Adaptive Neighborhood Metric Learning

Abstract

In this paper, we reveal that metric learning would suffer from serious inseparable problem if without informative sample mining. Since the inseparable samples are often mixed with hard samples, current informative sample mining strategies used to deal with inseparable problem may bring up some side-effects, such as instability of objective function, etc. To alleviate this problem, we propose a novel distance metric learning algorithm, named adaptive neighborhood metric learning (ANML). In ANML, we design two thresholds to adaptively identify the inseparable similar and dissimilar samples in the training procedure, thus inseparable sample removing and metric parameter learning are implemented in the same procedure. Due to the non-continuity of the proposed ANML, we develop an ingenious function, named *log-exp mean function* to construct a continuous formulation to surrogate it, which can be efficiently solved by the gradient descent method. Similar to Triplet loss, ANML can be used to

Stats

• citations21
• S2 citations—
• github stars0
• HF likes0
• heat score10.07
• arxiv keysong2022adaptive

Related papers

• Local Distance Metric Learning For Nearest Neighbor Algorithm (2018)0.00
• Active Nearest-neighbor Learning In Metric Spaces (2016)0.00
• MIC: Mining Interclass Characteristics For Improved Metric Learning (2019)11.93
• Adaptive Hierarchical Similarity Metric Learning With Noisy Labels (2021)10.74
• Acceleration Of Large Margin Metric Learning For Nearest Neighbor Classification Using Triplet Mining And Stratified Sampling (2020)2.26
• Dynamic Sampling For Deep Metric Learning (2020)5.84
• Deep Metric Learning Meets Deep Clustering: An Novel Unsupervised Approach For Feature Embedding (2020)2.26
• Threshold Auto-tuning Metric Learning (2018)2.26