Sparse All-Layer Connector for Domain Generalised Semantic Segmentation

arXiv:2610.15660 · cs.CV · Submitted 2026-10-11 · Read on arXiv

cs.CV

Submitted: 2026-10-11

Updated: 2026-10-11

Code: https://github.com/RuoyuGuo/SALC

Terminology

• Semantic Segmentation — 1× in this paper · explained in 2 episodes

Sources

• MMFuser: Multimodal Multi-Layer Feature Fuser for Fine-Grained Vision-Language Understanding
• EVLM: An Efficient Vision-Language Model for Visual Understanding
• Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learning
• From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models
• SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models
• Layer by layer, module by module: Choose both for optimal OOD probing of ViT
• DINOv2: Learning Robust Visual Features without Supervision

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models