Wei He

Chengcheng Wang, Wei He, Ying Nie et al.

In the past years, YOLO-series models have emerged as the leading approaches in the area of real-time object detection. Many studies pushed up the baseline to a higher level by modifying the architecture, augmenting data and designing new losses. However, we find previous models still suffer from information fusion problem, although Feature Pyramid Network (FPN) and Path Aggregation Network (PANet) have alleviated this. Therefore, this study provides an advanced Gatherand-Distribute mechanism (GD) mechanism, which is realized with convolution and self-attention operations. This new designed model named as Gold-YOLO, which boosts the multi-scale feature fusion capabilities and achieves an ideal balance between latency and accuracy across all model scales. Additionally, we implement MAE-style pretraining in the YOLO-series for the first time, allowing YOLOseries models could be to benefit from unsupervised pretraining. Gold-YOLO-N attains an outstanding 39.9% AP on the COCO val2017 datasets and 1030 FPS on a T4 GPU, which outperforms the previous SOTA model YOLOv6-3.0-N with similar FPS by +2.4%. The PyTorch code is available at https://github.com/huawei-noah/Efficient-Computing/tree/master/Detection/Gold-YOLO, and the MindSpore code is available at https://gitee.com/mindspore/models/tree/master/research/cv/Gold_YOLO.

Sanqing Qu, Guang Chen, Jing Zhang et al.

Source-free Domain Adaptation (SFDA) aims to adapt a pre-trained source model to the unlabeled target domain without accessing the well-labeled source data, which is a much more practical setting due to the data privacy, security, and transmission issues. To make up for the absence of source data, most existing methods introduced feature prototype based pseudo-labeling strategies to realize self-training model adaptation. However, feature prototypes are obtained by instance-level predictions based feature clustering, which is category-biased and tends to result in noisy labels since the visual domain gaps between source and target are usually different between categories. In addition, we found that a monocentric feature prototype may be ineffective to represent each category and introduce negative transfer, especially for those hard-transfer data. To address these issues, we propose a general class-Balanced Multicentric Dynamic prototype (BMD) strategy for the SFDA task. Specifically, for each target category, we first introduce a global inter-class balanced sampling strategy to aggregate potential representative target samples. Then, we design an intra-class multicentric clustering strategy to achieve more robust and representative prototypes generation. In contrast to existing strategies that update the pseudo label at a fixed training period, we further introduce a dynamic pseudo labeling strategy to incorporate network update information during model adaptation. Extensive experiments show that the proposed model-agnostic BMD strategy significantly improves representative SFDA methods to yield new state-of-the-art results. The code is available at https://github.com/ispc-lab/BMD.

Zhongzhan Huang, Senwei Liang, Mingfu Liang et al.

Recently many plug-and-play self-attention modules (SAMs) are proposed to enhance the model generalization by exploiting the internal information of deep convolutional neural networks (CNNs). In general, previous works ignore where to plug in the SAMs since they connect the SAMs individually with each block of the entire CNN backbone for granted, leading to incremental computational cost and the number of parameters with the growth of network depth. However, we empirically find and verify some counterintuitive phenomena that: (a) Connecting the SAMs to all the blocks may not always bring the largest performance boost, and connecting to partial blocks would be even better; (b) Adding the SAMs to a CNN may not always bring a performance boost, and instead it may even harm the performance of the original CNN backbone. Therefore, we articulate and demonstrate the Lottery Ticket Hypothesis for Self-attention Networks: a full self-attention network contains a subnetwork with sparse self-attention connections that can (1) accelerate inference, (2) reduce extra parameter increment, and (3) maintain accuracy. In addition to the empirical evidence, this hypothesis is also supported by our theoretical evidence. Furthermore, we propose a simple yet effective reinforcement-learning-based method to search the ticket, i.e., the connection scheme that satisfies the three above-mentioned conditions. Extensive experiments on widely-used benchmark datasets and popular self-attention networks show the effectiveness of our method. Besides, our experiments illustrate that our searched ticket has the capacity of transferring to some vision tasks, e.g., crowd counting and segmentation.

