# CondNet: Conditional Classifier for Scene Segmentation

Source: [CondNet: Conditional Classifier for Scene Segmentation](<https://www.sota2.com/research/paper/68fa6adb1e209131cea2ad59>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:33:18.384Z

Authors: Changqian Yu, Yuanjie Shao, Changxin Gao, Nong Sang

Published: 2021-09-21T17:19:09.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Semantic Segmentation on PASCAL Context (val)](<https://www.sota2.com/research/sota/semantic-segmentation-on-pascal-context-val.md>): Semantic segmentation; PASCAL Context (val); mIoU: 57.

- [Semantic Segmentation on ADE20K (val)](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-val.md>): Semantic segmentation; ADE20K (val); mIoU: 47.54.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2109.10322>)

[PDF](<https://arxiv.org/pdf/2109.10322.pdf>)

[Implementation](<https://git.io/CondNet>)
