Xiao‐Jun Wu

Xue-Feng Zhu, Tianyang Xu, Zhangyong Tang et al.

RGB-D object tracking has attracted considerable attention recently, achieving promising performance thanks to the symbiosis between visual and depth channels. However, given a limited amount of annotated RGB-D tracking data, most state-of-the-art RGB-D trackers are simple extensions of high-performance RGB-only trackers, without fully exploiting the underlying potential of the depth channel in the offline training stage. To address the dataset deficiency issue, a new RGB-D dataset named RGBD1K is released in this paper. The RGBD1K contains 1,050 sequences with about 2.5M frames in total. To demonstrate the benefits of training on a larger RGB-D data set in general, and RGBD1K in particular, we develop a transformer-based RGB-D tracker, named SPT, as a baseline for future visual object tracking studies using the new dataset. The results, of extensive experiments using the SPT tracker emonstrate the potential of the RGBD1K dataset to improve the performance of RGB-D tracking, inspiring future developments of effective tracker designs. The dataset and codes will be available on the project homepage: https://github.com/xuefeng-zhu5/RGBD1K.

Rongchang Li, Zhenhua Feng, Tianyang Xu et al.

Compositional actions consist of dynamic (verbs) and static (objects) concepts. Humans can easily recognize unseen compositions using the learned concepts. For machines, solving such a problem requires a model to recognize unseen actions composed of previously observed verbs and objects, thus requiring so-called compositional generalization ability. To facilitate this research, we propose a novel Zero-Shot Compositional Action Recognition (ZS-CAR) task. For evaluating the task, we construct a new benchmark, Something-composition (Sth-com), based on the widely used Something-Something V2 dataset. We also propose a novel Component-to-Composition (C2C) learning method to solve the new ZS-CAR task. C2C includes an independent component learning module and a composition inference module. Last, we devise an enhanced training strategy to address the challenges of component variations between seen and unseen compositions and to handle the subtle balance between learning seen and unseen actions. The experimental results demonstrate that the proposed framework significantly surpasses the existing compositional generalization methods and sets a new state-of-the-art. The new Sth-com benchmark and code are available at https://github.com/RongchangLi/ZSCAR_C2C.

Xue-Feng Zhu, Tianyang Xu, Jian Zhao et al.

Unmanned Aerial Vehicles (UAVs) have been widely used in many areas, including transportation, surveillance, and military. However, their potential for safety and privacy violations is an increasing issue and highly limits their broader applications, underscoring the critical importance of UAV perception and defense (anti-UAV). Still, previous works have simplified such an anti-UAV task as a tracking problem, where the prior information of UAVs is always provided; such a scheme fails in real-world anti-UAV tasks (i.e. complex scenes, indeterminate-appear and -reappear UAVs, and real-time UAV surveillance). In this paper, we first formulate a new and practical anti-UAV problem featuring the UAVs perception in complex scenes without prior UAVs information. To benchmark such a challenging task, we propose the largest UAV dataset dubbed AntiUAV600 and a new evaluation metric. The AntiUAV600 comprises 600 video sequences of challenging scenes with random, fast, and small-scale UAVs, with over 723K thermal infrared frames densely annotated with bounding boxes. Finally, we develop a novel anti-UAV approach via an evidential collaboration of global UAVs detection and local UAVs tracking, which effectively tackles the proposed problem and can serve as a strong baseline for future research. Extensive experiments show our method outperforms SOTA approaches and validate the ability of AntiUAV600 to enhance UAV perception performance due to its large scale and complexity. Our dataset, pretrained models, and source codes will be released publically.

Yanglin Deng, Tianyang Xu, Chunyang Cheng et al.

In recent years, Multi-Modality Image Fusion (MMIF) has been applied to many fields, which has attracted many scholars to endeavour to improve the fusion performance. However, the prevailing focus has predominantly been on the architecture design, rather than the training strategies. As a low-level vision task, image fusion is supposed to quickly deliver output images for observation and supporting downstream tasks. Thus, superfluous computational and storage overheads should be avoided. In this work, a lightweight Distilled Mini-Model with a Dynamic Refresh strategy (MMDRFuse) is proposed to achieve this objective. To pursue model parsimony, an extremely small convolutional network with a total of 113 trainable parameters (0.44 KB) is obtained by three carefully designed supervisions. First, digestible distillation is constructed by emphasising external spatial feature consistency, delivering soft supervision with balanced details and saliency for the target network. Second, we develop a comprehensive loss to balance the pixel, gradient, and perception clues from the source images. Third, an innovative dynamic refresh training strategy is used to collaborate history parameters and current supervision during training, together with an adaptive adjust function to optimise the fusion network. Extensive experiments on several public datasets demonstrate that our method exhibits promising advantages in terms of model efficiency and complexity, with superior performance in multiple image fusion tasks and downstream pedestrian detection application. The code of this work is publicly available at https://github.com/yanglinDeng/MMDRFuse.

Ziheng Chen, Yue Song, Xiao-Jun Wu et al.

Recent advances in Symmetric Positive Definite (SPD) matrix learning show that Riemannian metrics are fundamental to effective SPD neural networks. Motivated by this, we revisit the geometry of the Cholesky factors and uncover a simple product structure that enables convenient metric design. Building on this insight, we propose two fast and stable SPD metrics, Power--Cholesky Metric (PCM) and Bures--Wasserstein--Cholesky Metric (BWCM), derived via Cholesky decomposition. Compared with existing SPD metrics, the proposed metrics provide closed-form operators, computational efficiency, and improved numerical stability. We further apply our metrics to construct Riemannian Multinomial Logistic Regression (MLR) classifiers and residual blocks for SPD neural networks. Experiments on SPD deep learning, numerical stability analyses, and tensor interpolation demonstrate the effectiveness, efficiency, and robustness of our metrics. The code is available at https://github.com/GitZH-Chen/PCM_BWCM.

Ruyi Gan, Ziwei Wu, Renliang Sun et al.

Various large language models (LLMs) have been proposed in recent years, including closed- and open-source ones, continually setting new records on multiple benchmarks. However, the development of LLMs still faces several issues, such as high cost of training models from scratch, and continual pre-training leading to catastrophic forgetting, etc. Although many such issues are addressed along the line of research on LLMs, an important yet practical limitation is that many studies overly pursue enlarging model sizes without comprehensively analyzing and optimizing the use of pre-training data in their learning process, as well as appropriate organization and leveraging of such data in training LLMs under cost-effective settings. In this work, we propose Ziya2, a model with 13 billion parameters adopting LLaMA2 as the foundation model, and further pre-trained on 700 billion tokens, where we focus on pre-training techniques and use data-centric optimization to enhance the learning process of Ziya2 on different stages. We define three data attributes and firstly establish data-centric scaling laws to illustrate how different data impacts LLMs. Experiments show that Ziya2 significantly outperforms other models in multiple benchmarks especially with promising results compared to representative open-source ones. Ziya2 (Base) is released at https://huggingface.co/IDEA-CCNL/Ziya2-13B-Base and https://modelscope.cn/models/Fengshenbang/Ziya2-13B-Base/summary.

Cong Wu, Xiao-Jun Wu, Josef Kittler et al.

Contrastive learning has achieved great success in skeleton-based action recognition. However, most existing approaches encode the skeleton sequences as entangled spatiotemporal representations and confine the contrasts to the same level of representation. Instead, this paper introduces a novel contrastive learning framework, namely Spatiotemporal Clues Disentanglement Network (SCD-Net). Specifically, we integrate the decoupling module with a feature extractor to derive explicit clues from spatial and temporal domains respectively. As for the training of SCD-Net, with a constructed global anchor, we encourage the interaction between the anchor and extracted clues. Further, we propose a new masking strategy with structural constraints to strengthen the contextual associations, leveraging the latest development from masked image modelling into the proposed SCD-Net. We conduct extensive evaluations on the NTU-RGB+D (60&120) and PKU-MMD (I&II) datasets, covering various downstream tasks such as action recognition, action retrieval, transfer learning, and semi-supervised learning. The experimental results demonstrate the effectiveness of our method, which outperforms the existing state-of-the-art (SOTA) approaches significantly.

Rui Wang, Xiao-Jun Wu, Ziheng Chen et al.

Image set-based visual classification methods have achieved remarkable performance, via characterising the image set in terms of a non-singular covariance matrix on a symmetric positive definite (SPD) manifold. To adapt to complicated visual scenarios better, several Riemannian networks (RiemNets) for SPD matrix nonlinear processing have recently been studied. However, it is pertinent to ask, whether greater accuracy gains can be achieved by simply increasing the depth of RiemNets. The answer appears to be negative, as deeper RiemNets tend to lose generalization ability. To explore a possible solution to this issue, we propose a new architecture for SPD matrix learning. Specifically, to enrich the deep representations, we adopt SPDNet [1] as the backbone, with a stacked Riemannian autoencoder (SRAE) built on the tail. The associated reconstruction error term can make the embedding functions of both SRAE and of each RAE an approximate identity mapping, which helps to prevent the degradation of statistical information. We then insert several residual-like blocks with shortcut connections to augment the representational capacity of SRAE, and to simplify the training of a deeper network. The experimental evidence demonstrates that our DreamNet can achieve improved accuracy with increased depth of the network.

Shuang Wu, Xiaoning Song, Zhenhua Feng et al.

Recently, Flat-LAttice Transformer (FLAT) has achieved great success in Chinese Named Entity Recognition (NER). FLAT performs lexical enhancement by constructing flat lattices, which mitigates the difficulties posed by blurred word boundaries and the lack of word semantics. In FLAT, the positions of starting and ending characters are used to connect a matching word. However, this method is likely to match more words when dealing with long texts, resulting in long input sequences. Therefore, it significantly increases the memory and computational costs of the self-attention module. To deal with this issue, we advocate a novel lexical enhancement method, InterFormer, that effectively reduces the amount of computational and memory costs by constructing non-flat lattices. Furthermore, with InterFormer as the backbone, we implement NFLAT for Chinese NER. NFLAT decouples lexicon fusion and context feature encoding. Compared with FLAT, it reduces unnecessary attention calculations in "word-character" and "word-word". This reduces the memory usage by about 50% and can use more extensive lexicons or higher batches for network training. The experimental results obtained on several well-known benchmarks demonstrate the superiority of the proposed method over the state-of-the-art hybrid (character-word) models.

Yaozong Mo, Chaofeng Li, Wenqi Ren et al.

Deep learning-based methods have achieved significant performance for image defogging. However, existing methods are mainly developed for land scenes and perform poorly when dealing with overwater foggy images, since overwater scenes typically contain large expanses of sky and water. In this work, we propose a Prior map Guided CycleGAN (PG-CycleGAN) for defogging of images with overwater scenes. To promote the recovery of the objects on water in the image, two loss functions are exploited for the network where a prior map is designed to invert the dark channel and the min-max normalization is used to suppress the sky and emphasize objects. However, due to the unpaired training set, the network may learn an under-constrained domain mapping from foggy to fog-free image, leading to artifacts and loss of details. Thus, we propose an intuitive Upscaling Inception Module (UIM) and a Long-range Residual Coarse-to-fine framework (LRC) to mitigate this issue. Extensive experiments on qualitative and quantitative comparisons demonstrate that the proposed method outperforms the state-of-the-art supervised, semi-supervised, and unsupervised defogging approaches.

Ziheng Chen, Yue Song, Rui Wang et al.

Riemannian neural networks, which extend deep learning techniques to Riemannian spaces, have gained significant attention in machine learning. To better classify the manifold-valued features, researchers have started extending Euclidean multinomial logistic regression (MLR) into Riemannian manifolds. However, existing approaches suffer from limited applicability due to their strong reliance on specific geometric properties. This paper proposes a framework for designing Riemannian MLR over general geometries, referred to as RMLR. Our framework only requires minimal geometric properties, thus exhibiting broad applicability and enabling its use with a wide range of geometries. Specifically, we showcase our framework on the Symmetric Positive Definite (SPD) manifold and special orthogonal group, i.e., the set of rotation matrices. On the SPD manifold, we develop five families of SPD MLRs under five types of power-deformed metrics. On rotation matrices we propose Lie MLR based on the popular bi-invariant metric. Extensive experiments on different Riemannian backbone networks validate the effectiveness of our framework.

Wenhua Dong, Xiao-Jun Wu, Zhenhua Feng et al.

In most existing multi-view modeling scenarios, cross-view correspondence (CVC) between instances of the same target from different views, like paired image-text data, is a crucial prerequisite for effortlessly deriving a consistent representation. Nevertheless, this premise is frequently compromised in certain applications, where each view is organized and transmitted independently, resulting in the view-unaligned problem (VuP). Restoring CVC of unaligned multi-view data is a challenging and highly demanding task that has received limited attention from the research community. To tackle this practical challenge, we propose to integrate the permutation derivation procedure into the bipartite graph paradigm for view-unaligned clustering, termed Probabilistically Aligned View-unaligned Clustering with Adaptive Template Selection (PAVuC-ATS). Specifically, we learn consistent anchors and view-specific graphs by the bipartite graph, and derive permutations applied to the unaligned graphs by reformulating the alignment between two latent representations as a 2-step transition of a Markov chain with adaptive template selection, thereby achieving the probabilistic alignment. The convergence of the resultant optimization problem is validated both experimentally and theoretically. Extensive experiments on six benchmark datasets demonstrate the superiority of the proposed PAVuC-ATS over the baseline methods.

Jun Sun, Zhongjie Mao, Chao Li et al.

