Active Learning Of Ordinal Embeddings: A User Study On Football Data

Abstract

Humans innately measure distance between instances in an unlabeled dataset using an unknown similarity function. Distance metrics can only serve as proxy for similarity in information retrieval of similar instances. Learning a good similarity function from human annotations improves the quality of retrievals. This work uses deep metric learning to learn these user-defined similarity functions from few annotations for a large football trajectory dataset. We adapt an entropy-based active learning method with recent work from triplet mining to collect easy-to-answer but still informative annotations from human participants and use them to train a deep convolutional network that generalizes to unseen samples. Our user study shows that our approach improves the quality of the information retrieval compared to a previous deep metric learning approach that relies on a Siamese network. Specifically, we shed light on the strengths and weaknesses of passive sampling heuristics and active learner

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyloeffler2022active

Related papers

• SLADE: A Self-training Framework For Distance Metric Learning (2020)6.77
• Active Metric Learning And Classification Using Similarity Queries (2022)0.00
• Human Motion Analysis With Deep Metric Learning (2018)11.58
• Hierarchical Annotation Of Images With Two-alternative-forced-choice Metric Learning (2019)0.00
• Loop: Looking For Optimal Hard Negative Embeddings For Deep Metric Learning (2021)8.82
• Deep Metric Learning Using Similarities From Nonlinear Rank Approximations (2019)2.26
• Monotonic Cardinality Estimation Of Similarity Selection: A Deep Learning Approach (2020)9.59
• Visual-interactive Similarity Search For Complex Objects By Example Of Soccer Player Analysis (2017)7.16