paper-with-me

Papers

Global Adaptive Filtering Layer for Computer Vision

2020-10-02 · Viktor Shipitsin, Iaroslav Bespalov, Dmitry V. Dylov

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.

📄 PDF Abstract BibTeX arXiv:2010.01177

Code (0)

등록된 구현이 없습니다.

Tasks

Denoising

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Concatenated Skip Connection A Concatenated Skip Connection is a type of skip connection that seeks to reuse features by concatenating them to new layers, allowing more information to be retained from…
U-Net 설명 없음

Similar Papers 제목 키워드 기반

Pixel Adaptive Filtering Units

2019-11-24 · Filippos Kokkinos, Ioannis Marras, Matteo Maggioni, Gregory Slabaugh 외

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…

Translation

Adaptive Frequency Filters As Efficient Global Token Mixers

2023-07-26 · ICCV 2023 1 · Zhipeng Huang, Zhizheng Zhang, Cuiling Lan, Zheng-Jun Zha 외

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

2011-06-15 · Springer-Verlag Berlin Heidelberg 2011 6 · Cuong Cao Pham, Synh Viet Uyen Ha, and Jae Wook Jeon.

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

2023-03-22 · Anahita Nekoozadeh, Mohammad Reza Ahmadzadeh, Zahra Mardani

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 learning

Enhancing Transformer-Based Vision Models: Addressing Feature Map Anomalies Through Novel Optimization Strategies

2025-09-24 · Sumit Mamtani arxiv

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