pith. sign in

arXiv preprint arXiv:2404.16573 (2024)

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CV 2

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

Cross-Stage Attention Propagation for Efficient Semantic Segmentation

cs.CV · 2026-04-07 · unverdicted · novelty 7.0

CSAP computes attention at the deepest scale and propagates the maps to shallower stages, bypassing per-scale query-key computations to cut decoder FLOPs while preserving multi-scale performance and beating SegNeXt-Tiny on ADE20K, Cityscapes, and COCO-Stuff.

Diffusion Model as a Generalist Segmentation Learner

cs.CV · 2026-04-27 · unverdicted · novelty 6.0

DiGSeg repurposes diffusion U-Nets as generalist segmentation learners by conditioning on image-mask latents and multi-scale CLIP text features, achieving strong cross-domain performance.

citing papers explorer

Showing 2 of 2 citing papers.

  • Cross-Stage Attention Propagation for Efficient Semantic Segmentation cs.CV · 2026-04-07 · unverdicted · none · ref 29

    CSAP computes attention at the deepest scale and propagates the maps to shallower stages, bypassing per-scale query-key computations to cut decoder FLOPs while preserving multi-scale performance and beating SegNeXt-Tiny on ADE20K, Cityscapes, and COCO-Stuff.

  • Diffusion Model as a Generalist Segmentation Learner cs.CV · 2026-04-27 · unverdicted · none · ref 103

    DiGSeg repurposes diffusion U-Nets as generalist segmentation learners by conditioning on image-mask latents and multi-scale CLIP text features, achieving strong cross-domain performance.