SHACIRA - Scalable HAsh-grid Compression for Implicit Neural Representations

An end-to-end compression framework for feature-grid INRs

ChopNLearn - Generating Object-State Compositions

A benchmark for recognizing and generating object-state compositions from images and videos

ASIC - Aligning Sparse in-the-wild Image Collections

Learning dense correspondences for long-tail in-the-wild image collections

Teaching Matters - Investigating the Role of Supervision in Vision Transformers

ViTs trained via different supervisions show diverse range of behaviors in their representations and downstream tasks.

LilNetX - Lightweight Networks with EXtreme Model Compression and Structured Sparsification

A neural network optimization scheme that allows for trade-off between accuracy and compression during training itself

Neural Space-filling Curves

A data-driven approach to infer a context-based scan order for a set of images. Allows for better compression and sequential generative models

The Lottery Ticket Hypothesis for Object Recognition

How to find sparse neural networks (with up to 80% overall sparsity) on the tasks of object detection, segmentation, and pose estimation

An intro to torch distributions (1/2)

[torch distributions](https://pytorch.org/docs/stable/distributions.html)

Running object detection on Colab

Colaboratory is a Google research project created to help disseminate machine learning education and research

Deciphering a puzzle from a company's hiring page I came across

A friend asked me to look at a puzzle at the hiring page of a company he was applying to. Here is my attempt to the problem. Haven't seen the problem before, so I am not sure if I solved it completely, but sharing my attempt here

How to use GPU based Virtual Machines on Azure!

Microsoft recently (August 4, 2016) announced their Azure N-Series Virtual Machines. I was at the time evaluating options to serve deep learning models on GPUs and decided to give it a try. It was actually pretty straightforward

Performance shootout - python libraries for computer vision (Part 2/2)

Did a little performance comparison for different image processing/computer vision libraries for computing different kinds of features from image

Performance shootout - python libraries for computer vision (Part 1/2)

Did a little performance comparison for different image processing/computer vision libraries for simple morphological operations

Parallel processing in python

I stopped using Python's multiprocessing module for quite some time now. But decided to blog about it only recently (not because a blog post has been long due, but because pathos definitely deserves one)

You're up and running!

Moved to Jekyll and its sweet! Just need to update a markdown file per blog post and voilà!