Semi-supervised learning (SSL) has been proven to be a powerful method for leveraging unlabelled data to alleviate models' dependence on large labelled datasets. The common framework among recent approaches is to train the model on a large amount of unlabelled data with consistency regularization to constrain the model predictions to be invariant to input perturbation. However, the existing SSL frameworks still have room for improvement in the consistency regularization method. Instead of regularizing category predictions in the label space as in existing frameworks, this paper proposes a feature space renormalization (FSR) mechanism for SSL. First, we propose a feature space renormalization mechanism to substitute for the commonly used consistency regularization mechanism to learn better discriminative features. To apply this mechanism, we start by building a basic model and an empirical model and then introduce our mechanism to renormalize the feature learning of the basic model with the guidance of the empirical model. Second, we combine the proposed mechanism with pseudo-labelling to obtain a novel effective SSL model named FreMatch. The experimental results show that our method can achieve better performance on a variety of standard SSL benchmark datasets, and the proposed feature space renormalization mechanism can also enhance the performance of other SSL approaches.

Chunyang Cheng, Tianyang Xu, Xiao-Jun Wu et al.

Advanced image fusion methods are devoted to generating the fusion results by aggregating the complementary information conveyed by the source images. However, the difference in the source-specific manifestation of the imaged scene content makes it difficult to design a robust and controllable fusion process. We argue that this issue can be alleviated with the help of higher-level semantics, conveyed by the text modality, which should enable us to generate fused images for different purposes, such as visualisation and downstream tasks, in a controllable way. This is achieved by exploiting a vision-and-language model to build a coarse-to-fine association mechanism between the text and image signals. With the guidance of the association maps, an affine fusion unit is embedded in the transformer network to fuse the text and vision modalities at the feature level. As another ingredient of this work, we propose the use of textual attention to adapt image quality assessment to the fusion task. To facilitate the implementation of the proposed text-guided fusion paradigm, and its adoption by the wider research community, we release a text-annotated image fusion dataset IVT. Extensive experiments demonstrate that our approach (TextFusion) consistently outperforms traditional appearance-based fusion methods. Our code and dataset will be publicly available at https://github.com/AWCXV/TextFusion.

Pengcheng Shao, Tianyang Xu, Xuefeng Zhu et al.

Event-based bionic camera asynchronously captures dynamic scenes with high temporal resolution and high dynamic range, offering potential for the integration of events and RGB under conditions of illumination degradation and fast motion. Existing RGB-E tracking methods model event characteristics utilising attention mechanism of Transformer before integrating both modalities. Nevertheless, these methods involve aggregating the event stream into a single event frame, lacking the utilisation of the temporal information inherent in the event stream.Moreover, the traditional attention mechanism is well-suited for dense semantic features, while the attention mechanism for sparse event features require revolution. In this paper, we propose a dynamic event subframe splitting strategy to split the event stream into more fine-grained event clusters, aiming to capture spatio-temporal features that contain motion cues. Based on this, we design an event-based sparse attention mechanism to enhance the interaction of event features in temporal and spatial dimensions. The experimental results indicate that our method outperforms existing state-of-the-art methods on the FE240 and COESOT datasets, providing an effective processing manner for the event data.

Ruyi Gan, Xiaojun Wu, Junyu Lu et al.

With the open-sourcing of text-to-image models (T2I) such as stable diffusion (SD) and stable diffusion XL (SD-XL), there is an influx of models fine-tuned in specific domains based on the open-source SD model, such as in anime, character portraits, etc. However, there are few specialized models in certain domains, such as interior design, which is attributed to the complex textual descriptions and detailed visual elements inherent in design, alongside the necessity for adaptable resolution. Therefore, text-to-image models for interior design are required to have outstanding prompt-following capabilities, as well as iterative collaboration with design professionals to achieve the desired outcome. In this paper, we collect and optimize text-image data in the design field and continue training in both English and Chinese on the basis of the open-source CLIP model. We also proposed a fine-tuning strategy with curriculum learning and reinforcement learning from CLIP feedback to enhance the prompt-following capabilities of our approach so as to improve the quality of image generation. The experimental results on the collected dataset demonstrate the effectiveness of the proposed approach, which achieves impressive results and outperforms strong baselines.

Ziheng Chen, Xiao-Jun Wu, Bernhard Schölkopf et al.

Normalization layers are crucial for deep learning, but their Euclidean formulations are inadequate for data on manifolds. On the other hand, many Riemannian manifolds in machine learning admit gyro-structures, enabling principled extensions of Euclidean neural networks to non-Euclidean domains. Inspired by this, we introduce GyroBN, a principled Riemannian batch normalization framework for gyrogroups. We establish two necessary conditions, namely \emph{pseudo-reduction} and \emph{gyroisometric gyrations}, that guarantee GyroBN with theoretical control over sample statistics, and show that these conditions hold for all known gyrogroups in machine learning. Our framework also incorporates several existing Riemannian normalization methods as special cases. We further instantiate GyroBN on seven representative geometries, including the Grassmannian, five constant curvature spaces, and the correlation manifold, and derive novel gyro and Riemannian structures to enable these instantiations. Experiments across these geometries demonstrate the effectiveness of GyroBN. The code is available at https://github.com/GitZH-Chen/GyroBN.git.

Kaiwen Huang, Tao Zhou, Huazhu Fu et al.

Semi-supervised learning has gained considerable popularity in medical image segmentation tasks due to its capability to reduce reliance on expert-examined annotations. Several mean-teacher (MT) based semi-supervised methods utilize consistency regularization to effectively leverage valuable information from unlabeled data. However, these methods often heavily rely on the student model and overlook the potential impact of cognitive biases within the model. Furthermore, some methods employ co-training using pseudo-labels derived from different inputs, yet generating high-confidence pseudo-labels from perturbed inputs during training remains a significant challenge. In this paper, we propose an Uncertainty-aware Cross-training framework for semi-supervised medical image Segmentation (UC-Seg). Our UC-Seg framework incorporates two distinct subnets to effectively explore and leverage the correlation between them, thereby mitigating cognitive biases within the model. Specifically, we present a Cross-subnet Consistency Preservation (CCP) strategy to enhance feature representation capability and ensure feature consistency across the two subnets. This strategy enables each subnet to correct its own biases and learn shared semantics from both labeled and unlabeled data. Additionally, we propose an Uncertainty-aware Pseudo-label Generation (UPG) component that leverages segmentation results and corresponding uncertainty maps from both subnets to generate high-confidence pseudo-labels. We extensively evaluate the proposed UC-Seg on various medical image segmentation tasks involving different modality images, such as MRI, CT, ultrasound, colonoscopy, and so on. The results demonstrate that our method achieves superior segmentation accuracy and generalization performance compared to other state-of-the-art semi-supervised methods. Our code will be released at https://github.com/taozh2017/UCSeg.

