PixelSSL — Library For Pixel-Wise Computer Vision Tasks

PixelSSL is a library for pixel-by-pixel computer vision tasks. The library facilitates the training of semi-supervised models. PixelSSL currently only supports the object segmentation task. Implementations of 5 models are available in the library: SupOnly, MT, S4L, AdvSSL and GCT.

PixelSSL — Library For Pixel-Wise Computer Vision Tasks
Source: Github

📖 More about the library




A weekly digest of the new state-of-the-art (SOTA) Deep Learning approaches and solutions

Recommended from Medium

Deploying Azure Machine Learning Containers

Review: M²FCN — Multi-stage Multi-recursive-input Fully Convolutional Networks (Biomedical Image…


Deciding against a PhD

BASICS: Building a model which can identify diabetes

Reading: Galpin DCC’19 — CNN-Based Driving of Block Partitioning (VVC Intra Prediction)

This May Change the Way You Think About Deep Learning

Zero-Shot Text Classification

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

Explainable AI and Visual Interpretability -Introduction (Part 2)

Can you read this title with your peripheral vision?

Visualizing 3D Data from Point Distance Information with MDS-Algorithm in Python

attention package on CRAN