Using Deep Learning for Image-Based Plant Disease Detection

11 Apr 20164 code implementations

When testing the model on a set of images collected from trusted online sources - i. e. taken under conditions different from the images used for training - the model still achieves an accuracy of 31. 4%.

Caffe: Convolutional Architecture for Fast Feature Embedding

20 Jun 20141 code implementation

The framework is a BSD-licensed C++ library with Python and MATLAB bindings for training and deploying general-purpose convolutional neural networks and other deep models efficiently on commodity architectures.


Ristretto: Hardware-Oriented Approximation of Convolutional Neural Networks

20 May 20162 code implementations

Ristretto simulates the hardware arithmetic of a custom hardware accelerator.

Energy and Policy Considerations for Deep Learning in NLP

ACL 2019 2 code implementations

Recent progress in hardware and methodology for training neural networks has ushered in a new generation of large networks trained on abundant data.

SeesawFaceNets: sparse and robust face verification model for mobile platform

arXiv 2019 5 code implementations

Therefore, designing lightweight networks with low memory requirement and computational cost is one of the most practical solutions for face verification on mobile platform.


Submanifold Sparse Convolutional Networks

5 Jun 20172 code implementations

Convolutional network are the de-facto standard for analysing spatio-temporal data such as images, videos, 3D shapes, etc.

#2 best model for 3D Part Segmentation on ShapeNet-Part (Instance Average IoU metric)


Dynamic Graph CNN for Learning on Point Clouds

24 Jan 201811 code implementations

Point clouds provide a flexible geometric representation suitable for countless applications in computer graphics; they also comprise the raw output of most 3D data acquisition devices.

Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning

CVPR 2019 2 code implementations

We propose a new supervized learning framework for oversegmenting 3D point clouds into superpoints.


SegMap: 3D Segment Mapping using Data-Driven Descriptors

25 Apr 20181 code implementation

While current methods extract descriptors for the single task of localization, SegMap leverages a data-driven descriptor in order to extract meaningful features that can also be used for reconstructing a dense 3D map of the environment and for extracting semantic information.