Unified Transformation Research Articles

Enhancing transformer windings monitoring: An approach using longitudinal branch‐circuit conductance analysis

AbstractThe operating environment of transformers is getting more complex with the emergence of new energy sources and power electronic devices. This complexity can cause minor internal faults in transformer windings. Under the cumulative effect, minor faults gradually develop into serious faults, resulting in transformer damage. Conventional differential protection systems may have difficulty detecting these glitches and require avoiding the problem of protection false activation caused by inrush currents. This paper proposes a new online monitoring method for transformer windings based on longitudinal branch‐circuit conductance to address this issue. First, a unified transformer equivalent circuit is proposed to represent transformers under normal conditions, inrush currents, and internal faults. Then, an online transformer monitoring method based on branch conductance is proposed, which is immune to inrush currents. This method aims to prevent delayed detection of faults during inrush currents, improving sensitivity and response speed, especially for minor turn‐to‐turn faults hidden in inrush currents. The proposed method also provides higher sensitivity to minor turn‐to‐turn faults and larger protection margins. Simulation and experimental results validate the effectiveness of this method.

Underwater image restoration using physical models with generative adversarial network and unified transformer framework

Underwater image restoration using physical models with generative adversarial network and unified transformer framework

The Robin Problems in the Coupled System of Wave Equations on a Half-Line

This article investigates the local well-posedness of a coupled system of wave equations on a half-line, with a particular emphasis on Robin boundary conditions within Sobolev spaces. We provide estimates for the solutions to linear initial-boundary-value problems related to the coupled system of wave equations, utilizing the Unified Transform Method in conjunction with the Hadamard norm while considering the influence of external forces. Furthermore, we demonstrate that replacing the external force with a nonlinear term alters the iteration map defined by the unified transform solutions, making it a contraction map in a suitable solution space. By employing the contraction mapping theorem, we establish the existence of a unique solution. Finally, we show that the data-to-solution map is locally Lipschitz continuous, thus confirming the local well-posedness of the coupled system of wave equations under consideration.

Optimizing Convolution Neural Nets with a Unified Transformation Approach

Optimizing Convolution Neural Nets with a Unified Transformation Approach

The unified transformation approach to higher-order Gerdjikov-Ivanov model and Riemann-Hilbert problem

In this paper, a higher-order Gerdjikov-Ivanov (HOGI) model with cubic dispersion and quintic nonlinearity terms will be researched, which is a 3-order flow model of the well known GI system. The initial-boundary value problems of the HOGI model on the half-line will be given by the unified transformation approach. The solutions of the HOGI model will be expressed by forms of the solutions of a matrix Riemann-Hilbert problem (RHP). The relevant jump matrices of the RHP will be explicitly found by the two scattering matrices s(ϵ) and S(ϵ). Finally, the so-called global relation will be given.

UTMGAT: a unified transformer with memory encoder and graph attention networks for multidomain dialogue state tracking

UTMGAT: a unified transformer with memory encoder and graph attention networks for multidomain dialogue state tracking

Un-Gaze: A Unified Transformer for Joint Gaze-Location and Gaze-Object Detection

Un-Gaze: A Unified Transformer for Joint Gaze-Location and Gaze-Object Detection

Likelihood inference for unified transformation cure model with interval censored data

Likelihood inference for unified transformation cure model with interval censored data

UnifiedTT: Visual tracking with unified transformer

Target tracking is an important research task in computer vision. Existing tracking algorithms based on Siamese networks often suffer from the problem of information redundancy between adjacent frames and a lack of ability to capture global dependencies. When similar backgrounds appear around the target, the tracking performance usually significantly decreases. Although target tracking algorithms based on deep convolution and the Transformer have partially addressed these issues, achieving a good balance between the two remains a challenge. In this work, we propose a unified convolution and self-attention Siamese network for target tracking. By utilizing a feature extraction backbone network based on integrated convolution and self-attention styles, we are able to capture globally important regions and key frames while greatly reducing local redundant computations, thereby improving tracking performance. We apply this approach to the task of target tracking and enhance the feature extraction capabilities of both the target template and search template. Experimental results show that our proposed tracking algorithm outperforms some recent classical tracking algorithms, especially achieving improvements of 10.7 % on the high-diversity dataset GOT-10K and 24.7 % on the large-scale and high-quality LaSOT dataset.

UTSRMorph: A Unified Transformer and Superresolution Network for Unsupervised Medical Image Registration.

