paper-with-me

홈 › Papers

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 cope with the main limitation of random sampling in training a conventional triplet loss, which is a central issue for deep metric learning. Our main contributions are two-fold. (i) we construct a hierarchical class-level tree where neighboring classes are merged recursively. The hierarchical structure naturally captures the intrinsic data distribution over the whole database. (ii) we formulate the problem of triplet collection by introducing a new violate margin, which is computed dynamically based on the designed hierarchical tree. This allows it to automatically select meaningful hard samples with the guide of global context. It encourages the model to learn more discriminative features from visual similar classes, leading to faster convergence and better performance. Our method is evaluated on the tasks of image retrieval and face recognition, where it outperforms the standard triplet loss substantially by 1%-18%. It achieves new state-of-the-art performance on a number of benchmarks, with much fewer learning iterations.

📄 PDF Abstract BibTeX arXiv:1810.06951

Code (0)

등록된 구현이 없습니다.

Tasks

Face RecognitionImage RetrievalMetric LearningRetrievalTriplet

Methods 이 논문이 사용한 방법론

Triplet Loss The goal of Triplet loss, in the context of Siamese Networks, is to maximize the joint probability among all score-pairs i.e. the product of all probabilities. By using its…

Similar Papers 제목 키워드 기반

Acceleration of Large Margin Metric Learning for Nearest Neighbor Classification Using Triplet Mining and Stratified Sampling

2020-09-29 · Parisa Abdolrahim Poorheravi, Benyamin Ghojogh, Vincent Gaudet, Fakhri Karray 외

Metric learning is one of the techniques in manifold learning with the goal of finding a projection subspace for increasing and decreasing the inter- and intra-class variances, respectively. Some of the metric learning m…

Metric LearningTriplet

Strong but Simple Baseline with Dual-Granularity Triplet Loss for Visible-Thermal Person Re-Identification

2020-12-09 · Haijun Liu, Yanxia Chai, Xiaoheng Tan, Dong Li 외

In this letter, we propose a conceptually simple and effective dual-granularity triplet loss for visible-thermal person re-identification (VT-ReID). In general, ReID models are always trained with the sample-based triple…

Cross-Modal Person Re-IdentificationPerson Re-IdentificationTriplet

Rank-based loss for learning hierarchical representations

2021-10-11 · Ines Nolasco, Dan Stowell

Hierarchical taxonomies are common in many contexts, and they are a very natural structure humans use to organise information. In machine learning, the family of methods that use the 'extra' information is called hierarc…

Audio ClassificationTriplet

TripletGAN: Training Generative Model with Triplet Loss

2017-11-14 · Gongze Cao, Yezhou Yang, Jie Lei, Cheng Jin 외

As an effective way of metric learning, triplet loss has been widely used in many deep learning tasks, including face recognition and person-ReID, leading to many states of the arts. The main innovation of triplet loss i…

Face RecognitionGeneral ClassificationMetric Learningmodel+1

Hybrid Losses for Hierarchical Embedding Learning

2025-01-22 · Haokun Tian, Stefan Lattner, Brian McFee, Charalampos Saitis

In traditional supervised learning, the cross-entropy loss treats all incorrect predictions equally, ignoring the relevance or proximity of wrong labels to the correct answer. By leveraging a tree hierarchy for fine-grai…

Multi-Task LearningRetrievalTriplet