450 citations · 710 across the 7 of their papers we have counts for
7 papers
Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout
Zhao Chen, Jiquan Ngiam, Yanping Huang +4
The vast majority of deep models use multiple gradient signals, typically corresponding to a sum of multiple loss terms, to update a shared set of trainable weights. However, these…
DeepPerimeter: Indoor Boundary Estimation from Posed Monocular Sequences
Ameya Phalak, Zhao Chen, Darvin Yi +3
We present DeepPerimeter, a deep learning based pipeline for inferring a full indoor perimeter (i.e. exterior boundary map) from a sequence of posed RGB images. Our method relies o…
Gradient Adversarial Training of Neural Networks
Ayan Sinha, Zhao Chen, Vijay Badrinarayanan +1
We propose gradient adversarial training, an auxiliary deep learning framework applicable to different machine learning problems. In gradient adversarial training, we leverage a pr…
Estimating Depth from RGB and Sparse Sensing
Zhao Chen, Vijay Badrinarayanan, Gilad Drozdov +1
We present a deep model that can accurately produce dense depth maps given an RGB image with known depth at a very sparse set of pixels. The model works simultaneously for both ind…
GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks
Zhao Chen, Vijay Badrinarayanan, Chen-Yu Lee +1
Deep multitask networks, in which one neural network produces multiple predictive outputs, can offer better speed and performance than their single-task counterparts but are challe…
The Game Imitation: Deep Supervised Convolutional Networks for Quick Video Game AI
Zhao Chen, Darvin Yi
We present a vision-only model for gaming AI which uses a late integration deep convolutional network architecture trained in a purely supervised imitation learning context. Althou…
3-D Convolutional Neural Networks for Glioblastoma Segmentation
Darvin Yi, Mu Zhou, Zhao Chen +1
Convolutional Neural Networks (CNN) have emerged as powerful tools for learning discriminative image features. In this paper, we propose a framework of 3-D fully CNN models for Gli…