Search Results for author: Rahul Chand

Found 2 papers, 0 papers with code

DSFormer: Effective Compression of Text-Transformers by Dense-Sparse Weight Factorization

no code implementations20 Dec 2023 Rahul Chand, Yashoteja Prabhu, Pratyush Kumar

Extensive experiments on multiple natural language understanding benchmarks demonstrate that DSFormer obtains up to 40% better compression than the state-of-the-art low-rank factorizers, leading semi-structured sparsity baselines and popular knowledge distillation approaches.

Knowledge Distillation Natural Language Understanding

CapsFlow: Optical Flow Estimation with Capsule Networks

no code implementations1 Apr 2023 Rahul Chand, Rajat Arora, K Ram Prabhakar, R Venkatesh Babu

We present a framework to use recently introduced Capsule Networks for solving the problem of Optical Flow, one of the fundamental computer vision tasks.

Optical Flow Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.