665 citations · 4.3k across the 60 of their papers we have counts for
5 papers · 1 filter
On Feature Normalization and Data Augmentation
Boyi Li, Felix Wu, Ser-Nam Lim +2
The moments (a.k.a., mean and standard deviation) of latent features are often removed as noise when training image recognition models, to increase stability and reduce training ti…
Enhancing Adversarial Example Transferability with an Intermediate Level Attack
Qian Huang, Isay Katsman, Horace He +3
Neural networks are vulnerable to adversarial examples, malicious inputs crafted to fool trained models. Adversarial examples often exhibit black-box transfer, meaning that adversa…
Intermediate Level Adversarial Attack for Enhanced Transferability
Qian Huang, Zeqi Gu, Isay Katsman +5
Neural networks are vulnerable to adversarial examples, malicious inputs crafted to fool trained models. Adversarial examples often exhibit black-box transfer, meaning that adversa…
Sample-Efficient Reinforcement Learning through Transfer and Architectural Priors
Benjamin Spector, Serge Belongie
Recent work in deep reinforcement learning has allowed algorithms to learn complex tasks such as Atari 2600 games just from the reward provided by the game, but these algorithms pr…
Deep Learning is Robust to Massive Label Noise
David Rolnick, Andreas Veit, Serge Belongie +1
Deep neural networks trained on large supervised datasets have led to impressive results in image classification and other tasks. However, well-annotated datasets can be time-consu…