Hanhe Lin

Guangan Chen, Hanhe Lin, Oliver Wiedemann et al.

The just noticeable difference (JND) is the minimal difference between stimuli that can be detected by a person. The picture-wise just noticeable difference (PJND) for a given reference image and a compression algorithm represents the minimal level of compression that causes noticeable differences in the reconstruction. These differences can only be observed in some specific regions within the image, dubbed as JND-critical regions. Identifying these regions can improve the development of image compression algorithms. Due to the fact that visual perception varies among individuals, determining the PJND values and JND-critical regions for a target population of consumers requires subjective assessment experiments involving a sufficiently large number of observers. In this paper, we propose a novel framework for conducting such experiments using crowdsourcing. By applying this framework, we created a novel PJND dataset, KonJND++, consisting of 300 source images, compressed versions thereof under JPEG or BPG compression, and an average of 43 ratings of PJND and 129 self-reported locations of JND-critical regions for each source image. Our experiments demonstrate the effectiveness and reliability of our proposed framework, which is easy to be adapted for collecting a large-scale dataset. The source code and dataset are available at https://github.com/angchen-dev/LocJND.

Shaolin Su, Hanhe Lin, Vlad Hosu et al.

An accurate computational model for image quality assessment (IQA) benefits many vision applications, such as image filtering, image processing, and image generation. Although the study of face images is an important subfield in computer vision research, the lack of face IQA data and models limits the precision of current IQA metrics on face image processing tasks such as face superresolution, face enhancement, and face editing. To narrow this gap, in this paper, we first introduce the largest annotated IQA database developed to date, which contains 20,000 human faces -- an order of magnitude larger than all existing rated datasets of faces -- of diverse individuals in highly varied circumstances. Based on the database, we further propose a novel deep learning model to accurately predict face image quality, which, for the first time, explores the use of generative priors for IQA. By taking advantage of rich statistics encoded in well pretrained off-the-shelf generative models, we obtain generative prior information and use it as latent references to facilitate blind IQA. The experimental results demonstrate both the value of the proposed dataset for face IQA and the superior performance of the proposed model.

Jin Liu, Junbin Mao, Hanhe Lin et al.

Due to its complexity, graph learning-based multi-modal integration and classification is one of the most challenging obstacles for disease prediction. To effectively offset the negative impact between modalities in the process of multi-modal integration and extract heterogeneous information from graphs, we propose a novel method called MMKGL (Multi-modal Multi-Kernel Graph Learning). For the problem of negative impact between modalities, we propose a multi-modal graph embedding module to construct a multi-modal graph. Different from conventional methods that manually construct static graphs for all modalities, each modality generates a separate graph by adaptive learning, where a function graph and a supervision graph are introduced for optimization during the multi-graph fusion embedding process. We then propose a multi-kernel graph learning module to extract heterogeneous information from the multi-modal graph. The information in the multi-modal graph at different levels is aggregated by convolutional kernels with different receptive field sizes, followed by generating a cross-kernel discovery tensor for disease prediction. Our method is evaluated on the benchmark Autism Brain Imaging Data Exchange (ABIDE) dataset and outperforms the state-of-the-art methods. In addition, discriminative brain regions associated with autism are identified by our model, providing guidance for the study of autism pathology.

Ludi Li, Junbin Mao, Hanhe Lin et al.

Multi-pulse magnetic resonance imaging (MRI) is widely utilized for clinical practice such as Alzheimer's disease diagnosis. To train a robust model for multi-pulse MRI classification, it requires large and diverse data from various medical institutions while protecting privacy by preventing raw data sharing across institutions. Although federated learning (FL) is a feasible solution to address this issue, it poses challenges of model convergence due to the effect of data heterogeneity and substantial communication overhead due to large numbers of parameters transmitted within the model. To address these challenges, we propose CEPerFed, a communication-efficient personalized FL method. It mitigates the effect of data heterogeneity by incorporating client-side historical risk gradients and historical mean gradients to coordinate local and global optimization. The former is used to weight the contributions from other clients, enhancing the reliability of local updates, while the latter enforces consistency between local updates and the global optimization direction to ensure stable convergence across heterogeneous data distributions. To address the high communication overhead, we propose a hierarchical SVD (HSVD) strategy that transmits only the most critical information required for model updates. Experiments on five classification tasks demonstrate the effectiveness of the CEPerFed method. The code will be released upon acceptance at https://github.com/LD0416/CEPerFed.

Jiashuo Chang, Zhengyi Li, Jianxun Lou et al.

Macro photography (MP) is a specialized field of photography that captures objects at an extremely close range, revealing tiny details. Although an accurate macro photography image quality assessment (MPIQA) metric can benefit macro photograph capturing, which is vital in some domains such as scientific research and medical applications, the lack of MPIQA data limits the development of MPIQA metrics. To address this limitation, we conducted a large-scale MPIQA study. Specifically, to ensure diversity both in content and quality, we sampled 2,000 MP images from 15,700 MP images, collected from three public image websites. For each MP image, 17 (out of 21 after outlier removal) quality ratings and a detailed quality report of distortion magnitudes, types, and positions are gathered by a lab study. The images, quality ratings, and quality reports form our novel multi-labeled MPIQA database, MMP-2k. Experimental results showed that the state-of-the-art generic IQA metrics underperform on MP images. The database and supplementary materials are available at https://github.com/Future-IQA/MMP-2k.

Jianxun Lou, Hanhe Lin, David Marshall et al.

Visual saliency prediction using transformers - Convolutional neural networks (CNNs) have significantly advanced computational modelling for saliency prediction. However, accurately simulating the mechanisms of visual attention in the human cortex remains an academic challenge. It is critical to integrate properties of human vision into the design of CNN architectures, leading to perceptually more relevant saliency prediction. Due to the inherent inductive biases of CNN architectures, there is a lack of sufficient long-range contextual encoding capacity. This hinders CNN-based saliency models from capturing properties that emulate viewing behaviour of humans. Transformers have shown great potential in encoding long-range information by leveraging the self-attention mechanism. In this paper, we propose a novel saliency model that integrates transformer components to CNNs to capture the long-range contextual visual information. Experimental results show that the transformers provide added value to saliency prediction, enhancing its perceptual relevance in the performance. Our proposed saliency model using transformers has achieved superior results on public benchmarks and competitions for saliency prediction models. The source code of our proposed saliency model TranSalNet is available at: https://github.com/LJOVO/TranSalNet

Xiaoyu Zheng, Xu Tian, Bin Jiao et al.

Patients with dementia typically exhibit cognitive impairment, which is routinely assessed using the Mini-Mental State Examination (MMSE). Concurrently, their underlying neurophysiological abnormalities are reflected in Electroencephalography (EEG), providing a basis for joint modeling. However, traditional multi-task approaches suffer from feature entanglement, which leads to inter-task interference when handling heterogeneous objectives.To address this challenge, we propose a task-guided spatiotemporal network (TGSN) with diffusion augmentation for EEG-based dementia diagnosis and MMSE prediction. Specifically, TGSN integrates a multi-band feature fusion module to capture complementary spectral information from EEG. Meanwhile, a pre-trained data augmentation module utilizing a diffusion process is introduced toincrease sample diversity. To model the complex spatiotemporal patterns of EEG, we propose a gated spatiotemporal attention module that captures long-range spatial dependencies and temporal dynamics. Moreover, we design a task-guided query module to achieve task-specific feature extraction, thereby mitigating task interference. The effectiveness of TGSN is evaluated on the XY02 dataset. Experimental results demonstrate that the proposed network outperforms several state-of-the-art methods, achieving classification accuracies of 97.78\% for Alzheimer's Disease (AD)/Frontotemporal Dementia (FTD) and 83.93\% for AD/FTD/Vascular Cognitive Impairment (VCI), which exceed the best baselines by 16.39\% and 8.28\%, respectively. In parallel, it reduces the RMSE for MMSE prediction to 1.93 and 2.38, achieving significant error reductions of 1.44 and 1.43 compared to the best baselines. Additionally, validation on the DS004504 dataset demonstrates strong cross-dataset generalization...

Guangan Chen, Anh Minh Truong, Hanhe Lin et al.

Novel view synthesis in 360$^\circ$ scenes from extremely sparse input views is essential for applications like virtual reality and augmented reality. This paper presents a novel framework for novel view synthesis in extremely sparse-view cases. As typical structure-from-motion methods are unable to estimate camera poses in extremely sparse-view cases, we apply DUSt3R to estimate camera poses and generate a dense point cloud. Using the poses of estimated cameras, we densely sample additional views from the upper hemisphere space of the scenes, from which we render synthetic images together with the point cloud. Training 3D Gaussian Splatting model on a combination of reference images from sparse views and densely sampled synthetic images allows a larger scene coverage in 3D space, addressing the overfitting challenge due to the limited input in sparse-view cases. Retraining a diffusion-based image enhancement model on our created dataset, we further improve the quality of the point-cloud-rendered images by removing artifacts. We compare our framework with benchmark methods in cases of only four input views, demonstrating significant improvement in novel view synthesis under extremely sparse-view conditions for 360$^\circ$ scenes.

Hui Men, Hanhe Lin, Mohsen Jenadeleh et al.

In subjective full-reference image quality assessment, differences between perceptual image qualities of the reference image and its distorted versions are evaluated, often using degradation category ratings (DCR). However, the DCR has been criticized since differences between rating categories on this ordinal scale might not be perceptually equidistant, and observers may have different understandings of the categories. Pair comparisons (PC) of distorted images, followed by Thurstonian reconstruction of scale values, overcome these problems. In addition, PC is more sensitive than DCR, and it can provide scale values in fractional, just noticeable difference (JND) units that express a precise perceptional interpretation. Still, the comparison of images of nearly the same quality can be difficult. We introduce boosting techniques embedded in more general triplet comparisons (TC) that increase the sensitivity even more. Boosting amplifies the artefacts of distorted images, enlarges their visual representation by zooming, increases the visibility of the distortions by a flickering effect, or combines some of the above. Experimental results show the effectiveness of boosted TC for seven types of distortion. We crowdsourced over 1.7 million responses to triplet questions. A detailed analysis shows that boosting increases the discriminatory power and allows to reduce the number of subjective ratings without sacrificing the accuracy of the resulting relative image quality values. Our technique paves the way to fine-grained image quality datasets, allowing for more distortion levels, yet with high-quality subjective annotations. We also provide the details for Thurstonian scale reconstruction from TC and our annotated dataset, KonFiG-IQA, containing 10 source images, processed using 7 distortion types at 12 or even 30 levels, uniformly spaced over a span of 3 JND units.

Baptiste Roziere, Fabien Teytaud, Vlad Hosu et al.

We propose to use a quality estimator and evolutionary methods to search the latent space of generative adversarial networks trained on small, difficult datasets, or both. The new method leads to the generation of significantly higher quality images while preserving the original generator's diversity. Human raters preferred an image from the new version with frequency 83.7pc for Cats, 74pc for FashionGen, 70.4pc for Horses, and 69.2pc for Artworks, and minor improvements for the already excellent GANs for faces. This approach applies to any quality scorer and GAN generator.

Baptiste Roziere, Nathanal Carraz Rakotonirina, Vlad Hosu et al.

Super-resolution aims at increasing the resolution and level of detail within an image. The current state of the art in general single-image super-resolution is held by NESRGAN+, which injects a Gaussian noise after each residual layer at training time. In this paper, we harness evolutionary methods to improve NESRGAN+ by optimizing the noise injection at inference time. More precisely, we use Diagonal CMA to optimize the injected noise according to a novel criterion combining quality assessment and realism. Our results are validated by the PIRM perceptual score and a human study. Our method outperforms NESRGAN+ on several standard super-resolution datasets. More generally, our approach can be used to optimize any method based on noise injection.

Hanhe Lin, Vlad Hosu, Dietmar Saupe

Multi-level deep-features have been driving state-of-the-art methods for aesthetics and image quality assessment (IQA). However, most IQA benchmarks are comprised of artificially distorted images, for which features derived from ImageNet under-perform. We propose a new IQA dataset and a weakly supervised feature learning approach to train features more suitable for IQA of artificially distorted images. The dataset, KADIS-700k, is far more extensive than similar works, consisting of 140,000 pristine images, 25 distortions types, totaling 700k distorted versions. Our weakly supervised feature learning is designed as a multi-task learning type training, using eleven existing full-reference IQA metrics as proxies for differential mean opinion scores. We also introduce a benchmark database, KADID-10k, of artificially degraded images, each subjectively annotated by 30 crowd workers. We make use of our derived image feature vectors for (no-reference) image quality assessment by training and testing a shallow regression network on this database and five other benchmark IQA databases. Our method, termed DeepFL-IQA, performs better than other feature-based no-reference IQA methods and also better than all tested full-reference IQA methods on KADID-10k. For the other five benchmark IQA databases, DeepFL-IQA matches the performance of the best existing end-to-end deep learning-based methods on average.

Hui Men, Vlad Hosu, Hanhe Lin et al.

Current benchmarks for optical flow algorithms evaluate the estimation either directly by comparing the predicted flow fields with the ground truth or indirectly by using the predicted flow fields for frame interpolation and then comparing the interpolated frames with the actual frames. In the latter case, objective quality measures such as the mean squared error are typically employed. However, it is well known that for image quality assessment, the actual quality experienced by the user cannot be fully deduced from such simple measures. Hence, we conducted a subjective quality assessment crowdscouring study for the interpolated frames provided by one of the optical flow benchmarks, the Middlebury benchmark. We collected forced-choice paired comparisons between interpolated images and corresponding ground truth. To increase the sensitivity of observers when judging minute difference in paired comparisons we introduced a new method to the field of full-reference quality assessment, called artefact amplification. From the crowdsourcing data, we reconstructed absolute quality scale values according to Thurstone's model. As a result, we obtained a re-ranking of the 155 participating algorithms w.r.t. the visual quality of the interpolated frames. This re-ranking not only shows the necessity of visual quality assessment as another evaluation metric for optical flow and frame interpolation benchmarks, the results also provide the ground truth for designing novel image quality assessment (IQA) methods dedicated to perceptual quality of interpolated images. As a first step, we proposed such a new full-reference method, called WAE-IQA. By weighing the local differences between an interpolated image and its ground truth WAE-IQA performed slightly better than the currently best FR-IQA approach from the literature.

Hanhe Lin, Vlad Hosu, Chunling Fan et al.

The satisfied user ratio (SUR) curve for a lossy image compression scheme, e.g., JPEG, characterizes the complementary cumulative distribution function of the just noticeable difference (JND), the smallest distortion level that can be perceived by a subject when a reference image is compared to a distorted one. A sequence of JNDs can be defined with a suitable successive choice of reference images. We propose the first deep learning approach to predict SUR curves. We show how to apply maximum likelihood estimation and the Anderson-Darling test to select a suitable parametric model for the distribution function. We then use deep feature learning to predict samples of the SUR curve and apply the method of least squares to fit the parametric model to the predicted samples. Our deep learning approach relies on a siamese convolutional neural network, transfer learning, and deep feature learning, using pairs consisting of a reference image and a compressed image for training. Experiments on the MCL-JCI dataset showed state-of-the-art performance. For example, the mean Bhattacharyya distances between the predicted and ground truth first, second, and third JND distributions were 0.0810, 0.0702, and 0.0522, respectively, and the corresponding average absolute differences of the peak signal-to-noise ratio at a median of the first JND distribution were 0.58, 0.69, and 0.58 dB. Further experiments on the JND-Pano dataset showed that the method transfers well to high resolution panoramic images viewed on head-mounted displays.

Franz Götz-Hahn, Vlad Hosu, Hanhe Lin et al.

Video quality assessment (VQA) methods focus on particular degradation types, usually artificially induced on a small set of reference videos. Hence, most traditional VQA methods under-perform in-the-wild. Deep learning approaches have had limited success due to the small size and diversity of existing VQA datasets, either artificial or authentically distorted. We introduce a new in-the-wild VQA dataset that is substantially larger and diverse: KonVid-150k. It consists of a coarsely annotated set of 153,841 videos having five quality ratings each, and 1,596 videos with a minimum of 89 ratings each. Additionally, we propose new efficient VQA approaches (MLSP-VQA) relying on multi-level spatially pooled deep-features (MLSP). They are exceptionally well suited for training at scale, compared to deep transfer learning approaches. Our best method, MLSP-VQA-FF, improves the Spearman rank-order correlation coefficient (SRCC) performance metric on the commonly used KoNViD-1k in-the-wild benchmark dataset to 0.82. It surpasses the best existing deep-learning model (0.80 SRCC) and hand-crafted feature-based method (0.78 SRCC). We further investigate how alternative approaches perform under different levels of label noise, and dataset size, showing that MLSP-VQA-FF is the overall best method for videos in-the-wild. Finally, we show that the MLSP-VQA models trained on KonVid-150k sets the new state-of-the-art for cross-test performance on KoNViD-1k, LIVE-VQC, and LIVE-Qualcomm with a 0.83, 0.75, and 0.64 SRCC, respectively. For both KoNViD-1k and LIVE-VQC this inter-dataset testing outperforms intra-dataset experiments, showing excellent generalization.

Felix Wilhelm Siebert, Hanhe Lin

The continuous motorization of traffic has led to a sustained increase in the global number of road related fatalities and injuries. To counter this, governments are focusing on enforcing safe and law-abiding behavior in traffic. However, especially in developing countries where the motorcycle is the main form of transportation, there is a lack of comprehensive data on the safety-critical behavioral metric of motorcycle helmet use. This lack of data prohibits targeted enforcement and education campaigns which are crucial for injury prevention. Hence, we have developed an algorithm for the automated registration of motorcycle helmet usage from video data, using a deep learning approach. Based on 91,000 annotated frames of video data, collected at multiple observation sites in 7 cities across the country of Myanmar, we trained our algorithm to detect active motorcycles, the number and position of riders on the motorcycle, as well as their helmet use. An analysis of the algorithm's accuracy on an annotated test data set, and a comparison to available human-registered helmet use data reveals a high accuracy of our approach. Our algorithm registers motorcycle helmet use rates with an accuracy of -4.4% and +2.1% in comparison to a human observer, with minimal training for individual observation sites. Without observation site specific training, the accuracy of helmet use detection decreases slightly, depending on a number of factors. Our approach can be implemented in existing roadside traffic surveillance infrastructure and can facilitate targeted data-driven injury prevention campaigns with real-time speed. Implications of the proposed method, as well as measures that can further improve detection accuracy are discussed.

Vlad Hosu, Hanhe Lin, Tamas Sziranyi et al.

Deep learning methods for image quality assessment (IQA) are limited due to the small size of existing datasets. Extensive datasets require substantial resources both for generating publishable content and annotating it accurately. We present a systematic and scalable approach to creating KonIQ-10k, the largest IQA dataset to date, consisting of 10,073 quality scored images. It is the first in-the-wild database aiming for ecological validity, concerning the authenticity of distortions, the diversity of content, and quality-related indicators. Through the use of crowdsourcing, we obtained 1.2 million reliable quality ratings from 1,459 crowd workers, paving the way for more general IQA models. We propose a novel, deep learning model (KonCept512), to show an excellent generalization beyond the test set (0.921 SROCC), to the current state-of-the-art database LIVE-in-the-Wild (0.825 SROCC). The model derives its core performance from the InceptionResNet architecture, being trained at a higher resolution than previous models (512x384). Correlation analysis shows that KonCept512 performs similar to having 9 subjective scores for each test image.

Markus Wagner, Hanhe Lin, Shujun Li et al.

Subjective perceptual image quality can be assessed in lab studies by human observers. Objective image quality assessment (IQA) refers to algorithms for estimation of the mean subjective quality ratings. Many such methods have been proposed, both for blind IQA in which no original reference image is available as well as for the full-reference case. We compared 8 state-of-the-art algorithms for blind IQA and showed that an oracle, able to predict the best performing method for any given input image, yields a hybrid method that could outperform even the best single existing method by a large margin. In this contribution we address the research question whether established methods to learn such an oracle can improve blind IQA. We applied AutoFolio, a state-of-the-art system that trains an algorithm selector to choose a well-performing algorithm for a given instance. We also trained deep neural networks to predict the best method. Our results did not give a positive answer, algorithm selection did not yield a significant improvement over the single best method. Looking into the results in depth, we observed that the noise in images may have played a role in why our trained classifiers could not predict the oracle. This motivates the consideration of noisiness in IQA methods, a property that has so far not been observed and that opens up several interesting new research questions and applications.

Hui Men, Hanhe Lin, Vlad Hosu et al.

Current benchmarks for optical flow algorithms evaluate the estimation quality by comparing their predicted flow field with the ground truth, and additionally may compare interpolated frames, based on these predictions, with the correct frames from the actual image sequences. For the latter comparisons, objective measures such as mean square errors are applied. However, for applications like image interpolation, the expected user's quality of experience cannot be fully deduced from such simple quality measures. Therefore, we conducted a subjective quality assessment study by crowdsourcing for the interpolated images provided in one of the optical flow benchmarks, the Middlebury benchmark. We used paired comparisons with forced choice and reconstructed absolute quality scale values according to Thurstone's model using the classical least squares method. The results give rise to a re-ranking of 141 participating algorithms w.r.t. visual quality of interpolated frames mostly based on optical flow estimation. Our re-ranking result shows the necessity of visual quality assessment as another evaluation metric for optical flow and frame interpolation benchmarks.

Hanhe Lin, Vlad Hosu, Dietmar Saupe

The main challenge in applying state-of-the-art deep learning methods to predict image quality in-the-wild is the relatively small size of existing quality scored datasets. The reason for the lack of larger datasets is the massive resources required in generating diverse and publishable content. We present a new systematic and scalable approach to create large-scale, authentic and diverse image datasets for Image Quality Assessment (IQA). We show how we built an IQA database, KonIQ-10k, consisting of 10,073 images, on which we performed very large scale crowdsourcing experiments in order to obtain reliable quality ratings from 1,467 crowd workers (1.2 million ratings). We argue for its ecological validity by analyzing the diversity of the dataset, by comparing it to state-of-the-art IQA databases, and by checking the reliability of our user studies.