检索结果-内蒙古大学图书馆

FreqAlign: Excavating Perception-oriented Transferability for Blind Image Quality Assessment from A Frequency Perspective

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Xin Lu, Yiting Chen, Zhibo The CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Blind Image Quality Assessment (BIQA) is susceptible to poor transferability when the distribution shift occurs, e.g., from synthesis degradation to authentic degradation. To mitigate this, some studies have attempted to design unsupervised domain adaptation (UDA) based schemes for BIQA, which intends to eliminate the domain shift through adversarial-based feature alignment. However, the feature alignment is usually taken at the low-frequency space of features since the global average pooling operation. This ignores the transferable perception knowledge in other frequency components and causes the sub-optimal solution for the UDA of BIQA. To overcome this, from a novel frequency perspective, we propose an effective alignment strategy, i.e., Frequency Alignment (dubbed FreqAlign), to excavate the perception-oriented transferability of BIQA in the frequency space. Concretely, we study what frequency components of features are more proper for perception-oriented alignment. Based on this, we propose to improve the perception-oriented transferability of BIQA by performing feature frequency decomposition and selecting the frequency components that contained the most transferable perception knowledge for alignment. To achieve a stable and effective frequency selection, we further propose the frequency movement with a sliding window to find the optimal frequencies for alignment, which is composed of three strategies, i.e., warm up with pre-training, frequency movement-based selection, and perturbation-based finetuning. Extensive experiments under different domain adaptation settings of BIQA have validated the effectiveness of our proposed method. The code will be released at https://***/lixinustc/Openworld-IQA. Copyright © 2023, The Authors. All rights reserved.

关键词： Alignment

Domain-class correlation decomposition for generalizable person re-identification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yang, Kaiwen Tian, Xinmei CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Domain generalization in person re-identification is a highly important meaningful and practical task in which a model trained with data from several source domains is expected to generalize well to unseen target domains. Domain adversarial learning is a promising domain generalization method that aims to remove domain information in the latent representation through adversarial training. However, in person re-identification, the domain and class are correlated, and we theoretically show that domain adversarial learning will lose certain information about class due to this domain-class correlation. Inspired by casual inference, we propose to perform interventions to the domain factor d, aiming to decompose the domain-class correlation. To achieve this goal, we proposed estimating the resulting representation z∗ caused by the intervention through first- and second-order statistical characteristic matching. Specifically, we build a memory bank to restore the statistical characteristics of each domain. Then, we use the newly generated samples {z∗, y, d∗} to compute the loss function. These samples are domain-class correlation decomposed;thus, we can learn a domain-invariant representation that can capture more class-related features. Extensive experiments show that our model outperforms the state-of-the-art methods on the large-scale domain generalization Re-ID benchmark. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

No-reference light field image quality assessment based on micro-lens image

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Luo, Ziyuan Zhou, Wei Shi, Likun Chen, Zhibo CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Light field image quality assessment (LF-IQA) plays a significant role due to its guidance to Light Field (LF) contents acquisition, processing and application. The LF can be represented as 4-D signal, and its quality depends on both angular consistency and spatial quality. However, few existing LF-IQA methods concentrate on effects caused by angular inconsistency. Especially, no-reference methods lack effective utilization of 2-D angular information. In this paper, we focus on measuring the 2-D angular consistency for LF-IQA. The Micro-Lens Image (MLI) refers to the angular domain of the LF image, which can simultaneously record the angular information in both horizontal and vertical directions. Since the MLI contains 2-D angular information, we propose a No-Reference Light Field image Quality assessment model based on MLI (LF-QMLI). Specifically, we first utilize Global Entropy Distribution (GED) and Uniform Local Binary Pattern descriptor (ULBP) to extract features from the MLI, and then pool them together to measure angular consistency. In addition, the information entropy of Sub-Aperture Image (SAI) is adopted to measure spatial quality. Extensive experimental results show that LF-QMLI achieves the state-of-the-art performance. Copyright © 2019, The Authors. All rights reserved.

