Improved Techniques For Weakly-Supervised Object Localization

Abstract

We propose an improved technique for weakly-supervised object localization. Conventional methods have a limitation that they focus only on most discriminative parts of the target objects. The recent study addressed this issue and resolved this limitation by augmenting the training data for less discriminative parts. To this end, we employ an effective data augmentation for improving the accuracy of the object localization. In addition, we introduce improved learning techniques by optimizing Convolutional Neural Networks (CNN) based on the state-of-the-art model. Based on extensive experiments, we evaluate the effectiveness of the proposed approach both qualitatively and quantitatively. Especially, we observe that our method improves the Top-1 localization accuracy by 21.4 - 37.3% depending on configurations, compared to the current state-of-the-art technique of the weakly-supervised object localization.

arXiv commentSubmitted to BMVC 2018

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Conditional Image Synthesis With Auxiliary Classifier GANs
• On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima
• Entropy-SGD: Biasing Gradient Descent Into Wide Valleys
• Tell Me Where to Look: Guided Attention Inference Network
• Adversarial Complementary Learning for Weakly Supervised Object Localization
• Two-Phase Learning for Weakly Supervised Object Localization
• Combining Weakly and Webly Supervised Learning for Classifying Food Images

Cited by in corpus (3)

• Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator
• Informative Class Activation Maps
• Generative Adversarial Networks for Unsupervised Object Co-localization