June 21, 2021 Deep Learning

LiDAR-based Place Recognition using Spatiotemporal Higher-Order Pooling

Locus This repository is an open-source implementation of the ICRA 2021 paper: Locus: LiDAR-based Place Recognition using Spatiotemporal Higher-Order Pooling. More information: https://research.csiro.au/robotics/locus-pr/ Paper Pre-print: https://arxiv.org/abs/2011.14497 Method overview. Locus is a global descriptor for large-scale place recognition using sequential 3D LiDAR point clouds. It encodes topological relationships and temporal consistency of scene components to obtain a discriminative and view-point invariant scene representation. Usage Set up environment This project has been tested on Ubuntu 18.04 (with Open3D 0.11, tensorflow 1.8.0, pcl […]

June 21, 2021 3D

Towards Part-Based Understanding of RGB-D Scans

part-based-scan-understanding Towards Part-Based Understanding of RGB-D Scans (CVPR 2021) We propose the task of part-based scene understanding of real-world 3D environments: from an RGB-D scan of a scene, we detect objects, and for each object predict its decomposition into geometric part masks, which composed together form the complete geometry of the observed object. Download Paper (.pdf) Demo samples Get started The core of this repository is a network, which takes as input preprocessed scan voxel crops and produces voxelized part […]

June 21, 2021 Deep Learning

Deep Networks from the Principle of Rate Reduction

redunet_paper Deep Networks from the Principle of Rate ReductionThis repository is the official NumPy implementation of the paper Deep Networks from the Principle of Rate Reduction (2021) by Kwan Ho Ryan Chan* (UC Berkeley), Yaodong Yu* (UC Berkeley), Chong You* (UC Berkeley), Haozhi Qi (UC Berkeley), John Wright (Columbia), and Yi Ma (UC Berkeley). For PyTorch version of ReduNet, please visit https://github.com/ryanchankh/redunet. What is ReduNet? ReduNet is a deep neural network construcuted naturally by deriving the gradients of the Maximal […]

June 21, 2021 Machine Learning

A GAN implemented with the Perceptual Simplicity and Spatial Constriction constraints

PS-SC GAN This repository contains the main code for training a PS-SC GAN (a GAN implemented with the Perceptual Simplicity and Spatial Constriction constraints) introduced in the paper Where and What? Examining Interpretable Disentangled Representations. The code for computing the TPL for model checkpoints from disentanglemen_lib can be found in this repository. Abstract Capturing interpretable variations has long been one of the goals indisentanglement learning. However, unlike the independence assumption,interpretability has rarely been exploited to encourage disentanglementin the unsupervised setting. […]

June 21, 2021 Machine Learning

Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition

ABINet Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition The official code of ABINet (CVPR 2021, Oral). ABINet uses a vision model and an explicit language model to recognize text in the wild, which are trained in end-to-end way. The language model (BCN) achieves bidirectional language representation in simulating cloze test, additionally utilizing iterative correction strategy. Runtime Environment We provide a pre-built docker image using the Dockerfile from docker/Dockerfile Running in Docker $ [email protected]:FangShancheng/ABINet.git $ […]

June 21, 2021 Search

Prioritized Architecture Sampling with Monto-Carlo Tree Search

NAS-Bench-Macro This repository includes the benchmark and code for NAS-Bench-Macro in paper “Prioritized Architecture Sampling with Monto-Carlo Tree Search”, CVPR2021. NAS-Bench-Macro is a NAS benchmark on macro search space. The NAS-Bench-Macro consists of 6561 networks and their test accuracies, parameters, and FLOPs on CIFAR-10 dataset. Each architecture in NAS-Bench-Macro is trained from scratch isolatedly. Benchmark All the evaluated architectures are stored in file nas-bench-macro_cifar10.json with the following format: { arch1: { test_acc: [float, float, float], // the test accuracies of […]

June 21, 2021 Images

Polygonal Building Segmentation by Frame Field Learning

Polygonization-by-Frame-Field-Learning This repository contains the code for our fast polygonal building extraction from overhead images pipeline. We add a frame field output to an image segmentation neural network to improve segmentation quality and provide structural information for the subsequent polygonization step. Figure 1: Close-up of our additional frame field output on a test image. Figure 2: Given an overhead image, the model outputs an edge mask, an interior mask,and a frame field for buildings. The total loss includes terms that […]

June 21, 2021 Network

An unofficial PyTorch implemenation of EventProp

This is an unofficial PyTorch implemenation of EventProp, a method to compute exact gradients for Spiking Neural Networks. The repo currently contains code to train a 1-layer Spiking Neural Network with leaky integrate-and-fire (LIF) neurons for 10-way digit classification on MNIST. Implementation Details The implementation of EventProp itself is in models.py, in form of the forward and backward methods of the SpikingLinear module, which compute the forward passes of a spiking layer and its adjoint layer. In particular, the manual_forward […]

June 21, 2021 Visualization

Leaderboard and Visualization for RLCard with python

This is the GUI support for the RLCard project and DouZero project. RLCard-Showdown provides evaluation and visualization tools to help understand the performance of the agents. It includes a replay module, where you can analyze the replays, and a PvE module, where you can play with the AI interactively. Currently, we only support Leduc Hold’em and Dou Dizhu. The frontend is developed with React. The backend is based on Django and Flask. Have fun! Cite this work Zha, Daochen, et […]

June 21, 2021 Neural Machine Translation (NMT), NMT Leave a comment

Machine Translation Weekly 84: Order Agnostic Cross-Entropy

I tend to be a little biased against autoregressive models. The way they operate: say exactly one subword, think for a while, and then say again exactly one subword, just does not sound natural to me. Moreover, with current models, a subword can be anything from a single character to a word as long as “Ausgußreiniger”. Non-autoregressive models generate everything in a single step. That does seem to be really natural either, but at least they offer an interesting alternative. […]

« 1 … 17 18 19 20 21 … 42 »