Adversarial Complementary Learning for Weakly Supervised Object Localization

TL;DR

This paper introduces Adversarial Complementary Learning (ACoL), a novel weakly supervised object localization method that uses adversarial training of two classifiers to discover complete object regions, achieving state-of-the-art results.

Contribution

The paper proposes a new end-to-end adversarial learning framework with two classifiers that discover complementary object regions for improved weakly supervised localization.

Findings

Achieves 45.14% Top-1 localization error on ILSVRC dataset.

Proves class localization maps can be obtained from last convolutional layer feature maps.

Demonstrates superior performance over existing methods.

Abstract

In this work, we propose Adversarial Complementary Learning (ACoL) to automatically localize integral objects of semantic interest with weak supervision. We first mathematically prove that class localization maps can be obtained by directly selecting the class-specific feature maps of the last convolutional layer, which paves a simple way to identify object regions. We then present a simple network architecture including two parallel-classifiers for object localization. Specifically, we leverage one classification branch to dynamically localize some discriminative object regions during the forward pass. Although it is usually responsive to sparse parts of the target objects, this classifier can drive the counterpart classifier to discover new and complementary object regions by erasing its discovered regions from the feature maps. With such an adversarial learning, the two parallel-classifiers are forced to leverage complementary object regions for classification and can finally generate integral object localization together. The merits of ACoL are mainly two-fold: 1) it can be trained in an end-to-end manner; 2) dynamically erasing enables the counterpart classifier to discover complementary object regions more effectively. We demonstrate the superiority of our ACoL approach in a variety of experiments. In particular, the Top-1 localization error rate on the ILSVRC dataset is 45.14%, which is the new state-of-the-art.