Deep Learning
Large Scale Adversarial Representation Learning
Neural Information Processing Systems http://nips.cc/
3d4c0a618d0acd7921493e4f30395c22-Paper-Conference.pdf
Giventextual explanations, our proposed framework uses agenerative model conditioned on textual input to create data points representing the explanations. Bycomparing theneuron'sresponse tothese generated data points and control data points, we can estimate the quality of the explanation.
Semantic-Guided Multi-Attention Localization for Zero-Shot Learning
Yizhe Zhu, Jianwen Xie, Zhiqiang Tang, Xi Peng, Ahmed Elgammal
Neural Information Processing Systems http://nips.cc/
