-
Low-rank compression of neural nets: Learning the rank of each layer
Model compression is generally performed by using quantization, low-rank approximation or pruning, for which various algorithms have been researched in recent years. -
Part V: combining compressions
Model compression is generally performed by using quantization, low-rank approximation or pruning, for which various algorithms have been researched in recent years. -
Model compression as constrained optimization
Model compression is generally performed by using quantization, low-rank approximation or pruning, for which various algorithms have been researched in recent years. -
SWIN-Transformer
The SWIN-Transformer model is used for traffic map prediction. -
Generalization of Scaled Deep ResNets in the Mean-Field Regime
The dataset used in the paper is a binary classification dataset, where the goal is to find a hypothesis (i.e., a ResNet used in this work) f : X → Y such that f (x; Θ)... -
Liver Steatosis Segmentation with Deep Learning Methods
Liver steatosis segmentation dataset with deep learning methods -
3D Randomized Connection Network with Graph-based Label Inference
A novel 3D deep learning network is proposed for brain MR image segmentation with randomized connection, which can decrease the dependency between layers and increase the... -
Road Rutting Detection using Deep Learning on Images
A novel road rutting dataset containing 949 images from heterogeneous sources. -
DEFAKE: A Large-Scale Dataset for Real-World Face Forgery Detection
The DEFAKE dataset is a large-scale dataset for real-world face forgery detection, containing 6,000 images generated by Stable Diffusion. -
Transactions on Machine Learning Research
The dataset used in the Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning paper. -
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. -
An End-to-End Deep RL Framework for Task Arrangement in Crowdsourcing Platforms
A Deep Reinforcement Learning framework for task arrangement in crowdsourcing platforms. -
Deep Hashing Network for Unsupervised Domain Adaptation
The dataset is used for deep hashing network for unsupervised domain adaptation. -
Feature Tracking Cardiac Magnetic Resonance via Deep Learning and Spline Opti...
Feature tracking Cardiac Magnetic Resonance via Deep Learning and Spline Optimization -
A Novel Co-design Peta-scale Heterogeneous Cluster for Deep Learning Training
Large scale deep Convolution Neural Networks (CNNs) increasingly demands the computing power. -
A Deep Neural Network for Multiclass Bridge Element Parsing in Inspection Ima...
Aerial robots such as drones have been leveraged to perform bridge inspections. Inspection images with both recognizable structural elements and apparent surface defects can be... -
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... -
YouTube dataset
The dataset used in the paper is a large-scale graph dataset, consisting of users and shows with multi-attribute edges. The graph is constructed by selecting user IDs and side... -
Transform Quantization for CNN Compression
The dataset used in this paper is a collection of convolutional neural network (CNN) weights, which are compressed using transform quantization.
