RIC-CNN: Rotation-Invariant Coordinate Convolutional Neural Network
Due to the lack of rotation invariance in traditional convolution operations, even acting a slight rotation on the input can severely degrade […]
Lightweight Pixel Difference Networks for Efficient Visual Representation Learning
Recently, there have been tremendous efforts in developing lightweight Deep Neural Networks (DNNs) with satisfactory accuracy, which can enable the ubiquitous deployment […]
Domain Knowledge Powered Two-Stream Deep Network for Few-Shot SAR Vehicle Recognition
Synthetic aperture radar (SAR) target recognition faces the challenge that there are very little labeled data. Although few-shot learning methods are developed […]
Rank-Pooling-Based Features on Localized Regions for Automatic Micro-Expression Recognition
Facial micro-expression is a subtle and involuntary facial expression that exhibits short duration and low intensity where hidden feelings can be disclosed. […]
A Class Imbalance Loss for Imbalanced Object Recognition
The class imbalance problem exists widely in vision data. In these imbalanced datasets, the majority classes dominate the loss and influence the […]
DCNN based Real-time Adaptive Ship License Plate Recognition (DRASLPR)
Ship license plate recognition is challenging due to the diversity of plate locations and text types. This paper proposes a DCNN-based (deep […]