Deeply Cascaded U-Net for Multi-Task Image Processing
In current practice, many image processing tasks are done sequentially (e.g. denoising, dehazing, followed by semantic segmentation). In this paper, we propose a novel multi-task neural network architecture designed for combining sequential image processing tasks. We extend U-Net by additional decoding pathways for each individual task, and explore deep cascading of outputs and connectivity from one pathway to another. We demonstrate effectiveness of the proposed approach on denoising and semantic segmentation, as well as on progressive coarse-to-fine semantic segmentation, and achieve better performance than multiple individual or jointly-trained networks, with lower number of trainable parameters.
Code (0)
등록된 구현이 없습니다.
Tasks
DenoisingSegmentationSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Efficient Human Pose Estimation by Learning Deeply Aggregated Representations
In this paper, we propose an efficient human pose estimation network (DANet) by learning deeply aggregated representations. Most existing models explore multi-scale information mainly from features with different spatial…
CPUPose EstimationCACFNet: Cross-Modal Attention Cascaded Fusion Network for RGB-T Urban Scene Parsing
Color–thermal (RGB-T) urban scene parsing has recently attracted widespread interest. However, most existing approaches to RGB-T urban scene parsing do not deeply explore the information complementarity between RGB-T fea…
Scene ParsingThermal Image SegmentationMerging-ISP: Multi-Exposure High Dynamic Range Image Signal Processing
High dynamic range (HDR) imaging combines multiple images with different exposure times into a single high-quality image. The image signal processing pipeline (ISP) is a core component in digital cameras to perform these…
DemosaickingVocal Bursts Intensity PredictionHard-Aware Deeply Cascaded Embedding
Riding on the waves of deep neural networks, deep metric learning has also achieved promising results in various tasks using triplet network or Siamese network. Though the basic goal of making images from the same catego…
Metric LearningTripletReal-time interactive magnetic resonance (MR) temperature imaging in both aqueous and adipose tissues using cascaded deep neural networks for MR-guided focused ultrasound surgery (MRgFUS)
Purpose: To acquire the real-time interactive temperature map for aqueous and adipose tissue, the problems of long acquisition and processing time must be addressed. To overcome these major challenges, this paper propose…
Image Reconstruction