Semantic Diversity Learning For Zero-shot Multi-label Classification

Abstract

Training a neural network model for recognizing multiple labels associated with an image, including identifying unseen labels, is challenging, especially for images that portray numerous semantically diverse labels. As challenging as this task is, it is an essential task to tackle since it represents many real-world cases, such as image retrieval of natural images. We argue that using a single embedding vector to represent an image, as commonly practiced, is not sufficient to rank both relevant seen and unseen labels accurately. This study introduces an end-to-end model training for multi-label zero-shot learning that supports semantic diversity of the images and labels. We propose to use an embedding matrix having principal embedding vectors trained using a tailored loss function. In addition, during training, we suggest up-weighting in the loss function image samples presenting higher semantic diversity to encourage the diversity of the embedding matrix. Extensive experiments show th

Stats

• citations37
• S2 citations—
• github stars0
• HF likes0
• heat score11.85
• arxiv keybencohen2021semantic

Related papers

• Incremental Embedding Learning Via Zero-shot Translation (2020)8.09
• Transductive Zero-shot Hashing For Multilabel Image Retrieval (2019)8.82
• Learning Robust Visual-semantic Embeddings (2017)15.22
• Multi-head Attention With Diversity For Learning Grounded Multilingual Multimodal Representations (2019)7.81
• Keyword-based Diverse Image Retrieval By Semantics-aware Contrastive Learning And Transformer (2023)5.24
• Multi-level Similarity Learning For Low-shot Recognition (2019)0.00
• Visual Space Optimization For Zero-shot Learning (2019)0.00
• Hybrid-attention Based Decoupled Metric Learning For Zero-shot Image Retrieval (2019)12.93