activity
20162021
most citedWhen Ensembling Smaller Models is More Efficient than Single Large Models

24 citations · 62 across the 5 of their papers we have counts for

collaborators
Showing cs.CVShow all

8 papers · 1 filter

cs.CV2021

2.5D Visual Relationship Detection

Yu-Chuan Su, Soravit Changpinyo, Xiangning Chen +8

Visual 2.5D perception involves understanding the semantics and geometry of a scene through reasoning about object relationships with respect to the viewer in an environment. Howev…

cs.CV202117 cited

MoViNets: Mobile Video Networks for Efficient Video Recognition

Dan Kondratyuk, Liangzhe Yuan, Yandong Li +4

We present Mobile Video Networks (MoViNets), a family of computation and memory efficient video networks that can operate on streaming video for online inference. 3D convolutional…

cs.CV20216 cited

FiG-NeRF: Figure-Ground Neural Radiance Fields for 3D Object Category Modelling

Christopher Xie, Keunhong Park, Ricardo Martin-Brualla +1

We investigate the use of Neural Radiance Fields (NeRF) to learn high quality 3D object category models from collections of input images. In contrast to previous work, we are able…

cs.CV2020

GeLaTO: Generative Latent Textured Objects

Ricardo Martin-Brualla, Rohit Pandey, Sofien Bouaziz +2

Accurate modeling of 3D objects exhibiting transparency, reflections and thin structures is an extremely challenging problem. Inspired by billboards and geometric proxies used in c…

cs.CV2020

Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective

Muhammad Abdullah Jamal, Matthew Brown, Ming-Hsuan Yang +2

Object frequency in the real world often follows a power law, leading to a mismatch between datasets with long-tailed class distributions seen by a machine learning model and our e…

cs.CV2018

Extreme Augmentation : Can deep learning based medical image segmentation be trained using a single manually delineated scan?

Bilwaj Gaonkar, Matthew Edwards, Alex Bui +2

Yes, it can. Data augmentation is perhaps the oldest preprocessing step in computer vision literature. Almost every computer vision model trained on imaging data uses some form of…