# SOLOv2: Dynamic and Fast Instance Segmentation

arXiv: https://arxiv.org/abs/2003.10152 · HTML: https://mlsanity.com/paper/2003.10152/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Mar 2020.

## Built on by (most cited first, 30 of 37)

- [DexYCB: A Benchmark for Capturing Hand Grasping of Objects](https://mlsanity.com/paper/2104.04631/) (2021)
- [Simultaneously Localize, Segment and Rank the Camouflaged Objects](https://mlsanity.com/paper/2103.04011/) (2021)
- [RTMDet: An Empirical Study of Designing Real-Time Object Detectors](https://mlsanity.com/paper/2212.07784/) (2022)
- [Instances as Queries](https://mlsanity.com/paper/2105.01928/) (2021)
- [A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS](https://mlsanity.com/paper/2304.00501/) (2023)
- [ResT: An Efficient Transformer for Visual Recognition](https://mlsanity.com/paper/2105.13677/) (2021)
- [SOLQ: Segmenting Objects by Learning Queries](https://mlsanity.com/paper/2106.02351/) (2021)
- [Decoupled Dynamic Filter Networks](https://mlsanity.com/paper/2104.14107/) (2021)
- [OpenForensics: Large-Scale Challenging Dataset For Multi-Face Forgery Detection And Segmentation In-The-Wild](https://mlsanity.com/paper/2107.14480/) (2021)
- [SOLO: A Simple Framework for Instance Segmentation](https://mlsanity.com/paper/2106.15947/) (2021)
- [Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision](https://mlsanity.com/paper/2108.07682/) (2021)
- [PointConvFormer: Revenge of the Point-based Convolution](https://mlsanity.com/paper/2208.02879/) (2022)
- [Kernel Proposal Network for Arbitrary Shape Text Detection](https://mlsanity.com/paper/2203.06410/) (2022)
- [Quality-Aware Network for Human Parsing](https://mlsanity.com/paper/2103.05997/) (2021)
- [Deep Learning Serves Traffic Safety Analysis: A Forward-looking Review](https://mlsanity.com/paper/2203.10939/) (2022)
- [Video Instance Segmentation by Instance Flow Assembly](https://mlsanity.com/paper/2110.10599/) (2021)
- [Distractor-Aware Fast Tracking via Dynamic Convolutions and MOT Philosophy](https://mlsanity.com/paper/2104.12041/) (2021)
- [Generic Perceptual Loss for Modeling Structured Output Dependencies](https://mlsanity.com/paper/2103.10571/) (2021)
- [Human-centric Relation Segmentation: Dataset and Solution](https://mlsanity.com/paper/2105.11168/) (2021)
- [Training Generative Adversarial Networks in One Stage](https://mlsanity.com/paper/2103.00430/) (2021)
- [Real-time Instance Segmentation with Discriminative Orientation Maps](https://mlsanity.com/paper/2106.12204/) (2021)
- [SCD: A Stacked Carton Dataset for Detection and Segmentation](https://mlsanity.com/paper/2102.12808/) (2021)
- [Implicit Feature Refinement for Instance Segmentation](https://mlsanity.com/paper/2112.04709/) (2021)
- [Online Video Instance Segmentation via Robust Context Fusion](https://mlsanity.com/paper/2207.05580/) (2022)
- [AutoKary2022: A Large-Scale Densely Annotated Dataset for Chromosome Instance Segmentation](https://mlsanity.com/paper/2303.15839/) (2023)
- [Deep Learning Techniques for Video Instance Segmentation: A Survey](https://mlsanity.com/paper/2310.12393/) (2023)
- [PP-ShiTu: A Practical Lightweight Image Recognition System](https://mlsanity.com/paper/2111.00775/) (2021)
- [UniInst: Unique Representation for End-to-End Instance Segmentation](https://mlsanity.com/paper/2205.12646/) (2022)
- [SCR: Smooth Contour Regression with Geometric Priors](https://mlsanity.com/paper/2202.03784/) (2022)
- [SODAR: Segmenting Objects by DynamicallyAggregating Neighboring Mask Representations](https://mlsanity.com/paper/2202.07402/) (2022)

## Abstract (arXiv)

In this work, we aim at building a simple, direct, and fast instance segmentation framework with strong performance. We follow the principle of the SOLO method of Wang et al. "SOLO: segmenting objects by locations". Importantly, we take one step further by dynamically learning the mask head of the object segmenter such that the mask head is conditioned on the location. Specifically, the mask branch is decoupled into a mask kernel branch and mask feature branch, which are responsible for learning the convolution kernel and the convolved features respectively. Moreover, we propose Matrix NMS (non maximum suppression) to significantly reduce the inference time overhead due to NMS of masks. Our Matrix NMS performs NMS with parallel matrix operations in one shot, and yields better results. We demonstrate a simple direct instance segmentation system, outperforming a few state-of-the-art methods in both speed and accuracy. A light-weight version of SOLOv2 executes at 31.3 FPS and yields 37.1% AP. Moreover, our state-of-the-art results in object detection (from our mask byproduct) and panoptic segmentation show the potential to serve as a new strong baseline for many instance-level recognition tasks besides instance segmentation. Code is available at: https://git.io/AdelaiDet