AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

S$^2$-RL: Sample-Set Dual Reinforcement Learning for Generative Semantic Segmentation Dataset Distillation

Haoyu Wang, Fei Zhou, Qingqing Qiu, Lei Zhang, Wei Wei, Chen Ding

NeurIPS 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes S²-RL, a sample-set dual reinforcement learning framework for generative dataset distillation targeting semantic segmentation.

Problem

Dataset distillation for semantic segmentation: bi-level optimization is computationally expensive due to pixel-wise gradient unrolling, while proxy-based generative methods only add textures to fixed masks derived from real data.

Approach

Uses dual reinforcement learning over both individual samples and the sample set to jointly generate image-mask pairs for distillation, rather than texturing fixed masks; details beyond the truncated abstract are unknown.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add semantic alignment reward (R_align) to GRPO fine-tuning of SD3.5 (ablation)S2-RL · ADE20K, 1.0% budgetsegmentation performance: 21.66 -> 22.91Improved
add intra-class diversity reward (R_div) on top of alignment (ablation)S2-RL · ADE20K, 1.0% budgetsegmentation performance: 22.91 -> 24.73Improved
add set-level reward (R_set) on top of alignment and diversity (ablation)S2-RL · ADE20K, 1.0% budgetsegmentation performance: 24.73 -> 25.47Improved
add set-level reward (R_set) on top of alignment and diversity (ablation)S2-RL · ADE20K, 0.5% budgetsegmentation performance: 20.83 -> 21.52Improved
add set-level reward (R_set) on top of alignment and diversity (ablation)S2-RL · ADE20K, 0.25% budgetsegmentation performance: 15.17 -> 15.60Improved
full dual-reward RL fine-tuning of SD3.5 versus vanilla SD3.5 (ablation)SD3.5 Medium · ADE20K, 0.25% budgetsegmentation performance: 13.54 -> 15.60Improved
add set-level reward to broaden coverageS2-RL · ADE20K 1.0% layout diagnosticsgeometry coverage: .549 -> .693 (vs SD3.5)Improved
broaden generated category combinations via set-level rewardS2-RL · ADE20K 1.0% category-pairpair precision: .955 -> .898 (UniDD* vs S2-RL)Hurt
distill with S2-RL to different student architectures (ResNet-18 to 101, ConvNeXt, Swin, DeepLabV3, SegFormer)S2-RL distilled datasets · ADE20K student variationsegmentation performanceImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy