S4M: Segment Anything with 4 Extreme Points

• URL: http://arxiv.org/abs/2503.05534v1
• Date: Fri, 07 Mar 2025 16:02:11 GMT
• Title: S4M: Segment Anything with 4 Extreme Points
• Abstract summary: Segment Anything Model (SAM) primarily relies on sparse prompts such as point or bounding box.<n>S4M augments SAM by leveraging extreme points -- the top-, bottom-, left-, and right-most points of an instance -- prompts.<n>S4M outperforms other SAM-based approaches on three endoscopic surgical datasets.
• Score: 2.052287962818431
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The Segment Anything Model (SAM) has revolutionized open-set interactive image segmentation, inspiring numerous adapters for the medical domain. However, SAM primarily relies on sparse prompts such as point or bounding box, which may be suboptimal for fine-grained instance segmentation, particularly in endoscopic imagery, where precise localization is critical and existing prompts struggle to capture object boundaries effectively. To address this, we introduce S4M (Segment Anything with 4 Extreme Points), which augments SAM by leveraging extreme points -- the top-, bottom-, left-, and right-most points of an instance -- prompts. These points are intuitive to identify and provide a faster, structured alternative to box prompts. However, a na\"ive use of extreme points degrades performance, due to SAM's inability to interpret their semantic roles. To resolve this, we introduce dedicated learnable embeddings, enabling the model to distinguish extreme points from generic free-form points and better reason about their spatial relationships. We further propose an auxiliary training task through the Canvas module, which operates solely on prompts -- without vision input -- to predict a coarse instance mask. This encourages the model to internalize the relationship between extreme points and mask distributions, leading to more robust segmentation. S4M outperforms other SAM-based approaches on three endoscopic surgical datasets, demonstrating its effectiveness in complex scenarios. Finally, we validate our approach through a human annotation study on surgical endoscopic videos, confirming that extreme points are faster to acquire than bounding boxes.

