Latest Research
Turbo Autoencoder: Deep learning based channel codes for point-to-point communication channels
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.
Predicting Long-Term Skeletal Motions by a Spatio-Temporal Hierarchical Recurrent Network
• p0werHu/articulated-objects-motion-prediction
• 
The primary goal of skeletal motion prediction is to generate future motion by observing a sequence of 3D skeletons.
A Programmable Approach to Model Compression
• NVlabs/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
SCL: Towards Accurate Domain Adaptive Object Detection via Gradient Detach Based Stacked Complementary Losses
• harsh-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.
Minimax Nonparametric Two-sample Test
We consider the problem of comparing probability densities between two groups.
How can we fool LIME and SHAP? Adversarial Attacks on Post hoc Explanation Methods
In this paper, we demonstrate that post hoc explanations techniques that rely on input perturbations, such as LIME and SHAP, are not reliable.
Linear Support Vector Regression with Linear Constraints
This paper studies the addition of linear constraints to the Support Vector Regression (SVR) when the kernel is linear.
Towards Large yet Imperceptible Adversarial Image Perturbations with Perceptual Color Distance
• ZhengyuZhao/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.
Auptimizer -- an Extensible, Open-Source Framework for Hyperparameter Tuning
Tuning machine learning models at scale, especially finding the right hyperparameter values, can be difficult and time-consuming.
One Network to Segment Them All: A General, Lightweight System for Accurate 3D Medical Image Segmentation
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