Weight mechanism: adding a constant in concatenation of series connect
- URL: http://arxiv.org/abs/2003.03500v2
- Date: Wed, 18 Nov 2020 13:47:43 GMT
- Title: Weight mechanism: adding a constant in concatenation of series connect
- Authors: Xiaojie Qi
- Abstract summary: We propose a method named weight mechanism to reduce the gap between feature maps in concatenation of series connection.
Specifically, we design a new architecture named fused U-Net to test weight mechanism, and it also gains 0.12% mIoU improvement.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: It is a consensus that feature maps in the shallow layer are more related to
image attributes such as texture and shape, whereas abstract semantic
representation exists in the deep layer. Meanwhile, some image information will
be lost in the process of the convolution operation. Naturally, the direct
method is combining them together to gain lost detailed information through
concatenation or adding. In fact, the image representation flowed in feature
fusion can not match with the semantic representation completely, and the
semantic deviation in different layers also destroy the information
purification, that leads to useless information being mixed into the fusion
layers. Therefore, it is crucial to narrow the gap among the fused layers and
reduce the impact of noises during fusion. In this paper, we propose a method
named weight mechanism to reduce the gap between feature maps in concatenation
of series connection, and we get a better result of 0.80% mIoU improvement on
Massachusetts building dataset by changing the weight of the concatenation of
series connection in residual U-Net. Specifically, we design a new architecture
named fused U-Net to test weight mechanism, and it also gains 0.12% mIoU
improvement.
Related papers
- Fusion from Decomposition: A Self-Supervised Approach for Image Fusion and Beyond [74.96466744512992]
The essence of image fusion is to integrate complementary information from source images.
DeFusion++ produces versatile fused representations that can enhance the quality of image fusion and the effectiveness of downstream high-level vision tasks.
arXiv Detail & Related papers (2024-10-16T06:28:49Z) - Mutual-Guided Dynamic Network for Image Fusion [51.615598671899335]
We propose a novel mutual-guided dynamic network (MGDN) for image fusion, which allows for effective information utilization across different locations and inputs.
Experimental results on five benchmark datasets demonstrate that our proposed method outperforms existing methods on four image fusion tasks.
arXiv Detail & Related papers (2023-08-24T03:50:37Z) - A Task-guided, Implicitly-searched and Meta-initialized Deep Model for
Image Fusion [69.10255211811007]
We present a Task-guided, Implicit-searched and Meta- generalizationd (TIM) deep model to address the image fusion problem in a challenging real-world scenario.
Specifically, we propose a constrained strategy to incorporate information from downstream tasks to guide the unsupervised learning process of image fusion.
Within this framework, we then design an implicit search scheme to automatically discover compact architectures for our fusion model with high efficiency.
arXiv Detail & Related papers (2023-05-25T08:54:08Z) - A Mountain-Shaped Single-Stage Network for Accurate Image Restoration [9.431709365739462]
In image restoration, it is typically necessary to maintain a complex balance between spatial details and contextual information.
We propose a single-stage design base on a simple U-Net architecture, which removes or replaces unnecessary nonlinear activation functions.
Our approach, named as M3SNet, outperforms previous state-of-the-art models while using less than half the computational costs.
arXiv Detail & Related papers (2023-05-09T03:18:35Z) - LRRNet: A Novel Representation Learning Guided Fusion Network for
Infrared and Visible Images [98.36300655482196]
We formulate the fusion task mathematically, and establish a connection between its optimal solution and the network architecture that can implement it.
In particular we adopt a learnable representation approach to the fusion task, in which the construction of the fusion network architecture is guided by the optimisation algorithm producing the learnable model.
Based on this novel network architecture, an end-to-end lightweight fusion network is constructed to fuse infrared and visible light images.
arXiv Detail & Related papers (2023-04-11T12:11:23Z) - CoCoNet: Coupled Contrastive Learning Network with Multi-level Feature
Ensemble for Multi-modality Image Fusion [72.8898811120795]
We propose a coupled contrastive learning network, dubbed CoCoNet, to realize infrared and visible image fusion.
Our method achieves state-of-the-art (SOTA) performance under both subjective and objective evaluation.
arXiv Detail & Related papers (2022-11-20T12:02:07Z) - Integrative Feature and Cost Aggregation with Transformers for Dense
Correspondence [63.868905184847954]
The current state-of-the-art are Transformer-based approaches that focus on either feature descriptors or cost volume aggregation.
We propose a novel Transformer-based network that interleaves both forms of aggregations in a way that exploits their complementary information.
We evaluate the effectiveness of the proposed method on dense matching tasks and achieve state-of-the-art performance on all the major benchmarks.
arXiv Detail & Related papers (2022-09-19T03:33:35Z) - Semantic Image Fusion [2.4366811507669124]
This paper proposes a novel system for the semantic combination of visual content using pre-trained CNN network architectures.
Simple "choose maximum" and "local majority" filter based fusion rules are utilised for feature map fusion.
The developed methods are able to give equivalent low-level fusion performance to state of the art methods.
arXiv Detail & Related papers (2021-10-13T13:15:16Z) - Image deblurring based on lightweight multi-information fusion network [6.848061582669787]
We propose a lightweight multiinformation fusion network (LMFN) for image deblurring.
In the encoding stage, the image feature is reduced to various smallscale spaces for multi-scale information extraction and fusion.
Then, a distillation network is used in the decoding stage, which allows the network benefit the most from residual learning.
Our network can achieve state-of-the-art image deblurring result with smaller number of parameters and outperforms existing methods in model complexity.
arXiv Detail & Related papers (2021-01-14T00:37:37Z)
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.