TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Novel Object Detection	LVIS v1.0 val	Weng et al. Weng et al. (2021)*	Novel mAP	0.27	# 5
Novel Object Detection	LVIS v1.0 val	Weng et al. Weng et al. (2021)*	Known mAP	17.85	# 5
Novel Object Detection	LVIS v1.0 val	Weng et al. Weng et al. (2021)*	All mAP	1.62	# 5

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/unsupervised-discovery-of-the-long-tail-in/novel-object-detection-on-lvis-v1-0-val)](https://paperswithcode.com/sota/novel-object-detection-on-lvis-v1-0-val?p=unsupervised-discovery-of-the-long-tail-in)`

Unsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervision

CVPR 2021 · Zhenzhen Weng, Mehmet Giray Ogut, Shai Limonchik, Serena Yeung ·

Instance segmentation is an active topic in computer vision that is usually solved by using supervised learning approaches over very large datasets composed of object level masks. Obtaining such a dataset for any new domain can be very expensive and time-consuming. In addition, models trained on certain annotated categories do not generalize well to unseen objects. The goal of this paper is to propose a method that can perform unsupervised discovery of long-tail categories in instance segmentation, through learning instance embeddings of masked regions. Leveraging rich relationship and hierarchical structure between objects in the images, we propose self-supervised losses for learning mask embeddings. Trained on COCO dataset without additional annotations of the long-tail objects, our model is able to discover novel and more fine-grained objects than the common categories in COCO. We show that the model achieves competitive quantitative results on LVIS as compared to the supervised and partially supervised methods.