Multiple Instance Learning Convolutional Neural Networks for Object Recognition

no code implementations • 11 Oct 2016 • Miao Sun, Tony X. Han, Ming-Chang Liu, Ahmad Khodayari-Rostamabad

In this paper, we propose a weakly supervised CNN framework named Multiple Instance Learning Convolutional Neural Networks (MILCNN) to solve this problem.

Data Augmentation Multiple Instance Learning +4

Latent Model Ensemble with Auto-localization

no code implementations • 15 Apr 2016 • Miao Sun, Tony X. Han, Xun Xu, Ming-Chang Liu, Ahmad Khodayari-Rostamabad

Deep Convolutional Neural Networks (CNN) have exhibited superior performance in many visual recognition tasks including image classification, object detection, and scene label- ing, due to their large learning capacity and resistance to overfit.

Classification General Classification +3