Zixiang Xiong

Jiacong Xu, Zixiang Xiong, Shankar P. Bhattacharyya

Two-branch network architecture has shown its efficiency and effectiveness in real-time semantic segmentation tasks. However, direct fusion of high-resolution details and low-frequency context has the drawback of detailed features being easily overwhelmed by surrounding contextual information. This overshoot phenomenon limits the improvement of the segmentation accuracy of existing two-branch models. In this paper, we make a connection between Convolutional Neural Networks (CNN) and Proportional-Integral-Derivative (PID) controllers and reveal that a two-branch network is equivalent to a Proportional-Integral (PI) controller, which inherently suffers from similar overshoot issues. To alleviate this problem, we propose a novel three-branch network architecture: PIDNet, which contains three branches to parse detailed, context and boundary information, respectively, and employs boundary attention to guide the fusion of detailed and context branches. Our family of PIDNets achieve the best trade-off between inference speed and accuracy and their accuracy surpasses all the existing models with similar inference speed on the Cityscapes and CamVid datasets. Specifically, PIDNet-S achieves 78.6% mIOU with inference speed of 93.2 FPS on Cityscapes and 80.1% mIOU with speed of 153.7 FPS on CamVid.

Jiacong Xu, Riley Kilfoyle, Zixiang Xiong et al.

Machine learning (ML) applications to time series energy utilization forecasting problems are a challenging assignment due to a variety of factors. Chief among these is the non-homogeneity of the energy utilization datasets and the geographical dispersion of energy consumers. Furthermore, these ML models require vast amounts of training data and communications overhead in order to develop an effective model. In this paper, we propose a communication-efficient time series forecasting model combining the most recent advancements in transformer architectures implemented across a geographically dispersed series of EV charging stations and an efficient variant of federated learning (FL) to enable distributed training. The time series prediction performance and communication overhead cost of our FL are compared against their counterpart models and shown to have parity in performance while consuming significantly lower data rates during training. Additionally, the comparison is made across EV charging as well as other time series datasets to demonstrate the flexibility of our proposed model in generalized time series prediction beyond energy demand. The source code for this work is available at https://github.com/XuJiacong/LoGTST_PSGF

Wei Liu, Rui Jiang, Cheng Chen et al.

In reality, rain and fog are often present at the same time, which can greatly reduce the clarity and quality of the scene image. However, most unsupervised single image deraining methods mainly focus on rain streak removal by disregarding the fog, which leads to low-quality deraining performance. In addition, the samples are rather homogeneous generated by these methods and lack diversity, resulting in poor results in the face of complex rain scenes. To address the above issues, we propose a novel Asymetric Cycle Generative and Adversarial framework (ACGF) for single image deraining that trains on both synthetic and real rainy images while simultaneously capturing both rain streaks and fog features. ACGF consists of a Rain-fog2Clean (R2C) transformation block and a Clean2Rain-fog (C2R) transformation block. The former consists of parallel rain removal path and rain-fog feature extraction path by the rain and derain-fog network and the attention rain-fog feature extraction network (ARFE) , while the latter only contains a synthetic rain transformation path. In rain-fog feature extraction path, to better characterize the rain-fog fusion feature, we employ an ARFE to exploit the self-similarity of global and local rain-fog information by learning the spatial feature correlations. Moreover, to improve the translational capacity of C2R and the diversity of models, we design a rain-fog feature decoupling and reorganization network (RFDR) by embedding a rainy image degradation model and a mixed discriminator to preserve richer texture details in synthetic rain conversion path. Extensive experiments on benchmark rain-fog and rain datasets show that ACGF outperforms state-of-the-art deraining methods. We also conduct defogging performance evaluation experiments to further demonstrate the effectiveness of ACGF.

Wei Liu, Cheng Chen, Rui Jiang et al.

Adversarial learning-based image defogging methods have been extensively studied in computer vision due to their remarkable performance. However, most existing methods have limited defogging capabilities for real cases because they are trained on the paired clear and synthesized foggy images of the same scenes. In addition, they have limitations in preserving vivid color and rich textual details in defogging. To address these issues, we develop a novel generative adversarial network, called quad-path cycle consistent adversarial network (QPC-Net), for single image defogging. QPC-Net consists of a Fog2Fogfree block and a Fogfree2Fog block. In each block, there are three learning-based modules, namely, fog removal, color-texture recovery, and fog synthetic, which sequentially compose dual-path that constrain each other to generate high quality images. Specifically, the color-texture recovery model is designed to exploit the self-similarity of texture and structure information by learning the holistic channel-spatial feature correlations between the foggy image with its several derived images. Moreover, in the fog synthetic module, we utilize the atmospheric scattering model to guide it to improve the generative quality by focusing on an atmospheric light optimization with a novel sky segmentation network. Extensive experiments on both synthetic and real-world datasets show that QPC-Net outperforms state-of-the-art defogging methods in terms of quantitative accuracy and subjective visual quality.