关键词： Image quality

StyleAM: Perception-Oriented Unsupervised Domain Adaption for Non-reference Image Quality Assessment

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Lu, Yiting Li, Xin Liu, Jianzhao Chen, Zhibo The CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Deep neural networks (DNNs) have shown great potential in non-reference image quality assessment (NR-IQA). However, the annotation of NR-IQA is labor-intensive and time-consuming, which severely limits their application especially for authentic images. To relieve the dependence on quality annotation, some works have applied unsupervised domain adaptation (UDA) to NR-IQA. However, the above methods ignore that the alignment space used in classification is suboptimal, since the space is not elaborately designed for perception. To solve this challenge, we propose an effective perception-oriented unsupervised domain adaptation method StyleAM for NR-IQA, which transfers sufficient knowledge from label-rich source domain data to label-free target domain images via Style Alignment and Mixup. Specifically, we find a more compact and reliable space i.e., feature style space for perception-oriented UDA based on an interesting/amazing observation, that the feature style (i.e., the mean and variance) of the deep layer in DNNs is exactly associated with the quality score in NR-IQA. Therefore, we propose to align the source and target domains in a more perceptual-oriented space i.e., the feature style space, to reduce the intervention from other quality-irrelevant feature factors. Furthermore, to increase the consistency between quality score and its feature style, we also propose a novel feature augmentation strategy Style Mixup, which mixes the feature styles (i.e., the mean and variance) before the last layer of DNNs together with mixing their labels. Extensive experimental results on two typical cross-domain settings (i.e., synthetic to authentic, and multiple distortions to one distortion) have demonstrated the effectiveness of our proposed StyleAM on NR-IQA. Copyright © 2022, The Authors. All rights reserved.

关键词： Alignment

LIRA: Lifelong image restoration from unknown blended distortions

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Jianzhao Lin, Jianxin Li, Xin Zhou, Wei Liu, Sen Chen, Zhibo CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Most existing image restoration networks are designed in a disposable way and catastrophically forget previously learned distortions when trained on a new distortion removal task. To alleviate this problem, we raise the novel lifelong image restoration problem for blended distortions. We first design a base fork-join model in which multiple pre-trained expert models specializing in individual distortion removal task work cooperatively and adaptively to handle blended distortions. When the input is degraded by a new distortion, inspired by adult neurogenesis in human memory system, we develop a neural growing strategy where the previously trained model can incorporate a new expert branch and continually accumulate new knowledge without interfering with learned knowledge. Experimental results show that the proposed approach can not only achieve state-of-the-art performance on blended distortions removal tasks in both PSNR/SSIM metrics, but also maintain old expertise while learning new restoration tasks. Copyright © 2020, The Authors. All rights reserved.

关键词： Image reconstruction

A total suspended sediment retrieval model for multiple estuaries and coasts by Landsat imageries 4

学校读者我要写书评

暂无评论

A total suspended sediment retrieval model for multiple estu...

4th International Workshop on Earth Observation and Remote Sensing applications, EORSA 2016

作者： Chongyang, Wang Dan, Li Danni, Wang Chen, Shuisen Wei, Liu Guangdong Open Laboratory of Geospatial Information Technology and Application Guangdong Key Lab. of Remote Sensing and Geographical Information System Technology Application Guangzhou Institute of Geography Chinese Academy of Sciences University of Chinese Academy of Sciences Guangzhou Beijing510070/5lO640 China Department of Resources and the Urban Planning Xin Hua College of Sun Yat-Sen University Guangzhou510520 China

ISBN: (纸本)9781509014798

Based on 119 in-situ data from five estuaries and coasts of South China including Xunwen coast, estuary of Moyangjiang River, estuary and coast of Pearl River, estuary of Hanjiang River and estuary of Yangtze River, this paper aims to develop and establish a TSS retrieval model that applicable in different field conditions. After recalibrating and validating the form with the highest correlation coefficient between reflectance and TSS concentration and other TSS retrieval models that have been successful applied in many places, we found that the quadratic model of the ratio of logarithmic transformation of red band and near infrared band and logarithmic transformation of TSS concentration (QRLTSS) shows the highest performance. QRLTSS model based on Landsat OLI, ETM+ and TM can explained about 71% of the TSS concentration variation (4.3∼577.2 mg/L) in the five regions and has a high and acceptable validation accuracy with root mean square error (RMSE) of 21.5-25mg/L and mean relative error (MRE) of 27.2-32.2%. We concluded that QRLTSS model can be used to quantify the TSS concentration of multiple estuaries and coasts of south China which would be helpful to understand the temporal and spatial variation of TSS in a large region. QRLTSS model should be applied to Landsat imagery for further validation in the future. The approach proposed in the paper also could promote the research work of establishing regional and uniform TSS retrieval model forward. © 2016 IEEE.