Hui Li, Xiao-Jun Wu

Multimodal visual information fusion aims to integrate the multi-sensor data into a single image which contains more complementary information and less redundant features. However the complementary information is hard to extract, especially for infrared and visible images which contain big similarity gap between these two modalities. The common cross attention modules only consider the correlation, on the contrary, image fusion tasks need focus on complementarity (uncorrelation). Hence, in this paper, a novel cross attention mechanism (CAM) is proposed to enhance the complementary information. Furthermore, a two-stage training strategy based fusion scheme is presented to generate the fused images. For the first stage, two auto-encoder networks with same architecture are trained for each modality. Then, with the fixed encoders, the CAM and a decoder are trained in the second stage. With the trained CAM, features extracted from two modalities are integrated into one fused feature in which the complementary information is enhanced and the redundant features are reduced. Finally, the fused image can be generated by the trained decoder. The experimental results illustrate that our proposed fusion method obtains the SOTA fusion performance compared with the existing fusion networks. The codes are available at https://github.com/hli1221/CrossFuse

Xiaojun Wu, Dixiang Zhang, Ruyi Gan et al.

Recent advancements in text-to-image models have significantly enhanced image generation capabilities, yet a notable gap of open-source models persists in bilingual or Chinese language support. To address this need, we present Taiyi-Diffusion-XL, a new Chinese and English bilingual text-to-image model which is developed by extending the capabilities of CLIP and Stable-Diffusion-XL through a process of bilingual continuous pre-training. This approach includes the efficient expansion of vocabulary by integrating the most frequently used Chinese characters into CLIP's tokenizer and embedding layers, coupled with an absolute position encoding expansion. Additionally, we enrich text prompts by large vision-language model, leading to better images captions and possess higher visual quality. These enhancements are subsequently applied to downstream text-to-image models. Our empirical results indicate that the developed CLIP model excels in bilingual image-text retrieval.Furthermore, the bilingual image generation capabilities of Taiyi-Diffusion-XL surpass previous models. This research leads to the development and open-sourcing of the Taiyi-Diffusion-XL model, representing a notable advancement in the field of image generation, particularly for Chinese language applications. This contribution is a step forward in addressing the need for more diverse language support in multimodal research. The model and demonstration are made publicly available at \href{https://huggingface.co/IDEA-CCNL/Taiyi-Stable-Diffusion-XL-3.5B/}, fostering further research and collaboration in this domain.

Ziheng Chen, Yue Song, Gaowen Liu et al.

Deep neural networks for learning Symmetric Positive Definite (SPD) matrices are gaining increasing attention in machine learning. Despite the significant progress, most existing SPD networks use traditional Euclidean classifiers on an approximated space rather than intrinsic classifiers that accurately capture the geometry of SPD manifolds. Inspired by Hyperbolic Neural Networks (HNNs), we propose Riemannian Multinomial Logistics Regression (RMLR) for the classification layers in SPD networks. We introduce a unified framework for building Riemannian classifiers under the metrics pulled back from the Euclidean space, and showcase our framework under the parameterized Log-Euclidean Metric (LEM) and Log-Cholesky Metric (LCM). Besides, our framework offers a novel intrinsic explanation for the most popular LogEig classifier in existing SPD networks. The effectiveness of our method is demonstrated in three applications: radar recognition, human action recognition, and electroencephalography (EEG) classification. The code is available at https://github.com/GitZH-Chen/SPDMLR.git.

Ziheng Chen, Tianyang Xu, Xiao-Jun Wu et al.

The Symmetric Positive Definite (SPD) matrices have received wide attention for data representation in many scientific areas. Although there are many different attempts to develop effective deep architectures for data processing on the Riemannian manifold of SPD matrices, very few solutions explicitly mine the local geometrical information in deep SPD feature representations. Given the great success of local mechanisms in Euclidean methods, we argue that it is of utmost importance to ensure the preservation of local geometric information in the SPD networks. We first analyse the convolution operator commonly used for capturing local information in Euclidean deep networks from the perspective of a higher level of abstraction afforded by category theory. Based on this analysis, we define the local information in the SPD manifold and design a multi-scale submanifold block for mining local geometry. Experiments involving multiple visual tasks validate the effectiveness of our approach. The supplement and source code can be found in https://github.com/GitZH-Chen/MSNet.git.

He-Feng Yin, Xiao-Jun Wu, Xiaoning Song

Conventional subspace learning approaches based on image gradient orientations only employ the first-order gradient information. However, recent researches on human vision system (HVS) uncover that the neural image is a landscape or a surface whose geometric properties can be captured through the second order gradient information. The second order image gradient orientations (SOIGO) can mitigate the adverse effect of noises in face images. To reduce the redundancy of SOIGO, we propose compact SOIGO (CSOIGO) by applying linear complex principal component analysis (PCA) in SOIGO. Combined with collaborative representation based classification (CRC) algorithm, the classification performance of CSOIGO is further enhanced. CSOIGO is evaluated under real-world disguise, synthesized occlusion and mixed variations. Experimental results indicate that the proposed method is superior to its competing approaches with few training samples, and even outperforms some prevailing deep neural network based approaches. The source code of CSOIGO is available at https://github.com/yinhefeng/SOIGO.

Zhangyong Tang, Tianyang Xu, Xiao-Jun Wu

Visual object tracking with RGB and thermal infrared (TIR) spectra available, shorted in RGBT tracking, is a novel and challenging research topic which draws increasing attention nowadays. In this paper, we propose an RGBT tracker which takes spatio-temporal clues into account for robust appearance model learning, and simultaneously, constructs an adaptive fusion sub-network for cross-modal interactions. Unlike most existing RGBT trackers that implement object tracking tasks with only spatial information included, temporal information is further considered in this method. Specifically, different from traditional Siamese trackers, which only obtain one search image during the process of picking up template-search image pairs, an extra search sample adjacent to the original one is selected to predict the temporal transformation, resulting in improved robustness of tracking performance.As for multi-modal tracking, constrained to the limited RGBT datasets, the adaptive fusion sub-network is appended to our method at the decision level to reflect the complementary characteristics contained in two modalities. To design a thermal infrared assisted RGB tracker, the outputs of the classification head from the TIR modality are taken into consideration before the residual connection from the RGB modality. Extensive experimental results on three challenging datasets, i.e. VOT-RGBT2019, GTOT and RGBT210, verify the effectiveness of our method. Code will be shared at \textcolor{blue}{\emph{https://github.com/Zhangyong-Tang/TAAT}}.

Hui Li, Xiao-Jun Wu, Josef Kittler

In the image fusion field, the design of deep learning-based fusion methods is far from routine. It is invariably fusion-task specific and requires a careful consideration. The most difficult part of the design is to choose an appropriate strategy to generate the fused image for a specific task in hand. Thus, devising learnable fusion strategy is a very challenging problem in the community of image fusion. To address this problem, a novel end-to-end fusion network architecture (RFN-Nest) is developed for infrared and visible image fusion. We propose a residual fusion network (RFN) which is based on a residual architecture to replace the traditional fusion approach. A novel detail-preserving loss function, and a feature enhancing loss function are proposed to train RFN. The fusion model learning is accomplished by a novel two-stage training strategy. In the first stage, we train an auto-encoder based on an innovative nest connection (Nest) concept. Next, the RFN is trained using the proposed loss functions. The experimental results on public domain data sets show that, compared with the existing methods, our end-to-end fusion network delivers a better performance than the state-of-the-art methods in both subjective and objective evaluation. The code of our fusion method is available at https://github.com/hli1221/imagefusion-rfn-nest

Qingbei Guo, Xiao-Jun Wu, Josef Kittler et al.

