Papers › CondNet: Conditional Classifier for Scene Segmentation

CondNet: Conditional Classifier for Scene Segmentation

21 Sep 2021arXiv:2109.10322archive 2025-07-28

Changqian Yu, Yuanjie Shao, Changxin Gao, Nong Sang

The fully convolutional network (FCN) has achieved tremendous success in dense visual recognition tasks, such as scene segmentation. The last layer of FCN is typically a global classifier (1x1 convolution) to recognize each pixel to a semantic label. We empirically show that this global classifier, ignoring the intra-class distinction, may lead to sub-optimal results. In this work, we present a conditional classifier to replace the traditional global classifier, where the kernels of the classifier are generated dynamically conditioned on the input. The main advantages of the new classifier consist of: (i) it attends on the intra-class distinction, leading to stronger dense recognition capability; (ii) the conditional classifier is simple and flexible to be integrated into almost arbitrary FCN architectures to improve the prediction. Extensive experiments demonstrate that the proposed classifier performs favourably against the traditional classifier on the FCN architecture. The framework equipped with the conditional classifier (called CondNet) achieves new state-of-the-art performances on two datasets. The code and models are available at https://git.io/CondNet.

PaperPDFCode

Code

ycszen/CondNet officialmentioned on GitHubpytorch report
sithu31296/semantic-segmentation mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Scene SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation ADE20K CondNet(ResNest-101) Validation mIoU 47.54 #162 of 235 Archive leaderboard report
Semantic Segmentation ADE20K CondNet(ResNet-101) Validation mIoU 47.38 #164 of 235 Archive leaderboard report
Semantic Segmentation PASCAL Context CondNet(ResNest-101) mIoU 57 #21 of 66 Archive leaderboard report
Semantic Segmentation PASCAL Context CondNet(ResNet-101) mIoU 56.0 #26 of 66 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionFCNGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections