Generic Multi-label Annotation via Adaptive Graph and Marginalized Augmentation
- 20 July 2021
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 16 (1), 1-20
- https://doi.org/10.1145/3451884
Abstract
Multi-label learning recovers multiple labels from a single instance. It is a more challenging task compared with single-label manner. Most multi-label learning approaches need large-scale well-labeled samples to achieve high accurate performance. However, it is expensive to build such a dataset. In this work, we propose a generic multi-label learning framework based on Adaptive Graph and Marginalized Augmentation (AGMA) in a semi-supervised scenario. Generally speaking, AGMA makes use of a small amount of labeled data associated with a lot of unlabeled data to boost the learning performance. First, an adaptive similarity graph is learned to effectively capture the intrinsic structure within the data. Second, marginalized augmentation strategy is explored to enhance the model generalization and robustness. Third, a feature-label autoencoder is further deployed to improve inferring efficiency. All the modules are jointly trained to benefit each other. State-of-the-art benchmarks in both traditional and zero-shot multi-label learning scenarios are evaluated. Experiments and ablation studies illustrate the accuracy and efficiency of our AGMA method.Keywords
Funding Information
- U.S. Army Research Office Award (W911NF-17-1-0367)
This publication has 36 references indexed in Scilit:
- Attribute-Based Classification for Zero-Shot Visual Object CategorizationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Multilabel relationship learningACM Transactions on Knowledge Discovery From Data, 2013
- Multilabel dimensionality reduction via dependence maximizationACM Transactions on Knowledge Discovery From Data, 2010
- Distributed Optimization and Statistical Learning via the Alternating Direction Method of MultipliersFoundations and Trends® in Machine Learning, 2010
- Graph-based semi-supervised learning with multiple labelsJournal of Visual Communication and Image Representation, 2009
- Correlative multi-label video annotationPublished by Association for Computing Machinery (ACM) ,2007
- Collective multi-label classificationPublished by Association for Computing Machinery (ACM) ,2005
- Learning multi-label scene classificationPattern Recognition, 2004
- Discriminative Methods for Multi-labeled ClassificationLecture Notes in Computer Science, 2004
- Algorithm 432 [C2]: Solution of the matrix equation AX + XB = C [F4]Communications of the ACM, 1972