Complicated image registration is a key issue in medical image analysis, and deep learning-based methods have achieved better results than traditional methods. The methods include ConvNet-based and Transformer-based methods. Although ConvNets can effectively utilize local information to reduce redundancy via small neighborhood convolution, the limited receptive field results in the inability to capture global dependencies. Transformers can establish long-distance dependencies via a self-attention mechanism; however, the intense calculation of the relationships among all tokens leads to high redundancy. We propose a novel unsupervised image registration method named the unified Transformer and superresolution (UTSRMorph) network, which can enhance feature representation learning in the encoder and generate detailed displacement fields in the decoder to overcome these problems. We first propose a fusion attention block to integrate the advantages of ConvNets and Transformers, which inserts a ConvNet-based channel attention module into a multihead self-attention module. The overlapping attention block, a novel cross-attention method, uses overlapping windows to obtain abundant correlations with match information of a pair of images. Then, the blocks are flexibly stacked into a new powerful encoder. The decoder generation process of a high-resolution deformation displacement field from low-resolution features is considered as a superresolution process. Specifically, the superresolution module was employed to replace interpolation upsampling, which can overcome feature degradation. UTSRMorph was compared to state-of-the-art registration methods in the 3D brain MR (OASIS, IXI) and MR-CT datasets (abdomen, craniomaxillofacial). The qualitative and quantitative results indicate that UTSRMorph achieves relatively better performance. The code and datasets used are publicly available at https://github.com/Runshi-Zhang/UTSRMorph.

V2X-ViTv2: Improved Vision Transformers for Vehicle-to-Everything Cooperative Perception.

In this paper, we study the application of Vehicle-to-Everything (V2X) communication to improve the perception performance of autonomous vehicles. We present V2X-ViTs, a robust cooperative perception framework with V2X communication using novel vision Transformer models. First, we present V2X-ViTv1 containing holistic attention modules that can effectively fuse information across on-road agents (i.e., vehicles and infrastructure). Specifically, V2X-ViTv1 consists of alternating layers of heterogeneous multi-agent self-attention and multi-scale window self-attention, which captures inter-agent interaction and per-agent spatial relationships. These key modules are designed in a unified Transformer architecture to handle common V2X challenges, including asynchronous information sharing, pose errors, and heterogeneity of V2X components. Second, we propose an advanced architecture, V2X-ViTv2, that enjoys increased ability for multi-scale perception. We also propose advanced data augmentation techniques tailored for V2X applications to improve performance. We construct a large-scale V2X perception dataset using CARLA and OpenCDA to validate our approach. Extensive experimental results on both synthetic and real-world datasets show that V2X-ViTs achieve state-of-the-art performance for 3D object detection and are robust even under harsh, noisy environments. All the code and trained models will be available at https://github.com/DerrickXuNu/OpenCOOD.

A Unified Transformer Framework for Group-Based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection

Humans tend to mine objects by learning from a group of images or several frames of video since we live in a dynamic world. In the computer vision area, many researchers focus on co-segmentation (CoS), co-saliency detection (CoSD) and video salient object detection (VSOD) to discover the co-occurrent objects. However, previous approaches design different networks for these similar tasks separately, and they are difficult to apply to each other. Besides, they fail to take full advantage of the cues among inter- and intra-feature within a group of images. In this paper, we introduce a unified framework to tackle these issues from a unified view, term as UFGS (Unified Framework for Group-based Segmentation). Specifically, we first introduce a transformer block, which views the image feature as a patch token and then captures their long-range dependencies through the self-attention mechanism. This can help the network to excavate the patch-structured similarities among the relevant objects. Furthermore, we propose an intra-MLP learning module to produce self-mask to enhance the network to avoid partial activation. Extensive experiments on four CoS benchmarks (PASCAL, iCoseg, Internet and MSRC), three CoSD benchmarks (Cosal2015, CoSOD3k, and CocA) and five VSOD benchmarks (DAVIS <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$_{16}$</tex-math></inline-formula> , FBMS, ViSal, SegV2 and DAVSOD) show that our method outperforms other state-of-the-arts on three different tasks in both accuracy and speed by using the same network architecture, which can reach 140 FPS in real-time. Code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/suyukun666/UFO</uri>

PVPUFormer: Probabilistic Visual Prompt Unified Transformer for Interactive Image Segmentation.