Zhuohong Li, Wei He, Hongyan Zhang

Nowadays, many large-scale land-cover (LC) products have been released, however, current LC products for China either lack a fine resolution or nationwide coverage. With the rapid urbanization of China, there is an urgent need for creating a very-high-resolution (VHR) national-scale LC map for China. In this study, a novel 1-m resolution LC map of China covering $9,600,000 km^2$, called SinoLC-1, was produced by using a deep learning framework and multi-source open-access data. To efficiently generate the VHR national-scale LC map, firstly, the reliable LC labels were collected from three 10-m LC products and Open Street Map data. Secondly, the collected 10-m labels and 1-m Google Earth imagery were utilized in the proposed low-to-high (L2H) framework for training. With weak and self-supervised strategies, the L2H framework resolves the label noise brought by the mismatched resolution between training pairs and produces VHR results. Lastly, we compare the SinoLC-1 with five widely used products and validate it with a sample set including 10,6852 points and a statistical report collected from the government. The results show the SinoLC-1 achieved an OA of 74\% and a Kappa of 0.65. Moreover, as the first 1-m national-scale LC map for China, the SinoLC-1 shows overall acceptable results with the finest landscape details.

Jiepan Li, Wei He, Hongyan Zhang

Binary segmentation is used to distinguish objects of interest from background, and is an active area of convolutional encoder-decoder network research. The current decoders are designed for specific objects based on the common backbones as the encoders, but cannot deal with complex backgrounds. Inspired by the way human eyes detect objects of interest, a new unified dual-branch decoder paradigm named the difference-aware decoder is proposed in this paper to explore the difference between the foreground and the background and separate the objects of interest in optical images. The difference-aware decoder imitates the human eye in three stages using the multi-level features output by the encoder. In Stage A, the first branch decoder of the difference-aware decoder is used to obtain a guide map. The highest-level features are enhanced with a novel field expansion module and a dual residual attention module, and are combined with the lowest-level features to obtain the guide map. In Stage B, the other branch decoder adopts a middle feature fusion module to make trade-offs between textural details and semantic information and generate background-aware features. In Stage C, the proposed difference-aware extractor, consisting of a difference guidance model and a difference enhancement module, fuses the guide map from Stage A and the background-aware features from Stage B, to enlarge the differences between the foreground and the background and output a final detection result. The results demonstrate that the difference-aware decoder can achieve a higher accuracy than the other state-of-the-art binary segmentation methods for these tasks.

Jiepan Li, Fangxiao Lu, Nan Xue et al.

Camouflaged objects adaptively fit their color and texture with the environment, which makes them indistinguishable from the surroundings. Current methods revealed that high-level semantic features can highlight the differences between camouflaged objects and the backgrounds. Consequently, they integrate high-level semantic features with low-level detailed features for accurate camouflaged object detection (COD). Unlike previous designs for multi-level feature fusion, we state that enhancing low-level features is more impending for COD. In this paper, we propose an overlapped window cross-level attention (OWinCA) to achieve the low-level feature enhancement guided by the highest-level features. By sliding an aligned window pair on both the highest- and low-level feature maps, the high-level semantics are explicitly integrated into the low-level details via cross-level attention. Additionally, it employs an overlapped window partition strategy to alleviate the incoherence among windows, which prevents the loss of global information. These adoptions enable the proposed OWinCA to enhance low-level features by promoting the separability of camouflaged objects. The associated proposed OWinCANet fuses these enhanced multi-level features by simple convolution operation to achieve the final COD. Experiments conducted on three large-scale COD datasets demonstrate that our OWinCANet significantly surpasses the current state-of-the-art COD methods.

Zhuohong Li, Wei He, Jiepan Li et al.

Buildings, as fundamental man-made structures in urban environments, serve as crucial indicators for understanding various city function zones. Rapid urbanization has raised an urgent need for efficiently surveying building footprints and functions. In this study, we proposed a semi-supervised framework to identify every building's function in large-scale urban areas with multi-modality remote-sensing data. In detail, optical images, building height, and nighttime-light data are collected to describe the morphological attributes of buildings. Then, the area of interest (AOI) and building masks from the volunteered geographic information (VGI) data are collected to form sparsely labeled samples. Furthermore, the multi-modality data and weak labels are utilized to train a segmentation model with a semi-supervised strategy. Finally, results are evaluated by 20,000 validation points and statistical survey reports from the government. The evaluations reveal that the produced function maps achieve an OA of 82% and Kappa of 71% among 1,616,796 buildings in Shanghai, China. This study has the potential to support large-scale urban management and sustainable urban development. All collected data and produced maps are open access at https://github.com/LiZhuoHong/BuildingMap.

