paper-with-me

홈 › Papers

Construct Informative Triplet with Two-stage Hard-sample Generation

2021-12-04 · Chuang Zhu, Zheng Hu, Huihui Dong, Gang He, Zekuan Yu, Shangshang Zhang

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.

📄 PDF Abstract BibTeX arXiv:2112.02259

Code (0)

등록된 구현이 없습니다.

Tasks

Generative Adversarial NetworkMetric LearningTripletVocal Bursts Valence Prediction

Similar Papers 제목 키워드 기반

AdaSample: Adaptive Sampling of Hard Positives for Descriptor Learning

2019-11-27 · Xin-Yu Zhang, Le Zhang, Zao-Yi Zheng, Yun Liu 외

Triplet loss has been widely employed in a wide range of computer vision tasks, including local descriptor learning. The effectiveness of the triplet loss heavily relies on the triplet selection, in which a common practi…

InformativenessTriplet

MixKG: Mixing for harder negative samples in knowledge graph

2022-02-19 · Feihu Che, Guohua Yang, Pengpeng Shao, Dawei Zhang 외

Knowledge graph embedding~(KGE) aims to represent entities and relations into low-dimensional vectors for many real-world applications. The representations of entities and relations are learned via contrasting the positi…

Graph EmbeddingKnowledge Graph EmbeddingKnowledge Graphs

Deep Metric Learning with Hierarchical Triplet Loss

2018-10-16 · ECCV 2018 9 · Weifeng Ge, Weilin Huang, Dengke Dong, Matthew R. Scott

We present a novel hierarchical triplet loss (HTL) capable of automatically collecting informative training samples (triplets) via a defined hierarchical tree that encodes global context information. This allows us to co…

Face RecognitionImage RetrievalMetric LearningRetrieval+1

Do Lessons from Metric Learning Generalize to Image-Caption Retrieval?

2022-02-14 · Maurits Bleeker, Maarten de Rijke

The triplet loss with semi-hard negatives has become the de facto choice for image-caption retrieval (ICR) methods that are optimized from scratch. Recent progress in metric learning has given rise to new loss functions …

Image RetrievalMetric LearningRepresentation LearningRetrieval+1

Globally Correlation-Aware Hard Negative Generation

2024-11-20 · Wenjie Peng, Hongxiang Huang, Tianshui Chen, Quhui Ke 외

Hard negative generation aims to generate informative negative samples that help to determine the decision boundaries and thus facilitate advancing deep metric learning. Current works select pair/triplet samples, learn t…

Image RetrievalMetric LearningTriplet