Abstract
Inspired by the great success from deep convolutional neural networks (CNNs) for single-label visual-semantic embedding, we exploit extending these models for multilabel images. We propose a new learning paradigm for multilabel image classification, in which labels are ranked according to its relevance to the input image. In contrast to conventional CNN models that learn a latent vector representation (i.e., the image embedding vector), the developed visual model learns a mapping (i.e., a transformation matrix) from an image in an attempt to differentiate between its relevant and irrelevant labels. Despite the conceptual simplicity of our approach, the proposed model achieves state-of-the-art results on three public benchmark datasets.
Original language | English |
---|---|
Article number | 8691414 |
Pages (from-to) | 1530-1536 |
Number of pages | 7 |
Journal | IEEE Transactions on Pattern Analysis and Machine Intelligence |
Volume | 42 |
Issue number | 6 |
DOIs | |
Publication status | Published - 2020 Jun 1 |
Externally published | Yes |
Keywords
- convolutional neural networks
- Multilabel classification
- visual semantic embedding
ASJC Scopus subject areas
- Software
- Computer Vision and Pattern Recognition
- Computational Theory and Mathematics
- Artificial Intelligence
- Applied Mathematics