Aravind Srinivas

verfied profile

0 followers
berkeley college

Bottleneck Transformers for Visual Recognition

We present BoTNet, a conceptually simple yet powerful backbone architect...
01/27/2021 ∙ by Aravind Srinivas, et al. ∙ 83 ∙ share

read it
Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation

Building instance segmentation models that are data-efficient and can ha...
12/13/2020 ∙ by Golnaz Ghiasi, et al. ∙ 17 ∙ share

read it
D2RL: Deep Dense Architectures in Reinforcement Learning

While improvements in deep learning architectures have played a crucial ...
10/19/2020 ∙ by Samarth Sinha, et al. ∙ 0 ∙ share

read it
Evaluating Self-Supervised Pretraining Without Using Labels

A common practice in unsupervised representation learning is to use labe...
09/16/2020 ∙ by Colorado Reed, et al. ∙ 8 ∙ share

read it
SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning

Model-free deep reinforcement learning (RL) has been successful in a ran...
07/09/2020 ∙ by Kimin Lee, et al. ∙ 66 ∙ share

read it
Reinforcement Learning with Augmented Data

Learning from visual observations is a fundamental yet challenging probl...
04/30/2020 ∙ by Michael (Misha) Laskin, et al. ∙ 14 ∙ share

read it
CURL: Contrastive Unsupervised Representations for Reinforcement Learning

We present CURL: Contrastive Unsupervised Representations for Reinforcem...
04/08/2020 ∙ by Aravind Srinivas, et al. ∙ 23 ∙ share

read it
Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design

Flow-based generative models are powerful exact likelihood models with e...
02/01/2019 ∙ by Jonathan Ho, et al. ∙ 97 ∙ share

read it
Universal Planning Networks

A key challenge in complex visuomotor control is learning abstract repre...
04/02/2018 ∙ by Aravind Srinivas, et al. ∙ 0 ∙ share

read it

Aravind Srinivas

Featured Co-authors

Sergey Levine

Pieter Abbeel

Xi Chen

Trevor Darrell

Quoc V. Le

Chelsea Finn

Kurt Keutzer

Animesh Garg

Jonathon Shlens

Lerrel Pinto

Barret Zoph

Bottleneck Transformers for Visual Recognition

Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation

D2RL: Deep Dense Architectures in Reinforcement Learning

Evaluating Self-Supervised Pretraining Without Using Labels

SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning

Reinforcement Learning with Augmented Data

CURL: Contrastive Unsupervised Representations for Reinforcement Learning

Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design

Universal Planning Networks