AI Paper Atlas

Research map / Detection and segmentation / CNN features

Context-Guided Spatial Feature Reconstruction for Efficient Semantic Segmentation

Zhenliang Ni, Xinghao Chen, Yingjie Zhai, Yehui Tang, Yunhe Wang

ECCV 2024 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 122 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 Rectangular Self-Calibration Module for pyramid context extraction (ablation)CGRSeg-T · ADE20K valmIoU (%): 41.34 -> 42.57Improved
add RCM for spatial feature reconstruction (ablation)CGRSeg-T · ADE20K valmIoU (%): 42.57 -> 43.60Improved
add Dynamic Prototype Guided head (ablation)CGRSeg-T · ADE20K valmIoU (%): 40.86 -> 41.34Improved
use DPG head instead of HamHead (ablation)CGRSeg-T · ADE20K valmIoU (%): 42.1 -> 43.6Improved
use rectangular self-calibration attention instead of self-attention (ablation)CGRSeg-T · ADE20K valmIoU (%): 39.9 -> 43.6Improved
model key area with broadcast addition instead of multiplication (ablation)RCA · ADE20K valmIoU (%): 43.08 -> 43.61Improved
add shape self-calibration strip convolutions (1x11, 11x1) (ablation)RCA · ADE20K valmIoU (%): 41.27 -> 43.61Improved
use 3x3 depthwise conv in fusion function instead of 1x1 (ablation)RCA · ADE20K valmIoU (%): 41.70 -> 43.39Improved
use 5x5 local conv instead of 3x3 in fusion (ablation)RCA · ADE20K valmIoU (%): 43.39 -> 42.99Hurt
swap EfficientFormerV2 backbone for MSCAN-TCGRSeg-T · ADE20K valmIoU (%): SegNeXt 41.1 -> CGRSeg 42.6Improved

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