Patch Gradient descent: Training Neural Networks on Very Large Images

Deepak Gupta, Gowreesh Mago, Arnav Chavan, Dilip Prasad

Arxiv

[Preprint]

On Designing Light-Weight Object Trackers Through Network Pruning: Use CNNs or Transformers?

Saksham Aggarwal, Taneesh Gupta, Pawan Sahoo, Arnav Chavan, Rishabh Tiwari, Dilip Prasad, Deepak Gupta

International Conference on Acoustics, Speech, and Signal Processing (ICASSP'23)

[Preprint]  [Code]

Implicitly Rotation-Equivariant Neural Networks

Naman Khetan, Tushar Arora, Samee ur Rehman, Deepak Gupta

International Conference on Acoustics, Speech, and Signal Processing (ICASSP'23)

[Preprint]  [Code]

MixBin: Towards Budgeted Binarization

Udbhav Bamba, Neeraj Anand, Dilip Prasad, Deepak Gupta

Arxiv

[Preprint]

UltraMNIST Classification: A Benchmark to CNNs for Very Large Images

Deepak Gupta, Udbhav Bamba, Abhishek Thakur, Akash Gupta, Suraj Sharan, Ertugul Demir, Dilip Prasad

Arxiv

[Preprint]  [Code]  [Kaggle-challenge] [Dataset]