Smooth Adversarial Training

This is a PyTorch re-implementation of Axial-DeepLab (ECCV 2020 Spotlight)

DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution

Code for AutoNL on ImageNet (CVPR2020)

[ICLR 2020]: 'AtomNAS: Fine-Grained End-to-End Neural Architecture Search'

Waymo Open Dataset

PyTorch codes for our papers "Multiple Instance Detection Network with Online Instance Classifier Refinement" and "PCL: Proposal Cluster Learning for Weakly Supervised Object Detection".

DeepDiff: Deep Difference and search of any Python object/data. DeepHash: Hash of any object based on its contents. Delta: Use deltas to reconstruct objects by adding deltas together.

Source code for Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses (ECCV 2020)

A game theoretic approach to explain the output of any machine learning model.

Place holder

A collection of infrastructure and tools for research in neural network interpretability.

🐍 Geometric Computer Vision Library for Spatial AI

Learning Correspondence from the Cycle-consistency of Time (CVPR 2019)

Official implementation of paper "Learning Attraction Field Map for Robust Line Segment Detection" (CVPR 2019)

Standardizing weights to accelerate micro-batch training

ImageNet classifier with state-of-the-art adversarial robustness

Multi protocol support for handling remote files like local ones in Visual Studio Code.

Python Fire is a library for automatically generating command line interfaces (CLIs) from absolutely any Python object.

Codes for paper "Mask Scoring R-CNN".

rsync extension for visual studio code

Source code for Learning Transferable Adversarial Examples via Ghost Networks (AAAI2020)

A Simple and Versatile Framework for Object Detection and Instance Recognition

A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning

⚡ A Fast, Extensible Progress Bar for Python and CLI

An open IDE for web and native mobile development, built on top of Atom

Watches files and records, or triggers actions, when they change.

A PyTorch Implementation of Single Shot MultiBox Detector

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.