Xuewei Li

Guangcong Zheng, Xianpan Zhou, Xuewei Li et al.

Recently, diffusion models have achieved great success in image synthesis. However, when it comes to the layout-to-image generation where an image often has a complex scene of multiple objects, how to make strong control over both the global layout map and each detailed object remains a challenging task. In this paper, we propose a diffusion model named LayoutDiffusion that can obtain higher generation quality and greater controllability than the previous works. To overcome the difficult multimodal fusion of image and layout, we propose to construct a structural image patch with region information and transform the patched image into a special layout to fuse with the normal layout in a unified form. Moreover, Layout Fusion Module (LFM) and Object-aware Cross Attention (OaCA) are proposed to model the relationship among multiple objects and designed to be object-aware and position-sensitive, allowing for precisely controlling the spatial related information. Extensive experiments show that our LayoutDiffusion outperforms the previous SOTA methods on FID, CAS by relatively 46.35%, 26.70% on COCO-stuff and 44.29%, 41.82% on VG. Code is available at https://github.com/ZGCTroy/LayoutDiffusion.

Longrong Yang, Xianpan Zhou, Xuewei Li et al.

Knowledge distillation (KD) has shown potential for learning compact models in dense object detection. However, the commonly used softmax-based distillation ignores the absolute classification scores for individual categories. Thus, the optimum of the distillation loss does not necessarily lead to the optimal student classification scores for dense object detectors. This cross-task protocol inconsistency is critical, especially for dense object detectors, since the foreground categories are extremely imbalanced. To address the issue of protocol differences between distillation and classification, we propose a novel distillation method with cross-task consistent protocols, tailored for the dense object detection. For classification distillation, we address the cross-task protocol inconsistency problem by formulating the classification logit maps in both teacher and student models as multiple binary-classification maps and applying a binary-classification distillation loss to each map. For localization distillation, we design an IoU-based Localization Distillation Loss that is free from specific network structures and can be compared with existing localization distillation losses. Our proposed method is simple but effective, and experimental results demonstrate its superiority over existing methods. Code is available at https://github.com/TinyTigerPan/BCKD.

Xuewei Li, Tao Wu, Zhongang Qi et al.

As an important and challenging problem in computer vision, PAnoramic Semantic Segmentation (PASS) gives complete scene perception based on an ultra-wide angle of view. Usually, prevalent PASS methods with 2D panoramic image input focus on solving image distortions but lack consideration of the 3D properties of original $360^{\circ}$ data. Therefore, their performance will drop a lot when inputting panoramic images with the 3D disturbance. To be more robust to 3D disturbance, we propose our Spherical Geometry-Aware Transformer for PAnoramic Semantic Segmentation (SGAT4PASS), considering 3D spherical geometry knowledge. Specifically, a spherical geometry-aware framework is proposed for PASS. It includes three modules, i.e., spherical geometry-aware image projection, spherical deformable patch embedding, and a panorama-aware loss, which takes input images with 3D disturbance into account, adds a spherical geometry-aware constraint on the existing deformable patch embedding, and indicates the pixel density of original $360^{\circ}$ data, respectively. Experimental results on Stanford2D3D Panoramic datasets show that SGAT4PASS significantly improves performance and robustness, with approximately a 2% increase in mIoU, and when small 3D disturbances occur in the data, the stability of our performance is improved by an order of magnitude. Our code and supplementary material are available at https://github.com/TencentARC/SGAT4PASS.

Peihan Miao, Wei Su, Gaoang Wang et al.

As an important and challenging problem in vision-language tasks, referring expression comprehension (REC) generally requires a large amount of multi-grained information of visual and linguistic modalities to realize accurate reasoning. In addition, due to the diversity of visual scenes and the variation of linguistic expressions, some hard examples have much more abundant multi-grained information than others. How to aggregate multi-grained information from different modalities and extract abundant knowledge from hard examples is crucial in the REC task. To address aforementioned challenges, in this paper, we propose a Self-paced Multi-grained Cross-modal Interaction Modeling framework, which improves the language-to-vision localization ability through innovations in network structure and learning mechanism. Concretely, we design a transformer-based multi-grained cross-modal attention, which effectively utilizes the inherent multi-grained information in visual and linguistic encoders. Furthermore, considering the large variance of samples, we propose a self-paced sample informativeness learning to adaptively enhance the network learning for samples containing abundant multi-grained information. The proposed framework significantly outperforms state-of-the-art methods on widely used datasets, such as RefCOCO, RefCOCO+, RefCOCOg, and ReferItGame datasets, demonstrating the effectiveness of our method.

