# Deep Semantic Dictionary Learning for Multi-label Image Classification

arXiv: https://arxiv.org/abs/2012.12509 · HTML: https://mlsanity.com/paper/2012.12509/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Dec 2020.

## Built on by (most cited first, 20 of 20)

- [FoodLMM: A Versatile Food Assistant using Large Multi-modal Model](https://mlsanity.com/paper/2312.14991/) (2023)
- [Semantic-Aware Dual Contrastive Learning for Multi-label Image Classification](https://mlsanity.com/paper/2307.09715/) (2023)
- [Unleashing the Power of Shared Label Structures for Human Activity Recognition](https://mlsanity.com/paper/2301.03462/) (2023)
- [Semantic-Aware Graph Matching Mechanism for Multi-Label Image Recognition](https://mlsanity.com/paper/2304.11275/) (2023)
- [Positive Label Is All You Need for Multi-Label Classification](https://mlsanity.com/paper/2306.16016/) (2023)
- [Semantic Representation and Dependency Learning for Multi-Label Image Recognition](https://mlsanity.com/paper/2204.03795/) (2022)
- [Boosting Multi-Label Image Classification with Complementary Parallel Self-Distillation](https://mlsanity.com/paper/2205.10986/) (2022)
- [SpliceMix: A Cross-scale and Semantic Blending Augmentation Strategy for Multi-label Image Classification](https://mlsanity.com/paper/2311.15200/) (2023)
- [Batch Selection for Multi-Label Classification Guided by Uncertainty and Dynamic Label Correlations](https://mlsanity.com/paper/2412.16521/) (2024)
- [Global Meets Local: Effective Multi-Label Image Classification via Category-Aware Weak Supervision](https://mlsanity.com/paper/2211.12716/) (2022)
- [Perceptual Image Compression with Cooperative Cross-Modal Side Information](https://mlsanity.com/paper/2311.13847/) (2023)
- [Diverse and Tailored Image Generation for Zero-shot Multi-label Classification](https://mlsanity.com/paper/2404.03144/) (2024)
- [Semantic Embedded Deep Neural Network: A Generic Approach to Boost Multi-Label Image Classification Performance](https://mlsanity.com/paper/2305.05228/) (2023)
- [Evolving Dictionary Representation for Few-shot Class-incremental Learning](https://mlsanity.com/paper/2305.01885/) (2023)
- [ShuffleMix: Improving Representations via Channel-Wise Shuffle of Interpolated Hidden States](https://mlsanity.com/paper/2305.18684/) (2023)
- [A Consistent Lebesgue Measure for Multi-label Learning](https://mlsanity.com/paper/2402.00324/) (2024)
- [Subgraph Clustering and Atom Learning for Improved Image Classification](https://mlsanity.com/paper/2407.14772/) (2024)
- [Multi-Dictionary Learning for Low Rank Sparse Coding](https://mlsanity.com/paper/2509.10033/) (2025)
- [Addressing Imbalance in Multi-Label Data via Label-Specific Distance-based Oversampling](https://mlsanity.com/paper/2606.05927/) (2026)
- [Rethinking Multi-Label Image Classification With Deep Learning: Taxonomy, Challenge, and Outlook](https://mlsanity.com/paper/2607.00839/) (2026)

## Abstract (arXiv)

Compared with single-label image classification, multi-label image classification is more practical and challenging. Some recent studies attempted to leverage the semantic information of categories for improving multi-label image classification performance. However, these semantic-based methods only take semantic information as type of complements for visual representation without further exploitation. In this paper, we present an innovative path towards the solution of the multi-label image classification which considers it as a dictionary learning task. A novel end-to-end model named Deep Semantic Dictionary Learning (DSDL) is designed. In DSDL, an auto-encoder is applied to generate the semantic dictionary from class-level semantics and then such dictionary is utilized for representing the visual features extracted by Convolutional Neural Network (CNN) with label embeddings. The DSDL provides a simple but elegant way to exploit and reconcile the label, semantic and visual spaces simultaneously via conducting the dictionary learning among them. Moreover, inspired by iterative optimization of traditional dictionary learning, we further devise a novel training strategy named Alternately Parameters Update Strategy (APUS) for optimizing DSDL, which alternately optimizes the representation coefficients and the semantic dictionary in forward and backward propagation. Extensive experimental results on three popular benchmarks demonstrate that our method achieves promising performances in comparison with the state-of-the-arts. Our codes and models have been released at {https://github.com/ZFT-CQU/DSDL}.