Hunting Attributes: Context Prototype-Aware Learning for Weakly Supervised Semantic Segmentation

TL;DR

This paper introduces Context Prototype-Aware Learning (CPAL), a novel approach that leverages semantic context to improve prototype representations and enhance weakly supervised semantic segmentation performance.

Contribution

It proposes a new CPAL strategy that mitigates knowledge bias in prototypes, capturing diverse instance features and improving segmentation accuracy.

Findings

CPAL significantly outperforms existing methods on PASCAL VOC 2012.

Achieves state-of-the-art results on MS COCO 2014.

Enhances prototype representation for better instance understanding.

Abstract

Recent weakly supervised semantic segmentation (WSSS) methods strive to incorporate contextual knowledge to improve the completeness of class activation maps (CAM). In this work, we argue that the knowledge bias between instances and contexts affects the capability of the prototype to sufficiently understand instance semantics. Inspired by prototype learning theory, we propose leveraging prototype awareness to capture diverse and fine-grained feature attributes of instances. The hypothesis is that contextual prototypes might erroneously activate similar and frequently co-occurring object categories due to this knowledge bias. Therefore, we propose to enhance the prototype representation ability by mitigating the bias to better capture spatial coverage in semantic object regions. With this goal, we present a Context Prototype-Aware Learning (CPAL) strategy, which leverages semantic context to enrich instance comprehension. The core of this method is to accurately capture intra-class variations in object features through context-aware prototypes, facilitating the adaptation to the semantic attributes of various instances. We design feature distribution alignment to optimize prototype awareness, aligning instance feature distributions with dense features. In addition, a unified training framework is proposed to combine label-guided classification supervision and prototypes-guided self-supervision. Experimental results on PASCAL VOC 2012 and MS COCO 2014 show that CPAL significantly improves off-the-shelf methods and achieves state-of-the-art performance. The project is available at https://github.com/Barrett-python/CPAL.