Shangfei Wang, Jiaqiang Wu, Feiyi Zheng et al.

This paper introduces our method for the Emotional Reaction Intensity (ERI) Estimation Challenge, in CVPR 2023: 5th Workshop and Competition on Affective Behavior Analysis in-the-wild (ABAW). Based on the multimodal data provided by the originazers, we extract acoustic and visual features with different pretrained models. The multimodal features are mixed together by Transformer Encoders with cross-modal attention mechnism. In this paper, 1. better features are extracted with the SOTA pretrained models. 2. Compared with the baseline, we improve the Pearson's Correlations Coefficient a lot. 3. We process the data with some special skills to enhance performance ability of our model.

Jianrong Wang, Zixuan Wang, Xiaosheng Hu et al.

Previous works derive personalized speech features by training the model on a large dataset composed of his/her audio sounds. It was reported that face information has a strong link with the speech sound. Thus in this work, we innovatively extract personalized speech features from human faces to synthesize personalized speech using neural vocoder. A Face-based Residual Personalized Speech Synthesis Model (FR-PSS) containing a speech encoder, a speech synthesizer and a face encoder is designed for PSS. In this model, by designing two speech priors, a residual-guided strategy is introduced to guide the face feature to approach the true speech feature in the training. Moreover, considering the error of feature's absolute values and their directional bias, we formulate a novel tri-item loss function for face encoder. Experimental results show that the speech synthesized by our model is comparable to the personalized speech synthesized by training a large amount of audio data in previous works.

Xuewei Li, Yaqiao Zhu, Jie Gao et al.

Segmentation of nodules in thyroid ultrasound imaging plays a crucial role in the detection and treatment of thyroid cancer. However, owing to the diversity of scanner vendors and imaging protocols in different hospitals, the automatic segmentation model, which has already demonstrated expert-level accuracy in the field of medical image segmentation, finds its accuracy reduced as the result of its weak generalization performance when being applied in clinically realistic environments. To address this issue, the present paper proposes ASTN, a framework for thyroid nodule segmentation achieved through a new type co-registration network. By extracting latent semantic information from the atlas and target images and utilizing in-depth features to accomplish the co-registration of nodules in thyroid ultrasound images, this framework can ensure the integrity of anatomical structure and reduce the impact on segmentation as the result of overall differences in image caused by different devices. In addition, this paper also provides an atlas selection algorithm to mitigate the difficulty of co-registration. As shown by the evaluation results collected from the datasets of different devices, thanks to the method we proposed, the model generalization has been greatly improved while maintaining a high level of segmentation accuracy.

Xuewei Li, Weilun Zhang, Jie Gao et al.

Unsupervised domain adaptation(UDA) has been applied to image semantic segmentation to solve the problem of domain offset. However, in some difficult categories with poor recognition accuracy, the segmentation effects are still not ideal. To this end, in this paper, Intra-subdomain adaptation adversarial learning segmentation method based on Dynamic Pseudo Labels(IDPL) is proposed. The whole process consists of 3 steps: Firstly, the instance-level pseudo label dynamic generation module is proposed, which fuses the class matching information in global classes and local instances, thus adaptively generating the optimal threshold for each class, obtaining high-quality pseudo labels. Secondly, the subdomain classifier module based on instance confidence is constructed, which can dynamically divide the target domain into easy and difficult subdomains according to the relative proportion of easy and difficult instances. Finally, the subdomain adversarial learning module based on self-attention is proposed. It uses multi-head self-attention to confront the easy and difficult subdomains at the class level with the help of generated high-quality pseudo labels, so as to focus on mining the features of difficult categories in the high-entropy region of target domain images, which promotes class-level conditional distribution alignment between the subdomains, improving the segmentation performance of difficult categories. For the difficult categories, the experimental results show that the performance of IDPL is significantly improved compared with other latest mainstream methods.

Xuewei Li, Zewen Shang, Zhiqiang Liu et al.

