cs.CVNov 11, 2026

Hint-Informed Self-Distillation for Reasoning Segmentation

Authors: Kunze Jiang, Yuchen Wang, Kang Li, Qixing Zhang

Organizations: University of Science and Technology of China

Abstract

Reasoning segmentation requires identifying the target referred to by a query among visually similar objects, yet trajectory-level rewards cannot directly indicate which tokens provide relevant visual evidence. We propose Hint-Informed Self-Distillation (HISD), which uses target-disambiguation evidence for token-level credit assignment. An external model generates Segment Hints offline from training images, queries, and ground-truth target annotations, organizing target identity, discriminative attributes, confusable objects, and anchoring paths. A hint-conditioned exponential moving average teacher scores the student's own trajectories, and HISD computes the teacher-to-student evidence ratio over a token support set to adjust only the magnitudes of positive group-relative advantages, leaving nonpositive advantages unchanged. This design encourages concise reasoning while retaining the information needed for target disambiguation, and the student requires neither hints nor a teacher at inference. Under a unified training protocol, HISD improves ReasonSeg test gIoU and cIoU over our reproduction of DPAD by 3.00 and 3.55 percentage points, respectively. Across the five evaluated splits of ReasonSeg and the RefCOCO family, HISD achieves higher segmentation metrics than this baseline and reduces the average token count of valid reasoning spans by 80.17 to 91.83 percent.

Figures & tables

Explore similar work

CardsList
  1. AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation

    Apr 20, 2026Rui Qian, Chuanhang Deng, Qiang Huang +6Image SegmentationText-Guided Image Segmentation

  2. CR-Seg: Attention-Guided and CoT-Enhanced Coarse-to-Refined Reasoning Segmentation

    Jun 2, 2026Yifan Cao, Xiaocui Yang, Faxian Wan +3Text-Guided Image SegmentationPromptable Image Segmentation

  3. SegCompass: Exploring Interpretable Alignment with Sparse Autoencoders for Enhanced Reasoning Segmentation

    May 21, 2026Zhenyu Lu, Liupeng Li, Jinpeng Wang +4Image SegmentationText-Guided Image Segmentation