← Search

Deep Chakraborty

2 accepted papers

2025

Improving Pre-trained Self-Supervised Embeddings Through Effective Entropy Maximization

AISTATS 2025poster

A number of different architectures and loss functions have been applied to the problem of self-supervised learning (SSL), with the goal of developing embeddings that provide the best possible pre-training for as-yet-unknown, lightly supervised downstream tasks. One of these SSL criteria is to maxim…

Cited by 0SourceScholar
2018

Unsupervised Hard Example Mining from Videos for Improved Object Detection

ECCV 2018poster

Important gains have recently been obtained in object detection by using training objectives that focus on {em hard negative} examples, i.e., negative examples that are currently rated as positive or ambiguous by the detector. These examples can strongly influence parameters when the network is trai…

Cited by 90SourcePDFScholar