AI Paper Atlas

Research map / Detection and segmentation / CNN features

Vision Transformers: From Semantic Segmentation to Dense Prediction

Li Zhang, Jiachen Lu, Sixiao Zheng, Xinxuan Zhao, Xiatian Zhu, Yanwei Fu, Tao Xiang, Jianfeng Feng, Philip H. S. Torr

IJCV 2024 · Detection and segmentation › CNN features · approach: Plain and high-resolution ViTs · 33 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
add ImageNet-21K pretraining of the Transformer (vs random init) (ablation)SETR-PUP T-Large · Cityscapes valmIoU (%): 42.27 -> 78.39Improved
add auxiliary loss heads (ablation)SETR-Naive · Cityscapes val (40k)mIoU (%): 76.73 -> 77.37Improved
add auxiliary loss heads (ablation)SETR-Naive · Cityscapes val (80k)mIoU (%): 77.23 -> 77.90Improved
use 4 progressive upsample layers instead of 2 (ablation)SETR-PUP · Cityscapes val (40k)mIoU (%): 77.48 -> 78.39Improved
progressive upsampling decoder (PUP) instead of MLA (ablation)SETR T-Large · Cityscapes val (40k)mIoU (%): 76.65 -> 78.39Improved
MLA decoder instead of PUP (ablation)SETR T-Large · ADE20K val (MS)mIoU (%): 50.1 -> 50.3No clear effect
replace ViT IN-21K pretraining with BEiT IN-21K (ablation)SETR-PUP T-Large · Cityscapes val (80k)mIoU (%): 79.34 -> 80.43Improved
replace ViT IN-21K pretraining with BEiT IN-21K (ablation)SETR-PUP T-Large · ADE20K val (SS)mIoU (%): 48.6 -> 52.5Improved
use DeiT IN-1K pretraining instead of ViT IN-21K on T-Base (ablation)SETR-PUP T-Base · Cityscapes val (80k)mIoU (%): 78.02 -> 79.45Improved
use DeiT IN-1K T-Base instead of ViT IN-1K... T-Large on ADE20K (ablation)SETR-PUP · ADE20K val (SS)mIoU (%): 48.6 -> 46.3Hurt
pretrain FCN on IN-21K instead of IN-1K (ablation)FCN R-101 · ADE20K valmIoU (%): 39.91 -> 42.17Improved
pretrain FCN on IN-21K instead of IN-1K (ablation)FCN R-101 · Cityscapes valmIoU (%): 73.93 -> 76.38Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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