248 citations · 465 across the 17 of their papers we have counts for
9 papers · 1 filter
Diagnosing and Rectifying Vision Models using Language
Yuhui Zhang, Jeff Z. HaoChen, Shih-Cheng Huang +3
Recent multi-modal contrastive learning models have demonstrated the ability to learn an embedding space suitable for building strong vision classifiers, by leveraging the rich inf…
Variational Model Inversion Attacks
Kuan-Chieh Wang, Yan Fu, Ke Li +3
Given the ubiquity of deep neural networks, it is important that these models do not reveal information about sensitive data that they have been trained on. In model inversion atta…
Disentanglement and Generalization Under Correlation Shifts
Christina M. Funke, Paul Vicol, Kuan-Chieh Wang +3
Correlations between factors of variation are prevalent in real-world data. Exploiting such correlations may increase predictive performance on noisy data; however, often correlati…
Probing Few-Shot Generalization with Attributes
Mengye Ren, Eleni Triantafillou, Kuan-Chieh Wang +5
Despite impressive progress in deep learning, generalizing far beyond the training distribution is an important open challenge. In this work, we consider few-shot classification, a…
Understanding and Mitigating Exploding Inverses in Invertible Neural Networks
Jens Behrmann, Paul Vicol, Kuan-Chieh Wang +2
Invertible neural networks (INNs) have been used to design generative models, implement memory-saving gradient computation, and solve inverse problems. In this work, we show that c…
Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One
Will Grathwohl, Kuan-Chieh Wang, Jörn-Henrik Jacobsen +3
We propose to reinterpret a standard discriminative classifier of p(y|x) as an energy based model for the joint distribution p(x,y). In this setting, the standard class probabiliti…
Centroid-based deep metric learning for speaker recognition
Jixuan Wang, Kuan-Chieh Wang, Marc Law +2
Speaker embedding models that utilize neural networks to map utterances to a space where distances reflect similarity between speakers have driven recent progress in the speaker re…
Adversarial Distillation of Bayesian Neural Network Posteriors
Kuan-Chieh Wang, Paul Vicol, James Lucas +3
Bayesian neural networks (BNNs) allow us to reason about uncertainty in a principled way. Stochastic Gradient Langevin Dynamics (SGLD) enables efficient BNN learning by drawing sam…
Dualing GANs
Yujia Li, Alexander Schwing, Kuan-Chieh Wang +1
Generative adversarial nets (GANs) are a promising technique for modeling a distribution from samples. It is however well known that GAN training suffers from instability due to th…