Adversarial Complementary Learning for Weakly Supervised Object Localization

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.

CVPR 2018 Accepted

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Going Deeper with Convolutions
• Feature Pyramid Networks for Object Detection
• Few-Example Object Detection with Model Communication
• Two-Phase Learning for Weakly Supervised Object Localization
• Dual Path Networks
• Deep Self-Taught Learning for Weakly Supervised Object Localization

Cited by in corpus (16)

• Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A Survey
• Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation
• Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation
• Self-Erasing Network for Integral Object Attention
• Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximization
• Shallow Feature Matters for Weakly Supervised Object Localization
• Weakly Supervised Bilinear Attention Network for Fine-Grained Visual Classification
• Self-produced Guidance for Weakly-supervised Object Localization
• NETNet: Neighbor Erasing and Transferring Network for Better Single Shot Object Detection
• Combinational Class Activation Maps for Weakly Supervised Object Localization
• Improved Techniques For Weakly-Supervised Object Localization
• Sharpen Focus: Learning with Attention Separability and Consistency
• Adversarial Soft-detection-based Aggregation Network for Image Retrieval
• Class Activation Map generation by Multiple Level Class Grouping and Orthogonal Constraint
• TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection
• Beyond Attributes: Adversarial Erasing Embedding Network for Zero-shot Learning