Zhehui Wu, Yong Chen, Naoto Yokoya et al.

Hyperspectral images (HSIs) often suffer from diverse and unknown degradations during imaging, leading to severe spectral and spatial distortions. Existing HSI restoration methods typically rely on specific degradation assumptions, limiting their effectiveness in complex scenarios. In this paper, we propose \textbf{MP-HSIR}, a novel multi-prompt framework that effectively integrates spectral, textual, and visual prompts to achieve universal HSI restoration across diverse degradation types and intensities. Specifically, we develop a prompt-guided spatial-spectral transformer, which incorporates spatial self-attention and a prompt-guided dual-branch spectral self-attention. Since degradations affect spectral features differently, we introduce spectral prompts in the local spectral branch to provide universal low-rank spectral patterns as prior knowledge for enhancing spectral reconstruction. Furthermore, the text-visual synergistic prompt fuses high-level semantic representations with fine-grained visual features to encode degradation information, thereby guiding the restoration process. Extensive experiments on 9 HSI restoration tasks, including all-in-one scenarios, generalization tests, and real-world cases, demonstrate that MP-HSIR not only consistently outperforms existing all-in-one methods but also surpasses state-of-the-art task-specific approaches across multiple tasks. The code and models are available at https://github.com/ZhehuiWu/MP-HSIR.

Zhuohong Li, Wei He, Jiepan Li et al.

Large-scale high-resolution (HR) land-cover mapping is a vital task to survey the Earth's surface and resolve many challenges facing humanity. However, it is still a non-trivial task hindered by complex ground details, various landforms, and the scarcity of accurate training labels over a wide-span geographic area. In this paper, we propose an efficient, weakly supervised framework (Paraformer) to guide large-scale HR land-cover mapping with easy-access historical land-cover data of low resolution (LR). Specifically, existing land-cover mapping approaches reveal the dominance of CNNs in preserving local ground details but still suffer from insufficient global modeling in various landforms. Therefore, we design a parallel CNN-Transformer feature extractor in Paraformer, consisting of a downsampling-free CNN branch and a Transformer branch, to jointly capture local and global contextual information. Besides, facing the spatial mismatch of training data, a pseudo-label-assisted training (PLAT) module is adopted to reasonably refine LR labels for weakly supervised semantic segmentation of HR images. Experiments on two large-scale datasets demonstrate the superiority of Paraformer over other state-of-the-art methods for automatically updating HR land-cover maps from LR historical labels.

Zhelun Shen, Chenming Wu, Junsheng Zhou et al.

Digital human video generation is gaining traction in fields like education and e-commerce, driven by advancements in head-body animation and lip-syncing technologies. However, realistic Hand-Object Interaction (HOI) - the complex dynamics between human hands and objects - continues to pose challenges. Generating natural and believable HOI reenactments is difficult due to issues such as occlusion between hands and objects, variations in object shapes and orientations, and the necessity for precise physical interactions, and importantly, the ability to generalize to unseen humans and objects. This paper presents a novel framework iDiT-HOI that enables in-the-wild HOI reenactment generation. Specifically, we propose a unified inpainting-based token process method, called Inp-TPU, with a two-stage video diffusion transformer (DiT) model. The first stage generates a key frame by inserting the designated object into the hand region, providing a reference for subsequent frames. The second stage ensures temporal coherence and fluidity in hand-object interactions. The key contribution of our method is to reuse the pretrained model's context perception capabilities without introducing additional parameters, enabling strong generalization to unseen objects and scenarios, and our proposed paradigm naturally supports long video generation. Comprehensive evaluations demonstrate that our approach outperforms existing methods, particularly in challenging real-world scenes, offering enhanced realism and more seamless hand-object interactions.

Danfeng Hong, Wei He, Naoto Yokoya et al.

