AI Paper Atlas

Research map / Detection and segmentation / CNN features

A Holistically-Guided Decoder for Deep Representation Learning With Applications to Semantic Segmentation and Object Detection

Jianbo Liu, Junjun He, Yuanjie Zheng, Shuai Yi, Xiaogang Wang, Hongsheng Li

TPAMI 2021 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 15 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 bilinear/deconv skip-connected decoder with HGDEfficientFCN · PASCAL Context valmIoU (%): 49.3 -> 55.3Improved
add OS=16 and OS=8 maps to codeword-generation fusion (ablation)EfficientFCN · PASCAL Context valmIoU (%): 54.8 -> 55.3Improved
add OS=8 and OS=16 fusion to coefficient estimation (ablation)EfficientFCN · PASCAL Context valmIoU (%): 47.9 -> 55.3Improved
add additive codeword information transfer to coefficient branch (ablation)EfficientFCN · PASCAL Context valmIoU (%): 54.2 -> 55.3Improved
increase number of codewords from 32 to 512 (ablation)EfficientFCN · PASCAL Context valmIoU (%): 54.5 -> 55.5Improved
increase codewords from 512 to 1024 (ablation)EfficientFCN · PASCAL Context valmIoU (%): 55.5 -> 55.1Hurt
add holistic codewords on top of multi-scale fusion only (n=0,c=0) (ablation)HGD-FPN Faster R-CNN · COCO minivalAP: 37.5 -> 40.0Improved
add multi-scale fusion only (n=0,c=0) to FPN (ablation)Faster R-CNN FPN · COCO minivalAP: 36.3 -> 37.5Improved
increase recurrence k from 1 to 4 (ablation)HGD-FPN Faster R-CNN · COCO minivalAP: 37.9 -> 40.0Improved
increase recurrence k from 4 to 5 (ablation)HGD-FPN Faster R-CNN · COCO minivalAP: 40.0 -> 39.8Hurt
share parameters across recurrent HGD-FPN stages (ablation)HGD-FPN Faster R-CNN · COCO minivalAP: 39.6 -> 40.0Improved
replace FPN with HGD-FPNRetinaNet · COCO minivalAP: 35.3 -> 37.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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