AI Paper Atlas

Research map / Detection and segmentation / CNN features

SegViT v2: Exploring Efficient and Continual Semantic Segmentation with Plain Vision Transformers

Bowen Zhang, Liyang Liu, Vu Minh Hieu Phan, Zhi Tian, Chunhua Shen, Yifan Liu

IJCV 2023 · Detection and segmentation › CNN features · approach: Plain and high-resolution ViTs · 68 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace SETR decoder with ATM decoder (CE loss) (ablation)SegViT · ADE20K val (ViT-Base)mIoU (ss): 46.5 -> 47.0Improved
supervise ATM with decoupled mask loss instead of CE loss (ablation)SegViT ATM · ADE20K val (ViT-Base)mIoU (ss): 47.0 -> 49.6Improved
add lower-layer features (cascade [6,12]) (ablation)SegViT · ADE20K val (ViT-Base)mIoU (ss): 49.6 -> 50.9Improved
use three layers [6,8,12] instead of single layer (ablation)SegViT · ADE20K val (ViT-Base)mIoU (ss): 49.6 -> 51.3Improved
use four layers [3,6,9,12] instead of three (ablation)SegViT · ADE20K val (ViT-Base)mIoU (ss): 51.3 -> 51.2No clear effect
add query downsampling (QD) to single structure without upsampling (ablation)SegViT · ADE20K val (ViT-Base)mIoU (ss): 49.6 -> 46.9Hurt
add query upsampling (QU) after QD (Shrunk) (ablation)SegViT Shrunk · ADE20K val (ViT-Base)mIoU (ss): 46.9 -> 50.0Improved
use nearest token squeezing instead of edge-aware downsampling (Shrunk++) (ablation)SegViT Shrunk++ · ADE20K val (ViT-Base)mIoU (ss): 49.9 -> 43.3Hurt
add edge-aware downsampling to token squeezing (3x3) (ablation)SegViT Shrunk++ · ADE20K val (ViT-Base)mIoU (ss): 38.9 -> 47.9Improved
replace FPN decoder with ATM token merge (ablation)MaskFormer-style decoder · ADE20K val (ViT-Base)mIoU (ss): 46.7 -> 50.6Improved
add attention mask loss instead of dot product loss (ablation)SegViT · ADE20K val (ViT-Base)mIoU (ss): 50.6 -> 51.2Improved
downsample only query with nearest instead of learnable stride-2 conv (ablation)SegViT QD · ADE20K val (ViT-Large)mIoU (ss): 44.5 -> 53.9Improved

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