15 open source projects by CSAILVision

Light version of Network Dissection for Quantifying Interpretability of Networks

Pytorch-based tools for visualizing and understanding the neurons of a GAN. https://gandissect.csail.mit.edu/

The Places365-CNNs for Scene Classification

The Toolkit for Places Challenge 2017

MATLAB Toolbox for the LabelMe Image Database

MiniPlaces Challenge: an Educational Tool for Deep Learning in Computer Vision

Source code for the LabelMe annotation tool.

Eye Tracking for Everyone

Network Dissection http://netdissect.csail.mit.edu for quantifying interpretability of deep CNNs.

Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset

Development kit for MIT Scene Parsing Benchmark

Codebase and pretrained models for ECCV'18 Unified Perceptual Parsing

IBD: Interpretable Basis Decomposition for Visual Explanation

ADE20K Dataset