首页/论文/2002.11581

arXiv 2002.115812020-02-26eess.IVcs.CV

Automatically Searching for U-Net Image Translator Architecture

Huawei Noah’s Ark Lab（华为诺亚方舟实验室）

Han Shu, Yunhe Wang

英文摘要：

Image translators have been successfully applied to many important low level image processing tasks. However, classical network architecture of image translator like U-Net, is borrowed from other vision tasks like biomedical image segmentation. This straightforward adaptation may not be optimal and could cause redundancy in the network structure. In this paper, we propose an automatic architecture searching method for image translator. By utilizing evolutionary algorithm, we investigate a more efficient network architecture which costs less computation resources and achieves better performance than the original one. Extensive qualitative and quantitative experiments are conducted to demonstrate the effectiveness of the proposed method. Moreover, we transplant the searched network architecture to other datasets which are not involved in the architecture searching procedure. Efficiency of the searched architecture on these datasets further demonstrates the generalization of the method.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

BiX-NAS: Searching Efficient Bi-directional Architecture for Medical Image Segmentation

University of Sydney（悉尼大学）；University of New South Wales（新南威尔士大学）；University of Pittsburgh（匹兹堡大学）；JD Finance America Corporation（京东金融美国公司）

The recurrent mechanism has recently been introduced into U-Net in various medical image segmentation tasks. Existing studies have focused on promoting network recursion via reusing building blocks. Although network parameters could be greatly saved, computational costs still increase inevitably in accordance with the pre-set iteration time. In this work, we study a multi-scale upgrade of a bi-directional skip connected network and then automatically discover an efficient architecture by a novel two-phase Neural Architecture Search (NAS) algorithm, namely BiX-NAS. Our proposed method reduces t…

2021-07-01cs.CVeess.IV

Searching Learning Strategy with Reinforcement Learning for 3D Medical Image Segmentation

NVIDIA（英伟达）

Deep neural network (DNN) based approaches have been widely investigated and deployed in medical image analysis. For example, fully convolutional neural networks (FCN) achieve the state-of-the-art performance in several applications of 2D/3D medical image segmentation. Even the baseline neural network models (U-Net, V-Net, etc.) have been proven to be very effective and efficient when the training process is set up properly. Nevertheless, to fully exploit the potentials of neural networks, we propose an automated searching approach for the optimal training strategy with reinforcement learning.…

2020-06-10cs.CV

Coordinate Translator for Learning Deformable Medical Image Registration

Johns Hopkins University（约翰斯·霍普金斯大学）；National Institute on Aging（国家老龄化研究所）；National Institute of Health（美国国立卫生研究院）

The majority of deep learning (DL) based deformable image registration methods use convolutional neural networks (CNNs) to estimate displacement fields from pairs of moving and fixed images. This, however, requires the convolutional kernels in the CNN to not only extract intensity features from the inputs but also understand image coordinate systems. We argue that the latter task is challenging for traditional CNNs, limiting their performance in registration tasks. To tackle this problem, we first introduce Coordinate Translator, a differentiable module that identifies matched features between…

2022-07-31cs.CVeess.IV

PTSR：用于图像超分辨率的块翻译器

PTSR: Patch Translator for Image Super-Resolution

Indian Institute of Information Technology Allahabad（印度阿拉哈巴德信息技术学院）

针对图像超分辨率中transformer仍依赖卷积的问题，提出无卷积的基于transformer的GAN网络PTSR，通过多头注意力生成改进块，在多个基准上显著提升4倍超分辨率性能。

2023-10-20cs.CVeess.IV

Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentation

Tsinghua University（清华大学）；SenseTime Research（商汤科技研究院）；The Chinese University of Hong Kong（香港中文大学）；Qing Yuan Research Institute, Shanghai Jiao Tong University（上海交通大学清源研究院）

Designing proper loss functions is essential in training deep networks. Especially in the field of semantic segmentation, various evaluation metrics have been proposed for diverse scenarios. Despite the success of the widely adopted cross-entropy loss and its variants, the mis-alignment between the loss functions and evaluation metrics degrades the network performance. Meanwhile, manually designing loss functions for each specific metric requires expertise and significant manpower. In this paper, we propose to automate the design of metric-specific loss functions by searching differentiable su…

2020-12-03cs.CV

FasterSeg: Searching for Faster Real-time Semantic Segmentation

Horizon Robotics Inc.（地平线机器人公司）；Texas A&M University（德克萨斯农工大学）

We present FasterSeg, an automatically designed semantic segmentation network with not only state-of-the-art performance but also faster speed than current methods. Utilizing neural architecture search (NAS), FasterSeg is discovered from a novel and broader search space integrating multi-resolution branches, that has been recently found to be vital in manually designed segmentation models. To better calibrate the balance between the goals of high accuracy and low latency, we propose a decoupled and fine-grained latency regularization, that effectively overcomes our observed phenomenons that th…

