. Code: https://github.com/vladan-stojnic/LPOSS