With the achievements of Transformer in the field of natural language processing, the encoder-decoder and the attention mechanism in Transformer have been applied to computer vision. Recently, in multiple tasks of computer vision (image classification, object detection, semantic segmentation, etc.), state-of-the-art convolutional neural networks have introduced some concepts of Transformer. This proves that Transformer has a good prospect in the field of image recognition. After Vision Transformer was proposed, more and more works began to use self-attention to completely replace the convolutional layer. This work is based on Vision Transformer, combined with the pyramid architecture, using Split-transform-merge to propose the group encoder and name the network architecture Aggregated Pyramid Vision Transformer (APVT). We perform image classification tasks on the CIFAR-10 dataset and object detection tasks on the COCO 2017 dataset. Compared with other network architectures that use Transformer as the backbone, APVT has excellent results while reducing the computational cost. We hope this improved strategy can provide a reference for future Transformer research in computer vision.
Understanding the context of complex and cluttered scenes is a challenging problem for semantic segmentation. However, it is difficult to model the context without prior and additional supervision because the scene's factors, such as the scale, shape, and appearance of objects, vary considerably in these scenes. To solve this, we propose to learn the structures of objects and the hierarchy among objects because context is based on these intrinsic properties. In this study, we design novel hierarchical, contextual, and multiscale pyramidal representations to capture the properties from an input…
The prevalence of skin melanoma is rapidly increasing as well as the recorded death cases of its patients. Automatic image segmentation tools play an important role in providing standardized computer-assisted analysis for skin melanoma patients. Current state-of-the-art segmentation methods are based on fully convolutional neural networks, which utilize an encoder-decoder approach. However, these methods produce coarse segmentation masks due to the loss of location information during the encoding layers. Inspired by Pyramid Scene Parsing Network (PSP-Net), we propose an encoder-decoder model t…
Megvii Inc（旷视科技）；University of Chinese Academy of Sciences（中国科学院大学）；Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；Center for Research on Intelligent Perception and Computing（智能感知与计算研究中心）；National Laboratory of Pattern Recognition（模式识别国家重点实验室）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
In this paper, we propose an efficient human pose estimation network (DANet) by learning deeply aggregated representations. Most existing models explore multi-scale information mainly from features with different spatial sizes. Powerful multi-scale representations usually rely on the cascaded pyramid framework. This framework largely boosts the performance but in the meanwhile makes networks very deep and complex. Instead, we focus on exploiting multi-scale information from layers with different receptive-field sizes and then making full of use this information by improving the fusion method. …
Institute of Automation（自动化研究所）；JD Explore Academy（京东探索研究院）；SenseTime Research（商汤科技研究院）；ETH Zurich（苏黎世联邦理工学院）；Xiaomi（小米）
Video Instance Segmentation (VIS) is a new and inherently multi-task problem, which aims to detect, segment, and track each instance in a video sequence. Existing approaches are mainly based on single-frame features or single-scale features of multiple frames, where either temporal information or multi-scale information is ignored. To incorporate both temporal and scale information, we propose a Temporal Pyramid Routing (TPR) strategy to conditionally align and conduct pixel-level aggregation from a feature pyramid pair of two adjacent frames. Specifically, TPR contains two novel components, i…
Feature pyramid networks (FPN) are widely exploited for multi-scale feature fusion in existing advanced object detection frameworks. Numerous previous works have developed various structures for bidirectional feature fusion, all of which are shown to improve the detection performance effectively. We observe that these complicated network structures require feature pyramids to be stacked in a fixed order, which introduces longer pipelines and reduces the inference speed. Moreover, semantics from non-adjacent levels are diluted in the feature pyramid since only features at adjacent pyramid level…
Beijing Jiaotong University（北京交通大学）；National University of Singapore（新加坡国立大学）
Feature pyramid network (FPN) based models, which fuse the semantics and salient details in a progressive manner, have been proven highly effective in salient object detection. However, it is observed that these models often generate saliency maps with incomplete object structures or unclear object boundaries, due to the \emph{indirect} information propagation among distant layers that makes such fusion structure less effective. In this work, we propose a novel Cross-layer Feature Pyramid Network (CFPN), in which direct cross-layer communication is enabled to improve the progressive fusion in …
The workflow of extracting features from images using convolutional neural networks (CNN) and generating captions with recurrent neural networks (RNN) has become a de-facto standard for image captioning task. However, since CNN features are originally designed for classification task, it is mostly concerned with the main conspicuous element of the image, and often fails to correctly convey information on local, secondary elements. We propose to incorporate coding with vector of locally aggregated descriptors (VLAD) on spatial pyramid for CNN features of sub-regions in order to generate image r…