Although group convolution operators are increasingly used in deep convolutional neural networks to improve the computational efficiency and to reduce the number of parameters, most existing methods construct their group convolution architectures by a predefined partitioning of the filters of each convolutional layer into multiple regular filter groups with an equal spatial group size and data-independence, which prevents a full exploitation of their potential. To tackle this issue, we propose a novel method of designing self-grouping convolutional neural networks, called SG-CNN, in which the filters of each convolutional layer group themselves based on the similarity of their importance vectors. Concretely, for each filter, we first evaluate the importance value of their input channels to identify the importance vectors, and then group these vectors by clustering. Using the resulting \emph{data-dependent} centroids, we prune the less important connections, which implicitly minimizes the accuracy loss of the pruning, thus yielding a set of \emph{diverse} group convolution filters. Subsequently, we develop two fine-tuning schemes, i.e. (1) both local and global fine-tuning and (2) global only fine-tuning, which experimentally deliver comparable results, to recover the recognition capacity of the pruned network. Comprehensive experiments carried out on the CIFAR-10/100 and ImageNet datasets demonstrate that our self-grouping convolution method adapts to various state-of-the-art CNN architectures, such as ResNet and DenseNet, and delivers superior performance in terms of compression ratio, speedup and recognition accuracy. We demonstrate the ability of SG-CNN to generalise by transfer learning, including domain adaption and object detection, showing competitive results. Our source code is available at https://github.com/QingbeiGuo/SG-CNN.git.

He-Feng Yin, Xiao-Jun Wu, Zhen-Hua Feng et al.

During the past decade, representation-based classification methods have received considerable attention in pattern recognition. In particular, the recently proposed non-negative representation based classification (NRC) method has been reported to achieve promising results in a wide range of classification tasks. However, NRC has two major drawbacks. First, there is no regularization term in the formulation of NRC, which may result in unstable solution and misclassification. Second, NRC ignores the fact that data usually lies in a union of multiple affine subspaces, rather than linear subspaces in practical applications. To address the above issues, this paper presents an affine non-negative collaborative representation (ANCR) model for pattern classification. To be more specific, ANCR imposes a regularization term on the coding vector. Moreover, ANCR introduces an affine constraint to better represent the data from affine subspaces. The experimental results on several benchmarking datasets demonstrate the merits of the proposed ANCR method. The source code of our ANCR is publicly available at https://github.com/yinhefeng/ANCR.

Zi-Qi Li, Jun Sun, Xiao-Jun Wu et al.

Representation based classification methods have become a hot research topic during the past few years, and the two most prominent approaches are sparse representation based classification (SRC) and collaborative representation based classification (CRC). CRC reveals that it is the collaborative representation rather than the sparsity that makes SRC successful. Nevertheless, the dense representation of CRC may not be discriminative which will degrade its performance for classification tasks. To alleviate this problem to some extent, we propose a new method called sparse and collaborative-competitive representation based classification (SCCRC) for image classification. Firstly, the coefficients of the test sample are obtained by SRC and CCRC, respectively. Then the fused coefficient is derived by multiplying the coefficients of SRC and CCRC. Finally, the test sample is designated to the class that has the minimum residual. Experimental results on several benchmark databases demonstrate the efficacy of our proposed SCCRC. The source code of SCCRC is accessible at https://github.com/li-zi-qi/SCCRC.

He-Feng Yin, Xiao-Jun Wu, Josef Kittler

Face recognition has been widely studied due to its importance in smart cities applications. However, the case when both training and test images are corrupted is not well solved. To address such a problem, this paper proposes a locality constrained low rank representation and dictionary learning (LCLRRDL) algorithm for robust face recognition. In particular, we present three contributions in the proposed formulation. First, a low-rank representation is introduced to handle the possible contamination of the training as well as test data. Second, a locality constraint is incorporated to acknowledge the intrinsic manifold structure of training data. With the locality constraint term, our scheme induces similar samples to have similar representations. Third, a compact dictionary is learned to handle the problem of corrupted data. The experimental results on two public databases demonstrate the effectiveness of the proposed approach. Matlab code of our proposed LCLRRDL can be downloaded from https://github.com/yinhefeng/LCLRRDL.

He-Feng Yin, Xiao-Jun Wu, Su-Gen Chen

Discriminative dictionary learning (DDL) has recently gained significant attention due to its impressive performance in various pattern classification tasks. However, the locality of atoms is not fully explored in conventional DDL approaches which hampers their classification performance. In this paper, we propose a locality constraint dictionary learning with support vector discriminative term (LCDL-SV), in which the locality information is preserved by employing the graph Laplacian matrix of the learned dictionary. To jointly learn a classifier during the training phase, a support vector discriminative term is incorporated into the proposed objective function. Moreover, in the classification stage, the identity of test data is jointly determined by the regularized residual and the learned multi-class support vector machine. Finally, the resulting optimization problem is solved by utilizing the alternative strategy. Experimental results on benchmark databases demonstrate the superiority of our proposed method over previous dictionary learning approaches on both hand-crafted and deep features. The source code of our proposed LCDL-SV is accessible at https://github.com/yinhefeng/LCDL-SV

Tianyang Xu, Zhen-Hua Feng, Xiao-Jun Wu et al.

We propose a new Group Feature Selection method for Discriminative Correlation Filters (GFS-DCF) based visual object tracking. The key innovation of the proposed method is to perform group feature selection across both channel and spatial dimensions, thus to pinpoint the structural relevance of multi-channel features to the filtering system. In contrast to the widely used spatial regularisation or feature selection methods, to the best of our knowledge, this is the first time that channel selection has been advocated for DCF-based tracking. We demonstrate that our GFS-DCF method is able to significantly improve the performance of a DCF tracker equipped with deep neural network features. In addition, our GFS-DCF enables joint feature selection and filter learning, achieving enhanced discrimination and interpretability of the learned filters. To further improve the performance, we adaptively integrate historical information by constraining filters to be smooth across temporal frames, using an efficient low-rank approximation. By design, specific temporal-spatial-channel configurations are dynamically learned in the tracking process, highlighting the relevant features, and alleviating the performance degrading impact of less discriminative representations and reducing information redundancy. The experimental results obtained on OTB2013, OTB2015, VOT2017, VOT2018 and TrackingNet demonstrate the merits of our GFS-DCF and its superiority over the state-of-the-art trackers. The code is publicly available at https://github.com/XU-TIANYANG/GFS-DCF.

