Webly Supervised Semantic Embeddings for Large Scale Zero-Shot Learning
Yannick Le Cacheux (CEA LIST)*, Adrian Popescu (CEA LIST), Herve Le Borgne (CEA LIST)
Keywords: Datasets and Performance Analysis
Abstract:
Zero-shot learning (ZSL) makes object recognition in images possible in absence of visual training data for a part of the classes from a dataset. When the number of classes is large, classes are usually represented by semantic class prototypes learned automatically from unannotated text collections. This typically leads to much lower performances than with manually designed semantic prototypes such as attributes. While most ZSL works focus on the visual aspect and reuse standard semantic prototypes learned from generic text collections, we focus on the problem of semantic class prototype design for large scale ZSL. More specifically, we investigate the use of noisy textual metadata associated to photos as text collections, as we hypothesize they are likely to provide more plausible semantic embeddings for visual classes if exploited appropriately. We thus make use of a source-based filtering strategy to improve the robustness of semantic prototypes. Evaluation on the large scale ImageNet dataset shows a significant improvement in ZSL performances over two strong baselines, and over usual semantic embeddings used in previous works. We show that this improvement is obtained for several embedding methods, leading to state of the art results when one uses automatically created visual and text features.
SlidesLive
Similar Papers
Background Learnable Cascade for Zero-Shot Object Detection
Ye Zheng (Institute of Computing Technology, Chinese Academy of Sciences)*, Ruoran Huang (Institute of Computing Technology, Chinese Academy of Sciences), Chuanqi Han (Institute of Computing Technology, Chinese Academy of Sciences), Xi Huang (Institute of computing technology of the Chinese Academy of Sciences), Li Cui ( Institute of computing technology of the Chinese Academy of Sciences)

Meta-Learning with Context-Agnostic Initialisations
Toby Perrett (University of Bristol)*, Alessandro Masullo (University of Bristol), Tilo Burghardt (University of Bristol), Majid Mirmehdi (University of Bristol), Dima Damen (University of Bristol)

Addressing Class Imbalance in Scene Graph Parsing by Learning to Contrast and Score
He Huang (University of Illinois at Chicago)*, Shunta Saito (Preferred Networks, Inc.), Yuta Kikuchi (Preferred Networks, Inc.), Eiichi Matsumoto (Preferred Networks, Inc.), Wei Tang (University of Illinois at Chicago), Philip S. Yu (UIC)
