activity
20192022
collaborators

5 papers

cs.LG2022

When does mixup promote local linearity in learned representations?

Arslan Chaudhry, Aditya Krishna Menon, Andreas Veit +3

Mixup is a regularization technique that artificially produces new samples using convex combinations of original training points. This simple technique has shown strong empirical p…

cs.LG2021

Disentangling Sampling and Labeling Bias for Learning in Large-Output Spaces

Ankit Singh Rawat, Aditya Krishna Menon, Wittawat Jitkrittum +4

Negative sampling schemes enable efficient training given a large number of classes, by offering a means to approximate a computationally expensive loss function that takes all lab…

cs.CV2021

Less is more: Selecting informative and diverse subsets with balancing constraints

Srikumar Ramalingam, Daniel Glasner, Kaushal Patel +3

Deep learning has yielded extraordinary results in vision and natural language processing, but this achievement comes at a cost. Most models require enormous resources during train…

cs.LG2020

Kernelized Classification in Deep Networks

Sadeep Jayasumana, Srikumar Ramalingam, Sanjiv Kumar

We propose a kernelized classification layer for deep networks. Although conventional deep networks introduce an abundance of nonlinearity for representation (feature) learning, th…

cs.CV2019

Bipartite Conditional Random Fields for Panoptic Segmentation

Sadeep Jayasumana, Kanchana Ranasinghe, Mayuka Jayawardhana +2

We tackle the panoptic segmentation problem with a conditional random field (CRF) model. Panoptic segmentation involves assigning a semantic label and an instance label to each pix…