AI Paper Atlas

Research map / Detection and segmentation / CNN features

BiSeNet V2: Bilateral Network with Guided Aggregation for Real-Time Semantic Segmentation

Changqian Yu, Changxin Gao, Jingbo Wang, Gang Yu, Chunhua Shen, Nong Sang

IJCV 2021 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 1,909 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 Semantic Branch to Detail Branch (sum) (ablation)BiSeNetV2 · Cityscapes valmIoU: 62.35 -> 68.60Improved
add Detail Branch to Semantic Branch (sum) (ablation)BiSeNetV2 · Cityscapes valmIoU: 64.68 -> 68.60Improved
use Bilateral Guided Aggregation instead of summation (ablation)BiSeNetV2 · Cityscapes valmIoU: 68.60 -> 69.67Improved
use Bilateral Guided Aggregation instead of concatenation (ablation)BiSeNetV2 · Cityscapes valmIoU: 68.93 -> 69.67Improved
add booster training strategy (auxiliary heads) (ablation)BiSeNetV2 · Cityscapes valmIoU: 69.67 -> 73.19Improved
add OHEM online bootstrapping (ablation)BiSeNetV2 · Cityscapes valmIoU: 73.19 -> 73.36Improved
add a very light Semantic Branch (lambda=1/16) (ablation)Detail Branch · Cityscapes valmIoU: 62.35 -> 68.27Improved
use 3x3 Gather Layer instead of 1x1 convolution (ablation)GE Layer · Cityscapes valmIoU: 66.62 -> 69.67Improved
use double depth-wise convs instead of one 5x5 at stride 2 (ablation)GE Layer · Cityscapes valmIoU: 68.98 -> 69.67Improved
add context embedding to the GE layer (ablation)GE Layer · Cityscapes valmIoU: 69.01 -> 69.67Improved
increase expansion ratio from 6 to 8 (ablation)Semantic Branch · Cityscapes valmIoU: 69.67 -> 68.99Hurt
widen the model to alpha=2.0 (ablation)BiSeNetV2 · Cityscapes valmIoU: 73.36 -> 75.11Improved

Later papers that compared with this method

3 later accepted papers report BiSeNetV2 as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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