# YOLACT: Real-time Instance Segmentation

arXiv: https://arxiv.org/abs/1904.02689 · HTML: https://mlsanity.com/paper/1904.02689/

## Key facts

- Cited by 443 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2019.

## Built on by (most cited first, 30 of 443)

- [Segment Everything Everywhere All at Once](https://mlsanity.com/paper/2304.06718/) (2023)
- [Generalized Decoding for Pixel, Image, and Language](https://mlsanity.com/paper/2212.11270/) (2022)
- [Fast Segment Anything](https://mlsanity.com/paper/2306.12156/) (2023)
- [K-Net: Towards Unified Image Segmentation](https://mlsanity.com/paper/2106.14855/) (2021)
- [Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP](https://mlsanity.com/paper/2308.02487/) (2023)
- [RTMDet: An Empirical Study of Designing Real-Time Object Detectors](https://mlsanity.com/paper/2212.07784/) (2022)
- [SegGPT: Segmenting Everything In Context](https://mlsanity.com/paper/2304.03284/) (2023)
- [Universal Instance Perception as Object Discovery and Retrieval](https://mlsanity.com/paper/2303.06674/) (2023)
- [Semantic-SAM: Segment and Recognize Anything at Any Granularity](https://mlsanity.com/paper/2307.04767/) (2023)
- [RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Model](https://mlsanity.com/paper/2306.16269/) (2023)
- [ZipIt! Merging Models from Different Tasks without Training](https://mlsanity.com/paper/2305.03053/) (2023)
- [Towards Open Vocabulary Learning: A Survey](https://mlsanity.com/paper/2306.15880/) (2023)
- [Instances as Queries](https://mlsanity.com/paper/2105.01928/) (2021)
- [PolyFormer: Referring Image Segmentation as Sequential Polygon Generation](https://mlsanity.com/paper/2302.07387/) (2023)
- [Transformer-Based Visual Segmentation: A Survey](https://mlsanity.com/paper/2304.09854/) (2023)
- [Learning What Not to Segment: A New Perspective on Few-Shot Segmentation](https://mlsanity.com/paper/2203.07615/) (2022)
- [Foundational Models Defining a New Era in Vision: A Survey and Outlook](https://mlsanity.com/paper/2307.13721/) (2023)
- [Video Instance Segmentation using Inter-Frame Communication Transformers](https://mlsanity.com/paper/2106.03299/) (2021)
- [Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers](https://mlsanity.com/paper/2103.12340/) (2021)
- [FreeSOLO: Learning to Segment Objects without Annotations](https://mlsanity.com/paper/2202.12181/) (2022)
- [SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation](https://mlsanity.com/paper/2103.10284/) (2021)
- [Hi4D: 4D Instance Segmentation of Close Human Interaction](https://mlsanity.com/paper/2303.15380/) (2023)
- [AutoLaparo: A New Dataset of Integrated Multi-tasks for Image-guided Surgical Automation in Laparoscopic Hysterectomy](https://mlsanity.com/paper/2208.02049/) (2022)
- [Crossover Learning for Fast Online Video Instance Segmentation](https://mlsanity.com/paper/2104.05970/) (2021)
- [RF-DETR: Neural Architecture Search for Real-Time Detection Transformers](https://mlsanity.com/paper/2511.09554/) (2025)
- [Video Instance Segmentation with a Propose-Reduce Paradigm](https://mlsanity.com/paper/2103.13746/) (2021)
- [Multimodal Object Detection via Probabilistic Ensembling](https://mlsanity.com/paper/2104.02904/) (2021)
- [SOLQ: Segmenting Objects by Learning Queries](https://mlsanity.com/paper/2106.02351/) (2021)
- [Mask Transfiner for High-Quality Instance Segmentation](https://mlsanity.com/paper/2111.13673/) (2021)
- [A Comprehensive Survey on Segment Anything Model for Vision and Beyond](https://mlsanity.com/paper/2305.08196/) (2023)

## Abstract (arXiv)

We present a simple, fully-convolutional model for real-time instance segmentation that achieves 29.8 mAP on MS COCO at 33.5 fps evaluated on a single Titan Xp, which is significantly faster than any previous competitive approach. Moreover, we obtain this result after training on only one GPU. We accomplish this by breaking instance segmentation into two parallel subtasks: (1) generating a set of prototype masks and (2) predicting per-instance mask coefficients. Then we produce instance masks by linearly combining the prototypes with the mask coefficients. We find that because this process doesn't depend on repooling, this approach produces very high-quality masks and exhibits temporal stability for free. Furthermore, we analyze the emergent behavior of our prototypes and show they learn to localize instances on their own in a translation variant manner, despite being fully-convolutional. Finally, we also propose Fast NMS, a drop-in 12 ms faster replacement for standard NMS that only has a marginal performance penalty.