Detailed Dense Inference with Convolutional Neural Networks via Discrete Wavelet Transform
원문 초록
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 due to pooling in the encoder stage, or use dilated convolutions or high-resolution lanes to maintain detailed feature maps and predictions. Motivated by the structural analogy between multi-resolution wavelet analysis and the pooling/unpooling layers of CNNs, we introduce discrete wavelet transform (DWT) into the CNN encoder-decoder architecture and propose WCNN. The high-frequency wavelet coefficients are computed at encoder, which are later used at the decoder to unpooled jointly with coarse-resolution feature maps through the inverse DWT. The DWT/iDWT is further used to develop two wavelet pyramids to capture the global context, where the multi-resolution DWT is applied to successively reduce the spatial resolution and increase the receptive field. Experiment with the Cityscape dataset, the proposed WCNNs are computationally efficient and yield improvements the accuracy for high-resolution dense pixelwise prediction.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
LSegDiff: A Latent Diffusion Model for Medical Image Segmentation
DEU-Net: Dual-Encoder U-Net for Automated Skin Lesion Segmentation
SDSC-UNet: Dual Skip Connection ViT-based U-shaped Model for Building Extraction
Crosslink-Net: Double-Branch Encoder Network via Fusing Vertical and Horizontal Convolutions for Medical Image Segmentation
FRNet: Factorized and Regular Blocks Network for Semantic Segmentation in Road Scene
Transformer and CNN Hybrid Deep Neural Network for Semantic Segmentation of Very-High-Resolution Remote Sensing Imagery
토론
이 논문과 연결된 포럼 글이 아직 없습니다.