Hyperspectral imaging, also known as image spectrometry, is a landmark technique in geoscience and remote sensing (RS). In the past decade, enormous efforts have been made to process and analyze these hyperspectral (HS) products mainly by means of seasoned experts. However, with the ever-growing volume of data, the bulk of costs in manpower and material resources poses new challenges on reducing the burden of manual labor and improving efficiency. For this reason, it is, therefore, urgent to develop more intelligent and automatic approaches for various HS RS applications. Machine learning (ML) tools with convex optimization have successfully undertaken the tasks of numerous artificial intelligence (AI)-related applications. However, their ability in handling complex practical problems remains limited, particularly for HS data, due to the effects of various spectral variabilities in the process of HS imaging and the complexity and redundancy of higher dimensional HS signals. Compared to the convex models, non-convex modeling, which is capable of characterizing more complex real scenes and providing the model interpretability technically and theoretically, has been proven to be a feasible solution to reduce the gap between challenging HS vision tasks and currently advanced intelligent data processing models.

Wei He, Naoto Yokoya, Xin Yuan

Coded aperture snapshot spectral imaging (CASSI) is a promising technique to capture the three-dimensional hyperspectral image (HSI) using a single coded two-dimensional (2D) measurement, in which algorithms are used to perform the inverse problem. Due to the ill-posed nature, various regularizers have been exploited to reconstruct the 3D data from the 2D measurement. Unfortunately, the accuracy and computational complexity are unsatisfied. One feasible solution is to utilize additional information such as the RGB measurement in CASSI. Considering the combined CASSI and RGB measurement, in this paper, we propose a new fusion model for the HSI reconstruction. We investigate the spectral low-rank property of HSI composed of a spectral basis and spatial coefficients. Specifically, the RGB measurement is utilized to estimate the coefficients, meanwhile the CASSI measurement is adopted to provide the orthogonal spectral basis. We further propose a patch processing strategy to enhance the spectral low-rank property of HSI. The proposed model neither requires non-local processing or iteration, nor the spectral sensing matrix of the RGB detector. Extensive experiments on both simulated and real HSI dataset demonstrate that our proposed method outperforms previous state-of-the-art not only in quality but also speeds up the reconstruction more than 5000 times.

Linxi Huan, Nan Xue, Xianwei Zheng et al.

This paper presents a context-aware tracing strategy (CATS) for crisp edge detection with deep edge detectors, based on an observation that the localization ambiguity of deep edge detectors is mainly caused by the mixing phenomenon of convolutional neural networks: feature mixing in edge classification and side mixing during fusing side predictions. The CATS consists of two modules: a novel tracing loss that performs feature unmixing by tracing boundaries for better side edge learning, and a context-aware fusion block that tackles the side mixing by aggregating the complementary merits of learned side edges. Experiments demonstrate that the proposed CATS can be integrated into modern deep edge detectors to improve localization accuracy. With the vanilla VGG16 backbone, in terms of BSDS500 dataset, our CATS improves the F-measure (ODS) of the RCF and BDCN deep edge detectors by 12% and 6% respectively when evaluating without using the morphological non-maximal suppression scheme for edge detection.

Wei He, Quanming Yao, Chao Li et al.

Non-local low-rank tensor approximation has been developed as a state-of-the-art method for hyperspectral image (HSI) restoration, which includes the tasks of denoising, compressed HSI reconstruction and inpainting. Unfortunately, while its restoration performance benefits from more spectral bands, its runtime also substantially increases. In this paper, we claim that the HSI lies in a global spectral low-rank subspace, and the spectral subspaces of each full band patch group should lie in this global low-rank subspace. This motivates us to propose a unified paradigm combining the spatial and spectral properties for HSI restoration. The proposed paradigm enjoys performance superiority from the non-local spatial denoising and light computation complexity from the low-rank orthogonal basis exploration. An efficient alternating minimization algorithm with rank adaptation is developed. It is done by first solving a fidelity term-related problem for the update of a latent input image, and then learning a low-dimensional orthogonal basis and the related reduced image from the latent input image. Subsequently, non-local low-rank denoising is developed to refine the reduced image and orthogonal basis iteratively. Finally, the experiments on HSI denoising, compressed reconstruction, and inpainting tasks, with both simulated and real datasets, demonstrate its superiority with respect to state-of-the-art HSI restoration methods.

Tatsumi Uezato, Danfeng Hong, Naoto Yokoya et al.