Related papers

• Prompting Diffusion Models for Zero-Shot Instance Segmentation [74.37083707535778]
  We present Prompt2Seg, a spatial conditioning framework for diffusion-based segmentation.<n>Our approach takes spatial prompts, represented as 2D Gaussians or confidence maps, as explicit input signals, training the model to respond directly to user intent.<n>We evaluate on seven datasets ranging from standard benchmarks to more challenging domains, including paintings, egocentric views, and X-ray data.
  arXiv  Detail & Related papers  (2026-06-21T20:30:41Z)
• SCISSR: Scribble-Conditioned Interactive Surgical Segmentation and Refinement [6.1665244904503895]
  We present SCISSR, a scribble-promptable framework for interactive surgical scene segmentation.<n>It introduces a lightweight Scribble that converts freehand scribbles into dense prompt embeddings compatible with the mask decoder.<n> SCISSR achieves 95.41% Dice on EndoVis 2018 with five interaction rounds and 96.30% Dice on CholecSeg8k with three interaction rounds, outperforming iterative point prompting on both benchmarks.
  arXiv  Detail & Related papers  (2026-03-19T07:00:18Z)
• Boosting SAM for Cross-Domain Few-Shot Segmentation via Conditional Point Sparsification [116.2386061247855]
  We propose Point Sparsification (CPS), a training-free approach that adaptively guides SAM interactions for cross-domain images based on reference exemplars.<n>CPS outperforms existing training-free SAM-based methods across diverse CD-FSS datasets.
  arXiv  Detail & Related papers  (2026-02-05T02:17:38Z)
• Evaluating SAM2 for Video Semantic Segmentation [60.157605818225186]
  The Anything Model 2 (SAM2) has proven to be a powerful foundation model for promptable visual object segmentation in both images and videos.<n>This paper explores the extension of SAM2 to dense Video Semantic (VSS)<n>Our experiments suggest that leveraging SAM2 enhances overall performance in VSS, primarily due to its precise predictions of object boundaries.
  arXiv  Detail & Related papers  (2025-12-01T15:15:16Z)
• GeoSAM2: Unleashing the Power of SAM2 for 3D Part Segmentation [81.0871900167463]
  We introduce GeoSAM2, a prompt-controllable framework for 3D part segmentation.<n>Given a textureless object, we render normal and point maps from predefined viewpoints.<n>We accept simple 2D prompts - clicks or boxes - to guide part selection.<n>The predicted masks are back-projected to the object and aggregated across views.
  arXiv  Detail & Related papers  (2025-08-19T17:58:51Z)
• LIRA: Inferring Segmentation in Large Multi-modal Models with Local Interleaved Region Assistance [56.474856189865946]
  Large multi-modal models (LMMs) struggle with inaccurate segmentation and hallucinated comprehension.<n>We propose LIRA, a framework that capitalizes on the complementary relationship between visual comprehension and segmentation.<n>LIRA achieves state-of-the-art performance in both segmentation and comprehension tasks.
  arXiv  Detail & Related papers  (2025-07-08T07:46:26Z)
• Pro2SAM: Mask Prompt to SAM with Grid Points for Weakly Supervised Object Localization [54.91271106816616]
  We propose an innovative mask prompt to SAM (Pro2SAM) network with grid points for WSOL task.<n>First, we devise a Global Token Transformer (GTFormer) to generate a coarse-grained foreground map as a flexible mask prompt.<n> Secondly, we deliver grid points as dense prompts into SAM to maximize the probability of foreground mask.
  arXiv  Detail & Related papers  (2025-05-08T02:44:53Z)
• DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistency [91.30252180093333]
  We propose the Dual Consistency SAM (DCSAM) method based on prompttuning to adapt SAM and SAM2 for in-context segmentation. Our key insights are to enhance the features of the SAM's prompt encoder in segmentation by providing high-quality visual prompts. Although the proposed DC-SAM is primarily designed for images, it can be seamlessly extended to the video domain with the support SAM2.
  arXiv  Detail & Related papers  (2025-04-16T13:41:59Z)
• Bridge the Points: Graph-based Few-shot Segment Anything Semantically [79.1519244940518]
  Recent advancements in pre-training techniques have enhanced the capabilities of vision foundation models. Recent studies extend the SAM to Few-shot Semantic segmentation (FSS) We propose a simple yet effective approach based on graph analysis.
  arXiv  Detail & Related papers  (2024-10-09T15:02:28Z)
• One Shot is Enough for Sequential Infrared Small Target Segmentation [9.354927663020586]
  Infrared small target sequences exhibit strong similarities between frames and contain rich contextual information. We propose a one-shot and training-free method that perfectly adapts SAM's zero-shot generalization capability to sequential IRSTS. Experiments demonstrate that our method requires only one shot to achieve comparable performance to state-of-the-art IRSTS methods.
  arXiv  Detail & Related papers  (2024-08-09T02:36:56Z)
• CycleSAM: One-Shot Surgical Scene Segmentation using Cycle-Consistent Feature Matching to Prompt SAM [2.9500242602590565]
  CycleSAM is an approach for one-shot surgical scene segmentation using the training image-mask pair at test-time. We employ a ResNet50 encoder pretrained on surgical images in a self-supervised fashion, thereby maintaining high label-efficiency.
  arXiv  Detail & Related papers  (2024-07-09T12:08:07Z)
• SAM Fewshot Finetuning for Anatomical Segmentation in Medical Images [3.2099042811875833]
  We propose a strategy for adapting the Segment Anything (SAM) to anatomical segmentation tasks in medical images. We leverage few-shot embeddings derived from a limited set of labeled images as prompts for anatomical querying objects captured in image embeddings. Our method prioritizes the efficiency of the fine-tuning process by exclusively training the mask decoder through caching mechanisms.
  arXiv  Detail & Related papers  (2024-07-05T17:07:25Z)
• Performance Evaluation of Segment Anything Model with Variational Prompting for Application to Non-Visible Spectrum Imagery [15.748043194987075]
  This work assesses Segment Anything Model capabilities in segmenting objects of interest in the X-ray/infrared modalities. Our results show that SAM can segment objects in the X-ray modality when given a box prompt, but its performance varies for point prompts. We find that infrared objects are also challenging to segment with point prompts given the low-contrast nature of this modality.
  arXiv  Detail & Related papers  (2024-04-18T16:04:14Z)
• PosSAM: Panoptic Open-vocabulary Segment Anything [58.72494640363136]
  PosSAM is an open-vocabulary panoptic segmentation model that unifies the strengths of the Segment Anything Model (SAM) with the vision-native CLIP model in an end-to-end framework. We introduce a Mask-Aware Selective Ensembling (MASE) algorithm that adaptively enhances the quality of generated masks and boosts the performance of open-vocabulary classification during inference for each image.
  arXiv  Detail & Related papers  (2024-03-14T17:55:03Z)
• CPCM: Contextual Point Cloud Modeling for Weakly-supervised Point Cloud Semantic Segmentation [60.0893353960514]
  We study the task of weakly-supervised point cloud semantic segmentation with sparse annotations. We propose a Contextual Point Cloud Modeling ( CPCM) method that consists of two parts: a region-wise masking (RegionMask) strategy and a contextual masked training (CMT) method.
  arXiv  Detail & Related papers  (2023-07-19T04:41:18Z)
• Segment Anything Meets Point Tracking [116.44931239508578]
  This paper presents a novel method for point-centric interactive video segmentation, empowered by SAM and long-term point tracking. We highlight the merits of point-based tracking through direct evaluation on the zero-shot open-world Unidentified Video Objects (UVO) benchmark. Our experiments on popular video object segmentation and multi-object segmentation tracking benchmarks, including DAVIS, YouTube-VOS, and BDD100K, suggest that a point-based segmentation tracker yields better zero-shot performance and efficient interactions.
  arXiv  Detail & Related papers  (2023-07-03T17:58:01Z)
• Sparse Instance Activation for Real-Time Instance Segmentation [72.23597664935684]
  We propose a conceptually novel, efficient, and fully convolutional framework for real-time instance segmentation. SparseInst has extremely fast inference speed and achieves 40 FPS and 37.9 AP on the COCO benchmark.
  arXiv  Detail & Related papers  (2022-03-24T03:15:39Z)

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.