Feature Sharing Cooperative Network for Semantic Segmentation
- URL: http://arxiv.org/abs/2101.07905v1
- Date: Wed, 20 Jan 2021 00:22:00 GMT
- Title: Feature Sharing Cooperative Network for Semantic Segmentation
- Authors: Ryota Ikedo, Kazuhiro Hotta
- Abstract summary: We propose a semantic segmentation method using cooperative learning.
By sharing feature maps, one of two networks can obtain the information that cannot be obtained by a single network.
The proposed method achieved better segmentation accuracy than the conventional single network and ensemble of networks.
- Score: 10.305130700118399
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In recent years, deep neural networks have achieved high ac-curacy in the
field of image recognition. By inspired from human learning method, we propose
a semantic segmentation method using cooperative learning which shares the
information resembling a group learning. We use two same networks and paths for
sending feature maps between two networks. Two networks are trained
simultaneously. By sharing feature maps, one of two networks can obtain the
information that cannot be obtained by a single network. In addition, in order
to enhance the degree of cooperation, we propose two kinds of methods that
connect only the same layer and multiple layers. We evaluated our proposed idea
on two kinds of networks. One is Dual Attention Network (DANet) and the other
one is DeepLabv3+. The proposed method achieved better segmentation accuracy
than the conventional single network and ensemble of networks.
Related papers
- Cooperative Learning for Cost-Adaptive Inference [3.301728339780329]
The proposed framework is not tied to any specific architecture but can incorporate any existing models/architectures.
It provides comparable accuracy to its full network while various sizes of models are available.
arXiv Detail & Related papers (2023-12-13T21:42:27Z) - Connections between Operator-splitting Methods and Deep Neural Networks
with Applications in Image Segmentation [7.668812831777923]
How to make connections between deep neural networks and mathematical algorithms is still under development.
We show an algorithmic explanation for deep neural networks, especially in their connections with operator splitting.
We propose two networks inspired by operator-splitting methods solving the Potts model.
arXiv Detail & Related papers (2023-07-18T08:06:14Z) - Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural
Networks [49.808194368781095]
We show that three-layer neural networks have provably richer feature learning capabilities than two-layer networks.
This work makes progress towards understanding the provable benefit of three-layer neural networks over two-layer networks in the feature learning regime.
arXiv Detail & Related papers (2023-05-11T17:19:30Z) - Merging of neural networks [0.0]
We show that training two networks and merging them leads to better performance than training a single network for an extended period of time.
Our procedure might be used as a finalization step after one tries multiple starting seeds to avoid an unlucky one.
arXiv Detail & Related papers (2022-04-21T08:52:54Z) - DIAL: Deep Interactive and Active Learning for Semantic Segmentation in
Remote Sensing [34.209686918341475]
We propose to build up a collaboration between a deep neural network and a human in the loop.
In a nutshell, the agent iteratively interacts with the network to correct its initially flawed predictions.
We show that active learning based on uncertainty estimation enables to quickly lead the user towards mistakes.
arXiv Detail & Related papers (2022-01-04T09:11:58Z) - Unsupervised Domain-adaptive Hash for Networks [81.49184987430333]
Domain-adaptive hash learning has enjoyed considerable success in the computer vision community.
We develop an unsupervised domain-adaptive hash learning method for networks, dubbed UDAH.
arXiv Detail & Related papers (2021-08-20T12:09:38Z) - CRNet: Cross-Reference Networks for Few-Shot Segmentation [59.85183776573642]
Few-shot segmentation aims to learn a segmentation model that can be generalized to novel classes with only a few training images.
With a cross-reference mechanism, our network can better find the co-occurrent objects in the two images.
Experiments on the PASCAL VOC 2012 dataset show that our network achieves state-of-the-art performance.
arXiv Detail & Related papers (2020-03-24T04:55:43Z) - Data-Free Knowledge Amalgamation via Group-Stack Dual-GAN [80.17705319689139]
We propose a data-free knowledge amalgamate strategy to craft a well-behaved multi-task student network from multiple single/multi-task teachers.
The proposed method without any training data achieves the surprisingly competitive results, even compared with some full-supervised methods.
arXiv Detail & Related papers (2020-03-20T03:20:52Z) - Weakly-Supervised Semantic Segmentation by Iterative Affinity Learning [86.45526827323954]
Weakly-supervised semantic segmentation is a challenging task as no pixel-wise label information is provided for training.
We propose an iterative algorithm to learn such pairwise relations.
We show that the proposed algorithm performs favorably against the state-of-the-art methods.
arXiv Detail & Related papers (2020-02-19T10:32:03Z) - Feature-map-level Online Adversarial Knowledge Distillation [36.42703358752526]
We propose an online knowledge distillation method that transfers not only the knowledge of the class probabilities but also that of the feature map.
We train multiple networks simultaneously by employing discriminators to distinguish the feature map distributions of different networks.
We show that our method performs better than the conventional direct alignment method such as L1 and is more suitable for online distillation.
arXiv Detail & Related papers (2020-02-05T13:16:37Z) - Unpaired Multi-modal Segmentation via Knowledge Distillation [77.39798870702174]
We propose a novel learning scheme for unpaired cross-modality image segmentation.
In our method, we heavily reuse network parameters, by sharing all convolutional kernels across CT and MRI.
We have extensively validated our approach on two multi-class segmentation problems.
arXiv Detail & Related papers (2020-01-06T20:03:17Z)
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.