Global Adaptive Filtering Layer for Computer Vision
We devise a universal adaptive neural layer to "learn" optimal frequency filter for each image together with the weights of the base neural network that performs some computer vision task. The proposed approach takes the source image in the spatial domain, automatically selects the best frequencies from the frequency domain, and transmits the inverse-transform image to the main neural network. Remarkably, such a simple add-on layer dramatically improves the performance of the main network regardless of its design. We observe that the light networks gain a noticeable boost in the performance metrics; whereas, the training of the heavy ones converges faster when our adaptive layer is allowed to "learn" alongside the main architecture. We validate the idea in four classical computer vision tasks: classification, segmentation, denoising, and erasing, considering popular natural and medical data benchmarks.
Code (0)
등록된 구현이 없습니다.
Tasks
DenoisingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Pixel Adaptive Filtering Units
State-of-the-art methods for computer vision rely heavily on the translation equivariance and spatial sharing properties of convolutional layers without explicitly taking into consideration the input content. Modern tech…
TranslationAdaptive Frequency Filters As Efficient Global Token Mixers
Recent vision transformers, large-kernel CNNs and MLPs have attained remarkable successes in broad vision tasks thanks to their effective information fusion in the global scope. However, their efficient deployments, espe…
Adaptive Guided Image Filtering for Sharpness Enhancement and Noise Reduction
Sharpness enhancement and noise reduction play crucial roles in computer vision and image processing. The problem is to enhance the appearance and reduce the noise of the digital images without causing halo artifacts.…
Multiscale Attention via Wavelet Neural Operators for Vision Transformers
Transformers have achieved widespread success in computer vision. At their heart, there is a Self-Attention (SA) mechanism, an inductive bias that associates each token in the input with every other token through a weigh…
Inductive BiasOperator learningEnhancing Transformer-Based Vision Models: Addressing Feature Map Anomalies Through Novel Optimization Strategies
Vision Transformers (ViTs) have demonstrated superior performance across a wide range of computer vision tasks. However, structured noise artifacts in their feature maps hinder downstream applications such as segmentatio…
Depth Estimation