Search Results for author:
Found 9 papers, 7 papers with code
TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance
In this paper, we propose a novel cross-modal distillation method, called TinyCLIP, for large-scale language-image pre-trained models.
Dissecting Deep Metric Learning Losses for Image-Text Retrieval
In the event that the gradients are not integrable to a valid loss function, we implement our proposed objectives such that they would directly operate in the gradient space instead of on the losses in the embedding space.
Ranked #8 on
Cross-Modal Retrieval
on Flickr30k
(using extra training data)
Dissecting the impact of different loss functions with gradient surgery
Pair-wise loss is an approach to metric learning that learns a semantic embedding by optimizing a loss function that encourages images from the same semantic class to be mapped closer than images from different classes.
Ranked #7 on
Metric Learning
on In-Shop
Hard negative examples are hard, but useful
We offer a simple fix to the loss function and show that, with this fix, optimizing with hard negative examples becomes feasible.
Ranked #14 on
Metric Learning
on In-Shop
Extreme Triplet Learning: Effectively Optimizing Easy Positives and Hard Negatives
The Triplet Loss approach to Distance Metric Learning is defined by the strategy to select triplets and the loss function through which those triplets are optimized.
Visualizing How Embeddings Generalize
Deep metric learning is often used to learn an embedding function that captures the semantic differences within a dataset.
Improved Embeddings with Easy Positive Triplet Mining
Deep metric learning seeks to define an embedding where semantically similar images are embedded to nearby locations, and semantically dissimilar images are embedded to distant locations.
Ranked #6 on
Image Retrieval
on In-Shop
Hotels-50K: A Global Hotel Recognition Dataset
Recognizing a hotel from an image of a hotel room is important for human trafficking investigations.
Deep Randomized Ensembles for Metric Learning
Learning embedding functions, which map semantically related inputs to nearby locations in a feature space supports a variety of classification and information retrieval tasks.
