activity
20152021
most citedCyCADA: Cycle-Consistent Adversarial Domain Adaptation

630 citations · 2.4k across the 27 of their papers we have counts for

collaborators
Showing 2020Show all

19 papers · 1 filter

cs.CV202010 cited

Learning from Lexical Perturbations for Consistent Visual Question Answering

Spencer Whitehead, Hui Wu, Yi Ren Fung +3

Existing Visual Question Answering (VQA) models are often fragile and sensitive to input variations. In this paper, we propose a novel approach to address this issue based on modul…

cs.RO2020

How to Train your Quadrotor: A Framework for Consistently Smooth and Responsive Flight Control via Reinforcement Learning

Siddharth Mysore, Bassel Mabsout, Kate Saenko +1

We focus on the problem of reliably training Reinforcement Learning (RL) models (agents) for stable low-level control in embedded systems and test our methods on a high-performance…

cs.RO2020

Regularizing Action Policies for Smooth Control with Reinforcement Learning

Siddharth Mysore, Bassel Mabsout, Renato Mancuso +1

A critical problem with the practical utility of controllers trained with deep Reinforcement Learning (RL) is the notable lack of smoothness in the actions learned by the RL polici…

cs.CV2020

Fine-grained Angular Contrastive Learning with Coarse Labels

Guy Bukchin, Eli Schwartz, Kate Saenko +4

Few-shot learning methods offer pre-training techniques optimized for easier later adaptation of the model to new classes (unseen during training) using one or a few examples. This…

cs.CV2020

Temporal Action Detection with Multi-level Supervision

Baifeng Shi, Qi Dai, Judy Hoffman +3

Training temporal action detection in videos requires large amounts of labeled data, yet such annotation is expensive to collect. Incorporating unlabeled or weakly-labeled data to…

cs.LG2020

Auxiliary Task Reweighting for Minimum-data Learning

Baifeng Shi, Judy Hoffman, Kate Saenko +2

Supervised learning requires a large amount of training data, limiting its application where labeled data is scarce. To compensate for data scarcity, one possible method is to util…