AI Paper Atlas

Research map / Detection and segmentation / CNN features

Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation

Xiaokang Chen, Kwan-Yee Lin, Jingbo Wang, Wayne Wu, Chen Qian, Hongsheng Li, Gang Zeng

ECCV 2020 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 506 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 SA-Gate to the dual-path ResNet-50 (ablation)Res50 dual path · NYU Depth V2 test (no decoder)mIoU: 45.9 -> 47.4Improved
add BMP to the dual-path ResNet-50 (ablation)Res50 dual path · NYU Depth V2 test (no decoder)mIoU: 45.9 -> 47.8Improved
add both BMP and SA-Gate (ablation)Res50 dual path · NYU Depth V2 test (no decoder)mIoU: 45.9 -> 48.6Improved
use proposed cross-modality guided FS instead of product re-weighting (ablation)SA-Gate · NYU Depth V2 test (no decoder)mIoU: 47.5 -> 48.6Improved
use proposed FS instead of self-global filtering (ablation)SA-Gate · NYU Depth V2 test (no decoder)mIoU: 47.5 -> 48.6Improved
use proposed FA gating instead of addition (ablation)SA-Gate · NYU Depth V2 test (no decoder)mIoU: 47.8 -> 48.6Improved
use proposed FA gating instead of conv on concatenation (ablation)SA-Gate · NYU Depth V2 test (no decoder)mIoU: 48.0 -> 48.6Improved
place SA-Gate in block 1 instead of block 4 (ablation)Res50* · NYU Depth V2 test (no decoder)mIoU: 44.3 -> 47.8Improved
stack SA-Gate on blocks 1-3 rather than block 1 alone (ablation)Res50* · NYU Depth V2 test (no decoder)mIoU: 47.8 -> 48.3Improved
add SA-Gate at block 4 on top of blocks 1-3 (ablation)Res50* · NYU Depth V2 test (no decoder)mIoU: 48.3 -> 48.0Hurt
replace parallel DeepLab V3+ RGB-D baseline with the proposed encoderDeepLab V3+ · NYU Depth V2 testmIoU: 46.7 -> 50.4Improved
replace RGB-D baseline with the proposed encoderDeepLab V3+ RGB-D · CityScapes valmIoU: 80.5 -> 81.7Improved

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