Open World Compositional Zero-Shot Learning
| Autor: | Zeynep Akata, Massimiliano Mancini, Yongqin Xian, Muhammad Ferjad Naeem |
|---|---|
| Jazyk: | angličtina |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology Space (commercial competition) Machine learning computer.software_genre 030218 nuclear medicine & medical imaging Machine Learning (cs.LG) 03 medical and health sciences Knowledge-based systems 0302 clinical medicine Margin (machine learning) Simple (abstract algebra) 0202 electrical engineering electronic engineering information engineering Code (cryptography) business.industry Cosine similarity Visualization 020201 artificial intelligence & image processing State (computer science) Artificial intelligence business computer |
| Zdroj: | 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) IEEE/CVF Conference on Computer Vision and Pattern Recognition CVPR |
| DOI: | 10.1109/cvpr46437.2021.00518 |
| Popis: | Compositional Zero-Shot learning (CZSL) requires to recognize state-object compositions unseen during training. In this work, instead of assuming prior knowledge about the unseen compositions, we operate in the open world setting, where the search space includes a large number of unseen compositions some of which might be unfeasible. In this setting, we start from the cosine similarity between visual features and compositional embeddings. After estimating the feasibility score of each composition, we use these scores to either directly mask the output space or as a margin for the cosine similarity between visual features and compositional embeddings during training. Our experiments on two standard CZSL benchmarks show that all the methods suffer severe performance degradation when applied in the open world setting. While our simple CZSL model achieves state-of-the-art performances in the closed world scenario, our feasibility scores boost the performance of our approach in the open world setting, clearly outperforming the previous state of the art. Accepted in IEEE CVPR 2021 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|