Wind speed prediction is critical to the management of wind power generation. Due to the large range of wind speed fluctuations and wake effect, there may also be strong correlations between long-distance wind turbines. This difficult-to-extract feature has become a bottleneck for improving accuracy. History and future time information includes the trend of airflow changes, whether this dynamic information can be utilized will also affect the prediction effect. In response to the above problems, this paper proposes Windformer. First, Windformer divides the wind turbine cluster into multiple non-overlapping windows and calculates correlations inside the windows, then shifts the windows partially to provide connectivity between windows, and finally fuses multi-channel features based on detailed and global information. To dynamically model the change process of wind speed, this paper extracts time series in both history and future directions simultaneously. Compared with other current-advanced methods, the Mean Square Error (MSE) of Windformer is reduced by 0.5\% to 15\% on two datasets from NERL.

Xuewei Li, Xinghan Bao, Zhimin Chen et al.

As an important and challenging problem in computer vision, Panoramic Semantic Segmentation (PASS) aims to give complete scene perception based on an ultra-wide angle of view. Most PASS methods often focus on spherical geometry with RGB input or using the depth information in original or HHA format, which does not make full use of panoramic image geometry. To address these shortcomings, we propose REL-SF4PASS with our REL depth representation based on cylindrical coordinate and Spherical-dynamic Multi-Modal Fusion SMMF. REL is made up of Rectified Depth, Elevation-Gained Vertical Inclination Angle, and Lateral Orientation Angle, which fully represents 3D space in cylindrical coordinate style and the surface normal direction. SMMF aims to ensure the diversity of fusion for different panoramic image regions and reduce the breakage of cylinder side surface expansion in ERP projection, which uses different fusion strategies to match the different regions in panoramic images. Experimental results show that REL-SF4PASS considerably improves performance and robustness on popular benchmark, Stanford2D3D Panoramic datasets. It gains 2.35% average mIoU improvement on all 3 folds and reduces the performance variance by approximately 70% when facing 3D disturbance.

Jianrong Wang, Ziyue Tang, Xuewei Li et al.

Cued Speech (CS) is a visual communication system for the deaf or hearing impaired people. It combines lip movements with hand cues to obtain a complete phonetic repertoire. Current deep learning based methods on automatic CS recognition suffer from a common problem, which is the data scarcity. Until now, there are only two public single speaker datasets for French (238 sentences) and British English (97 sentences). In this work, we propose a cross-modal knowledge distillation method with teacher-student structure, which transfers audio speech information to CS to overcome the limited data problem. Firstly, we pretrain a teacher model for CS recognition with a large amount of open source audio speech data, and simultaneously pretrain the feature extractors for lips and hands using CS data. Then, we distill the knowledge from teacher model to the student model with frame-level and sequence-level distillation strategies. Importantly, for frame-level, we exploit multi-task learning to weigh losses automatically, to obtain the balance coefficient. Besides, we establish a five-speaker British English CS dataset for the first time. The proposed method is evaluated on French and British English CS datasets, showing superior CS recognition performance to the state-of-the-art (SOTA) by a large margin.

Tao Wu, Xuewei Li, Zhongang Qi et al.

Controllable spherical panoramic image generation holds substantial applicative potential across a variety of domains.However, it remains a challenging task due to the inherent spherical distortion and geometry characteristics, resulting in low-quality content generation.In this paper, we introduce a novel framework of SphereDiffusion to address these unique challenges, for better generating high-quality and precisely controllable spherical panoramic images.For the spherical distortion characteristic, we embed the semantics of the distorted object with text encoding, then explicitly construct the relationship with text-object correspondence to better use the pre-trained knowledge of the planar images.Meanwhile, we employ a deformable technique to mitigate the semantic deviation in latent space caused by spherical distortion.For the spherical geometry characteristic, in virtue of spherical rotation invariance, we improve the data diversity and optimization objectives in the training process, enabling the model to better learn the spherical geometry characteristic.Furthermore, we enhance the denoising process of the diffusion model, enabling it to effectively use the learned geometric characteristic to ensure the boundary continuity of the generated images.With these specific techniques, experiments on Structured3D dataset show that SphereDiffusion significantly improves the quality of controllable spherical image generation and relatively reduces around 35% FID on average.

Zhiao Feng, Xuewei Li, Junjie Yang et al.