The fusion of input and guidance images that have a tradeoff in their information (e.g., hyperspectral and RGB image fusion or pansharpening) can be interpreted as one general problem. However, previous studies applied a task-specific handcrafted prior and did not address the problems with a unified approach. To address this limitation, in this study, we propose a guided deep decoder network as a general prior. The proposed network is composed of an encoder-decoder network that exploits multi-scale features of a guidance image and a deep decoder network that generates an output image. The two networks are connected by feature refinement units to embed the multi-scale features of the guidance image into the deep decoder network. The proposed network allows the network parameters to be optimized in an unsupervised way without training data. Our results show that the proposed network can achieve state-of-the-art performance in various image fusion problems.

Naoto Yokoya, Kazuki Yamanoi, Wei He et al.

We propose a framework that estimates inundation depth (maximum water level) and debris-flow-induced topographic deformation from remote sensing imagery by integrating deep learning and numerical simulation. A water and debris flow simulator generates training data for various artificial disaster scenarios. We show that regression models based on Attention U-Net and LinkNet architectures trained on such synthetic data can predict the maximum water level and topographic deformation from a remote sensing-derived change detection map and a digital elevation model. The proposed framework has an inpainting capability, thus mitigating the false negatives that are inevitable in remote sensing image analysis. Our framework breaks the limits of remote sensing and enables rapid estimation of inundation depth and topographic deformation, essential information for emergency response, including rescue and relief activities. We conduct experiments with both synthetic and real data for two disaster events that caused simultaneous flooding and debris flows and demonstrate the effectiveness of our approach quantitatively and qualitatively.

Wei He, Yong Chen, Naoto Yokoya et al.

Hyperspectral super-resolution (HSR) fuses a low-resolution hyperspectral image (HSI) and a high-resolution multispectral image (MSI) to obtain a high-resolution HSI (HR-HSI). In this paper, we propose a new model, named coupled tensor ring factorization (CTRF), for HSR. The proposed CTRF approach simultaneously learns high spectral resolution core tensor from the HSI and high spatial resolution core tensors from the MSI, and reconstructs the HR-HSI via tensor ring (TR) representation (Figure~\ref{fig:framework}). The CTRF model can separately exploit the low-rank property of each class (Section \ref{sec:analysis}), which has been never explored in the previous coupled tensor model. Meanwhile, it inherits the simple representation of coupled matrix/CP factorization and flexible low-rank exploration of coupled Tucker factorization. Guided by Theorem~\ref{th:1}, we further propose a spectral nuclear norm regularization to explore the global spectral low-rank property. The experiments have demonstrated the advantage of the proposed nuclear norm regularized CTRF (NCTRF) as compared to previous matrix/tensor and deep learning methods.

Wei He, Quanming Yao, Chao Li et al.

Non-local low-rank tensor approximation has been developed as a state-of-the-art method for hyperspectral image (HSI) denoising. Unfortunately, with more spectral bands for HSI, while the running time of these methods significantly increases, their denoising performance benefits little. In this paper, we claim that the HSI underlines a global spectral low-rank subspace, and the spectral subspaces of each full band patch groups should underlie this global low-rank subspace. This motivates us to propose a unified spatial-spectral paradigm for HSI denoising. As the new model is hard to optimize, we further propose an efficient algorithm for optimization, which is motivated by alternating minimization. This is done by first learning a low-dimensional projection and the related reduced image from the noisy HSI. Then, the non-local low-rank denoising and iterative regularization are developed to refine the reduced image and projection, respectively. Finally, experiments on synthetic and both real datasets demonstrate the superiority against the other state-of-the-arts HSI denoising methods.

Yong Cheng, Wei Xu, Zhongjun He et al.

While end-to-end neural machine translation (NMT) has made remarkable progress recently, NMT systems only rely on parallel corpora for parameter estimation. Since parallel corpora are usually limited in quantity, quality, and coverage, especially for low-resource languages, it is appealing to exploit monolingual corpora to improve NMT. We propose a semi-supervised approach for training NMT models on the concatenation of labeled (parallel corpora) and unlabeled (monolingual corpora) data. The central idea is to reconstruct the monolingual corpora using an autoencoder, in which the source-to-target and target-to-source translation models serve as the encoder and decoder, respectively. Our approach can not only exploit the monolingual corpora of the target language, but also of the source language. Experiments on the Chinese-English dataset show that our approach achieves significant improvements over state-of-the-art SMT and NMT systems.