Search Results for author:
Found 13 papers, 3 papers with code
Scalability in Building Component Data Annotation: Enhancing Facade Material Classification with Synthetic Data
Computer vision models trained on Google Street View images can create material cadastres.
Domain Generalization through Meta-Learning: A Survey
Deep neural networks (DNNs) have revolutionized artificial intelligence but often lack performance when faced with out-of-distribution (OOD) data, a common scenario due to the inevitable domain shifts in real-world applications.
A Pre-study on Data Processing Pipelines for Roadside Object Detection Systems Towards Safer Road Infrastructure
Single-vehicle accidents are the most common type of fatal accidents in Sweden, where a car drives off the road and runs into hazardous roadside objects.
Building Efficient CNNs Using Depthwise Convolutional Eigen-Filters (DeCEF)
During the analysis, we observe that the effective rank of the vectorized Conv2D filters decreases with respect to the increasing depth in the network, which then leads to the implementation of the Depthwise Convolutional Eigen-Filter (DeCEF) layer.
Learning Hierarchical Feature Space Using CLAss-specific Subspace Multiple Kernel -- Metric Learning for Classification
An extension to a hierarchical learning structure is also proposed to further improve the classification performance, where on each layer, the CLASMK is computed based on a selected "marginal" subset and feature vectors are constructed by concatenating the features from all previous layers.
SSAP: Single-Shot Instance Segmentation With Affinity Pyramid
Moreover, incorporating with the learned affinity pyramid, a novel cascaded graph partition module is presented to sequentially generate instances from coarse to fine.
Elements of Effective Deep Reinforcement Learning towards Tactical Driving Decision Making
Tactical driving decision making is crucial for autonomous driving systems and has attracted considerable interest in recent years.
Parse Geometry from a Line: Monocular Depth Estimation with Partial Laser Observation
Many standard robotic platforms are equipped with at least a fixed 2D laser range finder and a monocular camera.
A Deep Visual Correspondence Embedding Model for Stereo Matching Costs
This paper presents a data-driven matching cost for stereo matching.
Look and Think Twice: Capturing Top-Down Visual Attention With Feedback Convolutional Neural Networks
While feedforward deep convolutional neural networks (CNNs) have been a great success in computer vision, it is important to remember that the human visual contex contains generally more feedback connections than foward connections.
DenseBox: Unifying Landmark Localization with End to End Object Detection
How can a single fully convolutional neural network (FCN) perform on object detection?
Object Detection by Labeling Superpixels
Object detection is always conducted by object proposal generation and classification sequentially.
Deep Multiple Instance Learning for Image Classification and Auto-Annotation
The recent development in learning deep representations has demonstrated its wide applications in traditional vision tasks like classification and detection.
