Adversarial Complementary Learning for Weakly Supervised Object Localization

• Published in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 1325 - 1334
• Main Authors: Zhang, Xiaolin, Wei, Yunchao, Feng, Jiashi, Yang, Yi, Huang, Thomas
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2018
• Subjects: Feature extraction; Head; Legged locomotion; Object recognition; Pattern recognition; Task analysis; Training

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 convo...