关键词： Estuaries

Learning omni-frequency region-adaptive representations for real image super-resolution

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Xin Jin, Xin Yu, Tao Pang, Yingxue Sun, Simeng Zhang, Zhizheng Chen, Zhibo CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Traditional single image super-resolution (SISR) methods that focus on solving single and uniform degradation (i.e., bicubic down-sampling), typically suffer from poor performance when applied into real-world low-resolution (LR) images due to the complicated realistic degradations. The key to solving this more challenging real image super-resolution (RealSR) problem lies in learning feature representations that are both informative and content-aware. In this paper, we propose an Omni-frequency Region-adaptive Network (OR-Net) to address both challenges, here we call features of all low, middle and high frequencies omni-frequency features. Specifically, we start from the frequency perspective and design a Frequency Decomposition (FD) module to separate different frequency components to comprehensively compensate the information lost for real LR image. Then, considering the different regions of real LR image have different frequency information lost, we further design a Region-adaptive Frequency Aggregation (RFA) module by leveraging dynamic convolution and spatial attention to adaptively restore frequency components for different regions. The extensive experiments endorse the effective, and scenario-agnostic nature of our OR-Net for RealSR. Copyright © 2020, The Authors. All rights reserved.

关键词： Optical resolving power

Spatial Decomposition and Temporal Fusion based Inter Prediction for Learned Video Compression

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sheng, Xihua Li, Li Liu, Dong Li, Houqiang The CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Video compression performance is closely related to the accuracy of inter prediction. It tends to be difficult to obtain accurate inter prediction for the local video regions with inconsistent motion and occlusion. Traditional video coding standards propose various technologies to handle motion inconsistency and occlusion, such as recursive partitions, geometric partitions, and long-term references. However, existing learned video compression schemes focus on obtaining an overall minimized prediction error averaged over all regions while ignoring the motion inconsistency and occlusion in local regions. In this paper, we propose a spatial decomposition and temporal fusion based inter prediction for learned video compression. To handle motion inconsistency, we propose to decompose the video into structure and detail (SDD) components first. Then we perform SDD-based motion estimation and SDD-based temporal context mining for the structure and detail components to generate short-term temporal contexts. To handle occlusion, we propose to propagate long-term temporal contexts by recurrently accumulating the temporal information of each historical reference feature and fuse them with short-term temporal contexts. With the SDD-based motion model and long short-term temporal contexts fusion, our proposed learned video codec can obtain more accurate inter prediction. Comprehensive experimental results demonstrate that our codec outperforms the reference software of H.266/VVC on all common test datasets for both PSNR and MS-SSIM. Copyright © 2024, The Authors. All rights reserved.

关键词： Image compression

Source-free Unsupervised Domain Adaptation for Blind Image Quality Assessment

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liu, Jianzhao Li, Xin An, Shukun Chen, Zhibo The CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Existing learning-based methods for blind image quality assessment (BIQA) are heavily dependent on large amounts of annotated training data, and usually suffer from a severe performance degradation when encountering the domain/distribution shift problem. Thanks to the development of unsupervised domain adaptation (UDA), some works attempt to transfer the knowledge from a label-sufficient source domain to a label-free target domain under domain shift with UDA. However, it requires the coexistence of source and target data, which might be impractical for source data due to the privacy or storage issues. In this paper, we take the first step towards the source-free unsupervised domain adaptation (SFUDA) in a simple yet efficient manner for BIQA to tackle the domain shift without access to the source data. Specifically, we cast the quality assessment task as a rating distribution prediction problem. Based on the intrinsic properties of BIQA, we present a group of well-designed self-supervised objectives to guide the adaptation of the BN affine parameters towards the target domain. Among them, minimizing the prediction entropy and maximizing the batch prediction diversity aim to encourage more confident results while avoiding the trivial solution. Besides, based on the observation that the IQA rating distribution of single image follows the Gaussian distribution, we apply Gaussian regularization to the predicted rating distribution to make it more consistent with the nature of human scoring. Extensive experimental results under cross-domain scenarios demonstrated the effectiveness of our proposed method to mitigate the domain shift. Copyright © 2022, The Authors. All rights reserved.

关键词： Forecasting