paper-with-me

Continual Semantic Segmentation

3개 벤치마크 · 논문 39편 · 이 태스크의 논문 보기 →

Benchmarks

ADE20K

결과 4개

PASCAL VOC 2012

결과 2개

ScanNet

결과 2개

Most implemented

Papers

Continual Segmentation under Joint Nonstationarity

2026-05-19 · Prashant Pandey, Himanshu Kumar, Devineni Sri Venkatraya Chowdary, Brejesh Lall arxiv

Evolving data streams induce joint nonstationarity in continual semantic segmentation, where semantic classes, input distributions, and supervision availability change simultaneously over time. This setting reflects prac…

Continual Semantic SegmentationStructured PredictionContinual Learning

MILE: Mixture of Incremental LoRA Experts for Continual Semantic Segmentation across Domains and Modalities

2026-05-05 · Shishir Muralidhara, Didier Stricker, René Schuster arxiv

Continual semantic segmentation requires models to adapt to new domains or modalities without sacrificing performance on previously learned tasks. Expert-based learning, in which task-specific modules specialize in diffe…

Continual Semantic Segmentation

Zero-Forgetting CISS via Dual-Phase Cognitive Cascades

2026-03-14 · Yuquan Lu, Yifu Guo, Zishan Xu, Siyu Zhang 외 arxiv

Continual semantic segmentation (CSS) is a cornerstone task in computer vision that enables a large number of downstream applications, but faces the catastrophic forgetting challenge. In conventional class-incremental se…

Continual Semantic SegmentationContinual Learning

Decoupling Continual Semantic Segmentation

2025-08-07 · Yifu Guo, Yuquan Lu, Wentao Zhang, Zishan Xu 외 arxiv

Continual Semantic Segmentation (CSS) requires learning new classes without forgetting previously acquired knowledge, addressing the fundamental challenge of catastrophic forgetting in dense prediction tasks. However, ex…

Continual Semantic SegmentationContinual Learning

Revisiting Continual Semantic Segmentation with Pre-trained Vision Models

2025-08-06 · Duzhen Zhang, Yong Ren, Wei Cong, Junhao Zheng 외 arxiv

Continual Semantic Segmentation (CSS) seeks to incrementally learn to segment novel classes while preserving knowledge of previously encountered ones. Recent advancements in CSS have been largely driven by the adoption o…

Continual Semantic Segmentation

Beyond Background Shift: Rethinking Instance Replay in Continual Semantic Segmentation

2025-03-28 · CVPR 2025 1 · Hongmei Yin, Tingliang Feng, Fan Lyu, Fanhua Shang 외

In this work, we focus on continual semantic segmentation (CSS), where segmentation networks are required to continuously learn new classes without erasing knowledge of previously learned ones. Although storing images of…

Continual Semantic SegmentationSemantic Segmentation

전체 39편 보기 →