mlsanityData to 7 Oct 2026

Hard Negative Mining for Metric Learning Based Zero-Shot Classification

arXiv 1608.07441 ↗First posted 26 Aug 2016cs.LG cs.AI cs.CVcited by 18

Not on the map. Why?

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.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Aug 2016.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 4; 2023: 2; 2024: 6; 2025: 4.

18 papers.

Sort:

  1. 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
  2. 2022Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddingscited by 75
  3. 2024Data curation via joint example selection further accelerates multimodal learningcited by 32
  4. 2024A Systematic Review on Long-Tailed Learningcited by 27
  5. 2022COARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentationcited by 15
  6. 2024Does Negative Sampling Matter? A Review with Insights into its Theory and Applicationscited by 14
  7. 2025ELIP: Enhanced Visual-Language Foundation Models for Image Retrievalcited by 9
  8. 2021SRPN: similarity-based region proposal networks for nuclei and cells detection in histology imagescited by 6
  9. 2024Globally Correlation-Aware Hard Negative Generationcited by 5
  10. 2025An Augmentation Overlap Theory of Contrastive Learningcited by 5
  11. 2022A Review and Roadmap of Deep Learning Causal Discovery in Different Variable Paradigmscited by 4
  12. 2024RealKIE: Five Novel Datasets for Enterprise Key Information Extractioncited by 4
6 more
  1. 2022Query-based Hard-Image Retrieval for Object Detection at Test Timecited by 2
  2. 2023S2vNTM: Semi-supervised vMF Neural Topic Modelingcited by 1
  3. 2024Multi-threshold Deep Metric Learning for Facial Expression Recognitioncited by 1
  4. 2025Dynamic Jointly Batch Selection for Data Efficient Machine Translation Fine-Tuningcited by 1
  5. 2023Not All Negatives Are Worth Attending to: Meta-Bootstrapping Negative Sampling Framework for Link Predictioncited by 0
  6. 2025Contrastive Learning Using Graph Embeddings for Domain Adaptation of Language Models in the Process Industrycited by 0