AI Paper Atlas

Research map / Detection and segmentation / CNN features

A Transformer-Based Decoder for Semantic Segmentation with Multi-level Context Mining

Bowen Shi, Dongsheng Jiang, Xiaopeng Zhang, Han Li, Wenrui Dai, Junni Zou, Hongkai Xiong, Qi Tian

ECCV 2022 · Detection and segmentation › CNN features · approach: Plain and high-resolution ViTs · 31 citations (OpenAlex)

This paper tried a common change: Add attention module

add the second attention layer Y_exter in external mining · ADE20K val · mIoU: 0.51% performance loss when removed Improved

What 492 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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 one-head internal self-attention in the decoder (ablation)SegFormer-B1 · ADE20K valmIoU: 40.97 -> 42.65Improved
use more heads, deeper or MLP in internal attention (ablation)SegFormer-B1 + internal attention · ADE20K valmIoU: 42.65 -> 42.53No clear effect
add MLP after internal attention (ablation)SegFormer-B1 + internal attention · ADE20K valmIoU: 42.65 -> 42.81Improved
use momentum-updated external tokens instead of none (ablation)SegFormer-B1 · ADE20K valmIoU: 40.97 -> 41.44Improved
use learnable instead of momentum external tokens with mid-level supervision (ablation)SegFormer-B1 · ADE20K valmIoU: 41.74 -> 42.37Improved
add category-specific loss L_attn to learnable external tokens (ablation)SegFormer-B1 · ADE20K valmIoU: 41.57 -> 42.37Improved
add decoupling of external tokens (ablation)SegFormer-B1 · ADE20K valmIoU: 42.37 -> 42.84Improved
add the second attention layer Y_exter in external mining (ablation)SegFormer-B1 · ADE20K valmIoU: 0.51% performance loss when removedImproved
add internal and external mining together (ablation)SegFormer-B1 · ADE20K valmIoU: 40.97 -> 44.05Improved
add SegDeformer to SegFormer-B2SegFormer-B2 · ADE20K valmIoU: 45.58 -> 47.49Improved
deepen the base decoder instead of using SegDeformer (ablation)SegFormer-B2 · ADE20K valmIoU: 45.58 -> 45.68No clear effect
replace UperNet with SegDeformer on Deit-SDeit-S · ADE20K valmIoU: 42.87 -> 43.93Improved

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