Integration of diverse visual prompts like clicks, scribbles, and boxes in interactive image segmentation significantly facilitates users' interaction as well as improves interaction efficiency. However, existing studies primarily encode the position or pixel regions of prompts without considering the contextual areas around them, resulting in insufficient prompt feedback, which is not conducive to performance acceleration. To tackle this problem, this paper proposes a simple yet effective Probabilistic Visual Prompt Unified Transformer (PVPUFormer) for interactive image segmentation, which allows users to flexibly input diverse visual prompts with the probabilistic prompt encoding and feature post-processing to excavate sufficient and robust prompt features for performance boosting. Specifically, we first propose a Probabilistic Prompt-unified Encoder (PPuE) to generate a unified one-dimensional vector by exploring both prompt and non-prompt contextual information, offering richer feedback cues to accelerate performance improvement. On this basis, we further present a Prompt-to-Pixel Contrastive (P2C) loss to accurately align both prompt and pixel features, bridging the representation gap between them to offer consistent feature representations for mask prediction. Moreover, our approach designs a Dual-cross Merging Attention (DMA) module to implement bidirectional feature interaction between image and prompt features, generating notable features for performance improvement. A comprehensive variety of experiments on several challenging datasets demonstrates that the proposed components achieve consistent improvements, yielding state-of-the-art interactive segmentation performance. Our code is available at https://github.com/XuZhang1211/PVPUFormer.

Refining one-class representation: A unified transformer for unsupervised time-series anomaly detection

The deep unsupervised time-series anomaly detector depends on the one-class representation, which is more effective by only formulating the normal samples. However, normal samples are always mixed with anomalies in the unlabeled training dataset. The learned one-class representation may be biased and violates the one-class setting. To address this problem, we refine the one-class representation and propose a unified AMFormer (Active Masked transFormer) framework, which integrates Transformer with the masked operation mechanism and cost-sensitive learning theory. Specifically, we first develop a network-driven masked operation with Hadamard product transformation to damage the initial input samples. The encoder and decoder representations rebuild the processed incomplete samples, which avoids identical shortcuts and further enhances robustness. Secondly, we exploit the active MSE (Mean Squared Error) loss function to purify the training samples. The different weights are dynamically added to different kinds of samples according to their rebuilding-errors-based pseudo labels. The pseudo anomalies with more significant rebuilding errors are removed by putting lower weights. Finally, extensive experiments are conducted on four benchmark datasets. The experimental results demonstrate that our AMFormer outperforms the nine relevant benchmark algorithms, boosting the mean f1-score from 0.851 to 0.937.

A Unified Transformation Framework for Studying Various Situations of Vertical/Oblique Drop Impact on Horizontal/Inclined Stationary/Moving Flat Surfaces

There are various situations of drop impact on solid surfaces widely occurred in natural phenomenon or used in different industrial applications. However, comparing and classifying these drop impact situations is not easy due to different states of the parameters affecting drop impact dynamics. In this article, a unified transformation framework is proposed to study various situations of vertical/oblique drop impact on horizontal/inclined stationary/moving flat surfaces with/without a crossflow. This simple framework consists of a coordinate with normal and tangential axes on a horizontal stationary surface. For each drop impact situation, the drop velocity, gravitational acceleration, possible induced flow due to the moving surface, and possible crossflow are transformed into the framework. Comparing the transformed versions of considered drop impact situations facilitates identification of their physical similarities/differences and determines which situations (and under what conditions) lead to identical results and can be used interchangeably. Although common situations of drop impact on moving surfaces (having tangential component of surface velocity) lead to asymmetric drop spreading, the possibility of symmetric drop spreading on moving surfaces is demonstrated and analyzed using the proposed transformation framework. This interesting possibility means that for related production lines or experimental setups, where symmetrical drop spreading is required, the surface does not need to be stationary. In such applications/setups, the use of moving surfaces (rather than stationary surfaces) can considerably accelerate the symmetric drop impact process. Our simulation results of several of the considered drop impact situations well confirm the facilities/predictions of the proposed transformation framework.

USCFormer: Unified Transformer With Semantically Contrastive Learning for Image Dehazing

Haze severely degrades the visibility of scene objects and deteriorates the performance of autonomous driving, traffic monitoring, and other vision-based intelligent transportation systems. As a potential remedy, we propose a novel unified Transformer with semantically contrastive learning for image dehazing, dubbed USCFormer. USCFormer has three key contributions. First, USCFormer absorbs the respective strengths of CNN and Transformer by incorporating them into a unified Transformer format. Thus, it allows the simultaneous capture of global-local dependency features for better image dehazing. Second, by casting clean/hazy images as the positive/negative samples, the contrastive constraint encourages the restored image to be closer to the ground-truth images (positives) and away from the hazy ones (negatives). Third, we regard the semantic information as important prior knowledge to help USCFormer mitigate the effects of haze on the scene and preserve image details and colors by leveraging intra-object semantic correlation. Experiments on synthetic datasets and real-world hazy photos fully validate the superiority of USCFormer in both perceptual quality assessment and subjective evaluation. Code is available at https://github.com/yz-wang/USCFormer.

