Synthesizing the Unseen for Zero-shot Object Detection
This work addresses the challenge of detecting unseen objects in zero-shot settings, which is crucial for real-world applications where not all object classes are available during training.
The paper tackles the problem of zero-shot object detection by synthesizing visual features for unseen classes, enabling the model to learn both seen and unseen objects in the visual domain. It achieves impressive gains over state-of-the-art methods on benchmarks like PASCAL VOC, MSCOCO, and ILSVRC detection.
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. Our codes are available at https://github.com/nasir6/zero_shot_detection.