722 citations · 5.1k across the 126 of their papers we have counts for
17 papers · 1 filter
Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Research
Krishna Murthy Jatavallabhula, Edward Smith, Jean-Francois Lafleche +6
We present Kaolin, a PyTorch library aiming to accelerate 3D deep learning research. Kaolin provides efficient implementations of differentiable 3D modules for use in deep learning…
CrevNet: Conditionally Reversible Video Prediction
Wei Yu, Yichao Lu, Steve Easterbrook +1
Applying resolution-preserving blocks is a common practice to maximize information preservation in video prediction, yet their high memory consumption greatly limits their applicat…
Neural Turtle Graphics for Modeling City Road Layouts
Hang Chu, Daiqing Li, David Acuna +6
We propose Neural Turtle Graphics (NTG), a novel generative model for spatial graphs, and demonstrate its applications in modeling city road layouts. Specifically, we represent the…
DMM-Net: Differentiable Mask-Matching Network for Video Object Segmentation
Xiaohui Zeng, Renjie Liao, Li Gu +3
In this paper, we propose the differentiable mask-matching network (DMM-Net) for solving the video object segmentation problem where the initial object masks are provided. Relying…
A Theoretical Analysis of the Number of Shots in Few-Shot Learning
Tianshi Cao, Marc Law, Sanja Fidler
Few-shot classification is the task of predicting the category of an example from a set of few labeled examples. The number of labeled examples per category is called the number of…
Video Face Clustering with Unknown Number of Clusters
Makarand Tapaswi, Marc T. Law, Sanja Fidler
Understanding videos such as TV series and movies requires analyzing who the characters are and what they are doing. We address the challenging problem of clustering face tracks ba…
Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer
Wenzheng Chen, Jun Gao, Huan Ling +4
Many machine learning models operate on images, but ignore the fact that images are 2D projections formed by 3D geometry interacting with light, in a process called rendering. Enab…
Gated-SCNN: Gated Shape CNNs for Semantic Segmentation
Towaki Takikawa, David Acuna, Varun Jampani +1
Current state-of-the-art methods for image segmentation form a dense image representation where the color, shape and texture information are all processed together inside a deep CN…
Neural Graph Evolution: Towards Efficient Automatic Robot Design
Tingwu Wang, Yuhao Zhou, Sanja Fidler +1
Despite the recent successes in robotic locomotion control, the design of robot relies heavily on human engineering. Automatic robot design has been a long studied subject, but the…
EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis
Chaoqi Wang, Roger Grosse, Sanja Fidler +1
Reducing the test time resource requirements of a neural network while preserving test accuracy is crucial for running inference on resource-constrained devices. To achieve this go…
DARNet: Deep Active Ray Network for Building Segmentation
Dominic Cheng, Renjie Liao, Sanja Fidler +1
In this paper, we propose a Deep Active Ray Network (DARNet) for automatic building segmentation. Taking an image as input, it first exploits a deep convolutional neural network (C…
Meta-Sim: Learning to Generate Synthetic Datasets
Amlan Kar, Aayush Prakash, Ming-Yu Liu +6
Training models to high-end performance requires availability of large labeled datasets, which are expensive to get. The goal of our work is to automatically synthesize labeled dat…
Action Recognition from Single Timestamp Supervision in Untrimmed Videos
Davide Moltisanti, Sanja Fidler, Dima Damen
Recognising actions in videos relies on labelled supervision during training, typically the start and end times of each action instance. This supervision is not only subjective, bu…
Devil is in the Edges: Learning Semantic Boundaries from Noisy Annotations
David Acuna, Amlan Kar, Sanja Fidler
We tackle the problem of semantic boundary prediction, which aims to identify pixels that belong to object(class) boundaries. We notice that relevant datasets consist of a signific…
Mimicking the In-Camera Color Pipeline for Camera-Aware Object Compositing
Jun Gao, Xiao Li, Liwei Wang +2
We present a method for compositing virtual objects into a photograph such that the object colors appear to have been processed by the photo's camera imaging pipeline. Compositing…
Fast Interactive Object Annotation with Curve-GCN
Huan Ling, Jun Gao, Amlan Kar +2
Manually labeling objects by tracing their boundaries is a laborious process. In Polygon-RNN++ the authors proposed Polygon-RNN that produces polygonal annotations in a recurrent m…
ACTRCE: Augmenting Experience via Teacher's Advice For Multi-Goal Reinforcement Learning
Harris Chan, Yuhuai Wu, Jamie Kiros +2
Sparse reward is one of the most challenging problems in reinforcement learning (RL). Hindsight Experience Replay (HER) attempts to address this issue by converting a failed experi…