Dual-attention Guided Dropblock Module for Weakly Supervised Object Localization

TL;DR

This paper introduces a dual-attention guided dropblock module (DGDM) for weakly supervised object localization, which enhances feature learning by focusing on informative patterns and reducing over-reliance on discriminative regions.

Contribution

The paper proposes a novel DGDM with channel and spatial attention components that improve localization accuracy by modeling interdependencies and erasing dominant features.

Findings

Achieves state-of-the-art localization performance

Effectively captures less discriminative object parts

Reduces attention misdirection between foreground and background

Abstract

Attention mechanisms is frequently used to learn the discriminative features for better feature representations. In this paper, we extend the attention mechanism to the task of weakly supervised object localization (WSOL) and propose the dual-attention guided dropblock module (DGDM), which aims at learning the informative and complementary visual patterns for WSOL. This module contains two key components, the channel attention guided dropout (CAGD) and the spatial attention guided dropblock (SAGD). To model channel interdependencies, the CAGD ranks the channel attentions and treats the top-k attentions with the largest magnitudes as the important ones. It also keeps some low-valued elements to increase their value if they become important during training. The SAGD can efficiently remove the most discriminative information by erasing the contiguous regions of feature maps rather than individual pixels. This guides the model to capture the less discriminative parts for classification. Furthermore, it can also distinguish the foreground objects from the background regions to alleviate the attention misdirection. Experimental results demonstrate that the proposed method achieves new state-of-the-art localization performance.