Boosting Segment Anything Model to Generalize Visually Non-Salient Scenarios

• URL: http://arxiv.org/abs/2601.00537v1
• Date: Fri, 02 Jan 2026 02:42:04 GMT
• Title: Boosting Segment Anything Model to Generalize Visually Non-Salient Scenarios
• Abstract summary: We propose Visually Non-Salient SAM (VNS-SAM) for visually non-salient scenarios.<n>VNS-SAM aims to enhance SAM's perception of visually non-salient scenarios while preserving its original zero-shot generalizability.<n>Designs help the SAM decoder gain a deeper understanding of non-salient characteristics with only marginal parameter increments.
• Score: 31.56671125284146
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Segment Anything Model (SAM), known for its remarkable zero-shot segmentation capabilities, has garnered significant attention in the community. Nevertheless, its performance is challenged when dealing with what we refer to as visually non-salient scenarios, where there is low contrast between the foreground and background. In these cases, existing methods often cannot capture accurate contours and fail to produce promising segmentation results. In this paper, we propose Visually Non-Salient SAM (VNS-SAM), aiming to enhance SAM's perception of visually non-salient scenarios while preserving its original zero-shot generalizability. We achieve this by effectively exploiting SAM's low-level features through two designs: Mask-Edge Token Interactive decoder and Non-Salient Feature Mining module. These designs help the SAM decoder gain a deeper understanding of non-salient characteristics with only marginal parameter increments and computational requirements. The additional parameters of VNS-SAM can be optimized within 4 hours, demonstrating its feasibility and practicality. In terms of data, we established VNS-SEG, a unified dataset for various VNS scenarios, with more than 35K images, in contrast to previous single-task adaptations. It is designed to make the model learn more robust VNS features and comprehensively benchmark the model's segmentation performance and generalizability on VNS scenarios. Extensive experiments across various VNS segmentation tasks demonstrate the superior performance of VNS-SAM, particularly under zero-shot settings, highlighting its potential for broad real-world applications. Codes and datasets are publicly available at https://guangqian-guo.github.io/VNS-SAM.

Related papers

• Frequency and Edge-Guided Segment Anything Model for Remote Sensing Image Semantic Segmentation [39.9598566181483]
  Segment Anything Model (SAM) offers strong segmentation performance and generalization capabilities for RSISS tasks.<n>FE-SAM is a scalable and efficient framework for RSISS.<n>Experiments on three benchmark datasets demonstrate that FE-SAM outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-08-15T05:55:41Z)
• Don't waste SAM [0.0]
  The fine-tuned SAM-ViT-H model outperforms the state-ofthe-art Zerowaste, and TACO datasets with a significant increase of +30 in IoU.<n>It closely approaches performance levels of TrashCan 1.0, with only a -1.44 difference.
  arXiv  Detail & Related papers  (2026-06-09T10:53:33Z)
• Adapting Segment Anything Model for Unseen Object Instance Segmentation [70.60171342436092]
  Unseen Object Instance (UOIS) is crucial for autonomous robots operating in unstructured environments. We propose UOIS-SAM, a data-efficient solution for the UOIS task. UOIS-SAM integrates two key components: (i) a Heatmap-based Prompt Generator (HPG) to generate class-agnostic point prompts with precise foreground prediction, and (ii) a Hierarchical Discrimination Network (HDNet) that adapts SAM's mask decoder.
  arXiv  Detail & Related papers  (2024-09-23T19:05:50Z)
• Multi-Scale and Detail-Enhanced Segment Anything Model for Salient Object Detection [58.241593208031816]
  Segment Anything Model (SAM) has been proposed as a visual fundamental model, which gives strong segmentation and generalization capabilities. We propose a Multi-scale and Detail-enhanced SAM (MDSAM) for Salient Object Detection (SOD) Experimental results demonstrate the superior performance of our model on multiple SOD datasets.
  arXiv  Detail & Related papers  (2024-08-08T09:09:37Z)
• TS-SAM: Fine-Tuning Segment-Anything Model for Downstream Tasks [10.75125721857487]
  There is still a significant performance gap between fine-tuned SAMs and domain-specific models. We propose Two-Stream SAM (TS-SAM), which integrates the powerful features from SAM into side network training for comprehensive feature fusion. Extensive experiments on ten public datasets from three tasks demonstrate that TS-SAM not only significantly outperforms the recently proposed SAM-Adapter and SSOM, but achieves competitive performance with the SOTA domain-specific models.
  arXiv  Detail & Related papers  (2024-08-03T18:08:51Z)
• ASAM: Boosting Segment Anything Model with Adversarial Tuning [9.566046692165884]
  This paper introduces ASAM, a novel methodology that amplifies a foundation model's performance through adversarial tuning. We harness the potential of natural adversarial examples, inspired by their successful implementation in natural language processing. Our approach maintains the photorealism of adversarial examples and ensures alignment with original mask annotations.
  arXiv  Detail & Related papers  (2024-05-01T00:13:05Z)
• WSI-SAM: Multi-resolution Segment Anything Model (SAM) for histopathology whole-slide images [8.179859593451285]
  We present WSI-SAM, enhancing Segment Anything Model (SAM) with precise object segmentation capabilities for histopathology images. To fully exploit pretrained knowledge while minimizing training overhead, we keep SAM frozen, introducing only minimal extra parameters. Our model outperforms SAM by 4.1 and 2.5 percent points on a ductal carcinoma in situ (DCIS) segmentation tasks and breast cancer metastasis segmentation task.
  arXiv  Detail & Related papers  (2024-03-14T10:30:43Z)
• ClassWise-SAM-Adapter: Parameter Efficient Fine-tuning Adapts Segment Anything to SAR Domain for Semantic Segmentation [6.229326337093342]
  Segment Anything Model (SAM) excels in various segmentation scenarios relying on semantic information and generalization ability. The ClassWiseSAM-Adapter (CWSAM) is designed to adapt the high-performing SAM for landcover classification on space-borne Synthetic Aperture Radar (SAR) images. CWSAM showcases enhanced performance with fewer computing resources.
  arXiv  Detail & Related papers  (2024-01-04T15:54:45Z)
• BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model [65.92173280096588]
  We address the challenge of image resolution variation for the Segment Anything Model (SAM) SAM, known for its zero-shot generalizability, exhibits a performance degradation when faced with datasets with varying image sizes. We present a bias-mode attention mask that allows each token to prioritize neighboring information.
  arXiv  Detail & Related papers  (2024-01-04T15:34:44Z)
• TinySAM: Pushing the Envelope for Efficient Segment Anything Model [73.06322749886483]
  We propose a framework to obtain a tiny segment anything model (TinySAM) while maintaining the strong zero-shot performance.<n>With all these proposed methods, our TinySAM leads to orders of magnitude computational reduction and pushes the envelope for efficient segment anything task.
  arXiv  Detail & Related papers  (2023-12-21T12:26:11Z)
• Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation [63.15257949821558]
  Referring Remote Sensing Image (RRSIS) is a new challenge that combines computer vision and natural language processing. Traditional Referring Image (RIS) approaches have been impeded by the complex spatial scales and orientations found in aerial imagery. We introduce the Rotated Multi-Scale Interaction Network (RMSIN), an innovative approach designed for the unique demands of RRSIS.
  arXiv  Detail & Related papers  (2023-12-19T08:14:14Z)
• RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation [53.4319652364256]
  This paper presents the RefSAM model, which explores the potential of SAM for referring video object segmentation. Our proposed approach adapts the original SAM model to enhance cross-modality learning by employing a lightweight Cross-RValModal. We employ a parameter-efficient tuning strategy to align and fuse the language and vision features effectively.
  arXiv  Detail & Related papers  (2023-07-03T13:21:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.