4 accepted papers
Dynamic data pruning techniques aim to reduce computational cost while minimizing information loss, by periodically selecting representative subsets of input data during model training. However, existing methods often struggle to maintain strong worst-group accuracy, particularly at high pruning rat
Deep neural networks have achieved state-of-the-art performance in multiple domains but are increasingly resource-intensive, limiting their deployment on constrained devices. We introduce Structured Pruning via Ranking (SPvR), a novel structured pruning approach to address this challenge for classif
A translation framework that produces images as if they were captured with a telephoto lens, from images captured with a wide-angle lens, will help in reducing the necessity of complex, expensive and bulky lenses on smartphones. To this end, we propose an image-to-image translation pipeline to simul…
The query-document term matching plays an important role in information retrieval. However, the retrieval performance degrades when the documents get matched with the extraneous terms of the query which frequently arises in verbose queries. To address this problem, we generate the dense vector of th…