# Construct Informative Triplet with Two-stage Hard-sample Generation

arXiv: https://arxiv.org/abs/2112.02259 · HTML: https://mlsanity.com/paper/2112.02259/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 44 references that are in the map.
- First posted on arXiv 4 Dec 2021.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Fine-tuning CNN Image Retrieval with No Human Annotation](https://mlsanity.com/paper/1711.02512/) (2017)
- [Deep Metric Learning via Lifted Structured Feature Embedding](https://mlsanity.com/paper/1511.06452/) (2015)
- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [Sampling Matters in Deep Embedding Learning](https://mlsanity.com/paper/1706.07567/) (2017)
- [Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking](https://mlsanity.com/paper/1803.11285/) (2018)
- [Beyond triplet loss: a deep quadruplet network for person re-identification](https://mlsanity.com/paper/1704.01719/) (2017)
- [Particular object retrieval with integral max-pooling of CNN activations](https://mlsanity.com/paper/1511.05879/) (2015)
- [Deep Metric Learning with Hierarchical Triplet Loss](https://mlsanity.com/paper/1810.06951/) (2018)
- [Revisiting Training Strategies and Generalization Performance in Deep Metric Learning](https://mlsanity.com/paper/2002.08473/) (2020)
- [Aggregating Deep Convolutional Features for Image Retrieval](https://mlsanity.com/paper/1510.07493/) (2015)
- [CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples](https://mlsanity.com/paper/1604.02426/) (2016)
- [Hardness-Aware Deep Metric Learning](https://mlsanity.com/paper/1903.05503/) (2019)
- [Hard-Aware Deeply Cascaded Embedding](https://mlsanity.com/paper/1611.05720/) (2016)
- [Signal-to-Noise Ratio: A Robust Distance Metric for Deep Metric Learning](https://mlsanity.com/paper/1904.02616/) (2019)
- [Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning](https://mlsanity.com/paper/2003.02546/) (2020)
- [Fine-grained Categorization and Dataset Bootstrapping using Deep Metric Learning with Humans in the Loop](https://mlsanity.com/paper/1512.05227/) (2015)
- [Factors of Transferability for a Generic ConvNet Representation](https://mlsanity.com/paper/1406.5774/) (2014)
- [Symmetrical Synthesis for Deep Metric Learning](https://mlsanity.com/paper/2001.11658/) (2020)
- [Hard-Aware Point-to-Set Deep Metric for Person Re-identification](https://mlsanity.com/paper/1807.11206/) (2018)
- [Mode Collapse and Regularity of Optimal Transportation Maps](https://mlsanity.com/paper/1902.02934/) (2019)

## Built on by (most cited first, 2 of 2)

- [Globally Correlation-Aware Hard Negative Generation](https://mlsanity.com/paper/2411.13145/) (2024)
- [No Pairs Left Behind: Improving Metric Learning with Regularized Triplet Objective](https://mlsanity.com/paper/2210.09506/) (2022)

## Abstract (arXiv)

In this paper, we propose a robust sample generation scheme to construct informative triplets. The proposed hard sample generation is a two-stage synthesis framework that produces hard samples through effective positive and negative sample generators in two stages, respectively. The first stage stretches the anchor-positive pairs with piecewise linear manipulation and enhances the quality of generated samples by skillfully designing a conditional generative adversarial network to lower the risk of mode collapse. The second stage utilizes an adaptive reverse metric constraint to generate the final hard samples. Extensive experiments on several benchmark datasets verify that our method achieves superior performance than the existing hard-sample generation algorithms. Besides, we also find that our proposed hard sample generation method combining the existing triplet mining strategies can further boost the deep metric learning performance.