Using Sentences as Semantic Representations in Large Scale Zero-Shot Learning

Yannick Le Cacheux (1, 2) , Hervé Le Borgne (1) , Michel Crucianu (2)

1 LIST (CEA) - Laboratoire d'Intégration des Systèmes et des Technologies
2 CEDRIC - VERTIGO - CEDRIC. Données complexes, apprentissage et représentations

Zero-shot learning aims to recognize instances of unseen classes, for which no visual instance is available during training, by learning mul-timodal relations between samples from seen classes and corresponding class semantic representations. These class representations usually consist of either attributes, which do not scale well to large datasets, or word embeddings, which lead to poorer performance. A good trade-off could be to employ short sentences in natural language as class descriptions. We explore different solutions to use such short descriptions in a ZSL setting and show that while simple methods cannot achieve very good results with sentences alone, a combination of usual word embeddings and sentences can significantly outperform current state-of-the-art 3 .

Domaines: Intelligence artificielle [cs.AI]

Yannick Le Cacheux, Hervé Le Borgne, Michel Crucianu. Using Sentences as Semantic Representations in Large Scale Zero-Shot Learning. ECCV 2020 workshop Transferring and adapting source knowledge in computer vision (TASK-CV), Aug 2020, Glasgow, United Kingdom. ⟨hal-03003689⟩