In the case of incremental object detection, OW-DETR outperforms the state-of-the-art for all settings on PASCAL VOC.
We note that the best existing multi-label ZSL method takes a shared approach towards attending to region features with a common set of attention maps for all the classes.
Ranked #1 on Multi-label zero-shot learning on Open Images V4
Nevertheless, computing reliable attention maps for unseen classes during inference in a multi-label setting is still a challenge.
Ranked #4 on Multi-label zero-shot learning on NUS-WIDE
The proposed algorithm is developed for the discrete state and action space and utilizes a multi-class support vector machine (SVM) to represent the policy.
We propose to enforce semantic consistency at all stages of (generalized) zero-shot learning: training, feature synthesis and classification.
Ranked #1 on Zero-Shot Learning on SUN Attribute
Compared to existing small-scale aerial image based instance segmentation datasets, iSAID contains 15$\times$ the number of object categories and 5$\times$ the number of instances.
Ranked #1 on Object Detection on iSAID