A Novel Learnable Orthogonal Wavelet Unit Neural Network with Perfection Reconstruction Constraint Relaxation for Image Classification
Year: 2023
Type: conference-paper
Abstract: CNNs utilize lowpass frequency features, evidenced by max pooling operations that preserve dominant features. Addressing this, we used a one-layer FCN using both coarse and detailed components via DWT. We then developed UwU, a learnable wavelet-based unit that integrates the PR constraint relaxation, allowing feature map component fine-tuning. Distinctively, UwU’s coefficients are trainable, unlike prior studies. This is the first work that utilizes PR constraint relaxation to enhance CNNs. Our innovative techniques serve to enhance stride-convolution, pooling, and downsampling units in CNNs. We tested these improved units using the ResNet family architectures against traditional frequency and wavelet-based units. Performance metrics from CIFAR10, ImageNet1K, and the DTD show promising results. Particularly, while CIFAR10 results are on par with other methods, there’s a marked performance improvement on ImageNet1K and DTD. Further, integrating UwU into the ResNet18-based encoder of the CFLOW-AD system yields competitive anomaly detection results, particularly for hazelnut images in the MVTecAD dataset.
Authors: An D Le, Shiwei Jin, You Suk Bae, Truong Nguyen
Institutions: University of California San Diego, Tech University of Korea
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4391306365