# A weakly supervised adaptive triplet loss for deep metric learning

arXiv: https://arxiv.org/abs/1909.12939 · HTML: https://mlsanity.com/paper/1909.12939/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Sep 2019.

## Built on by (most cited first, 9 of 9)

- [Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding](https://mlsanity.com/paper/2306.08832/) (2023)
- [Adaptive Contrast for Image Regression in Computer-Aided Disease Assessment](https://mlsanity.com/paper/2112.11700/) (2021)
- [Structure-Aware 3D VR Sketch to 3D Shape Retrieval](https://mlsanity.com/paper/2209.09043/) (2022)
- [Content-Based Medical Image Retrieval with Opponent Class Adaptive Margin Loss](https://mlsanity.com/paper/2211.15371/) (2022)
- [Transformer Decoders with MultiModal Regularization for Cross-Modal Food Retrieval](https://mlsanity.com/paper/2204.09730/) (2022)
- [Deep Boosting Learning: A Brand-new Cooperative Approach for Image-Text Matching](https://mlsanity.com/paper/2404.18114/) (2024)
- [No Pairs Left Behind: Improving Metric Learning with Regularized Triplet Objective](https://mlsanity.com/paper/2210.09506/) (2022)
- [OmniFashion: Towards Generalist Fashion Intelligence via Multi-Task Vision-Language Learning](https://mlsanity.com/paper/2603.02658/) (2026)
- [A Unified Model for Highly Accurate ECG-Free Dynamic Coronary Roadmapping Using Spatio-Temporal Transformers](https://mlsanity.com/paper/2607.09805/) (2026)

## Abstract (arXiv)

We address the problem of distance metric learning in visual similarity search, defined as learning an image embedding model which projects images into Euclidean space where semantically and visually similar images are closer and dissimilar images are further from one another. We present a weakly supervised adaptive triplet loss (ATL) capable of capturing fine-grained semantic similarity that encourages the learned image embedding models to generalize well on cross-domain data. The method uses weakly labeled product description data to implicitly determine fine grained semantic classes, avoiding the need to annotate large amounts of training data. We evaluate on the Amazon fashion retrieval benchmark and DeepFashion in-shop retrieval data. The method boosts the performance of triplet loss baseline by 10.6% on cross-domain data and out-performs the state-of-art model on all evaluation metrics.