FOCUS: Forcing In-Context Object Localization through Visual Support Constraints and Policy Optimization

• URL: http://arxiv.org/abs/2605.31145v1
• Date: Fri, 29 May 2026 10:53:52 GMT
• Title: FOCUS: Forcing In-Context Object Localization through Visual Support Constraints and Policy Optimization
• Abstract summary: In-context localization (ICL) seeks to localize a target object specified by a small set of support examples in a query image.<n>Existing methods are fragile and rely on explicit category supervision.<n>We introduce a two-stage training framework that explicitly optimize in-context attention between support bounding boxes and query images.
• Score: 9.2112812802555
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In-context localization (ICL) seeks to localize a target object specified by a small set of support examples in a query image, operating on the fly without training or parameter updates. Despite rapid advances in vision-language models (VLMs), achieving category-agnostic and visually grounded ICL remains an open problem, even though it is essential for applications such as image editing, personalized visual search, and retrieval. Existing methods are fragile and rely on explicit category supervision, which not only limits applicability in realistic settings with unnamed or instance-specific objects but also introduces category bias that steers predictions toward semantic priors rather than visual evidence. We introduce a two-stage training framework that explicitly optimizes in-context attention between support bounding boxes and query images without category supervision. We further refine localization via reinforcement learning using Group Relative Policy Optimization (GRPO) to directly minimize localization error. This formulation enforces visual correspondence over semantic priors, yielding robust instance-level localization. Empirically, a 7B-parameter model trained with our objectives outperforms models up to 72B parameters, demonstrating that context-aware localization objectives can surpass scaling alone. Comprehensive ablations validate the contribution of each component.

Related papers

• Primitive-Driven Compositional Forensic Visual Prompting for Open-World Face Anti-Spoofing [59.765442274924595]
  We propose a compositional visual prompt learning framework that operates entirely in the visual feature space.<n>The framework employs patch-aware attention to refine a shared set of learnable micro-forensic primitives into localized forensic evidence units.<n>Experiments on nine open-world protocols demonstrate state-of-the-art performance, strong cross-domain generalization, and robust adaptation to unseen attacks.
  arXiv  Detail & Related papers  (2026-08-18T04:18:08Z)
• Dynamic Parsing and Updating Natural Language Specification using VLMs for Robust Vision-Language Tracking [61.91472604294714]
  We propose a novel language dependency parsing mechanism to distill tracking principal components.<n>We exploit the powerful cross-modal understanding capability of the pre-trained vision-language model Qwen-VL.<n>Our method achieves consistent and superior tracking performance on multiple large-scale vision-language tracking benchmarks.
  arXiv  Detail & Related papers  (2026-06-28T12:12:18Z)
• ExACT: Exemplar-Driven Calibrated Refinement for Training-Free Visual Grounding in Remote Sensing Images [51.53960096934913]
  Remote sensing visual grounding (RSVG) aims to locate specific objects in high-resolution RS imagery using free-form natural language descriptions.<n>Recent advances in multimodal large language models (MLLMs) show great potential for such open-vocabulary RSVG.<n>We propose Exemplar-driven Calibrated Refinement (ExACT), a training-free framework driven by a one-shot visual prompting mechanism.
  arXiv  Detail & Related papers  (2026-06-27T13:50:39Z)
• LAGO: Language-Guided Adaptive Object-Region Focus for Zero-Shot Visual-Text Alignment [11.785675631199455]
  In fine-grained settings, the relevant evidence often lies in localized parts, attributes, or textures rather than in the full image.<n>Recent localized visual-text alignment methods address this by comparing class descriptions with multiple image regions.<n>We propose LAGO, a framework for efficient and robust zero-shot localized visual-text alignment.
  arXiv  Detail & Related papers  (2026-05-04T09:07:00Z)
• LoGoSeg: Integrating Local and Global Features for Open-Vocabulary Semantic Segmentation [12.192429756057132]
  Open-vocabulary semantic segmentation (OVSS) extends traditional closed-set segmentation by enabling pixel-wise annotation for both seen and unseen categories.<n>LoGoSeg integrates three key innovations: (i) an object existence prior that dynamically weights relevant categories through global image-text similarity, effectively reducing hallucinations; (ii) a region-aware alignment module that establishes precise region-level visual-textual correspondences; and (iii) a dual-stream fusion mechanism that optimally combines local structural information with global semantic context.
  arXiv  Detail & Related papers  (2026-02-05T12:03:11Z)
• Constrained Prompt Enhancement for Improving Zero-Shot Generalization of Vision-Language Models [57.357091028792325]
  Vision-language models (VLMs) pre-trained on web-scale data exhibit promising zero-shot generalization but often suffer from semantic misalignment.<n>We propose a novel constrained prompt enhancement (CPE) method to improve visual-textual alignment.<n>Our approach consists of two key components: Topology-Guided Synonymous Semantic Generation (TGSSG) and Category-Agnostic Discriminative Region Selection (CADRS)
  arXiv  Detail & Related papers  (2025-08-24T15:45:22Z)
• Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception [71.26728044621458]
  DeCLIP is a novel framework that enhances CLIP by decoupling the self-attention module to obtain content'' and context'' features respectively.<n>It consistently achieves state-of-the-art performance across a broad spectrum of tasks, including 2D detection and segmentation, 3D instance segmentation, video instance segmentation, and 6D object pose estimation.
  arXiv  Detail & Related papers  (2025-08-15T06:43:51Z)
• Helping CLIP See Both the Forest and the Trees: A Decomposition and Description Approach [43.419607730361996]
  Vision-Language Models (VLMs) like CLIP achieve cross-modal alignment through contrastive learning.<n>Traditional prompt engineering relies on coarse-grained category labels, neglecting fine-grained local semantics.<n>We propose a plug-and-play solution that enables CLIP to process localized visual descriptors.
  arXiv  Detail & Related papers  (2025-07-04T10:24:26Z)
• Teaching VLMs to Localize Specific Objects from In-context Examples [56.797110842152]
  We find that present-day Vision-Language Models (VLMs) lack a fundamental cognitive ability: learning to localize specific objects in a scene by taking into account the context.<n>This work is the first to explore and benchmark personalized few-shot localization for VLMs.
  arXiv  Detail & Related papers  (2024-11-20T13:34:22Z)
• Domain Adaptation with a Single Vision-Language Embedding [45.93202559299953]
  We present a new framework for domain adaptation relying on a single Vision-Language (VL) latent embedding instead of full target data. We show that these mined styles can be used for zero-shot (i.e., target-free) and one-shot unsupervised domain adaptation.
  arXiv  Detail & Related papers  (2024-10-28T17:59:53Z)
• Grounding Everything: Emerging Localization Properties in Vision-Language Transformers [51.260510447308306]
  We show that pretrained vision-language (VL) models allow for zero-shot open-vocabulary object localization without any fine-tuning. We propose a Grounding Everything Module (GEM) that generalizes the idea of value-value attention introduced by CLIPSurgery to a self-self attention path. We evaluate the proposed GEM framework on various benchmark tasks and datasets for semantic segmentation.
  arXiv  Detail & Related papers  (2023-12-01T19:06:12Z)
• Bootstrap Fine-Grained Vision-Language Alignment for Unified Zero-Shot Anomaly Localization [63.61093388441298]
  Contrastive Language-Image Pre-training models have shown promising performance on zero-shot visual recognition tasks. In this work, we propose AnoCLIP for zero-shot anomaly localization.
  arXiv  Detail & Related papers  (2023-08-30T10:35:36Z)

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.