1.8k citations · 3.3k across the 8 of their papers we have counts for
10 papers
PointRend: Image Segmentation as Rendering
Alexander Kirillov, Yuxin Wu, Kaiming He +1
We present a new method for efficient high-quality image segmentation of objects and scenes. By analogizing classical computer graphics methods for efficient rendering with over- a…
Momentum Contrast for Unsupervised Visual Representation Learning
Kaiming He, Haoqi Fan, Yuxin Wu +2
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…
Feature Denoising for Improving Adversarial Robustness
Cihang Xie, Yuxin Wu, Laurens van der Maaten +2
Adversarial attacks to image classification systems present challenges to convolutional networks and opportunities for understanding them. This study suggests that adversarial pert…
Learning and Planning with a Semantic Model
Yi Wu, Yuxin Wu, Aviv Tamar +3
Building deep reinforcement learning agents that can generalize and adapt to unseen environments remains a fundamental challenge for AI. This paper describes progresses on this cha…
Group Normalization
Yuxin Wu, Kaiming He
Batch Normalization (BN) is a milestone technique in the development of deep learning, enabling various networks to train. However, normalizing along the batch dimension introduces…
Building Generalizable Agents with a Realistic and Rich 3D Environment
Yi Wu, Yuxin Wu, Georgia Gkioxari +1
Teaching an agent to navigate in an unseen 3D environment is a challenging task, even in the event of simulated environments. To generalize to unseen environments, an agent needs t…
ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games
Yuandong Tian, Qucheng Gong, Wenling Shang +2
In this paper, we propose ELF, an Extensive, Lightweight and Flexible platform for fundamental reinforcement learning research. Using ELF, we implement a highly customizable real-t…
Effective Quantization Methods for Recurrent Neural Networks
Qinyao He, He Wen, Shuchang Zhou +4
Reducing bit-widths of weights, activations, and gradients of a Neural Network can shrink its storage size and memory usage, and also allow for faster training and inference by exp…
DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
Shuchang Zhou, Yuxin Wu, Zekun Ni +3
We propose DoReFa-Net, a method to train convolutional neural networks that have low bitwidth weights and activations using low bitwidth parameter gradients. In particular, during…
Exploiting Local Structures with the Kronecker Layer in Convolutional Networks
Shuchang Zhou, Jia-Nan Wu, Yuxin Wu +1
In this paper, we propose and study a technique to reduce the number of parameters and computation time in convolutional neural networks. We use Kronecker product to exploit the lo…