Image editing has made great progress on planar images, but panoramic image editing remains underexplored. Due to their spherical geometry and projection distortions, panoramic images present three key challenges: boundary discontinuity, trajectory deformation, and uneven pixel density. To tackle these issues, we propose SphereDrag, a novel panoramic editing framework utilizing spherical geometry knowledge for accurate and controllable editing. Specifically, adaptive reprojection (AR) uses adaptive spherical rotation to deal with discontinuity; great-circle trajectory adjustment (GCTA) tracks the movement trajectory more accurate; spherical search region tracking (SSRT) adaptively scales the search range based on spherical location to address uneven pixel density. Also, we construct PanoBench, a panoramic editing benchmark, including complex editing tasks involving multiple objects and diverse styles, which provides a standardized evaluation framework. Experiments show that SphereDrag gains a considerable improvement compared with existing methods in geometric consistency and image quality, achieving up to 10.5% relative improvement.

Ruiguo Yu, Yiyang Zhang, Yuan Tian et al.

Deep learning-based segmentation methods are widely utilized for detecting lesions in ultrasound images. Throughout the imaging procedure, the attenuation and scattering of ultrasound waves cause contour blurring and the formation of artifacts, limiting the clarity of the acquired ultrasound images. To overcome this challenge, we propose a contour-based probabilistic segmentation model CP-UNet, which guides the segmentation network to enhance its focus on contour during decoding. We design a novel down-sampling module to enable the contour probability distribution modeling and encoding stages to acquire global-local features. Furthermore, the Gaussian Mixture Model utilizes optimized features to model the contour distribution, capturing the uncertainty of lesion boundaries. Extensive experiments with several state-of-the-art deep learning segmentation methods on three ultrasound image datasets show that our method performs better on breast and thyroid lesions segmentation.

Ruiyu Li, Peilin Zhao, Guangxia Li et al.

Online multi-task learning (OMTL) enhances streaming data processing by leveraging the inherent relations among multiple tasks. It can be described as an optimization problem in which a single loss function is defined for multiple tasks. Existing gradient-descent-based methods for this problem might suffer from gradient vanishing and poor conditioning issues. Furthermore, the centralized setting hinders their application to online parallel optimization, which is vital to big data analytics. Therefore, this study proposes a novel OMTL framework based on the alternating direction multiplier method (ADMM), a recent breakthrough in optimization suitable for the distributed computing environment because of its decomposable and easy-to-implement nature. The relations among multiple tasks are modeled dynamically to fit the constant changes in an online scenario. In a classical distributed computing architecture with a central server, the proposed OMTL algorithm with the ADMM optimizer outperforms SGD-based approaches in terms of accuracy and efficiency. Because the central server might become a bottleneck when the data scale grows, we further tailor the algorithm to a decentralized setting, so that each node can work by only exchanging information with local neighbors. Experimental results on a synthetic and several real-world datasets demonstrate the efficiency of our methods.

Xuewei Li, Zhenzhen Nie, Mei Yu et al.

Instance features in images exhibit spurious correlations with background features, affecting the training process of deep neural classifiers. This leads to insufficient attention to instance features by the classifier, resulting in erroneous classification outcomes. In this paper, we propose a data augmentation method called Spurious Correlations Guided Synthesis (SCGS) that mitigates spurious correlations through image generation model. This approach does not require expensive spurious attribute (group) labels for the training data and can be widely applied to other debiasing methods. Specifically, SCGS first identifies the incorrect attention regions of a pre-trained classifier on the training images, and then uses an image generation model to generate new training data based on these incorrect attended regions. SCGS increases the diversity and scale of the dataset to reduce the impact of spurious correlations on classifiers. Changes in the classifier's attention regions and experimental results on three different domain datasets demonstrate that this method is effective in reducing the classifier's reliance on spurious correlations.

Jianrong Wang, Nan Gu, Mei Yu et al.

