Bhavya Vasudeva, Umapada Pal, Saumik Bhattacharya, Puneesh Deora, Sukalpa Chanda
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Deep metric learning has been effectively used to learn distance metrics for different visual tasks like image retrieval, clustering, etc. In order to aid the training process, existing methods either use a hard mining strategy to extract the most informative samples or seek to generate hard synthetics using an additional network. Such approaches face different challenges and can lead to biased embeddings in the former case, and (i) harder optimization (ii) slower training speed (iii) higher model complexity in the latter case. In order to overcome these challenges, we propose a novel approach that looks for optimal hard negatives (LoOp) in the embedding space, taking full advantage of each tuple by calculating the minimum distance between a pair of positives and a pair of negatives. Unlike miningbased methods, our approach considers the entire space between pairs of embeddings to calculate the optimal hard negatives. Extensive experiments combining our approach and representative metric learning losses reveal a significant boost in performance on three benchmark datasets 1 .
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2108.09335")
get_code_for_paper("2108.09335")
have("2108.09335")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2108.09335.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2108.09335)
Connect an agent — have() is free.