activity
20172019
most citedTowards a Hypothesis on Visual Transformation based Self-Supervision

5 citations · 8 across the 5 of their papers we have counts for

collaborators

8 papers

cs.LG20195 cited

Towards a Hypothesis on Visual Transformation based Self-Supervision

Dipan K. Pal, Sreena Nallamothu, Marios Savvides

We propose the first qualitative hypothesis characterizing the behavior of visual transformation based self-supervision, called the VTSS hypothesis. Given a dataset upon which a se…

cs.LG2019

Learning Non-Parametric Invariances from Data with Permanent Random Connectomes

Dipan K. Pal, Akshay Chawla, Marios Savvides

One of the fundamental problems in supervised classification and in machine learning in general, is the modelling of non-parametric invariances that exist in data. Most prior art h…

cs.CV2019

Proximal Splitting Networks for Image Restoration

Raied Aljadaany, Dipan K. Pal, Marios Savvides

Image restoration problems are typically ill-posed requiring the design of suitable priors. These priors are typically hand-designed and are fully instantiated throughout the proce…

cs.CV2018

Ring loss: Convex Feature Normalization for Face Recognition

Yutong Zheng, Dipan K. Pal, Marios Savvides

We motivate and present Ring loss, a simple and elegant feature normalization approach for deep networks designed to augment standard loss functions such as Softmax. We argue that…

cs.CV2017

Class Correlation affects Single Object Localization using Pre-trained ConvNets

Pokkalla Harsha Vardhan, Kunal Sekhri, Dipan K. Pal +1

The problem of object localization has become one of the mainstream problems of vision. Most of the algorithms proposed involve the design for the model to be specifically for loca…

cs.LG20173 cited

Max-Margin Invariant Features from Transformed Unlabeled Data

Dipan K. Pal, Ashwin A. Kannan, Gautam Arakalgud +1

The study of representations invariant to common transformations of the data is important to learning. Most techniques have focused on local approximate invariance implemented with…