Zhe Chen, Xiao-Jun Wu, Josef Kittler

Discriminative least squares regression (DLSR) has been shown to achieve promising performance in multi-class image classification tasks. Its key idea is to force the regression labels of different classes to move in opposite directions by means of the proposed the joint use of the $ε$-draggings technique, yielding discriminative regression model exhibiting wider margins, and the Fisher criterion. The $ε$-draggings technique ignores an important problem: its non-negative relaxation matrix is dynamically updated in optimization, which means the dragging values can also cause the labels from the same class to be uncorrelated. In order to learn a more powerful discriminative projection, as well as regression labels, we propose a Fisher regularized DLSR (FDLSR) framework by constraining the relaxed labels using the Fisher criterion. On one hand, the Fisher criterion improves the intra-class compactness of the relaxed labels during relaxation learning. On the other hand, it is expected further to enhance the inter-class separability of $ε$-draggings technique. FDLSR for the first time ever attempts to integrate the Fisher discriminant criterion and $ε$-draggings technique into one unified model because they are absolutely complementary in learning discriminative projection. Extensive experiments on various datasets demonstrate that the proposed FDLSR method achieves performance that is superior to other state-of-the-art classification methods. The Matlab codes of this paper are available at https://github.com/chenzhe207/FDLSR.

Hui Li, Xiao-Jun Wu, Tariq Durrani

Multi-focus noisy image fusion represents an important task in the field of image fusion which generates a single, clear and focused image from all source images. In this paper, we propose a novel multi-focus noisy image fusion method based on low-rank representation (LRR) which is a powerful tool in representation learning. A multi-scale transform framework is adopted in which source images are decomposed into low frequency and high frequency coefficients, respectively. For low frequency coefficients, the fused low frequency coefficients are determined by a spatial frequency strategy, while the high frequency coefficients are fused by the LRR-based fusion strategy. Finally, the fused image is reconstructed by inverse multi-scale transforms with fused coefficients. Experimental results demonstrate that the proposed algorithm offers state-of-the-art performance even when the source images contain noise. The Code of our fusion method is available at https://github.com/hli1221/imagefusion_noisy_lrr

Hui Li, Xiao-Jun Wu

Infrared and visible image fusion is an important problem in the field of image fusion which has been applied widely in many fields. To better preserve the useful information from source images, in this paper, we propose a novel image fusion method based on latent low-rank representation(LatLRR) which is simple and effective. Firstly, the source images are decomposed into low-rank parts(global structure) and salient parts(local structure) by LatLRR. Then, the low-rank parts are fused by weighted-average strategy to preserve more contour information. Then, the salient parts are simply fused by sum strategy which is a efficient operation in this fusion framework. Finally, the fused image is obtained by combining the fused low-rank part and the fused salient part. Compared with other fusion methods experimentally, the proposed method has better fusion performance than state-of-the-art fusion methods in both subjective and objective evaluation. The Code of our fusion method is available at https://github.com/hli1221/imagefusion\_Infrared\_visible\_latlrr

Hui Li, Xiao-Jun Wu, Josef Kittler

In recent years, deep learning has become a very active research tool which is used in many image processing fields. In this paper, we propose an effective image fusion method using a deep learning framework to generate a single image which contains all the features from infrared and visible images. First, the source images are decomposed into base parts and detail content. Then the base parts are fused by weighted-averaging. For the detail content, we use a deep learning network to extract multi-layer features. Using these features, we use l_1-norm and weighted-average strategy to generate several candidates of the fused detail content. Once we get these candidates, the max selection strategy is used to get final fused detail content. Finally, the fused image will be reconstructed by combining the fused base part and detail content. The experimental results demonstrate that our proposed method achieves state-of-the-art performance in both objective assessment and visual quality. The Code of our fusion method is available at https://github.com/hli1221/imagefusion_deeplearning

Jianghu Shen, Xiaojun Wu

In the field of remote sensing, we often utilize oriented bounding boxes (OBB) to bound the objects. This approach significantly reduces the overlap among dense detection boxes and minimizes the inclusion of background content within the bounding boxes. To enhance the detection accuracy of oriented objects, we propose a unique loss function based on edge gradients, inspired by the similarity measurement function used in template matching task. During this process, we address the issues of non-differentiability of the function and the semantic alignment between gradient vectors in ground truth (GT) boxes and predicted boxes (PB). Experimental results show that our proposed loss function achieves $0.6\%$ mAP improvement compared to the commonly used Smooth L1 loss in the baseline algorithm. Additionally, we design an edge-based self-attention module to encourage the detection network to focus more on the object edges. Leveraging these two innovations, we achieve a mAP increase of 1.3% on the DOTA dataset.

Huan Kang, Hui Li, Xiao-Jun Wu et al.

In the field of image fusion, promising progress has been made by modeling data from different modalities as linear subspaces. However, in practice, the source images are often located in a non-Euclidean space, where the Euclidean methods usually cannot encapsulate the intrinsic topological structure. Typically, the inner product performed in the Euclidean space calculates the algebraic similarity rather than the semantic similarity, which results in undesired attention output and a decrease in fusion performance. While the balance of low-level details and high-level semantics should be considered in infrared and visible image fusion task. To address this issue, in this paper, we propose a novel attention mechanism based on Grassmann manifold for infrared and visible image fusion (GrFormer). Specifically, our method constructs a low-rank subspace mapping through projection constraints on the Grassmann manifold, compressing attention features into subspaces of varying rank levels. This forces the features to decouple into high-frequency details (local low-rank) and low-frequency semantics (global low-rank), thereby achieving multi-scale semantic fusion. Additionally, to effectively integrate the significant information, we develop a cross-modal fusion strategy (CMS) based on a covariance mask to maximise the complementary properties between different modalities and to suppress the features with high correlation, which are deemed redundant. The experimental results demonstrate that our network outperforms SOTA methods both qualitatively and quantitatively on multiple image fusion benchmarks. The codes are available at https://github.com/Shaoyun2023.

Zeyang Zhang, Hui Li, Tianyang Xu et al.

In a scenario where multi-modal cameras are operating together, the problem of working with non-aligned images cannot be avoided. Yet, existing image fusion algorithms rely heavily on strictly registered input image pairs to produce more precise fusion results, as a way to improve the performance of downstream high-level vision tasks. In order to relax this assumption, one can attempt to register images first. However, the existing methods for registering multiple modalities have limitations, such as complex structures and reliance on significant semantic information. This paper aims to address the problem of image registration and fusion in a single framework, called BusRef. We focus on Infrared-Visible image registration and fusion task (IVRF). In this framework, the input unaligned image pairs will pass through three stages: Coarse registration, Fine registration and Fusion. It will be shown that the unified approach enables more robust IVRF. We also propose a novel training and evaluation strategy, involving the use of masks to reduce the influence of non-reconstructible regions on the loss functions, which greatly improves the accuracy and robustness of the fusion task. Last but not least, a gradient-aware fusion network is designed to preserve the complementary information. The advanced performance of this algorithm is demonstrated by

Weixuan Sun, Jucai Zhai, Dengfeng Liu et al.

