-
BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation
Instance segmentation is one of the fundamental vision tasks. Recently, fully convolutional instance segmentation methods have drawn much attention as they are often simpler and... -
Liver Steatosis Segmentation with Deep Learning Methods
Liver steatosis segmentation dataset with deep learning methods -
Classification of Electroencephalograms during Mathematical Calculations Using...
The dataset consists of Before Calculation Signals (BCS) and During Calculation Signals (DCS). The dataset consisted of 36 participants. -
ImageNet 2012
The ImageNet 2012 dataset is used to evaluate the performance of the proposed neural network decoupling approach on large-scale image classification tasks. -
Symmetric parallax attention for stereo image super-resolution
Symmetric parallax attention for stereo image super-resolution. -
Learning parallax attention for stereo image super-resolution
Learning parallax attention for stereo image super-resolution. -
Feedback network for mutually boosted stereo image super-resolution and dispa...
Stereo image super-resolution aims at enhancing the quality of super-resolution results by utilizing the complementary information provided by binocular systems. -
ThermoPore: Predicting Part Porosity Based on Thermal Images Using Deep Learning
Thermal images of Laser Powder Bed Fusion fabricated samples utilizing in-situ thermal image monitoring data. -
Multispectral Object Detection with Deep Learning
Multispectral Object Detection with Deep Learning -
Feature Tracking Cardiac Magnetic Resonance via Deep Learning and Spline Opti...
Feature tracking Cardiac Magnetic Resonance via Deep Learning and Spline Optimization -
Video Restoration with a Deep Plug-and-Play Prior
This paper presents a novel method for restoring digital videos via a Deep Plug-and-Play (PnP) approach. -
A Novel Co-design Peta-scale Heterogeneous Cluster for Deep Learning Training
Large scale deep Convolution Neural Networks (CNNs) increasingly demands the computing power. -
AutoPET 2022 challenge
Tumor segmentation in PET-CT images is challenging due to the dual nature of the acquired information: low metabolic information in CT and low spatial resolution in PET. -
Classification of Diabetic Retinopathy using Pre-Trained Deep Learning Models
Diabetic Retinopathy dataset containing 1000 color fundus images from KAGGLE -
Learning for video compression with hierarchical quality and recurrent enhanc...
A learning-based video compression method -
Learning image and video compression through spatial-temporal energy compaction
A learning-based video compression method -
ImageNet and Cifar10
The dataset used for the ImageNet benchmark and the Cifar10 benchmark. -
Tied-Augment: Controlling Representation Similarity Improves Data Augmentation
Data augmentation methods have played an important role in the recent advance of deep learning models, and have become an indispensable component of state-of-the-art models in...
