BALD-SAM: Disagreement-based Active Prompting in Interactive Segmentation

• URL: http://arxiv.org/abs/2603.10828v1
• Date: Wed, 11 Mar 2026 14:34:55 GMT
• Title: BALD-SAM: Disagreement-based Active Prompting in Interactive Segmentation
• Abstract summary: We present BALD-SAM, a principled framework adapting Bayesian Active Learning by Disagreement to spatial prompt selection.<n>BALD-SAM demonstrates strong cross-domain performance, ranking first or second on 14 of 16 benchmarks.<n>We validate these gains through a comprehensive ablation suite covering 3 SAM backbones and 35 Laplace posterior configurations.
• Score: 12.449732626554967
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The Segment Anything Model (SAM) has revolutionized interactive segmentation through spatial prompting. While existing work primarily focuses on automating prompts in various settings, real-world annotation workflows involve iterative refinement where annotators observe model outputs and strategically place prompts to resolve ambiguities. Current pipelines typically rely on the annotator's visual assessment of the predicted mask quality. We postulate that a principled approach for automated interactive prompting is to use a model-derived criterion to identify the most informative region for the next prompt. In this work, we establish active prompting: a spatial active learning approach where locations within images constitute an unlabeled pool and prompts serve as queries to prioritize information-rich regions, increasing the utility of each interaction. We further present BALD-SAM: a principled framework adapting Bayesian Active Learning by Disagreement (BALD) to spatial prompt selection by quantifying epistemic uncertainty. To do so, we freeze the entire model and apply Bayesian uncertainty modeling only to a small learned prediction head, making intractable uncertainty estimation practical for large multi-million parameter foundation models. Across 16 datasets spanning natural, medical, underwater, and seismic domains, BALD-SAM demonstrates strong cross-domain performance, ranking first or second on 14 of 16 benchmarks. We validate these gains through a comprehensive ablation suite covering 3 SAM backbones and 35 Laplace posterior configurations, amounting to 38 distinct ablation settings. Beyond strong average performance, BALD-SAM surpasses human prompting and, in several categories, even oracle prompting, while consistently outperforming one-shot baselines in final segmentation quality, particularly on thin and structurally complex objects.

Related papers

• Beyond Instance Slots: Semantically Rich World Models for Physical Interaction Planning [3.284163275977256]
  We present the Semantically Rich World Model (SR-WM), a task-conditioned world model structured around five functional roles.<n>Within SR-WM, a visual entity encoder extracts soft entity hypotheses from pretrained patch features, allowing segmentation masks to serve as optional proposal priors.<n>A role binder maps these hypotheses to task-specific roles, while an action conditioned dynamics model predicts role transitions alongside fine-grained semantics.
  arXiv  Detail & Related papers  (2026-08-23T08:37:59Z)
• Domain-Guided Prompting of the Segment Anything Model for Seismic Interpretation: The Role of Attributes, Visualization, and Hybrid Prompts [0.1529342790344802]
  We introduce a principled framework for zero shot adaptation of foundation models to seismic data.<n>The framework is built on two key components: (1) aligning seismic attributes and visualization choices with the geological target of interest, and (2) employing a hybrid prompting strategy.<n>Our results demonstrate that geologic target aware selection of seismic attributes and colormaps, combined with hybrid prompting, enhances the separability of geological features.
  arXiv  Detail & Related papers  (2026-06-14T12:40:02Z)
• SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks [73.92333717662558]
  SpatialWorld is a benchmark for evaluating the interactive spatial understanding of multimodal agents in complex real-world tasks.<n>It features 760 human-annotated tasks across diverse domains (e.g., household routines, travel, social collaboration)<n>For reliable evaluation, each task includes a human-validated initial state, a reference trajectory, and a terminal-state verifier.
  arXiv  Detail & Related papers  (2026-06-08T15:51:51Z)
• ReSAM: Refine, Requery, and Reinforce: Self-Prompting Point-Supervised Segmentation for Remote Sensing Images [0.5076419064097732]
  We propose a self-prompting, point-supervised framework that adapts interactive segmentation models to remote sensing imagery.<n>We evaluate our proposed method on three RSI benchmark datasets, including WHU, HRSID, and NWPU VHR-10.<n>Our results demonstrate that self-prompting and semantic alignment provide an efficient path towards scalable, point-level adaptation of foundation segmentation models for remote sensing applications.
  arXiv  Detail & Related papers  (2025-11-26T17:26:00Z)
• CLAPS: A CLIP-Unified Auto-Prompt Segmentation for Multi-Modal Retinal Imaging [47.04292769940597]
  We propose CLIP-unified Auto-Prompt (CLAPS), a novel method for unified segmentation across diverse tasks and modalities in retinal imaging.<n>Our approach begins by pre-training a CLIP-based image encoder on a large, multi-modal retinal dataset.<n>To unify tasks and resolve ambiguity, we use text prompts enhanced with a unique "modality signature" for each imaging modality.
  arXiv  Detail & Related papers  (2025-09-10T14:14:49Z)
• Stochastic Encodings for Active Feature Acquisition [100.47043816019888]
  Active Feature Acquisition is an instance-wise, sequential decision making problem.<n>The aim is to dynamically select which feature to measure based on current observations, independently for each test instance.<n>Common approaches either use Reinforcement Learning, which experiences training difficulties, or greedily maximize the conditional mutual information of the label and unobserved features, which makes myopic.<n>We introduce a latent variable model, trained in a supervised manner. Acquisitions are made by reasoning about the features across many possible unobserved realizations in a latent space.
  arXiv  Detail & Related papers  (2025-08-03T23:48:46Z)
• No time to train! Training-Free Reference-Based Instance Segmentation [15.061599989448867]
  This work investigates the task of object segmentation when provided with only a small set of reference images.<n>Our key insight is to leverage strong semantic priors, as learned by foundation models, to identify corresponding regions between a reference and a target image.<n>We find that correspondences enable automatic generation of instance-level segmentation masks for downstream tasks and instantiate our ideas via a multi-stage, training-free method.
  arXiv  Detail & Related papers  (2025-07-03T16:59:01Z)
• Can foundation models actively gather information in interactive environments to test hypotheses? [43.42688356541211]
  Foundation models excel at single-turn reasoning but struggle with multi-turn exploration in dynamic environments.<n>We evaluated these models on their ability to learn from experience, adapt, and gather information.
  arXiv  Detail & Related papers  (2024-12-09T12:27:21Z)
• 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)
• AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning [61.666973416903005]
  Segment Anything Model (SAM) has demonstrated its impressive generalization capabilities in open-world scenarios with the guidance of prompts. We propose a novel framework, termed AlignSAM, designed for automatic prompting for aligning SAM to an open context.
  arXiv  Detail & Related papers  (2024-06-01T16:21:39Z)
• Boosting Segment Anything Model Towards Open-Vocabulary Learning [69.24734826209367]
  Segment Anything Model (SAM) has emerged as a new paradigmatic vision foundation model.<n>Despite SAM finding applications and adaptations in various domains, its primary limitation lies in the inability to grasp object semantics.<n>We present Sambor to seamlessly integrate SAM with the open-vocabulary object detector in an end-to-end framework.
  arXiv  Detail & Related papers  (2023-12-06T17:19:00Z)
• 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)

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.