The automated repair of C++ compilation errors presents a significant challenge, the resolution of which is critical for developer productivity. Progress in this domain is constrained by two primary factors: the scarcity of large-scale, high-fidelity datasets and the limitations of conventional supervised methods, which often fail to generate semantically correct patches.This paper addresses these gaps by introducing a comprehensive framework with three core contributions. First, we present CCrepair, a novel, large-scale C++ compilation error dataset constructed through a sophisticated generate-and-verify pipeline. Second, we propose a Reinforcement Learning (RL) paradigm guided by a hybrid reward signal, shifting the focus from mere compilability to the semantic quality of the fix. Finally, we establish the robust, two-stage evaluation system providing this signal, centered on an LLM-as-a-Judge whose reliability has been rigorously validated against the collective judgments of a panel of human experts. This integrated approach aligns the training objective with generating high-quality, non-trivial patches that are both syntactically and semantically correct. The effectiveness of our approach was demonstrated experimentally. Our RL-trained Qwen2.5-1.5B-Instruct model achieved performance comparable to a Qwen2.5-14B-Instruct model, validating the efficiency of our training paradigm. Our work provides the research community with a valuable new dataset and a more effective paradigm for training and evaluating robust compilation repair models, paving the way for more practical and reliable automated programming assistants.

Qianliang Wu, Haobo Jiang, Yaqing Ding et al.

Establishing reliable correspondences is crucial for all registration tasks, including 2D image registration, 3D point cloud registration, and 2D-3D image-to-point cloud registration. However, these tasks are often complicated by challenges such as scale inconsistencies, symmetry, and large deformations, which can lead to ambiguous matches. Previous feature-based and correspondence-based methods typically rely on geometric or semantic features to generate or polish initial potential correspondences. Some methods typically leverage specific geometric priors, such as topological preservation, to devise diverse and innovative strategies tailored to a given enhancement goal, which cannot be exhaustively enumerated. Additionally, many previous approaches rely on a single-step prediction head, which can struggle with local minima in complex matching scenarios. To address these challenges, we introduce an innovative paradigm that leverages a diffusion model in matrix space for robust matching matrix estimation. Our model treats correspondence estimation as a denoising diffusion process in the matching matrix space, gradually refining the intermediate matching matrix to the optimal one. Specifically, we apply the diffusion model in the doubly stochastic matrix space for 3D-3D and 2D-3D registration tasks. In the 2D image registration task, we deploy the diffusion model in a matrix subspace where dual-softmax projection regularization is applied. For all three registration tasks, we provide adaptive matching matrix embedding implementations tailored to the specific characteristics of each task while maintaining a consistent "match-to-warp" encoding pattern. Furthermore, we adopt a lightweight design for the denoising module. In inference, once points or image features are extracted and fixed, this module performs multi-step denoising predictions through reverse sampling.

Xiao-Jun Wu, Cai-Jun Zhao, Chun Meng et al.

The p16/Ki-67 dual staining method is a new approach for cervical cancer screening with high sensitivity and specificity. However, there are issues of mis-detection and inaccurate recognition when the YOLOv5s algorithm is directly applied to dual-stained cell images. This paper Proposes a novel cervical cancer dual-stained image recognition (DSIR-YOLO) model based on an YOLOv5. By fusing the Swin-Transformer module, GAM attention mechanism, multi-scale feature fusion, and EIoU loss function, the detection performance is significantly improved, with mAP@0.5 and mAP@0.5:0.95 reaching 92.6% and 70.5%, respectively. Compared with YOLOv5s in five-fold cross-validation, the accuracy, recall, mAP@0.5, and mAP@0.5:0.95 of the improved algorithm are increased by 2.3%, 4.1%, 4.3%, and 8.0%, respectively, with smaller variances and higher stability. Compared with other detection algorithms, DSIR-YOLO in this paper sacrifices some performance requirements to improve the network recognition effect. In addition, the influence of dataset quality on the detection results is studied. By controlling the sealing property of pixels, scale difference, unlabelled cells, and diagonal annotation, the model detection accuracy, recall, mAP@0.5, and mAP@0.5:0.95 are improved by 13.3%, 15.3%, 18.3%, and 30.5%, respectively.

Yu-Hong Cai, Xiao-Jun Wu, Zhe Chen

Linear regression is a supervised method that has been widely used in classification tasks. In order to apply linear regression to classification tasks, a technique for relaxing regression targets was proposed. However, methods based on this technique ignore the pressure on a single transformation matrix due to the complex information contained in the data. A single transformation matrix in this case is too strict to provide a flexible projection, thus it is necessary to adopt relaxation on transformation matrix. This paper proposes a double transformation matrices learning method based on latent low-rank feature extraction. The core idea is to use double transformation matrices for relaxation, and jointly projecting the learned principal and salient features from two directions into the label space, which can share the pressure of a single transformation matrix. Firstly, the low-rank features are learned by the latent low rank representation (LatLRR) method which processes the original data from two directions. In this process, sparse noise is also separated, which alleviates its interference on projection learning to some extent. Then, two transformation matrices are introduced to process the two features separately, and the information useful for the classification is extracted. Finally, the two transformation matrices can be easily obtained by alternate optimization methods. Through such processing, even when a large amount of redundant information is contained in samples, our method can also obtain projection results that are easy to classify. Experiments on multiple data sets demonstrate the effectiveness of our approach for classification, especially for complex scenarios.

Dongyu Rao, Xiao-Jun Wu, Tianyang Xu

The end-to-end image fusion framework has achieved promising performance, with dedicated convolutional networks aggregating the multi-modal local appearance. However, long-range dependencies are directly neglected in existing CNN fusion approaches, impeding balancing the entire image-level perception for complex scenario fusion. In this paper, therefore, we propose an infrared and visible image fusion algorithm based on a lightweight transformer module and adversarial learning. Inspired by the global interaction power, we use the transformer technique to learn the effective global fusion relations. In particular, shallow features extracted by CNN are interacted in the proposed transformer fusion module to refine the fusion relationship within the spatial scope and across channels simultaneously. Besides, adversarial learning is designed in the training process to improve the output discrimination via imposing competitive consistency from the inputs, reflecting the specific characteristics in infrared and visible images. The experimental performance demonstrates the effectiveness of the proposed modules, with superior improvement against the state-of-the-art, generalising a novel paradigm via transformer and adversarial learning in the fusion task.

Xue-Feng Zhu, Tianyang Xu, Xiao-Jun Wu

The development of visual object tracking has continued for decades. Recent years, as the wide accessibility of the low-cost RGBD sensors, the task of visual object tracking on RGB-D videos has drawn much attention. Compared to conventional RGB-only tracking, the RGB-D videos can provide more information that facilitates objecting tracking in some complicated scenarios. The goal of this review is to summarize the relative knowledge of the research filed of RGB-D tracking. To be specific, we will generalize the related RGB-D tracking benchmarking datasets as well as the corresponding performance measurements. Besides, the existing RGB-D tracking methods are summarized in the paper. Moreover, we discuss the possible future direction in the field of RGB-D tracking.

