UDHF2-Net: An Uncertainty-diffusion-model-based High-Frequency TransFormer Network for High-accuracy Interpretation of Remotely Sensed Imagery
- URL: http://arxiv.org/abs/2406.16129v1
- Date: Sun, 23 Jun 2024 15:03:35 GMT
- Title: UDHF2-Net: An Uncertainty-diffusion-model-based High-Frequency TransFormer Network for High-accuracy Interpretation of Remotely Sensed Imagery
- Authors: Pengfei Zhang, Chang Li, Yongjun Zhang, Rongjun Qin,
- Abstract summary: Uncertainty-diffusion-model-based high-Frequency TransFormer network (UDHF2-Net) is proposed for remotely sensed image high-accuracy interpretation (RSIHI)
- Score: 12.24506241611653
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Remotely sensed image high-accuracy interpretation (RSIHI), including tasks such as semantic segmentation and change detection, faces the three major problems: (1) complementarity problem of spatially stationary-and-non-stationary frequency; (2) edge uncertainty problem caused by down-sampling in the encoder step and intrinsic edge noises; and (3) false detection problem caused by imagery registration error in change detection. To solve the aforementioned problems, an uncertainty-diffusion-model-based high-Frequency TransFormer network (UDHF2-Net) is the proposed for RSIHI, the superiority of which is as following: (1) a spatially-stationary-and-non-stationary high-frequency connection paradigm (SHCP) is proposed to enhance the interaction of spatially stationary and non-stationary frequency features to yield high-fidelity edge extraction result. Inspired by HRFormer, SHCP remains the high-frequency stream through the whole encoder-decoder process with parallel high-to-low frequency streams and reduces the edge loss by a downsampling operation; (2) a mask-and-geo-knowledge-based uncertainty diffusion module (MUDM) is proposed to improve the robustness and edge noise resistance. MUDM could further optimize the uncertain region to improve edge extraction result by gradually removing the multiple geo-knowledge-based noises; (3) a semi-pseudo-Siamese UDHF2-Net for change detection task is proposed to reduce the pseudo change by registration error. It adopts semi-pseudo-Siamese architecture to extract above complemental frequency features for adaptively reducing registration differencing, and MUDM to recover the uncertain region by gradually reducing the registration error besides above edge noises. Comprehensive experiments were performed to demonstrate the superiority of UDHF2-Net. Especially ablation experiments indicate the effectiveness of UDHF2-Net.
Related papers
- Stable Neighbor Denoising for Source-free Domain Adaptive Segmentation [91.83820250747935]
Pseudo-label noise is mainly contained in unstable samples in which predictions of most pixels undergo significant variations during self-training.
We introduce the Stable Neighbor Denoising (SND) approach, which effectively discovers highly correlated stable and unstable samples.
SND consistently outperforms state-of-the-art methods in various SFUDA semantic segmentation settings.
arXiv Detail & Related papers (2024-06-10T21:44:52Z) - A Noise-robust Multi-head Attention Mechanism for Formation Resistivity Prediction: Frequency Aware LSTM [7.466740264582114]
The prediction of formation resistivity plays a crucial role in the evaluation of oil and gas reservoirs.
Traditional well logging techniques fail to measure accurate resistivity in cased boreholes.
A frequency-aware framework and temporal anti-noise block are proposed to build frequency aware LSTM.
arXiv Detail & Related papers (2024-06-06T08:31:52Z) - DenoDet: Attention as Deformable Multi-Subspace Feature Denoising for Target Detection in SAR Images [20.11145540094807]
We propose a network aided by explicit frequency domain transform to calibrate convolutional biases and pay more attention to high-frequencies.
We design TransDeno, a dynamic frequency domain attention module that performs as a transform domain soft thresholding operation.
Our plug-and-play TransDeno sets state-of-the-art scores on multiple SAR target detection datasets.
arXiv Detail & Related papers (2024-06-05T01:05:26Z) - M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoising [63.39134873744748]
Existing industrial anomaly detection methods primarily concentrate on unsupervised learning with pristine RGB images.
This paper proposes a novel noise-resistant M3DM-NR framework to leverage strong multi-modal discriminative capabilities of CLIP.
Extensive experiments show that M3DM-NR outperforms state-of-the-art methods in 3D-RGB multi-modal noisy anomaly detection.
arXiv Detail & Related papers (2024-06-04T12:33:02Z) - Adaptive Semantic-Enhanced Denoising Diffusion Probabilistic Model for Remote Sensing Image Super-Resolution [7.252121550658619]
Denoising Diffusion Probabilistic Model (DDPM) has shown promising performance in image reconstructions.
High-frequency details generated by DDPM often suffer from misalignment with HR images due to model's tendency to overlook long-range semantic contexts.
An adaptive semantic-enhanced DDPM (ASDDPM) is proposed to enhance the detail-preserving capability of the DDPM.
arXiv Detail & Related papers (2024-03-17T04:08:58Z) - Global Context Aggregation Network for Lightweight Saliency Detection of
Surface Defects [70.48554424894728]
We develop a Global Context Aggregation Network (GCANet) for lightweight saliency detection of surface defects on the encoder-decoder structure.
First, we introduce a novel transformer encoder on the top layer of the lightweight backbone, which captures global context information through a novel Depth-wise Self-Attention (DSA) module.
The experimental results on three public defect datasets demonstrate that the proposed network achieves a better trade-off between accuracy and running efficiency compared with other 17 state-of-the-art methods.
arXiv Detail & Related papers (2023-09-22T06:19:11Z) - Iterative Adaptive Spectroscopy of Short Signals [0.1338174941551702]
We develop an adaptive frequency sensing protocol based on Ramsey interferometry.
High precision is achieved by enhancing the Ramsey sequence to prepare with high fidelity both the sensing and readout state.
arXiv Detail & Related papers (2022-04-10T18:07:50Z) - Adaptive Frequency Learning in Two-branch Face Forgery Detection [66.91715092251258]
We propose Adaptively learn Frequency information in the two-branch Detection framework, dubbed AFD.
We liberate our network from the fixed frequency transforms, and achieve better performance with our data- and task-dependent transform layers.
arXiv Detail & Related papers (2022-03-27T14:25:52Z) - The KFIoU Loss for Rotated Object Detection [115.334070064346]
In this paper, we argue that one effective alternative is to devise an approximate loss who can achieve trend-level alignment with SkewIoU loss.
Specifically, we model the objects as Gaussian distribution and adopt Kalman filter to inherently mimic the mechanism of SkewIoU.
The resulting new loss called KFIoU is easier to implement and works better compared with exact SkewIoU.
arXiv Detail & Related papers (2022-01-29T10:54:57Z) - Deep Unfolding of Iteratively Reweighted ADMM for Wireless RF Sensing [22.467957268653077]
We address the detection of material defects inside a layered material structure using compressive sensing based multiple-output (MIMO) wireless radar.
In many scenarios, the number of defects challenging the layered structure can be modeled as a low-rank structure.
arXiv Detail & Related papers (2021-06-07T15:00:33Z) - ADRN: Attention-based Deep Residual Network for Hyperspectral Image
Denoising [52.01041506447195]
We propose an attention-based deep residual network to learn a mapping from noisy HSI to the clean one.
Experimental results demonstrate that our proposed ADRN scheme outperforms the state-of-the-art methods both in quantitative and visual evaluations.
arXiv Detail & Related papers (2020-03-04T08:36:27Z)
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.