The Startup
Published in

The Startup

SipMask — New SOTA in Instance Segmentation

SipMask is a one-stage neural network for instance segmentation of objects in an image. The model bypasses the previous one-stage state-of-the-art approaches on the COCO test-dev dataset. Compared to TensorMask, SipMask gives a 1% AP gain. Moreover, the model produces predictions 4 times faster. The model bypasses YOLACT by 3% in AP. The source code of the project is available in the repository on GitHub.

Instance Segmentation with SipMask. Source: Arxiv

--

--

--

Get smarter at building your thing. Follow to join The Startup’s +8 million monthly readers & +756K followers.

Recommended from Medium

Review — SimCLR: A Simple Framework for Contrastive Learning of Visual Representations

GLASS CLASSIFICATION USING VARIOUS MACHINE LEARNING TECHNIQUES

How To Create An MVP for Mental Health With Machine Learning

How did I pass the TensorFlow Developer Certificate exam?

1D & 3D Convolutions explained with… MS Excel!

Transposed Convolutions explained with… MS Excel!

How Can I Start Machine Learning

A MACHINE LEARNING APPROACH TO IMAGE COMPRESSION TECHNIQUE

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Mikhail Raevskiy

Mikhail Raevskiy

Bioinformatician at Oncobox Inc. (@oncobox). Research Associate

More from Medium

Semantic segmentation with an off-the-shelf model

Train a Custom Computer Vision Model Using OCI Vision Service

Building a coral segmentation model using sparse data

A timelapse of coral reefs turning white from dying.

1st Deep learning Project