Cued Speech (CS) is a communication system for deaf people or hearing impaired people, in which a speaker uses it to aid a lipreader in phonetic level by clarifying potentially ambiguous mouth movements with hand shape and positions. Feature extraction of multi-modal CS is a key step in CS recognition. Recent supervised deep learning based methods suffer from noisy CS data annotations especially for hand shape modality. In this work, we first propose a self-supervised contrastive learning method to learn the feature representation of image without using labels. Secondly, a small amount of manually annotated CS data are used to fine-tune the first module. Thirdly, we present a module, which combines Bi-LSTM and self-attention networks to further learn sequential features with temporal and contextual information. Besides, to enlarge the volume and the diversity of the current limited CS datasets, we build a new British English dataset containing 5 native CS speakers. Evaluation results on both French and British English datasets show that our model achieves over 90% accuracy in hand shape recognition. Significant improvements of 8.75% (for French) and 10.09% (for British English) are achieved in CS phoneme recognition correctness compared with the state-of-the-art.

Jiabao Cui, Xuewei Li, Bin Li et al.

In this paper, we propose a novel learning scheme called epoch-evolving Gaussian Process Guided Learning (GPGL), which aims at characterizing the correlation information between the batch-level distribution and the global data distribution. Such correlation information is encoded as context labels and needs renewal every epoch. With the guidance of the context label and ground truth label, GPGL scheme provides a more efficient optimization through updating the model parameters with a triangle consistency loss. Furthermore, our GPGL scheme can be further generalized and naturally applied to the current deep models, outperforming the existing batch-based state-of-the-art models on mainstream datasets (CIFAR-10, CIFAR-100, and Tiny-ImageNet) remarkably.

Jianrong Wang, Ge Zhang, Zhenyu Wu et al.

In self-supervised monocular depth estimation, the depth discontinuity and motion objects' artifacts are still challenging problems. Existing self-supervised methods usually utilize a single view to train the depth estimation network. Compared with static views, abundant dynamic properties between video frames are beneficial to refined depth estimation, especially for dynamic objects. In this work, we propose a novel self-supervised joint learning framework for depth estimation using consecutive frames from monocular and stereo videos. The main idea is using an implicit depth cue extractor which leverages dynamic and static cues to generate useful depth proposals. These cues can predict distinguishable motion contours and geometric scene structures. Furthermore, a new high-dimensional attention module is introduced to extract clear global transformation, which effectively suppresses uncertainty of local descriptors in high-dimensional space, resulting in a more reliable optimization in learning framework. Experiments demonstrate that the proposed framework outperforms the state-of-the-art(SOTA) on KITTI and Make3D datasets.

Xuewei Li, Songyuan Li, Bourahla Omar et al.

Knowledge distillation, aimed at transferring the knowledge from a heavy teacher network to a lightweight student network, has emerged as a promising technique for compressing neural networks. However, due to the capacity gap between the heavy teacher and the lightweight student, there still exists a significant performance gap between them. In this paper, we see knowledge distillation in a fresh light, using the knowledge gap, or the residual, between a teacher and a student as guidance to train a much more lightweight student, called a res-student. We combine the student and the res-student into a new student, where the res-student rectifies the errors of the former student. Such a residual-guided process can be repeated until the user strikes the balance between accuracy and cost. At inference time, we propose a sample-adaptive strategy to decide which res-students are not necessary for each sample, which can save computational cost. Experimental results show that we achieve competitive performance with 18.04$\%$, 23.14$\%$, 53.59$\%$, and 56.86$\%$ of the teachers' computational costs on the CIFAR-10, CIFAR-100, Tiny-ImageNet, and ImageNet datasets. Finally, we do thorough theoretical and empirical analysis for our method.

Ruiguo Yu, Zhiqiang Liu, Xuewei Li et al.

Wind power prediction is of vital importance in wind power utilization. There have been a lot of researches based on the time series of the wind power or speed, but In fact, these time series cannot express the temporal and spatial changes of wind, which fundamentally hinders the advance of wind power prediction. In this paper, a new kind of feature that can describe the process of temporal and spatial variation is proposed, namely, Spatio-Temporal Features. We first map the data collected at each moment from the wind turbine to the plane to form the state map, namely, the scene, according to the relative positions. The scene time series over a period of time is a multi-channel image, i.e. the Spatio-Temporal Features. Based on the Spatio-Temporal Features, the deep convolutional network is applied to predict the wind power, achieving a far better accuracy than the existing methods. Compared with the starge-of-the-art method, the mean-square error (MSE) in our method is reduced by 49.83%, and the average time cost for training models can be shortened by a factor of more than 150.