Learning Context-aware Classifier for Semantic Segmentation
This work improves semantic segmentation accuracy for computer vision applications, though it is incremental as it builds on existing models by dynamically adapting the classifier.
The paper tackles the problem of semantic segmentation by addressing varying feature distributions across scenes with a context-aware classifier, achieving decent performance gains on challenging benchmarks with negligible additional parameters and only a 2% increase in inference time.
Semantic segmentation is still a challenging task for parsing diverse contexts in different scenes, thus the fixed classifier might not be able to well address varying feature distributions during testing. Different from the mainstream literature where the efficacy of strong backbones and effective decoder heads has been well studied, in this paper, additional contextual hints are instead exploited via learning a context-aware classifier whose content is data-conditioned, decently adapting to different latent distributions. Since only the classifier is dynamically altered, our method is model-agnostic and can be easily applied to generic segmentation models. Notably, with only negligible additional parameters and +2\% inference time, decent performance gain has been achieved on both small and large models with challenging benchmarks, manifesting substantial practical merits brought by our simple yet effective method. The implementation is available at \url{https://github.com/tianzhuotao/CAC}.