Rethinking Multi-Label Image Classification With Deep Learning: Taxonomy, Challenge, and Outlook
2026-07-01 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors review recent progress in multi-label image classification, a task where a computer identifies multiple objects or ideas in one picture. They explain how deep learning techniques like convolutional and recurrent neural networks, as well as Transformers, help improve accuracy and adaptability in different settings. They organize existing methods into six categories based on their focus, such as regions in images or label handling. The authors also discuss current challenges and future directions to guide researchers in this area.
multi-label image classificationdeep learningconvolutional neural networksrecurrent neural networksTransformersvisual representationclassification metricsarchitecture-oriented methodsregion-oriented methodslearning methods
Authors
Xuelin Zhu, Xiu-Shen Wei, Jiawei Ge, Shuai Xu, Bing Wang
Abstract
Multi-label image classification (MLIC), a fundamental task in computer vision, focuses on identifying multiple objects or concepts within an image, underpinning numerous read-world applications, such as autonomous driving, disease diagnosis, recommendation system, and mobile service robot. Over the past decade, deep learning paradigms based on convolutional neural networks, recurrent neural networks, and Transformers have significantly advanced this field, owing to their powerful capability in visual representation and relationship modeling. These advances have markedly improved the robustness, scalability, and generalization ability of MLIC models across diverse datasets and application domains. In this survey, we provide a comprehensive review of the deep learning-based literature on MLIC. Concretely, we first revisit the background, including problem definition, datasets, backbones and evaluation metrics. Next, we develop a plausible taxonomy for the deep learning-based MLIC approaches, organizing them into six groups: region-oriented methods, label-oriented methods, architecture-oriented methods, representation-oriented methods, learning-oriented methods, and data-oriented methods. Finally, we provide an insightful exposition of the underlying learning game in MLIC and its implications for other vision domains, and we empirically summarize the key challenges and research directions in MLIC while outlining promising avenues for future development. We believe this survey offers the research community a holistic and systematic perspective on MLIC, thereby facilitating subsequent exploration and innovation in this field and beyond.