CXChao Xu

Chao Xu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Chao Xu has a total of 26 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    E2LNet: An Efficient and Effective Lightweight Network for Panoramic Depth Estimation

    by Jiayue Xu, Jianping Zhao, Hua Li, Cheng Han, Chao Xu

    Monocular panoramic depth estimation has various applications in robotics and autonomous driving due to its ability to perceive the entire field of view. However, panoramic depth estimation faces two significant challenges: global context capturing and distortion awareness. In this paper, we propose a new framework for panoramic depth estimation that can simultaneously address panoramic distortion and extract global context information, thereby improving the performance of panoramic depth estimation. Specifically, we introduce an attention mechanism into the multi-scale dilated convolution and adaptively adjust the receptive field size between different spatial positions, designing the adaptive attention dilated convolution module, which effectively perceives distortion. At the same time, we design the global scene understanding module to integrate global context information into the feature maps generated using the feature extractor. Finally, we trained and evaluated our model on three benchmark datasets which contains the virtual and real-world RGB-D panorama datasets. The experimental results show that the proposed method achieves competitive performance, comparable to existing techniques in both quantitative and qualitative evaluations. Furthermore, our method has fewer parameters and more flexibility, making it a scalable solution in mobile AR.


  • Open Access

    Ghost-Depth: A Lightweight Encoder-Decoder Network for Monocular Depth Estimation

    by Wei Quan, Jingjing Liu, Chao Xu, Cheng Han, Jia Song, Shanshan Qi

    In recent years, convolutional neural networks especially those based on encoder-decoder architecture have been used in the task of monocular depth estimation, and it has brought great success. However, the parameters and computational cost of networks are increasing constantly so as to improve predicting accuracy. In view of this situation, a network model based on a lightweight encoder-decoder structure is designed to estimate monocular depth in this paper, which has good accuracy and reduces the number of parameters. In order to design a lightweight network, a lightweight network named GhostNet was chose when encoding. In the upsampling process in decoder, Ghost convolution with fewer parameters was used instead of conventional convolutions. And a lightweight attentional feature fusion module was combined with traditional skip connections when upsampling. It compensated for the loss of detail information in feature maps due to downsampling, and further improved the model accuracy. Experiments on dataset NYU-Depth V2 demonstrate that the number of parameters is 2.7M and the accuracy is 79.7%. Our proposed method is lightweight and efficient and outperforms most lightweight methods.

  • Open Access

    PCformer: A parallel convolutional transformer network for 360° depth estimation

    by Chao Xu, Huamin Yang, Cheng Han, Chao Zhang

    360° depth estimation has been extensively studied because 360° images provide a full field of view of the surrounding environment as well as a detailed description of the entire scene. However, most well‐studied convolutional neural networks (CNNs) for 360° depth estimation can extract local features well, but fail to capture rich global features from the panorama due to a fixed receptive field in CNNs. PCformer, a parallel convolutional transformer network that combines the benefits of CNNs and transformers, is proposed for 360° depth estimation. The transformer has the nature to model long‐range dependency and extract global features. With PCformer, both global dependency and local spatial features can be efficiently captured. To fully incorporate global and local features, a dual attention fusion module is designed. Besides, a distortion‐weighted loss function is designed to reduce the distortion in panoramas. Extensive experiments demonstrate that the proposed method achieves competitive results against the state‐of‐the‐art methods on three benchmark datasets. Additional experiments also demonstrate that the proposed model has benefits in terms of model complexity and generalisation capability.


  • Open Access

    An Image Patch is a Wave: Phase-Aware Vision MLP

    by Yehui Tang, Kai Han, Jianyuan Guo, Chang Xu, Yanxi Li, Chao Xu, Yunhe Wang

    In the field of computer vision, recent works show that a pure MLP architecture mainly stacked by fully-connected layers can achieve competing performance with CNN and transformer. An input image of vision MLP is usually split into multiple tokens (patches), while the existing MLP models directly aggregate them with fixed weights, neglecting the varying semantic information of tokens from different images. To dynamically aggregate tokens, we propose to represent each token as a wave function with two parts, amplitude and phase. Amplitude is the original feature and the phase term is a complex value changing according to the semantic contents of input images. Introducing the phase term can dynamically modulate the relationship between tokens and fixed weights in MLP. Based on the wave-like token representation, we establish a novel Wave-MLP architecture for vision tasks. Extensive experiments demonstrate that the proposed Wave-MLP is superior to the state-of-the-art MLP architectures on various vision tasks such as image classification, object detection and semantic segmentation. The source code is available at https://github.com/huawei-noah/CV-Backbones/tree/master/wavemlp_pytorch and https://gitee.com/mindspore/models/tree/master/research/cv/wave_mlp.


  • Open Access

    Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks

    by Yehui Tang, Yunhe Wang, Yixing Xu, Boxin Shi, Chao Xu, Chunjing Xu, Chang Xu

    Deep neural networks often consist of a great number of trainable parameters for extracting powerful features from given datasets. On one hand, massive trainable parameters significantly enhance the performance of these deep networks. On the other hand, they bring the problem of over-fitting. To this end, dropout based methods disable some elements in the output feature maps during the training phase for reducing the co-adaptation of neurons. Although the generalization ability of the resulting models can be enhanced by these approaches, the conventional binary dropout is not the optimal solution. Therefore, we investigate the empirical Rademacher complexity related to intermediate layers of deep neural networks and propose a feature distortion method (Disout) for addressing the aforementioned problem. In the training period, randomly selected elements in the feature maps will be replaced with specific values by exploiting the generalization error bound. The superiority of the proposed feature map distortion for producing deep neural network with higher testing performance is analyzed and demonstrated on several benchmark image datasets.