UniFormer: Unifying Convolution and Self-Attention for Visual Recognition.

It is a challenging task to learn discriminative representation from images and videos, due to large local redundancy and complex global dependency in these visual data. Convolution neural networks (CNNs) and vision transformers (ViTs) have been two dominant frameworks in the past few years. Though CNNs can efficiently decrease local redundancy by convolution within a small neighborhood, the limited receptive field makes it hard to capture global dependency. Alternatively, ViTs can effectively capture long-range dependency via self-attention, while blind similarity comparisons among all the tokens lead to high redundancy. To resolve these problems, we propose a novel Unified transFormer (UniFormer), which can seamlessly integrate the merits of convolution and self-attention in a concise transformer format. Different from the typical transformer blocks, the relation aggregators in our UniFormer block are equipped with local and global token affinity respectively in shallow and deep layers, allowing tackling both redundancy and dependency for efficient and effective representation learning. Finally, we flexibly stack our blocks into a new powerful backbone, and adopt it for various vision tasks from image to video domain, from classification to dense prediction. Without any extra training data, our UniFormer achieves 86.3 top-1 accuracy on ImageNet-1 K classification task. With only ImageNet-1 K pre-training, it can simply achieve state-of-the-art performance in a broad range of downstream tasks. It obtains 82.9/84.8 top-1 accuracy on Kinetics-400/600, 60.9/71.2 top-1 accuracy on Something-Something V1/V2 video classification tasks, 53.8 box AP and 46.4 mask AP on COCO object detection task, 50.8 mIoU on ADE20 K semantic segmentation task, and 77.4 AP on COCO pose estimation task. Moreover, we build an efficient UniFormer with a concise hourglass design of token shrinking and recovering, which achieves 2-4[Formula: see text] higher throughput than the recent lightweight models.

Unified Transformer with Cross-Modal Mixture Experts for Remote-Sensing Visual Question Answering

Remote-sensing visual question answering (RSVQA) aims to provide accurate answers to remote sensing images and their associated questions by leveraging both visual and textual information during the inference process. However, most existing methods ignore the significance of the interaction between visual and language features, which typically adopt simple feature fusion strategies and fail to adequately model cross-modal attention, struggling to capture the complex semantic relationships between questions and images. In this study, we introduce a unified transformer with cross-modal mixture expert (TCMME) model to address the RSVQA problem. Specifically, we utilize the vision transformer (VIT) and BERT to extract visual and language features, respectively. Furthermore, we incorporate cross-modal mixture experts (CMMEs) to facilitate cross-modal representation learning. By leveraging the shared self-attention and cross-modal attention within CMMEs, as well as the modality experts, we effectively capture the intricate interactions between visual and language features and better focus on their complex semantic relationships. Finally, we conduct qualitative and quantitative experiments on two benchmark datasets: RSVQA-LR and RSVQA-HR. The results demonstrate that our proposed method surpasses the current state-of-the-art (SOTA) techniques. Additionally, we perform an extensive analysis to validate the effectiveness of different components in our framework.

Unified Transformer With Isomorphic Branches for Natural Language Tracking

Natural language tracking aims to localize the target object referred to by a language description using a sequence of bounding boxes in video frames. Compared with traditional visual single object tracking initialized with only a bounding box (BBox), this task introduces high-level semantic information to reduce the ambiguity of BBox and enhance the ability to retrieve the target in a global manner. Thus, it can yield more accurate and robust tracking results. Previous methods usually adopt off-the-shelf grounding and tracking branches to tackle this task, where feature representations are learned in isolation without benefiting each other. The two branches can associate with each other to discover crucial clues since the language description and the template image provide information from different sources. Therefore, we propose a unified transformer method for natural language tracking named TransNLT, which utilizes isomorphic Transformer structures for grounding and tracking branches where collaborative learning is enabled to construct comprehensive features for the target. In addition, we propose a Selective Feature Gathering (SFG) module which can integrate cross-modal global information of the tracking target from the visual template and language description. Through effective interaction of visual and language information, we can achieve better results than tracking with only a single modality. Extensive experiments on three popular natural language tracking benchmarks show our proposed TransNLT outperforms previous state-of-the-art methods.

Fixed-time safe tracking control of uncertain high-order nonlinear pure-feedback systems via unified transformation functions

Fixed-time safe tracking control of uncertain high-order nonlinear pure-feedback systems via unified transformation functions