Semi-supervised Semantic Segmentation with Directional Context-aware Consistency

06/27/2021
by   Xin Lai, et al.
0

Semantic segmentation has made tremendous progress in recent years. However, satisfying performance highly depends on a large number of pixel-level annotations. Therefore, in this paper, we focus on the semi-supervised segmentation problem where only a small set of labeled data is provided with a much larger collection of totally unlabeled images. Nevertheless, due to the limited annotations, models may overly rely on the contexts available in the training data, which causes poor generalization to the scenes unseen before. A preferred high-level representation should capture the contextual information while not losing self-awareness. Therefore, we propose to maintain the context-aware consistency between features of the same identity but with different contexts, making the representations robust to the varying environments. Moreover, we present the Directional Contrastive Loss (DC Loss) to accomplish the consistency in a pixel-to-pixel manner, only requiring the feature with lower quality to be aligned towards its counterpart. In addition, to avoid the false-negative samples and filter the uncertain positive samples, we put forward two sampling strategies. Extensive experiments show that our simple yet effective method surpasses current state-of-the-art methods by a large margin and also generalizes well with extra image-level annotations.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 8

04/27/2021

Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank

This work presents a novel approach for semi-supervised semantic segment...
08/20/2021

Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentation

We present a novel semi-supervised semantic segmentation method which jo...
10/15/2021

Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation

Rapid progress in 3D semantic segmentation is inseparable from the advan...
12/01/2020

A Three-Stage Self-Training Framework for Semi-Supervised Semantic Segmentation

Semantic segmentation has been widely investigated in the community, in ...
04/09/2021

Bootstrapping Semantic Segmentation with Regional Contrast

We present ReCo, a contrastive learning framework designed at a regional...
08/22/2022

Multi-Granularity Distillation Scheme Towards Lightweight Semi-Supervised Semantic Segmentation

Albeit with varying degrees of progress in the field of Semi-Supervised ...
04/29/2019

Casting Geometric Constraints in Semantic Segmentation as Semi-Supervised Learning

We propose a simple yet effective method to learn to segment new indoor ...