Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentation

TL;DR

This paper introduces AugSeg, a straightforward semi-supervised semantic segmentation method that emphasizes tailored data augmentations and adaptive label injection, achieving state-of-the-art results with minimal complexity.

Contribution

AugSeg presents a simple, effective approach focusing on data perturbations and adaptive label injection within a teacher-student framework for semi-supervised segmentation.

Findings

Achieves new state-of-the-art performance on SSS benchmarks.

Utilizes simplified intensity-based data augmentation techniques.

Demonstrates effectiveness without complex network modifications.

Abstract

Recent studies on semi-supervised semantic segmentation (SSS) have seen fast progress. Despite their promising performance, current state-of-the-art methods tend to increasingly complex designs at the cost of introducing more network components and additional training procedures. Differently, in this work, we follow a standard teacher-student framework and propose AugSeg, a simple and clean approach that focuses mainly on data perturbations to boost the SSS performance. We argue that various data augmentations should be adjusted to better adapt to the semi-supervised scenarios instead of directly applying these techniques from supervised learning. Specifically, we adopt a simplified intensity-based augmentation that selects a random number of data transformations with uniformly sampling distortion strengths from a continuous space. Based on the estimated confidence of the model on different unlabeled samples, we also randomly inject labelled information to augment the unlabeled samples in an adaptive manner. Without bells and whistles, our simple AugSeg can readily achieve new state-of-the-art performance on SSS benchmarks under different partition protocols.