Li Chu, Rui Wang, Xiao-Jun Wu

Collaborative representation-based classification (CRC) has demonstrated remarkable progress in the past few years because of its closed-form analytical solutions. However, the existing CRC methods are incapable of processing the nonlinear variational information directly. Recent advances illustrate that how to effectively model these nonlinear variational information and learn invariant representations is an open challenge in the community of computer vision and pattern recognition To this end, we try to design a new algorithm to handle this problem. Firstly, the second-order statistic, i.e., covariance matrix is applied to model the original image sets. Due to the space formed by a set of nonsingular covariance matrices is a well-known Symmetric Positive Definite (SPD) manifold, generalising the Euclidean collaborative representation to the SPD manifold is not an easy task. Then, we devise two strategies to cope with this issue. One attempts to embed the SPD manifold-valued data representations into an associated tangent space via the matrix logarithm map. Another is to embed them into a Reproducing Kernel Hilbert Space (RKHS) by utilizing the Riemannian kernel function. After these two treatments, CRC is applicable to the SPD manifold-valued features. The evaluations on four banchmarking datasets justify its effectiveness.

Rongchang Li, Xiao-Jun Wu, Tianyang Xu

In the field of action recognition, video clips are always treated as ordered frames for subsequent processing. To achieve spatio-temporal perception, existing approaches propose to embed adjacent temporal interaction in the convolutional layer. The global semantic information can therefore be obtained by stacking multiple local layers hierarchically. However, such global temporal accumulation can only reflect the high-level semantics in deep layers, neglecting the potential low-level holistic clues in shallow layers. In this paper, we first propose to transform a video sequence into a graph to obtain direct long-term dependencies among temporal frames. To preserve sequential information during transformation, we devise a structured graph module (SGM), achieving fine-grained temporal interactions throughout the entire network. In particular, SGM divides the neighbors of each node into several temporal regions so as to extract global structural information with diverse sequential flows. Extensive experiments are performed on standard benchmark datasets, i.e., Something-Something V1 & V2, Diving48, Kinetics-400, UCF101, and HMDB51. The reported performance and analysis demonstrate that SGM can achieve outstanding precision with less computational complexity.

Donglin Zhang, Xiao-Jun Wu, He-Feng Yin et al.

In recent years, cross-media hashing technique has attracted increasing attention for its high computation efficiency and low storage cost. However, the existing approaches still have some limitations, which need to be explored. 1) A fixed hash length (e.g., 16bits or 32bits) is predefined before learning the binary codes. Therefore, these models need to be retrained when the hash length changes, that consumes additional computation power, reducing the scalability in practical applications. 2) Existing cross-modal approaches only explore the information in the original multimedia data to perform the hash learning, without exploiting the semantic information contained in the learned hash codes. To this end, we develop a novel Multiple hash cOdes jOint learNing method (MOON) for cross-media retrieval. Specifically, the developed MOON synchronously learns the hash codes with multiple lengths in a unified framework. Besides, to enhance the underlying discrimination, we combine the clues from the multimodal data, semantic labels and learned hash codes for hash learning. As far as we know, the proposed MOON is the first work to simultaneously learn different length hash codes without retraining in cross-media retrieval. Experiments on several databases show that our MOON can achieve promising performance, outperforming some recent competitive shallow and deep methods.

D. Y. Rao, X. J. Wu, H. Li et al.

In this paper, we propose a photorealistic style transfer network to emphasize the natural effect of photorealistic image stylization. In general, distortion of the image content and lacking of details are two typical issues in the style transfer field. To this end, we design a novel framework employing the U-Net structure to maintain the rich spatial clues, with a multi-layer feature aggregation (MFA) method to simultaneously provide the details obtained by the shallow layers in the stylization processing. In particular, an encoder based on the dense block and a decoder form a symmetrical structure of U-Net are jointly staked to realize an effective feature extraction and image reconstruction. Besides, a transfer module based on MFA and "adaptive instance normalization" (AdaIN) is inserted in the skip connection positions to achieve the stylization. Accordingly, the stylized image possesses the texture of a real photo and preserves rich content details without introducing any mask or post-processing steps. The experimental results on public datasets demonstrate that our method achieves a more faithful structural similarity with a lower style loss, reflecting the effectiveness and merit of our approach.

Yu Fu, TianYang Xu, XiaoJun Wu et al.

The Transformer architecture has witnessed a rapid development in recent years, outperforming the CNN architectures in many computer vision tasks, as exemplified by the Vision Transformers (ViT) for image classification. However, existing visual transformer models aim to extract semantic information for high-level tasks, such as classification and detection.These methods ignore the importance of the spatial resolution of the input image, thus sacrificing the local correlation information of neighboring pixels. In this paper, we propose a Patch Pyramid Transformer(PPT) to effectively address the above issues.Specifically, we first design a Patch Transformer to transform the image into a sequence of patches, where transformer encoding is performed for each patch to extract local representations. In addition, we construct a Pyramid Transformer to effectively extract the non-local information from the entire image. After obtaining a set of multi-scale, multi-dimensional, and multi-angle features of the original image, we design the image reconstruction network to ensure that the features can be reconstructed into the original input. To validate the effectiveness, we apply the proposed Patch Pyramid Transformer to image fusion tasks. The experimental results demonstrate its superior performance, compared to the state-of-the-art fusion approaches, achieving the best results on several evaluation indicators. Thanks to the underlying representational capacity of the PPT network, it can directly be applied to different image fusion tasks without redesigning or retraining the network.

Qingbei Guo, Xiao-Jun Wu, Josef Kittler et al.

Automated neural network design has received ever-increasing attention with the evolution of deep convolutional neural networks (CNNs), especially involving their deployment on embedded and mobile platforms. One of the biggest problems that neural architecture search (NAS) confronts is that a large number of candidate neural architectures are required to train, using, for instance, reinforcement learning and evolutionary optimisation algorithms, at a vast computation cost. Even recent differentiable neural architecture search (DNAS) samples a small number of candidate neural architectures based on the probability distribution of learned architecture parameters to select the final neural architecture. To address this computational complexity issue, we introduce a novel \emph{architecture parameterisation} based on scaled sigmoid function, and propose a general \emph{Differentiable Neural Architecture Learning} (DNAL) method to optimize the neural architecture without the need to evaluate candidate neural networks. Specifically, for stochastic supernets as well as conventional CNNs, we build a new channel-wise module layer with the architecture components controlled by a scaled sigmoid function. We train these neural network models from scratch. The network optimization is decoupled into the weight optimization and the architecture optimization. We address the non-convex optimization problem of neural architecture by the continuous scaled sigmoid method with convergence guarantees. Extensive experiments demonstrate our DNAL method delivers superior performance in terms of neural architecture search cost. The optimal networks learned by DNAL surpass those produced by the state-of-the-art methods on the benchmark CIFAR-10 and ImageNet-1K dataset in accuracy, model size and computational complexity.