Search Results for author:
Found 2 papers, 0 papers with code
Selectively Hard Negative Mining for Alleviating Gradient Vanishing in Image-Text Matching
To alleviate the gradient vanishing problem, we propose a Selectively Hard Negative Mining (SelHN) strategy, which chooses whether to mine hard negative samples according to the gradient vanishing condition.
Unified Loss of Pair Similarity Optimization for Vision-Language Retrieval
More specifically, Triplet loss with Hard Negative mining (Triplet-HN), which is widely used in existing retrieval models to improve the discriminative ability, is easy to fall into local minima in training.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
