Synthesizing the Unseen for Zero-shot Object Detection
Nasir Hayat (IIAI), Munawar Hayat (IIAI)*, Shafin Rahman (North South University), Salman Khan (Australian National University (ANU)), Syed Waqas Zamir (IIAI), Fahad Shahbaz Khan (Inception Institute of Artificial Intelligence)
Keywords: Recognition: Feature Detection, Indexing, Matching, and Shape Representation
Abstract:
The existing zero-shot detection approaches project visual features to the semantic domain for seen objects, hoping to map unseen objects to their corresponding semantics during inference. However, since the unseen objects are never visualized during training, the detection model is skewed towards seen content, thereby labeling unseen as background or a seen class. In this work, we propose to synthesize visual features for unseen classes, so that the model learns both seen and unseen objects in the visual domain. Consequently, the major challenge becomes, how to accurately synthesize unseen objects merely using their class semantics? Towards this ambitious goal, we propose a novel generative model that uses class-semantics to not only generate the features but also to discriminatively separate them. Further, using a unified model, we ensure the synthesized features have high diversity that represents the intra-class differences and variable localization precision in the detected bounding boxes. We test our approach on three object detection benchmarks, PASCAL VOC, MSCOCO, and ILSVRC detection, under both conventional and generalized settings, showing impressive gains over the state-of-the-art methods.
SlidesLive
Similar Papers
Any-Shot Object Detection
Shafin Rahman (North South University)*, Salman Khan (IIAI), Nick Barnes (ANU), Fahad Shahbaz Khan (Inception Institute of Artificial Intelligence)

Do We Need Sound for Sound Source Localization?
Takashi Oya (Waseda University)*, Shohei Iwase (Waseda University ), Ryota Natsume (Waseda University), Takahiro Itazuri (Waseda University), Shugo Yamaguchi (Waseda University), Shigeo Morishima (Waseda Research Institute for Science and Engineering)

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)
