# Hard Negative Mining for Metric Learning Based Zero-Shot Classification

arXiv: https://arxiv.org/abs/1608.07441 · HTML: https://mlsanity.com/paper/1608.07441/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Aug 2016.

## Built on by (most cited first, 18 of 18)

- [Exploring Cross-Image Pixel Contrast for Semantic Segmentation](https://mlsanity.com/paper/2101.11939/) (2021)
- [Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings](https://mlsanity.com/paper/2202.06671/) (2022)
- [Data curation via joint example selection further accelerates multimodal learning](https://mlsanity.com/paper/2406.17711/) (2024)
- [A Systematic Review on Long-Tailed Learning](https://mlsanity.com/paper/2408.00483/) (2024)
- [COARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentation](https://mlsanity.com/paper/2210.01784/) (2022)
- [Does Negative Sampling Matter? A Review with Insights into its Theory and Applications](https://mlsanity.com/paper/2402.17238/) (2024)
- [ELIP: Enhanced Visual-Language Foundation Models for Image Retrieval](https://mlsanity.com/paper/2502.15682/) (2025)
- [SRPN: similarity-based region proposal networks for nuclei and cells detection in histology images](https://mlsanity.com/paper/2106.13556/) (2021)
- [Globally Correlation-Aware Hard Negative Generation](https://mlsanity.com/paper/2411.13145/) (2024)
- [An Augmentation Overlap Theory of Contrastive Learning](https://mlsanity.com/paper/2511.03114/) (2025)
- [A Review and Roadmap of Deep Learning Causal Discovery in Different Variable Paradigms](https://mlsanity.com/paper/2209.06367/) (2022)
- [RealKIE: Five Novel Datasets for Enterprise Key Information Extraction](https://mlsanity.com/paper/2403.20101/) (2024)
- [Query-based Hard-Image Retrieval for Object Detection at Test Time](https://mlsanity.com/paper/2209.11559/) (2022)
- [S2vNTM: Semi-supervised vMF Neural Topic Modeling](https://mlsanity.com/paper/2307.04804/) (2023)
- [Multi-threshold Deep Metric Learning for Facial Expression Recognition](https://mlsanity.com/paper/2406.16434/) (2024)
- [Dynamic Jointly Batch Selection for Data Efficient Machine Translation Fine-Tuning](https://mlsanity.com/paper/2511.04406/) (2025)
- [Not All Negatives Are Worth Attending to: Meta-Bootstrapping Negative Sampling Framework for Link Prediction](https://mlsanity.com/paper/2312.04815/) (2023)
- [Contrastive Learning Using Graph Embeddings for Domain Adaptation of Language Models in the Process Industry](https://mlsanity.com/paper/2510.04631/) (2025)

## Abstract (arXiv)

Zero-Shot learning has been shown to be an efficient strategy for domain adaptation. In this context, this paper builds on the recent work of Bucher et al. [1], which proposed an approach to solve Zero-Shot classification problems (ZSC) by introducing a novel metric learning based objective function. This objective function allows to learn an optimal embedding of the attributes jointly with a measure of similarity between images and attributes. This paper extends their approach by proposing several schemes to control the generation of the negative pairs, resulting in a significant improvement of the performance and giving above state-of-the-art results on three challenging ZSC datasets.