Inception Institute of Artificial Intelligence（起始人工智能研究院）；Terminus Group（特斯联科技集团）；The Chinese University of Hong Kong（香港中文大学）；The Hong Kong University of Science and Technology（香港科技大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
This paper presents a Refinement Pyramid Transformer (RePFormer) for robust facial landmark detection. Most facial landmark detectors focus on learning representative image features. However, these CNN-based feature representations are not robust enough to handle complex real-world scenarios due to ignoring the internal structure of landmarks, as well as the relations between landmarks and context. In this work, we formulate the facial landmark detection task as refining landmark queries along pyramid memories. Specifically, a pyramid transformer head (PTH) is introduced to build both homologo…
Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；Tsinghua University（清华大学）
In this paper, we propose an attention pyramid method for person re-identification. Unlike conventional attention-based methods which only learn a global attention map, our attention pyramid exploits the attention regions in a multi-scale manner because human attention varies with different scales. Our attention pyramid imitates the process of human visual perception which tends to notice the foreground person over the cluttered background, and further focus on the specific color of the shirt with close observation. Specifically, we describe our attention pyramid by a "split-attend-merge-stack…
Traffic scene recognition is an important and challenging issue in Intelligent Transportation Systems (ITS). Recently, Convolutional Neural Network (CNN) models have achieved great success in many applications, including scene classification. The remarkable representational learning capability of CNN remains to be further explored for solving real-world problems. Vector of Locally Aggregated Descriptors (VLAD) encoding has also proved to be a powerful method in catching global contextual information. In this paper, we attempted to solve the traffic scene recognition problem by combining the fe…
Retinal blood vessel can assist doctors in diagnosis of eye-related diseases such as diabetes and hypertension, and its segmentation is particularly important for automatic retinal image analysis. However, it is challenging to segment these vessels structures, especially the thin capillaries from the color retinal image due to low contrast and ambiguousness. In this paper, we propose pyramid U-Net for accurate retinal vessel segmentation. In pyramid U-Net, the proposed pyramid-scale aggregation blocks (PSABs) are employed in both the encoder and decoder to aggregate features at higher, current…
Institute for Infocomm Research (I2R)（信息通信研究院（I2R））；Institute of High Performance Computing (IHPC)（高性能计算研究院（IHPC））；ETH Zürich（苏黎世联邦理工学院）；School of Information and Communication Engineering, UESTC（电子科技大学信息与通信工程学院）
UAGLNet: Uncertainty-Aggregated Global-Local Fusion Network with Cooperative CNN-Transformer for Building Extraction
School of Computer Science (National Pilot Software Engineering School), Beijing University Of Posts and Telecommunications（计算机学院（国家级试点软件工程学院），北京邮电大学）；School of Cyber Science and Technology, Shenzhen Campus, Sun Yat-sen University（网络科学与技术学院，中山大学深圳校区）
Expert-Like Reparameterization of Heterogeneous Pyramid Receptive Fields in Efficient CNNs for Fair Medical Image Classification
Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering, Southern University of Science and Technology（可信自主系统研究所和南方科技大学计算机科学与工程系）；Center for High Performance Computing and Shenzhen Key Laboratory of Intelligent Bioinformatics, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（高性能计算中心和深圳智能生物信息学重点实验室，深圳先进技术研究院，中国科学院）；Tomey Corporation（Tomey公司）；Changchun University（长春大学）；School of computer science, University of Nottingham Ningbo China（Nottingham Ningbo中国大学计算机学院）；School of Ophthalmology and Optometry, Wenzhou Medical University（眼科学与视光学学院，温州医科大学）
We present Local Naive Bayes Nearest Neighbor, an improvement to the NBNN image classification algorithm that increases classification accuracy and improves its ability to scale to large numbers of object classes. The key observation is that only the classes represented in the local neighborhood of a descriptor contribute significantly and reliably to their posterior probability estimates. Instead of maintaining a separate search structure for each class, we merge all of the reference data together into one search structure, allowing quick identification of a descriptor's local neighborhood. W…
Burstormer: Burst Image Restoration and Enhancement Transformer
Mohamed bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学）；Inception Institute of AI（Inception人工智能研究院）；Australian National University（澳大利亚国立大学）；Linköping University（林雪平大学）；University of California, Merced（加州大学默塞德分校）；Yonsei University（延世大学）；Google Research（谷歌研究院）
Beihang University（北京航空航天大学）；XuanWu Hospital, Capital Medical University（首都医科大学宣武医院）；Beijing Diagnostic Center of Vascular Ultrasound（北京血管超声诊断中心）
Carotid arteries vulnerable plaques are a crucial factor in the screening of atherosclerosis by ultrasound technique. However, the plaques are contaminated by various noises such as artifact, speckle noise, and manual segmentation may be time-consuming. This paper proposes an automatic convolutional neural network (CNN) method for plaque segmentation in carotid ultrasound images using a small dataset. First, a parallel network with three independent scale decoders is utilized as our base segmentation network, pyramid dilation convolutions are used to enlarge receptive fields in the three segme…
Real-Time Crowd Counting for Embedded Systems with Lightweight Architecture
Institute of Artificial Intelligence (TeleAI)（人工智能研究所（TeleAI））；China Telecom（中国电信）；School of Artifcial Intelligence, Optics and Electronics (iOPEN)（人工智能、光学与电子学学院（iOPEN））；Northwestern Polytechnical University（西北工业大学）；Honors College（荣誉学院）
