Towards Bi-directional Skip Connections in Encoder-Decoder Architectures
and Beyond
- URL: http://arxiv.org/abs/2203.05709v1
- Date: Fri, 11 Mar 2022 01:38:52 GMT
- Title: Towards Bi-directional Skip Connections in Encoder-Decoder Architectures
and Beyond
- Authors: Tiange Xiang, Chaoyi Zhang, Xinyi Wang, Yang Song, Dongnan Liu, Heng
Huang, Weidong Cai
- Abstract summary: We propose backward skip connections that bring decoded features back to the encoder.
Our design can be jointly adopted with forward skip connections in any encoder-decoder architecture.
We propose a novel two-phase Neural Architecture Search (NAS) algorithm, namely BiX-NAS, to search for the best multi-scale skip connections.
- Score: 95.46272735589648
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: U-Net, as an encoder-decoder architecture with forward skip connections, has
achieved promising results in various medical image analysis tasks. Many recent
approaches have also extended U-Net with more complex building blocks, which
typically increase the number of network parameters considerably. Such
complexity makes the inference stage highly inefficient for clinical
applications. Towards an effective yet economic segmentation network design, in
this work, we propose backward skip connections that bring decoded features
back to the encoder. Our design can be jointly adopted with forward skip
connections in any encoder-decoder architecture forming a recurrence structure
without introducing extra parameters. With the backward skip connections, we
propose a U-Net based network family, namely Bi-directional O-shape networks,
which set new benchmarks on multiple public medical imaging segmentation
datasets. On the other hand, with the most plain architecture (BiO-Net),
network computations inevitably increase along with the pre-set recurrence
time. We have thus studied the deficiency bottleneck of such recurrent design
and propose a novel two-phase Neural Architecture Search (NAS) algorithm,
namely BiX-NAS, to search for the best multi-scale bi-directional skip
connections. The ineffective skip connections are then discarded to reduce
computational costs and speed up network inference. The finally searched
BiX-Net yields the least network complexity and outperforms other
state-of-the-art counterparts by large margins. We evaluate our methods on both
2D and 3D segmentation tasks in a total of six datasets. Extensive ablation
studies have also been conducted to provide a comprehensive analysis for our
proposed methods.
Related papers
- RC-Net: A Convolutional Neural Network for Retinal Vessel Segmentation [3.0846824529023387]
We present RC-Net, a fully convolutional network, where the number of filters per layer is optimized to reduce feature overlapping and complexity.
In our experiments, RC-Net is quite competitive, outperforming alternatives vessels segmentation methods with two or even three orders of magnitude less trainable parameters.
arXiv Detail & Related papers (2021-12-21T10:24:01Z) - PDFNet: Pointwise Dense Flow Network for Urban-Scene Segmentation [0.0]
We propose a novel lightweight architecture named point-wise dense flow network (PDFNet)
In PDFNet, we employ dense, residual, and multiple shortcut connections to allow a smooth gradient flow to all parts of the network.
Our method significantly outperforms baselines in capturing small classes and in few-data regimes.
arXiv Detail & Related papers (2021-09-21T10:39:46Z) - BiX-NAS: Searching Efficient Bi-directional Architecture for Medical
Image Segmentation [85.0444711725392]
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 the network computational cost by sifting out ineffective multi-scale features at different levels and iterations.
We evaluate BiX-NAS on two segmentation tasks using three different medical image datasets, and the experimental results show that our BiX-NAS searched architecture achieves the state-of-the-art performance with significantly lower computational cost.
arXiv Detail & Related papers (2021-06-26T14:33:04Z) - Hierarchical Neural Architecture Search for Deep Stereo Matching [131.94481111956853]
We propose the first end-to-end hierarchical NAS framework for deep stereo matching.
Our framework incorporates task-specific human knowledge into the neural architecture search framework.
It is ranked at the top 1 accuracy on KITTI stereo 2012, 2015 and Middlebury benchmarks, as well as the top 1 on SceneFlow dataset.
arXiv Detail & Related papers (2020-10-26T11:57:37Z) - Suppress and Balance: A Simple Gated Network for Salient Object
Detection [89.88222217065858]
We propose a simple gated network (GateNet) to solve both issues at once.
With the help of multilevel gate units, the valuable context information from the encoder can be optimally transmitted to the decoder.
In addition, we adopt the atrous spatial pyramid pooling based on the proposed "Fold" operation (Fold-ASPP) to accurately localize salient objects of various scales.
arXiv Detail & Related papers (2020-07-16T02:00:53Z) - Neural Architecture Optimization with Graph VAE [21.126140965779534]
We propose an efficient NAS approach to optimize network architectures in a continuous space.
The framework jointly learns four components: the encoder, the performance predictor, the complexity predictor and the decoder.
arXiv Detail & Related papers (2020-06-18T07:05:48Z) - Fitting the Search Space of Weight-sharing NAS with Graph Convolutional
Networks [100.14670789581811]
We train a graph convolutional network to fit the performance of sampled sub-networks.
With this strategy, we achieve a higher rank correlation coefficient in the selected set of candidates.
arXiv Detail & Related papers (2020-04-17T19:12:39Z) - Toward fast and accurate human pose estimation via soft-gated skip
connections [97.06882200076096]
This paper is on highly accurate and highly efficient human pose estimation.
We re-analyze this design choice in the context of improving both the accuracy and the efficiency over the state-of-the-art.
Our model achieves state-of-the-art results on the MPII and LSP datasets.
arXiv Detail & Related papers (2020-02-25T18:51:51Z) - Exploring the Connection Between Binary and Spiking Neural Networks [1.329054857829016]
We bridge the recent algorithmic progress in training Binary Neural Networks and Spiking Neural Networks.
We show that training Spiking Neural Networks in the extreme quantization regime results in near full precision accuracies on large-scale datasets.
arXiv Detail & Related papers (2020-02-24T03:46:51Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.