Landskape

a tiny research group on the edge of theoretical deep learning

Find out more

Projects

Drawing tickets from a canvas

LTH using importance sampling in an anytime learning setting.

What makes an augmentation a good augmentation?

Investigating augmentation from a classicial image processing perspective.

Robustness Survey of Graph Neural Networks

Extensive thorough survey on robustness of Graph Neural Networks.

Publications

Rotate to Attend: Convolutional Triplet Attention Module

Diganta Misra , Trikay Nalamada , Ajay Uppili Arasanipalai , Qibin Hou

Winter Conference on Applications of Computer Vision (WACV)

November, 2020

Details PDF Slides Video Code Cite

Mish: A Self Regularized Non-Monotonic Activation Function

Diganta Misra

31st British Machine Vision Conference (BMVC)

September, 2020

Details PDF Video Code Cite SOTA in Object Detection on COCO-testdev BMVC 2020 Machine Learning Cafe Podcast Sicara Deep Club Computer Vision Talks

Team

Diganta Misra

Research MSc student, MILA

Himanshu Arora

Machine Learning Engineer III, Workday

Trikay Nalamada

Undergraduate Student, Indian Institute of Technology, Guwahati

Ajay Uppili Arasanipalai

Undergraduate Student, University of Illinois at Urbana-Champaign

Bharat Runwal

Undergraduate Student, IIT Delhi

Alex Gu

Graduate CS Student, MIT

Ching Lam Choi

Undergraduate Student, CUHK

Jaegul Choo

Associate Professor, Graduate School of Artificial Intelligence, KAIST

Contact

In collaboration with:

Continual AI

Weights & Biases

Supported by contributions from:

NCSA

OpenPOWER Foundation