paper-with-me

Papers

Wavelet Pooling for Convolutional Neural Networks

2018-01-01 · ICLR 2018 1 · Travis Williams, Robert Li

Convolutional Neural Networks continuously advance the progress of 2D and 3D image and object classification. The steadfast usage of this algorithm requires constant evaluation and upgrading of foundational concepts to maintain progress. Network regularization techniques typically focus on convolutional layer operations, while leaving pooling layer operations without suitable options. We introduce Wavelet Pooling as another alternative to traditional neighborhood pooling. This method decomposes features into a second level decomposition, and discards the first-level subbands to reduce feature dimensions. This method addresses the overfitting problem encountered by max pooling, while reducing features in a more structurally compact manner than pooling via neighborhood regions. Experimental results on four benchmark classification datasets demonstrate our proposed method outperforms or performs comparatively with methods like max, mean, mixed, and stochastic pooling.

📄 PDF Abstract BibTeX

Code (1)

Fraunhofer-SCAI/wavelet_pooling pytorch

Tasks

General Classification

Similar Papers 제목 키워드 기반

Learnable Discrete Wavelet Pooling (LDW-Pooling) For Convolutional Networks

2021-09-13 · Bor-Shiun Wang, Jun-Wei Hsieh, Ming-Ching Chang, Ping-Yang Chen 외

Pooling is a simple but essential layer in modern deep CNN architectures for feature aggregation and extraction. Typical CNN design focuses on the conv layers and activation functions, while leaving the pooling layers wi…

Detailed Dense Inference with Convolutional Neural Networks via Discrete Wavelet Transform

2018-08-06 · Lingni Ma, Jörg Stückler, Tao Wu, Daniel Cremers

Dense pixelwise prediction such as semantic segmentation is an up-to-date challenge for deep convolutional neural networks (CNNs). Many state-of-the-art approaches either tackle the loss of high-resolution information du…

DecoderSemantic Segmentation

DC-WCNN: A deep cascade of wavelet based convolutional neural networks for MR Image Reconstruction

2020-01-08 · Sriprabha Ramanarayanan, Balamurali Murugesan, Keerthi Ram, Mohanasankar Sivaprakasam

Several variants of Convolutional Neural Networks (CNN) have been developed for Magnetic Resonance (MR) image reconstruction. Among them, U-Net has shown to be the baseline architecture for MR image reconstruction. Howev…

DecoderImage Reconstruction

Multi-level Wavelet Convolutional Neural Networks

2019-07-06 · Pengju Liu, Hongzhi Zhang, Wei Lian, WangMeng Zuo

In computer vision, convolutional networks (CNNs) often adopts pooling to enlarge receptive field which has the advantage of low computational complexity. However, pooling can cause information loss and thus is detriment…

Computational EfficiencyDenoisingImage DenoisingImage Restoration+2

Exploring Novel Pooling Strategies for Edge Preserved Feature Maps in Convolutional Neural Networks

2021-10-17 · Adithya Sineesh, Mahesh Raveendranatha Panicker

With the introduction of anti-aliased convolutional neural networks (CNN), there has been some resurgence in relooking the way pooling is done in CNNs. The fundamental building block of the anti-aliased CNN has been the …

Segmentation