Search
Search Results
-
Towards Flexible Inductive Bias via Progressive Reparameterization Scheduling
There are two de facto standard architectures in recent computer vision: Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). Strong...
-
Structural Reparameterization Network on Point Cloud Semantic Segmentation
In recent years, 3D point cloud semantic segmentation has made remarkable progress. However, most existing work focuses on designing intricate...
-
Real-time traffic sign detection model based on multi-branch convolutional reparameterization
Intelligent detection of traffic signs has great potential in autonomous driving. Certain elements can make the detection difficult. In the road...
-
A Method for Small Object Contamination Detection of Lentinula Edodes Logs Integrating SPD-Conv and Structural Reparameterization
A small object contamination detection method (SRW-YOLO) integrating SPD-Conv and structural reparameterization was proposed to address the problem...
-
Differentiable Feature Selection, A Reparameterization Approach
We consider the task of feature selection for reconstruction which consists in choosing a small subset of features from which whole data instances...
-
An Improved YOLOv5 with Structural Reparameterization for Surface Defect Detection
Surface defects produced by the manufacturing process directly degrades the quality of industrial materials such as hot-rolled steel. However,...
-
Implicitly adaptive optimal proposal in variational inference for Bayesian learning
Overdispersed black-box variational inference uses importance sampling to decrease the variance of the Monte Carlo gradient in variational inference....
-
RDPNet: a single-path lightweight CNN with re-parameterization for CPU-type edge devices
Deep convolutional neural networks have produced excellent results when utilized for image classification tasks, and they are being applied in a...
-
PiDiNeXt: An Efficient Edge Detector Based on Parallel Pixel Difference Networks
The Pixel Difference Network (PiDiNet) is well-known for its success in edge detection. Combining traditional operators with deep learning, PiDiNet...
-
Auto-encoding score distribution regression for action quality assessment
Assessing the quality of actions in videos is a challenging vision task, as the relationship between videos and action scores can be difficult to...
-
A Closer Look at Few-Shot Object Detection
Few-shot object detection, which aims to detect unseen classes in data-scarce scenarios, remains a challenging task. Most existing works adopt Faster...
-
An adversarial defense algorithm based on robust U-net
Due to the continuous development of neural network technology, it has been widely applied in fields such as autonomous driving and biomedicine....
-
Forecasting VIX using Bayesian deep learning
Recently, deep learning techniques are gradually replacing traditional statistical and machine learning models as the first choice for price...
-
Stable local interpretable model-agnostic explanations based on a variational autoencoder
For humans to trust in artificial intelligence (AI) systems, it is essential for machine learning (ML) models to be interpretable to users. For...
-
Flow-Based End-to-End Model for Hierarchical Time Series Forecasting via Trainable Attentive-Reconciliation
Time Series (TS) is one of the most common data formats in modern world, which often takes hierarchical structures, and is normally complicated with...
-
Temporal Alignment of Human Motion Data: A Geometric Point of View
Temporal alignment is an inherent task in most applications dealing with videos: action recognition, motion transfer, virtual trainers,...
-
Performance Modelling-Driven Optimization of RISC-V Hardware for Efficient SpMV
The growing need for inference on edge devices brings with it a necessity for efficient hardware, optimized for particular computational kernels,...
-
Small object Lentinula Edodes logs contamination detection method based on improved YOLOv7 in edge-cloud computing
A small object Lentinus Edodes logs contamination detection method (SRW-YOLO) based on improved YOLOv7 in edge-cloud computing environment was...
-
Applying Kumaraswamy distribution on stick-breaking process: a Dirichlet neural topic model approach
In recent years, neural topic modeling has increasingly raised extensive attention due to its capacity on generating coherent topics and flexible...
-
Direct Evolutionary Optimization of Variational Autoencoders with Binary Latents
Many types of data are generated at least partly by discrete causes. Deep generative models such as variational autoencoders (VAEs) with binary...