Turbo Autoencoder: Deep learning based channel codes for point-to-point communication channels

8 Nov 2019yihanjiang/turboae

Designing codes that combat the noise in a communication medium has remained a significant area of research in information theory as well as wireless communications.

7
08 Nov 2019

Predicting Long-Term Skeletal Motions by a Spatio-Temporal Hierarchical Recurrent Network

6 Nov 2019p0werHu/articulated-objects-motion-prediction

The primary goal of skeletal motion prediction is to generate future motion by observing a sequence of 3D skeletons.

9
06 Nov 2019

A Programmable Approach to Model Compression

6 Nov 2019NVlabs/condensa

However, while the results are desirable, finding the best compression strategy for a given neural network, target platform, and optimization objective often requires extensive experimentation.

IMAGE CLASSIFICATION LANGUAGE MODELLING MODEL COMPRESSION QUANTIZATION

65
06 Nov 2019

SCL: Towards Accurate Domain Adaptive Object Detection via Gradient Detach Based Stacked Complementary Losses

6 Nov 2019harsh-99/SCL

Unsupervised domain adaptive object detection aims to learn a robust detector in the domain shift circumstance, where the training (source) domain is label-rich with bounding box annotations, while the testing (target) domain is label-agnostic and the feature distributions between training and testing domains are dissimilar or even totally different.

OBJECT DETECTION REGRESSION

17
06 Nov 2019

Minimax Nonparametric Two-sample Test

6 Nov 2019BioAlgs/Parallelism

We consider the problem of comparing probability densities between two groups.

0
06 Nov 2019

How can we fool LIME and SHAP? Adversarial Attacks on Post hoc Explanation Methods

6 Nov 2019dylan-slack/Fooling-LIME-SHAP

In this paper, we demonstrate that post hoc explanations techniques that rely on input perturbations, such as LIME and SHAP, are not reliable.

0
06 Nov 2019

Linear Support Vector Regression with Linear Constraints

6 Nov 2019Klopfe/LSVR

This paper studies the addition of linear constraints to the Support Vector Regression (SVR) when the kernel is linear.

REGRESSION

1
06 Nov 2019

Towards Large yet Imperceptible Adversarial Image Perturbations with Perceptual Color Distance

6 Nov 2019ZhengyuZhao/PerC-Adversarial

The success of image perturbations that are designed to fool image classification is assessed in terms of both adversarial effect and visual imperceptibility.

IMAGE CLASSIFICATION

4
06 Nov 2019

Auptimizer -- an Extensible, Open-Source Framework for Hyperparameter Tuning

6 Nov 2019LGE-ARC-AdvancedAI/auptimizer

Tuning machine learning models at scale, especially finding the right hyperparameter values, can be difficult and time-consuming.

HYPERPARAMETER OPTIMIZATION NEURAL ARCHITECTURE SEARCH

74
06 Nov 2019

One Network to Segment Them All: A General, Lightweight System for Accurate 3D Medical Image Segmentation

5 Nov 2019perslev/MultiPlanarUNet

The system relies on multi-planar data augmentation which facilitates the application of a single 2D architecture based on the familiar U-Net.

DATA AUGMENTATION MEDICAL IMAGE SEGMENTATION MODEL SELECTION SEMANTIC SEGMENTATION

37
05 Nov 2019