Yuda Qiu, Zhangyang Xiong, Kai Han et al.

In this paper we examine the problem of inverse rendering of real face images. Existing methods decompose a face image into three components (albedo, normal, and illumination) by supervised training on synthetic face data. However, due to the domain gap between real and synthetic face images, a model trained on synthetic data often does not generalize well to real data. Meanwhile, since no ground truth for any component is available for real images, it is not feasible to conduct supervised learning on real face images. To alleviate this problem, we propose a weakly supervised training approach to train our model on real face videos, based on the assumption of consistency of albedo and normal across different frames, thus bridging the gap between real and synthetic face images. In addition, we introduce a learning framework, called IlluRes-SfSNet, to further extract the residual map to capture the global illumination effects that give the fine details that are largely ignored in existing methods. Our network is trained on both real and synthetic data, benefiting from both. We comprehensively evaluate our methods on various benchmarks, obtaining better inverse rendering results than the state-of-the-art.

Lingteng Qiu, Xuanye Zhang, Yanran Li et al.

Although occlusion widely exists in nature and remains a fundamental challenge for pose estimation, existing heatmap-based approaches suffer serious degradation on occlusions. Their intrinsic problem is that they directly localize the joints based on visual information; however, the invisible joints are lack of that. In contrast to localization, our framework estimates the invisible joints from an inference perspective by proposing an Image-Guided Progressive GCN module which provides a comprehensive understanding of both image context and pose structure. Moreover, existing benchmarks contain limited occlusions for evaluation. Therefore, we thoroughly pursue this problem and propose a novel OPEC-Net framework together with a new Occluded Pose (OCPose) dataset with 9k annotated images. Extensive quantitative and qualitative evaluations on benchmarks demonstrate that OPEC-Net achieves significant improvements over recent leading works. Notably, our OCPose is the most complex occlusion dataset with respect to average IoU between adjacent instances. Source code and OCPose will be publicly available.

Bin Zhang, Shenyao Jin, Yili Xia et al.

Deep learning based image denoising methods have been extensively investigated. In this paper, attention mechanism enhanced kernel prediction networks (AME-KPNs) are proposed for burst image denoising, in which, nearly cost-free attention modules are adopted to first refine the feature maps and to further make a full use of the inter-frame and intra-frame redundancies within the whole image burst. The proposed AME-KPNs output per-pixel spatially-adaptive kernels, residual maps and corresponding weight maps, in which, the predicted kernels roughly restore clean pixels at their corresponding locations via an adaptive convolution operation, and subsequently, residuals are weighted and summed to compensate the limited receptive field of predicted kernels. Simulations and real-world experiments are conducted to illustrate the robustness of the proposed AME-KPNs in burst image denoising.

Xiaoguang Han, Zhaoxuan Zhang, Dong Du et al.

We present a deep reinforcement learning method of progressive view inpainting for 3D point scene completion under volume guidance, achieving high-quality scene reconstruction from only a single depth image with severe occlusion. Our approach is end-to-end, consisting of three modules: 3D scene volume reconstruction, 2D depth map inpainting, and multi-view selection for completion. Given a single depth image, our method first goes through the 3D volume branch to obtain a volumetric scene reconstruction as a guide to the next view inpainting step, which attempts to make up the missing information; the third step involves projecting the volume under the same view of the input, concatenating them to complete the current view depth, and integrating all depth into the point cloud. Since the occluded areas are unavailable, we resort to a deep Q-Network to glance around and pick the next best view for large hole completion progressively until a scene is adequately reconstructed while guaranteeing validity. All steps are learned jointly to achieve robust and consistent results. We perform qualitative and quantitative evaluations with extensive experiments on the SUNCG data, obtaining better results than the state of the art.

Zizheng Yan, Xiaoguang Han, Changmiao Wang et al.

Diabetic retinopathy is the most important complication of diabetes. Early diagnosis of retinal lesions helps to avoid visual loss or blindness. Due to high-resolution and small-size lesion regions, applying existing methods, such as U-Nets, to perform segmentation on fundus photography is very challenging. Although downsampling the input images could simplify the problem, it loses detailed information. Conducting patch-level analysis helps reaching fine-scale segmentation yet usually leads to misunderstanding as the lack of context information. In this paper, we propose an efficient network that combines them together, not only being aware of local details but also taking fully use of the context perceptions. This is implemented by integrating the decoder parts of a global-level U-net and a patch-level one. The two streams are jointly optimized, ensuring that they are enhanced mutually. Experimental results demonstrate our new framework significantly outperforms existing patch-based and global-based methods, especially when the lesion regions are scattered and small-scaled.