1 code implementation • ICCV 2023 • Kan Wu, Houwen Peng, Zhenghong Zhou, Bin Xiao, Mengchen Liu, Lu Yuan, Hong Xuan, Michael Valenzuela, Xi, Chen, Xinggang Wang, Hongyang Chao, Han Hu
In this paper, we propose a novel cross-modal distillation method, called TinyCLIP, for large-scale language-image pre-trained models.
2 code implementations • 21 Oct 2022 • Hong Xuan, Xi Chen
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 COCO 2014 (using extra training data)
no code implementations • 27 Jan 2022 • Hong Xuan, Robert Pless
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
1 code implementation • ECCV 2020 • Hong Xuan, Abby Stylianou, Xiaotong Liu, Robert Pless
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
no code implementations • 25 Sep 2019 • Hong Xuan, Robert Pless
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.
1 code implementation • 16 Sep 2019 • Xiaotong Liu, Hong Xuan, Zeyu Zhang, Abby Stylianou, Robert Pless
Deep metric learning is often used to learn an embedding function that captures the semantic differences within a dataset.
3 code implementations • 8 Apr 2019 • Hong Xuan, Abby Stylianou, Robert Pless
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
1 code implementation • 26 Jan 2019 • Abby Stylianou, Hong Xuan, Maya Shende, Jonathan Brandt, Richard Souvenir, Robert Pless
Recognizing a hotel from an image of a hotel room is important for human trafficking investigations.
1 code implementation • ECCV 2018 • Hong Xuan, Richard Souvenir, Robert Pless
Learning embedding functions, which map semantically related inputs to nearby locations in a feature space supports a variety of classification and information retrieval tasks.