DGSeg: Dynamic Gating of Semantic-Spatial Guided Predictions for Reasoning Segmentation

• URL: http://arxiv.org/abs/2607.04779v1
• Date: Mon, 06 Jul 2026 08:10:03 GMT
• Title: DGSeg: Dynamic Gating of Semantic-Spatial Guided Predictions for Reasoning Segmentation
• Abstract summary: Reasoning segmentation aims to predict pixel-wise masks for targets given complex language queries.<n>We propose DGSeg, a framework that learns to fuse predictions guided by semantic and spatial cues.<n>Experiments demonstrate that DGSeg consistently outperforms strong baselines on multiple benchmarks.
• Score: 5.5825182710791275
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reasoning segmentation aims to predict pixel-wise masks for targets given complex language queries. Existing approaches leverage Multimodal Large Language Models (MLLMs) for vision-language reasoning and generate intermediate target cues (e.g., points or boxes) to guide a segmentation model. However, compressing rich reasoning into sparse cues often introduces ambiguity and noise, preventing these cues from accurately preserving the reasoning intent. While multiple complementary cues can enrich target information, existing methods typically feed them jointly into a single segmentation process, allowing ambiguous or erroneous cues to affect the entire prediction. Therefore, we propose DGSeg, a reasoning segmentation framework that learns to fuse predictions guided by semantic and spatial cues. Specifically, the MLLM jointly reasons about both target identity and spatial location, producing complementary semantic and spatial cues that are fed into separate segmentation branches. Their predictions are adaptively integrated by a lightweight dynamic gating module trained with relative branch-quality supervision to suppress noisy or conflicting regions. Extensive experiments demonstrate that DGSeg consistently outperforms strong baselines on multiple benchmarks and achieves 69.6% and 67.3% gIoU on the challenging ReasonSeg validation and test splits. Code is available at https://github.com/RZZeng/DGSeg.

Related papers

• Multi-Agent Reasoning with Adaptive Worker Allocation for Stance Detection [2.8758927043198206]
  We introduce a multi-agent reasoning framework with adaptive worker allocation for stance detection.<n>The framework shifts aggregation from label-level voting to reasoning-level synthesis.<n>We evaluate the proposed framework on SemEval-2016, P-Stance, and COVID-19 Stance using Llama, Mistral, and Gemini.
  arXiv  Detail & Related papers  (2026-06-10T03:20:55Z)
• CR-Seg: Attention-Guided and CoT-Enhanced Coarse-to-Refined Reasoning Segmentation [26.21876180083083]
  Reasoning segmentation aims to segment target objects described by complex language through joint visual-textual reasoning.<n>Existing methods rely on either learned semantic tokens to bridge Multimodal Large Language Models (MLLMs) and segmentation models, suffering from difficult cross-modal alignment.<n>We propose Attention-Guided and CoT-Enhanced Coarse-to-Refined Reasoning, termed CR-Seg, a two-stage framework for coarse-to-refined spatial segmentation.
  arXiv  Detail & Related papers  (2026-06-02T12:30:04Z)
• Seg-Agent: Test-Time Multimodal Reasoning for Training-Free Language-Guided Segmentation [52.8308168727975]
  Seg-Agent is a completely training-free framework that pioneers Explicit Multimodal Chain-of-Reasoning.<n>Our approach constructs an interactive visual reasoning loop comprising three stages: generation, selection, and refinement.<n>Various-LangSeg is a novel benchmark covering explicit semantic, generic object, and reasoning-guided segmentation tasks.
  arXiv  Detail & Related papers  (2026-05-13T03:36:44Z)
• AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation [56.21301367698041]
  We introduce AnchorSeg, which reformulates reasoning segmentation as a structured conditional generation process over image tokens.<n>We model spatial conditioning as a factorized distribution over image tokens, where the anchor query determines localization signals.<n>We propose Token--Mask Cycle Consistency (TMCC), a bidirectional training objective that enforces alignment across resolutions.
  arXiv  Detail & Related papers  (2026-04-20T17:49:22Z)
• ConInfer: Context-Aware Inference for Training-Free Open-Vocabulary Remote Sensing Segmentation [12.428190609914594]
  Training-free open-vocabulary remote sensing segmentation (OVRSS) has emerged as a promising paradigm for achieving category-agnostic semantic understanding in remote sensing imagery.<n>We propose ConInfer, a context-aware inference framework for OVRSS that performs joint prediction across multiple spatial units.<n>Our method significantly enhances segmentation consistency, robustness, and generalization in complex remote sensing environments.
  arXiv  Detail & Related papers  (2026-03-31T05:12:02Z)
• CORE-Seg: Reasoning-Driven Segmentation for Complex Lesions via Reinforcement Learning [48.77689764063103]
  We introduce ComLesion-14K, the first diverse Chain-of-Thought benchmark for reasoning-driven complex lesion segmentation.<n>We propose CORE-Seg, an end-to-end framework integrating reasoning with segmentation through a Semantic-Guided Prompt Adapter.<n>Our Method achieves state-of-the-art results with a mean Dice of 37.06% (14.89% higher than the second-best baseline), while reducing the failure rate to 18.42%.
  arXiv  Detail & Related papers  (2026-03-06T04:58:55Z)
• Bridging Semantics and Geometry: A Decoupled LVLM-SAM Framework for Reasoning Segmentation in Remote Sensing [8.731693840957716]
  Think2Seg-RS is a framework that trains an LVLM prompter to control a frozen Segment Anything Model (SAM) via structured geometric prompts.<n>The framework achieves state-of-the-art performance on the EarthReason dataset.<n> compact segmenters outperform larger ones under semantic-level supervision, and that negative prompts are ineffective in heterogeneous aerial backgrounds.
  arXiv  Detail & Related papers  (2025-12-22T11:46:42Z)
• CoPRS: Learning Positional Prior from Chain-of-Thought for Reasoning Segmentation [51.25997439181537]
  CoPRS bridges language reasoning to segmentation through a differentiable and interpretable positional prior instantiated as a heatmap.<n>A learnable concentration token aggregates features of the image and reasoning text to generate this positional prior, which is decoded to precise masks through a lightweight decoder.
  arXiv  Detail & Related papers  (2025-10-13T09:07:54Z)
• LIRA: Inferring Segmentation in Large Multi-modal Models with Local Interleaved Region Assistance [54.683384204063934]
  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)
• Localization and Expansion: A Decoupled Framework for Point Cloud Few-shot Semantic Segmentation [39.7657197805346]
  Point cloud few-shot semantic segmentation (PC-FSS) aims to segment targets of novel categories in a given query point cloud with only a few annotated support samples. We propose a simple yet effective framework in the spirit of Decoupled Localization and Expansion (DLE) DLE, including a structural localization module (SLM) and a self-expansion module (SEM), enjoys several merits.
  arXiv  Detail & Related papers  (2024-08-25T07:34:32Z)
• Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentation [63.910211095033596]
  Few-shot segmentation aims to segment unseen-class objects given only a handful of densely labeled samples. We propose a simple yet versatile framework in the spirit of divide-and-conquer. Our proposed approach, named divide-and-conquer proxies (DCP), allows for the development of appropriate and reliable information.
  arXiv  Detail & Related papers  (2022-04-21T06:21:14Z)

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.