UniT: Unified Knowledge Transfer for Any-shot Object Detection and Segmentation
This addresses the annotation bottleneck for computer vision tasks, offering a flexible solution that bridges weakly-supervised and few-shot methods, though it appears incremental in combining existing ideas.
The authors tackled the problem of object detection and segmentation requiring large-scale instance-level annotations by proposing a unified semi-supervised model that works across zero-shot to few-shot supervision, showing improved performance on MS-COCO and Pascal VOC benchmarks.
Methods for object detection and segmentation rely on large scale instance-level annotations for training, which are difficult and time-consuming to collect. Efforts to alleviate this look at varying degrees and quality of supervision. Weakly-supervised approaches draw on image-level labels to build detectors/segmentors, while zero/few-shot methods assume abundant instance-level data for a set of base classes, and none to a few examples for novel classes. This taxonomy has largely siloed algorithmic designs. In this work, we aim to bridge this divide by proposing an intuitive and unified semi-supervised model that is applicable to a range of supervision: from zero to a few instance-level samples per novel class. For base classes, our model learns a mapping from weakly-supervised to fully-supervised detectors/segmentors. By learning and leveraging visual and lingual similarities between the novel and base classes, we transfer those mappings to obtain detectors/segmentors for novel classes; refining them with a few novel class instance-level annotated samples, if available. The overall model is end-to-end trainable and highly flexible. Through extensive experiments on MS-COCO and Pascal VOC benchmark datasets we show improved performance in a variety of settings.