Deep Image Translation with an Affinity-Based Change Prior for
Unsupervised Multimodal Change Detection
- URL: http://arxiv.org/abs/2001.04271v2
- Date: Mon, 8 Mar 2021 13:57:53 GMT
- Title: Deep Image Translation with an Affinity-Based Change Prior for
Unsupervised Multimodal Change Detection
- Authors: Luigi Tommaso Luppino, Michael Kampffmeyer, Filippo Maria Bianchi,
Gabriele Moser, Sebastiano Bruno Serpico, Robert Jenssen, and Stian Normann
Anfinsen
- Abstract summary: We propose two new network architectures trained with loss functions weighted by priors that reduce the impact of change pixels on the learning objective.
The proposed neural networks are compared with state-of-the-art algorithms.
- Score: 20.485370285874613
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Image translation with convolutional neural networks has recently been used
as an approach to multimodal change detection. Existing approaches train the
networks by exploiting supervised information of the change areas, which,
however, is not always available. A main challenge in the unsupervised problem
setting is to avoid that change pixels affect the learning of the translation
function. We propose two new network architectures trained with loss functions
weighted by priors that reduce the impact of change pixels on the learning
objective. The change prior is derived in an unsupervised fashion from
relational pixel information captured by domain-specific affinity matrices.
Specifically, we use the vertex degrees associated with an absolute affinity
difference matrix and demonstrate their utility in combination with cycle
consistency and adversarial training. The proposed neural networks are compared
with state-of-the-art algorithms. Experiments conducted on three real datasets
show the effectiveness of our methodology.
Related papers
- Deep Multi-Threshold Spiking-UNet for Image Processing [51.88730892920031]
This paper introduces the novel concept of Spiking-UNet for image processing, which combines the power of Spiking Neural Networks (SNNs) with the U-Net architecture.
To achieve an efficient Spiking-UNet, we face two primary challenges: ensuring high-fidelity information propagation through the network via spikes and formulating an effective training strategy.
Experimental results show that, on image segmentation and denoising, our Spiking-UNet achieves comparable performance to its non-spiking counterpart.
arXiv Detail & Related papers (2023-07-20T16:00:19Z) - Scene Change Detection Using Multiscale Cascade Residual Convolutional
Neural Networks [0.0]
Scene change detection is an image processing problem related to partitioning pixels of a digital image into foreground and background regions.
In this work, we propose a novel Multiscale Residual Processing Module, with a Convolutional Neural Network that integrates a Residual Processing Module.
Experiments conducted on two different datasets support the overall effectiveness of the proposed approach, achieving an average overall effectiveness of $boldsymbol0.9622$ and $boldsymbol0.9664$ over Change Detection 2014 and PetrobrasROUTES datasets respectively.
arXiv Detail & Related papers (2022-12-20T16:48:51Z) - A Perturbation Resistant Transformation and Classification System for
Deep Neural Networks [0.685316573653194]
Deep convolutional neural networks accurately classify a diverse range of natural images, but may be easily deceived when designed.
In this paper, we design a multi-pronged training, unbounded input transformation, and image ensemble system that is attack and not easily estimated.
arXiv Detail & Related papers (2022-08-25T02:58:47Z) - dual unet:a novel siamese network for change detection with cascade
differential fusion [4.651756476458979]
We propose a novel Siamese neural network for change detection task, namely Dual-UNet.
In contrast to previous individually encoded the bitemporal images, we design an encoder differential-attention module to focus on the spatial difference relationships of pixels.
Experiments demonstrate that the proposed approach consistently outperforms the most advanced methods on popular seasonal change detection datasets.
arXiv Detail & Related papers (2022-08-12T14:24:09Z) - Interpolation-based Correlation Reduction Network for Semi-Supervised
Graph Learning [49.94816548023729]
We propose a novel graph contrastive learning method, termed Interpolation-based Correlation Reduction Network (ICRN)
In our method, we improve the discriminative capability of the latent feature by enlarging the margin of decision boundaries.
By combining the two settings, we extract rich supervision information from both the abundant unlabeled nodes and the rare yet valuable labeled nodes for discnative representation learning.
arXiv Detail & Related papers (2022-06-06T14:26:34Z) - Learning Discriminative Shrinkage Deep Networks for Image Deconvolution [122.79108159874426]
We propose an effective non-blind deconvolution approach by learning discriminative shrinkage functions to implicitly model these terms.
Experimental results show that the proposed method performs favorably against the state-of-the-art ones in terms of efficiency and accuracy.
arXiv Detail & Related papers (2021-11-27T12:12:57Z) - Joint Learning of Neural Transfer and Architecture Adaptation for Image
Recognition [77.95361323613147]
Current state-of-the-art visual recognition systems rely on pretraining a neural network on a large-scale dataset and finetuning the network weights on a smaller dataset.
In this work, we prove that dynamically adapting network architectures tailored for each domain task along with weight finetuning benefits in both efficiency and effectiveness.
Our method can be easily generalized to an unsupervised paradigm by replacing supernet training with self-supervised learning in the source domain tasks and performing linear evaluation in the downstream tasks.
arXiv Detail & Related papers (2021-03-31T08:15:17Z) - Encoding Robustness to Image Style via Adversarial Feature Perturbations [72.81911076841408]
We adapt adversarial training by directly perturbing feature statistics, rather than image pixels, to produce robust models.
Our proposed method, Adversarial Batch Normalization (AdvBN), is a single network layer that generates worst-case feature perturbations during training.
arXiv Detail & Related papers (2020-09-18T17:52:34Z) - Code-Aligned Autoencoders for Unsupervised Change Detection in
Multimodal Remote Sensing Images [18.133760118780128]
Image translation with convolutional autoencoders has recently been used as an approach to multimodal change detection in bitemporal satellite images.
A main challenge is the alignment of the code spaces by reducing the contribution of change pixels to the learning of the translation function.
We propose to extract relational pixel information captured by domain-specific affinity matrices at the input and use this to enforce alignment of the code spaces.
arXiv Detail & Related papers (2020-04-15T11:24:51Z) - From W-Net to CDGAN: Bi-temporal Change Detection via Deep Learning
Techniques [43.58400031452662]
We propose an end-to-end dual-branch architecture termed as the W-Net, with each branch taking as input one of the two bi-temporal images.
We also apply the recently popular Generative Adversarial Network (GAN) in which our W-Net serves as the Generator.
To train our networks and also facilitate future research, we construct a large scale dataset by collecting images from Google Earth.
arXiv Detail & Related papers (2020-03-14T09:24:08Z) - CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistency [119.45667331836583]
Unsupervised domain adaptation algorithms aim to transfer the knowledge learned from one domain to another.
We present a novel pixel-wise adversarial domain adaptation algorithm.
arXiv Detail & Related papers (2020-01-09T19:00:35Z)
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.