SOLOv2: Dynamic and Fast Instance Segmentation

Xinlong Wang, Rufeng Zhang, Tao Kong, Lei Li, Chunhua Shen

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 38 functions out of this paper's own repositories and ran 20 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• WXinlong/SOLO — marked official in Papers with Code
• Fei-dong/SOLO_SORT
• MY-Swich/SOLO
• MY-Swich/SOLO_my
• MY-Swich/solo-len
• OpenFirework/pytorch_solov2
• XXXVincent/SOLO
• divyachandana/solo-semantic-segmentation
• hades12580/solov2_mmdet
• hukefei/SOLO-master
• lifuguan/SOLOv2-mmdet
• mvpzhangqiu/SOLOV2
• trhieu310/customDataset
• universea/SOLOv2
• zymk9/Yet-Another-Anime-Segmenter
• PaddlePaddle/PaddleDetection
• fastestimator/fastestimator
• open-mmlab/mmdetection

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this work, we design a simple, direct, and fast framework for instance segmentation with strong performance. To this end, we propose a novel and effective approach, termed SOLOv2, following the principle of the SOLO method of Wang et al. "SOLO: segmenting objects by locations" [1]. First, our new framework is empowered by an efficient and holistic instance mask representation scheme, which dynamically segments each instance in the image, without resorting to bounding box detection. Specifically, the object mask generation is decoupled into a mask kernel prediction and mask feature learning, which are responsible for generating convolution kernels and the feature maps to be convolved with, respectively. Second, SOLOv2 significantly reduces inference overhead with our novel matrix non-maximum suppression (NMS) technique. Our Matrix NMS performs NMS with parallel matrix operations in one shot, and yields better results. We demonstrate that our SOLOv2 outperforms most state-of-the-art instance segmentation methods in both speed and accuracy. A light-weight version of SOLOv2 executes at 31.3 FPS and yields 37.1% AP on COCO test-dev. Moreover, our state-of-the-art results in object detection (from our mask byproduct) and panoptic segmentation show the potential of SOLOv2 to serve as a new strong baseline for many instancelevel recognition tasks. Code is available at https://git.io/AdelaiDet

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2003.10152")
get_code_for_paper("2003.10152")
have("2003.10152")

Connect an agent — have() is free.