2020-01-16cs.CVcs.LG

更多相关论文收起更多论文

UXNet: Searching Multi-level Feature Aggregation for 3D Medical Image Segmentation

The University of Hong Kong（香港大学）；SenseTime Research（商汤科技研究院）；Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen（香港中文大学深圳大数据研究院）

Aggregating multi-level feature representation plays a critical role in achieving robust volumetric medical image segmentation, which is important for the auxiliary diagnosis and treatment. Unlike the recent neural architecture search (NAS) methods that typically searched the optimal operators in each network layer, but missed a good strategy to search for feature aggregations, this paper proposes a novel NAS method for 3D medical image segmentation, named UXNet, which searches both the scale-wise feature aggregation strategies as well as the block-wise operators in the encoder-decoder network…

2020-09-16cs.CV

面向热红外行人跟踪的轻量级网络架构搜索

Searching a Lightweight Network Architecture for Thermal Infrared Pedestrian Tracking

Qufu Normal University（曲阜师范大学）；Harbin Institute of Technology Shenzhen（哈尔滨工业大学（深圳））

本文针对热红外行人跟踪任务，提出基于单底/双底单元和随机通道选择策略的自动网络架构搜索方法，联合多种损失重训练，得到参数与计算高效的轻量级高性能架构。

2024-09-30cs.CVcs.LG

MixSearch: Searching for Domain Generalized Medical Image Segmentation Architectures

College of Computer Science and Software Engineering（计算机与软件学院）；Tencent Jarvis Lab（腾讯贾维斯实验室）；College of Information Science and Electronic Engineering（信息与电子工程学院）；Zhejiang University（浙江大学）；University of Hong Kong（香港大学）

Considering the scarcity of medical data, most datasets in medical image analysis are an order of magnitude smaller than those of natural images. However, most Network Architecture Search (NAS) approaches in medical images focused on specific datasets and did not take into account the generalization ability of the learned architectures on unseen datasets as well as different domains. In this paper, we address this point by proposing to search for generalizable U-shape architectures on a composited dataset that mixes medical images from multiple segmentation tasks and domains creatively, which …

2021-02-26cs.AIcs.CV

Realistic Endoscopic Image Generation Method Using Virtual-to-real Image-domain Translation

Nagoya University（名古屋大学）；Kyoto Second Red Cross Hospital（京都第二红十字医院）；Sapporo-Minami-Sanjo Hospital（札幌南三条医院）；Sapporo-Kosei General Hospital（札幌厚生综合医院）；Keiwakai Nishioka Hospital（惠和会西冈医院）；National Institute of Informatics（国立信息学研究所）

This paper proposes a realistic image generation method for visualization in endoscopic simulation systems. Endoscopic diagnosis and treatment are performed in many hospitals. To reduce complications related to endoscope insertions, endoscopic simulation systems are used for training or rehearsal of endoscope insertions. However, current simulation systems generate non-realistic virtual endoscopic images. To improve the value of the simulation systems, improvement of reality of their generated images is necessary. We propose a realistic image generation method for endoscopic simulation systems…

2022-01-13cs.CVeess.IV

Searching Efficient Model-guided Deep Network for Image Denoising

Xidian University（西安电子科技大学）；West Virginia University（西弗吉尼亚大学）

Neural architecture search (NAS) has recently reshaped our understanding on various vision tasks. Similar to the success of NAS in high-level vision tasks, it is possible to find a memory and computationally efficient solution via NAS with highly competent denoising performance. However, the optimization gap between the super-network and the sub-architectures has remained an open issue in both low-level and high-level vision. In this paper, we present a novel approach to filling in this gap by connecting model-guided design with NAS (MoD-NAS) and demonstrate its application into image denoisin…

2021-04-06cs.CVeess.IV

Triple-level Model Inferred Collaborative Network Architecture for Video Deraining

Zhejiang University of Technology（浙江工业大学）；Dalian University of Technology（大连理工大学）；Pazhou Lab（琶洲实验室）

Video deraining is an important issue for outdoor vision systems and has been investigated extensively. However, designing optimal architectures by the aggregating model formation and data distribution is a challenging task for video deraining. In this paper, we develop a model-guided triple-level optimization framework to deduce network architecture with cooperating optimization and auto-searching mechanism, named Triple-level Model Inferred Cooperating Searching (TMICS), for dealing with various video rain circumstances. In particular, to mitigate the problem that existing methods cannot cov…

2021-11-08cs.CVeess.IV

LotteryCodec：在随机网络中搜索隐式表征以实现低复杂度图像压缩

LotteryCodec: Searching the Implicit Representation in a Random Network for Low-Complexity Image Compression

本研究提出并验证彩票编解码器假设，据此构建LotteryCodec方法，通过过拟合二值掩码、共享随机初始化网络及回退调制机制，实现优于VTM的单图像压缩性能，还可通过调掩码比例适配不同设备需求。

2025-09-03cs.ITeess.IVmath.IT