Research map / Detection and segmentation / CNN features

Beyond Pixel-wise Supervision: Local Structure Regularization for Semantic Segmentation

NeurIPS 2026 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation

Read the paperCheck your idea against 108,967 papers

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

Proposes local structure regularization as a complement to pixel-wise supervision to improve boundary recovery in semantic segmentation built on visual foundation models.

Problem

Accurate boundary recovery for fine structures and semantic transitions remains hard in semantic segmentation with visual foundation models, because conventional pixel-level supervision treats pixels independently and does not model local structure.

Approach

Adds a local structure regularization term on top of pixel-wise supervision so that neighboring pixels' relations are explicitly modeled, rather than supervising each pixel independently. Full method details are not available beyond the abstract.

Closest papers by meaning

• W2P: Switching from Weak Supervision to Partial Supervision for Semantic Segmentation (AAAI 2024 · similarity 0.88)
• Hierarchy-Agnostic Unsupervised Segmentation: Parsing Semantic Image Structure (NeurIPS 2024 · similarity 0.87)
• Unleashing the Power of Visual Foundation Models for Generalizable Semantic Segmentation (AAAI 2025 · similarity 0.87)
• Leveraging Depth and Language for Open-Vocabulary Domain-Generalized Semantic Segmentation (NeurIPS 2025 · similarity 0.87)
• Stronger Fewer & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation (CVPR 2024 · similarity 0.87)
• LAGD: Local Topological-Alignment and Global Semantic-Deconstruction for Incremental 3D Semantic Segmentation (AAAI 2025 · similarity 0.87)