BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model

• URL: http://arxiv.org/abs/2401.02317v4
• Date: Wed, 20 Mar 2024 02:03:52 GMT
• Title: BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model
• Authors: Yiran Song, Qianyu Zhou, Xiangtai Li, Deng-Ping Fan, Xuequan Lu, Lizhuang Ma,
• Abstract summary: 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.
• Score: 65.92173280096588
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, 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. Previous approaches tend to resize the image to a fixed size or adopt structure modifications, hindering the preservation of SAM's rich prior knowledge. Besides, such task-specific tuning necessitates a complete retraining of the model, which is cost-expensive and unacceptable for deployment in the downstream tasks. In this paper, we reformulate this issue as a length extrapolation problem, where token sequence length varies while maintaining a consistent patch size for images of different sizes. To this end, we propose Scalable Bias-Mode Attention Mask (BA-SAM) to enhance SAM's adaptability to varying image resolutions while eliminating the need for structure modifications. Firstly, we introduce a new scaling factor to ensure consistent magnitude in the attention layer's dot product values when the token sequence length changes. Secondly, we present a bias-mode attention mask that allows each token to prioritize neighboring information, mitigating the impact of untrained distant information. Our BA-SAM demonstrates efficacy in two scenarios: zero-shot and fine-tuning. Extensive evaluation on diverse datasets, including DIS5K, DUTS, ISIC, COD10K, and COCO, reveals its ability to significantly mitigate performance degradation in the zero-shot setting and achieve state-of-the-art performance with minimal fine-tuning. Furthermore, we propose a generalized model and benchmark, showcasing BA-SAM's generalizability across all four datasets simultaneously. Code is available at https://github.com/zongzi13545329/BA-SAM

Related papers

• Promptable Anomaly Segmentation with SAM Through Self-Perception Tuning [63.55145330447408]
  Segment Anything Model (SAM) has made great progress in anomaly segmentation tasks due to its impressive generalization ability. Existing methods that directly apply SAM through prompting often overlook the domain shift issue. We propose a novel Self-Perceptinon Tuning (SPT) method, aiming to enhance SAM's perception capability for anomaly segmentation.
  arXiv  Detail & Related papers  (2024-11-26T08:33:25Z)
• 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)
• Generalized SAM: Efficient Fine-Tuning of SAM for Variable Input Image Sizes [3.8506666685467343]
  We propose a novel efficient fine-tuning method that allows the input image size of Segment Anything Model (SAM) to be variable. Generalized SAM (GSAM) is the first to apply random cropping during training with SAM, thereby significantly reducing the computational cost of training.
  arXiv  Detail & Related papers  (2024-08-22T13:58:08Z)
• 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)
• BLO-SAM: Bi-level Optimization Based Overfitting-Preventing Finetuning of SAM [37.1263294647351]
  We introduce BLO-SAM, which finetunes the Segment Anything Model (SAM) based on bi-level optimization (BLO) BLO-SAM reduces the risk of overfitting by training the model's weight parameters and the prompt embedding on two separate subsets of the training dataset. Results demonstrate BLO-SAM's superior performance over various state-of-the-art image semantic segmentation methods.
  arXiv  Detail & Related papers  (2024-02-26T06:36:32Z)
• Stable Segment Anything Model [79.9005670886038]
  The Segment Anything Model (SAM) achieves remarkable promptable segmentation given high-quality prompts. This paper presents the first comprehensive analysis on SAM's segmentation stability across a diverse spectrum of prompt qualities. Our solution, termed Stable-SAM, offers several advantages: 1) improved SAM's segmentation stability across a wide range of prompt qualities, while 2) retaining SAM's powerful promptable segmentation efficiency and generality.
  arXiv  Detail & Related papers  (2023-11-27T12:51:42Z)
• How to Efficiently Adapt Large Segmentation Model(SAM) to Medical Images [15.181219203629643]
  Segment Anything (SAM) exhibits impressive capabilities in zero-shot segmentation for natural images. However, when applied to medical images, SAM suffers from noticeable performance drop. In this work, we propose to freeze SAM encoder and finetune a lightweight task-specific prediction head.
  arXiv  Detail & Related papers  (2023-06-23T18:34:30Z)
• Personalize Segment Anything Model with One Shot [52.54453744941516]
  We propose a training-free Personalization approach for Segment Anything Model (SAM) Given only a single image with a reference mask, PerSAM first localizes the target concept by a location prior. PerSAM segments it within other images or videos via three techniques: target-guided attention, target-semantic prompting, and cascaded post-refinement.
  arXiv  Detail & Related papers  (2023-05-04T17:59:36Z)
• Shunted Self-Attention via Multi-Scale Token Aggregation [124.16925784748601]
  Recent Vision Transformer(ViT) models have demonstrated encouraging results across various computer vision tasks. We propose shunted self-attention(SSA) that allows ViTs to model the attentions at hybrid scales per attention layer. The SSA-based transformer achieves 84.0% Top-1 accuracy and outperforms the state-of-the-art Focal Transformer on ImageNet.
  arXiv  Detail & Related papers  (2021-11-30T08:08:47Z)

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.