Abstract: We present Momentum Contrast (MoCo) for unsupervised visual representation learning. From a perspective on contrastive learning as dictionary look-up, we build a dynamic dictionary with a ...
Abstract: We propose a technique for producing `visual explanations' for decisions from a large class of Convolutional Neural Network (CNN)-based models, making them more transparent. Our approach - ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback