This study addresses the limitations of existing dynamic pseudo-labeling (DPL) techniques, which often utilize static or dynamic thresholds for confident sample selection. The existing methods fail to capture the non-linear relationship between task accuracy and model confidence, particularly in the context of overconfidence. This can limit the model’s learning opportunities for high entropy samples that significantly influence a model’s generalization ability. To solve this, we propose a novel gradient pass-based DPL technique that incorporates the high-entropy samples, which are typically overlooked. Our approach introduces two classifiers–low gradient pass (LGP) and high gradient pass (HGP)–to derive over- and under-confident dynamic thresholds that indicate the class-wise overconfidence acceleration, respectively. By combining the under- and overconfident states from the GP classifiers, we create a more adaptive and accurate PL method. Our main contributions highlight the importance of considering both low and high-confidence samples in enhancing the model’s robustness and generalization for improved PL performance.

Skeleton-based hand gesture recognition plays a crucial role in enabling intuitive human–computer interaction. Traditional methods have primarily relied on hand-crafted features—such as distances between joints or positional changes across frames—to alleviate issues from viewpoint variation or body proportion differences. However, these hand-crafted features often fail to capture the full spatio-temporal information in raw skeleton data, exhibit poor interpretability, and depend heavily on dataset-specific preprocessing, limiting generalization. In addition, normalization strategies in traditional methods, which rely on training data, can introduce domain gaps between training and testing environments, further hindering robustness in diverse real-world settings. To overcome these challenges, we exclude traditional hand-crafted features and propose Skeleton Kinematics Extraction Through Coordinated grapH (SKETCH), a novel framework that directly utilizes raw four-dimensional (time, x, y, and z) skeleton sequences and transforms them into intuitive visual graph representations. The proposed framework incorporates a novel learnable Dynamic Range Embedding (DRE) to preserve axis-wise motion magnitudes lost during normalization and visual graph representations, enabling richer and more discriminative feature learning. This approach produces a graph image that richly captures the raw data’s inherent information and provides interpretable visual attention cues. Furthermore, SKETCH applies independent min–max normalization on fixed-length temporal windows in real time, mitigating degradation from absolute coordinate fluctuations caused by varying sensor viewpoints or differences in individual body proportions. Through these designs, our approach becomes inherently topology-agnostic, avoiding fragile dependencies on dataset- or sensor-specific skeleton definitions. By leveraging pre-trained vision backbones, SKETCH achieves efficient convergence and superior recognition accuracy. Experimental results on SHREC’19 and SHREC’22 benchmarks show that it outperforms state-of-the-art methods in both robustness and generalization, establishing a new paradigm for skeleton-based hand gesture recognition. The code is available at https://github.com/capableofanything/SKETCH.

Source-free domain adaptation (SFDA) aims to adapt a pre-trained source model to an unlabeled target domain without requiring labeled source data. In a self supervised setting, relying on pseudo labels on target domain samples facilitates the domain adaptation performance providing strong supervision. However, a critical problem of this approach is the inherent instability of the pre-trained source model in the target domain, leading to unreliable pseudo labels for the target domain data. To tackle this, we propose a novel Dual-perspective pseudo labeling strategy that jointly leverages a task-specific perspective and a domain-invariant perspective, assigning pseudo labels only to target samples on which the target model’s predictions and CLIP’s predictions agree. To further enhance representation learning without introducing noisy supervision, we apply consistency training to uncertain samples. Additionally, we introduce a Tsallis mutual information(TMI)-based vision optimization strategy guided by an Uncertainty-based adaptation index (UAI), which dynamically modulates entropy sensitivity based on the model’s adaptation uncertainty. The UAI-based training paradigm enables stable and adaptive domain alignment by effectively balancing exploration and exploitation processes during the optimization process. Our proposed method achieves state-of-the-art performance on domain adaptation benchmark datasets, improving adaptation accuracy by 1.6% on Office-Home, 1.4% on VisDA-C, and 2.9% on DomainNet-126, demonstrating its effectiveness in SFDA. The code is publicly available at https://github.com/l3umblee/duet-sfda.

While existing supervised deep learning-based lane detection methods achieve exceptional detection performance, constructing a large real-world dataset with labels is a cost-intensive task. Therefore, we propose a novel sim-to-real unsupervised domain adaptation method specialized in lane detection. In this paper, we present a disentangled feature alignment approach that performs selective adaptation for lane and background features. By performing the disentangled prototype-based local and global feature alignments, we solve the negative transfer problem of an existing adversarial feature alignment-based domain adaptation for lane detection. In addition, the lane detection task requires accurate localization of the lanes even in occluded parts. Therefore, we adopt a consistency regularization strategy using masked images to improve the detection accuracy in the occluded area. Additionally, we introduce an adaptive resolution adjustment of the masked-out patch based on training maturity for context learning. By applying a simple framework, we achieve superior lane detection accuracy with lower false positives and false negatives in the target domain compared to conventional methods. Extensive experiments demonstrate the superiority of the proposed method.

The consistency training (CT)-based semi-supervised learning (SSL) bites state-of-the-art performance on SSL-based image classification. However, the existing CT-based SSL methods do not highlight the non-Euclidean characteristics and class-wise varieties of embedding spaces in an SSL model, thus they cannot fully utilize the effectiveness of CT. Thus, we propose a metric tensor-based consistency regularization, exploiting the class-variant geometrical structure of embeddings on the high-dimensional feature space. The proposed method not only minimizes the prediction discrepancy between different views of a given image but also estimates the intrinsic geometric curvature of embedding spaces by employing the global and local metric tensors. The global metric tensor is used to globally estimate the class-invariant embeddings from the whole data distribution while the local metric tensor is exploited to estimate the class-variant embeddings of each cluster. The two metric tensors are optimized by the consistency regularization based on the weak and strong augmentation strategy. The proposed method provides the highest classification accuracy on average compared to the existing state-of-the-art SSL methods on conventional datasets.

The motivation of the semi-supervised domain adaptation (SSDA) is to train a model by leveraging knowledge acquired from the plentiful labeled source combined with extremely scarce labeled target data to achieve the lowest error on the unlabeled target data at the testing time. However, due to inter-domain and intra-domain discrepancies, the improvement of classification accuracy is limited. To solve these, we propose the Trico-training method that utilizes a multilayer perceptron (MLP) classifier and two graph convolutional network (GCN) classifiers called interview GCN and intra-view GCN classifiers. The first co-training strategy exploits a correlation between MLP and inter-view GCN classifiers to minimize the inter-domain discrepancy, in which the inter-view GCN classifier provides its pseudo labels to teach the MLP classifier, which encourages class representation alignment across domains. In contrast, the MLP classifier gives feedback to the inter-view GCN classifier by using a new concept, ‘pseudo-edge’, for neighbor’s feature aggregation. Doing this increases the data structure mining ability of the inter-view GCN classifier; thus, the quality of generated pseudo labels is improved. The second co-training strategy between MLP and intra-view GCN is conducted in a similar way to reduce the intra-domain discrepancy by enhancing the correlation between labeled and unlabeled target data. Due to an imbalance in classification accuracy between inter-view and intra-view GCN classifiers, we propose the third co-training strategy that encourages them to cooperate to address this problem. We verify the effectiveness of the proposed method on three standard SSDA benchmark datasets: Office-31, Office-Home, and DomainNet. The extended experimental results show that our method surpasses the prior state-of-the-art approaches in SSDA.

Recently, due to the rapid development of deep neural networks in the field of computer vision, many studies have been conducted in the field of image deblurring. However, previous methods cannot attain satisfactory deblurring performance in object boundaries and local regions containing image details in restored results. This paper proposes a new method that uses a locally adaptive channel attention module for a spectral–spatial network to resolve the problem of single-image deblurring. Unlike existing methods, our proposed method consists of a spectral restorer and spatial restorer that adopt a locally adaptive attention mechanism in the spectral–spatial domains. In addition, unlike a conventional spectral–spatial network that only considers the magnitude of the frequency coefficients, the proposed method uses both the magnitude and phase of the frequency coefficients in the training stage. Our locally adaptive channel attention spectral–spatial network can focus on informative channels that are closely related to blur artifacts. Specifically, the spatial restorer, which guides the intensity of the blur image to fit the ground truth by exploring the interdependencies of feature channels, can efficiently restore scene characteristics while the spectral restorer, which guides the magnitude and phase of the blur image’s frequency coefficients to fit those of the ground truth by exploring the interdependencies of feature channels, fine-tunes the details of structures. The experimental results show that the proposed method outperformed the deblurring results compared to benchmark methods in terms of both qualitative evaluation and quantitative metrics.

Multitarget domain adaptation (MTDA) is a transfer learning task that uses knowledge extracted from a labeled source domain to adapt across multiple unlabeled target domains. The MTDA setting is more complicated than the single-source-single-target domain adaptation (S3TDA) setting because domain shift not only exists in each pair of a source–target domain but also exists among different target domains. In addition, multiple-target domains have their own unique characteristics because they are often collected from various conditions. The semantic information in each target domain can be damaged when they are naïvely merged into a single-target domain. Therefore, the trained model struggles to distinguish between representations in the combined target domain, which degrades the classification performance. Furthermore, the knowledge transferability from the source domain to multiple-target domains in prior studies leaves room for improvement because they only focus on exploiting the relationship of source–target pairs while failing to consider the correlation among multiple-target domains. This article introduces an easy-to-hard adaption structure to solve these problems in MTDA. The proposed method consists of three components: Extracting source representations, Hierarchical intratarget feature Alignment, and Collaborative intertarget feature Alignment, called EHACA. These components are used to encode the semantic information in each target domain and explore the relationships between the source and target domains, and among different target domains. The proposed method shows outstanding classification performance over five remote sensing datasets of MTDA tasks, surpassing state-of-the-art approaches in most experimental scenarios.

In this work, we observed that a nonlinear line could be expressed with a set of linear lines. We propose a novel lane detection method with polyline-based reconstruction based on this hypothesis. We define the optimal principal points with a new metric, the principal score, to generate the polyline. According to the principal score, we select principal points having a high influence on lane reconstruction and simply reproduce the target lane by connecting them. Additionally, conventional methods predict a fixed number of parameters to express each lane. However, this can limit an ability to represent a lane curvature and cause inaccurate detection results. Therefore, we set the number of principal points to be dynamically changed depending on the lane curvature to solve this problem. This allows the model to make flexible detection results reflecting the characteristics of each lane. We also propose a training strategy with a new piece-wise linear equation-based loss function. With this strategy, the model is fine-tuned to predict the principal points representing the curved parts of the lane well. Last, we propose a spatial context-aware feature flip fusion module to exploit the symmetric property of road images. This module helps the model selectively utilize the spatial context in the flipped feature map based on the lane density. We effectively reduce the adverse effects, especially the false positives of the existing feature flip fusion module misaligned on asymmetrical images. The experiments show that the proposed method provides competitive lane detection results compared to state-of-the-art methods.

Due to the unique characteristics of remote sensing (RS) data, it is challenging to collect richer labeled samples for training the deep learning model compared with the natural image data. To solve this problem, recently, multi-source-single-target (MS2T) scenarios have started receiving significant attention in which the knowledge from multiple sources is integrated to transfer to a target domain with the assumption that label spaces of each source and target domain are the same. However, in real-world applications, it can be challenging to find a source domain that completely includes all classes of the target domain. Therefore, to cover all class information of the target domain, they often naïvely merge multiple sources into a complete single source. However, each source domain typically has a different data distribution; thus, the semantic information of each source domain can be damaged, leading to degrading the classification accuracy of the target domain. To address this problem, we propose a unified framework termed Multi-Expert Collaboration for Knowledge Adaptation (MECKA) from various sources. MECKA includes two main processes: multiple-view generation and collaborative learning. Multiview learning plays an essential role in preserving the unique characteristics of each source domain. In contrast, collaborative learning is responsible for connecting these views that leverage complementary information from each other to perform on an unseen target domain robustly. Experimental results showed that the proposed method achieved the best classification accuracy on remote sensing scene benchmark datasets on both complete and incomplete multisource unsupervised domain adaptation (UDA) tasks compared to benchmark methods.

Displays and content have various resolutions and aspect ratios, requiring an image downscaler to adaptively reduce the image resolution. However, research on downscaling has garnered less attention than upscaling, including super-resolution. In practical display systems, simple interpolation, such as a bicubic filter that cannot preserve image details well, is still widely used for image downscaling rather than frame optimization-based or learning-based methods because of following reasons: frame optimization-based methods can effectively preserve image details after downscaling but are difficult to implement due to hardware costs. Learning-based methods have not been developed because defining a target downscaled image for training is difficult and training all downscaling factors is impossible. We propose a novel kernel-learning-based image downscaler to improve detail-preservation quality while supporting arbitrary downscaling factors using simple linear mapping. For this, a method to produce the ideal target downscaling result considering aliasing artifacts and detail preservation after downscaling is proposed. Then, we propose a training technique using the positional relationship between input and output pixels and a hierarchical region analysis to reproduce target images through simple kernel-based linear mapping. Lastly, a kernel-sharing technique is proposed to generate downscaling results for downscaling factors using a minimum number of trained kernels. In the simulation results, the proposed method demonstrated excellent edge preservation by improving the recall, precision, and F1 score, measuring the edge consistency between input and downscaled images, by up to 0.141, 0.079, 0.053, respectively, compared to benchmark methods. In a paired-comparison-based user study, the proposed method obtained the highest preference among benchmark methods using simple operations.

Video retargeting is a technique used to transform a given video to a target aspect ratio. Current methods often cause severe visual distortion due to frequent temporal incoherence during the retargeting. In this study, we propose a new extrapolation-based video retargeting method using an image-to-warping vector generation network to maintain temporal coherence and prevent deformation of an input frame by extending the side area of an input frame. Backward warping-based extrapolation is performed using a displacement vector (DV) that is generated by a proposed convolutional neural network (CNN). The DV is defined as the displacement between the current hole to be filled in the extended area and a pixel in the input frame used to fill the hole. We also propose a technique to efficiently train the CNN including a method for ground-truth DV generation. After the extrapolation, we propose a technique for the maintenance of temporal coherence of the extended region and a distortion suppression scheme (DSC) for minimizing visual artifacts. The simulation results demonstrated that the proposed method improved bidirectional similarity (BDS) up to 3.69, which is a measure of the quality of video retargeting, compared with existing video retargeting methods.

This study proposes a video retargeting method using deep neural network-based object detection. First, the meaningful regions of the input video denoted by bounding boxes of the object detection are extracted. In this case, the area is defined considering the size and number of bounding boxes for objects detected. The bounding boxes of each frame image are considered as regions of interest (RoIs). Second, the Siamese object tracking network is used to address high computational complexity of the object detection network. By dividing the video into scenes, object detection is performed for the first frame image of each scene to obtain the first bounding box. Object tracking is performed for the next sequential frame image until a scene change is detected. Third, the image is resized in the horizontal direction to alter the aspect ratio of the image and obtain the 1D RoIs of the image by projecting bounding boxes in the vertical direction. Then, the proposed method computes the grid map from the 1D RoIs to calculate new coordinates of each column data of the image. Finally, the retargeted video is obtained by rearranging all retargeted frame images. Comparative experiments conducted with various benchmark methods show an average bidirectional similarity score of 1.92, which is higher than other conventional methods. The proposed method was stable and satisfied viewers without causing cognitive discomfort as conventional methods.

Video retargeting is a method of adjusting the aspect ratio of a given video to the target aspect ratio. However, temporal incoherence of video contents, which can occur frequently by video retargeting, is the most dominant factor that degrades the quality of retargeted videos. Current methods to maintain temporal coherence use the entire frames of the input videos; however, these methods cannot be implemented as on-time systems because of their tremendous computational complexity. As far as we know, there is no existing on-time video retargeting method that can avoid spatial distortion while perfectly maintaining temporal coherence. In this paper, we propose a novel on-time video retargeting method that can perfectly maintain temporal coherence and prevent the spatial distortion by using only two consecutive input frames. In our method, the maximum a posteriori-based foreground aware-block matching is used for the extrapolation that extends the side area of a given video to adjust its aspect ratio to the target. To maintain the temporal coherence of the extended area, the result of block matching for backward warping-based extrapolation of the start frame after the scene change occurs, is reused for the other frames until the next scene change occurs. In addition, we propose a scene scenario-adaptive fallback scheme to prevent severe distortions that can occur with reusing block matching results or extrapolation-based side extension. The simulation results showed that the proposed method greatly improved the bidirectional similarity value, which can measure the quality of video retargeting, by up to 10.26 compared with the existing on-time video retargeting methods.

We propose a novel image denoising method based on a convolutional neural network (CNN), which uses the separable convolution and the gradient prior to reduce the computational complexity while enhancing the denoising performance. The proposed method converts the existing convolution filter in the conventional CNN denoiser to cascaded vertical and horizontal separable convolutions and reduces the number of feature channels between these convolutions by analyzing the distribution of convolution weights. The proposed separable convolution with feature dimension shrinking can greatly reduce the number of multiplications for CNN while minimizing the degradation of denoising quality. In addition, gradients of a given image are used as input for the proposed CNN denoiser by exploiting the relation between an anisotropic diffusion-based denoiser and a residual CNN denoiser to improve the quality of the image denoising. The simulation results showed that the proposed method provided comparable denoising quality while reducing the number of multiplications to 41% compared to the existing state-of-the-art CNN denoiser.

We propose an advanced anisotropic-diffusion (AD)-based approach for an image denoising method, which utilizes a geodesic path to produce single-pass adaptive smoothing by analyzing the diffusion continuity. The proposed method consists of the following four procedures: element-weight determination, geodesic path-based kernel (GPK) generation, single-pass smoothing using the GPK, and post-processing of the GPK smoothing. In the first procedure, weights for neighboring pixels are calculated by diffusivity analysis. In the second procedure, a geodesic path is selected using a geodesic distance that is calculated by a diffusion continuity analysis. In the third procedure, GPK-based smoothing is applied to a given noisy image to extract the noise-free pixel value. Finally, a distant AD that uses the double diffusion length is applied to the resultant image by the GPK filtering to enhance the quality of noise suppression in smooth regions. In addition to the main procedures, schemes for the robust outlier reduction and complexity reduction are introduced. The simulation results showed that the proposed method improved the denoising quality by increasing the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) by up to 4.094 dB and 0.057, respectively, compared to the AD-based benchmark methods. Compared to block-matching and 3-D filtering, the proposed method showed comparable quality of noise reduction with similar PSNR and SSIM values, which it accomplished with much less computation time.

This paper proposes a foreground-based approach to generating a depth map which will be used for 2D-to-3D conversion. For a given input image, the proposed approach determines if the image is an object-view (OV) scene or a non-object-view (NOV) scene, depending on the existence of foreground objects which are clearly distinguishable from the background. If the input image is an OV scene, the proposed approach extracts a foreground using block-wise background modeling and performs segmentation using adaptive background region selection and color modeling. Then, it performs segment-wise depth merging and cross bilateral filtering (CBF) to generate a final depth map. On the other hand, for the NOV scene, the proposed approach uses a conventional color-based depth map generation method [9] which has simple operations but provides a 3D depth map of good quality. Human beings are usually more sensitive to depth map quality, and 3D images, for OV scenes than for NOV scenes. With the proposed approach, it is possible to improve the quality of a depth map for OV scenes than using the conventional methods only. The performance of the proposed approach was evaluated through the subjective evaluation after 2D-to-3D conversion using a 3D display, and the proposed one provided the best depth quality and visual comfort among the benchmark methods.

This study presents an advanced histogram‐based image segmentation method that enhances image segmentation quality, while greatly reducing the computational complexity. Unlike existing histogram‐based methods, the authors optimise the size of bins in the colour histogram by using human perception‐based colour quantisation and the clustering centroids are selected effectively without using a complex process. Additionally, an over‐segmentation removal technique based on connected‐component labelling is employed. This improves the segmentation quality by connectivity analysis. A comparison between the experimental results on the Berkeley Segmentation Dataset by the proposed method and the benchmark methods demonstrated that the proposed method enhanced the segmentation quality by improving the Probabilistic Rand Index and the Segmentation Covering values compared with those of the benchmark methods. The computation time using the proposed method is reduced by up to 91.63% compared with the computation time using benchmark methods.