A Caltech Library Service

FreeSOLO: Learning to Segment Objects without Annotations

Wang, Xinlong and Yu, Zhiding and De Mello, Shalini and Kautz, Jan and Anandkumar, Anima and Shen, Chunhua and Alvarez, Jose M. (2022) FreeSOLO: Learning to Segment Objects without Annotations. In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE , Piscataway, NJ, pp. 14156-14166.

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item:


Instance segmentation is a fundamental vision task that aims to recognize and segment each object in an image. However, it requires costly annotations such as bounding boxes and segmentation masks for learning. In this work, we propose a fully unsupervised learning method that learns class-agnostic instance segmentation without any annotations. We present FreeSOLO, a self-supervised instance segmentation framework built on top of the simple instance segmentation method SOLO. Our method also presents a novel localization-aware pre-training framework, where objects can be discovered from complicated scenes in an unsupervised manner. FreeSOLO achieves 9.8% AP₅₀ on the challenging COCO dataset, which even outperforms several segmentation proposal methods that use manual annotations. For the first time, we demonstrate unsupervised class-agnostic instance segmen-tation successfully. FreeSOLO's box localization significantly outperforms state-of-the-art unsupervised object de-tection/discovery methods, with about 100% relative improvements in COCO AP. FreeSOLO further demonstrates superiority as a strong pre-training method, outperforming state-of-the-art self-supervised pre-training methods by +9.8% AP when fine-tuning instance segmentation with only 5% COCO masks. Code is available at:

Item Type:Book Section
Related URLs:
URLURL TypeDescription ItemCode ItemDiscussion Paper
Yu, Zhiding0000-0003-1776-996X
Kautz, Jan0000-0002-8830-429X
Anandkumar, Anima0000-0002-6974-6797
Shen, Chunhua0000-0002-8648-8718
Additional Information:Part of this work was done when XW was an intern at NVIDIA, and CS was with The Univerity of Adelaide.
Record Number:CaltechAUTHORS:20230315-336403000.4
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:120063
Deposited By: George Porter
Deposited On:16 Mar 2023 19:15
Last Modified:16 Mar 2023 19:15

Repository Staff Only: item control page