We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

The ImageNet Large Scale Visual Recognition Challenge is a benchmark in object category classification and detection on hundreds of object categories and millions of images. The challenge has been run annually from 2010 to present, attracting participation from more than fifty institutions. This paper describes the creation of this benchmark dataset and the advances in object recognition that have been possible as a result. We discuss the challenges of collecting large-scale ground truth annotation, highlight key breakthroughs in categorical object recognition, provide a detailed analysis of the current state of the field of large-scale image classification and object detection, and compare the state-of-the-art computer vision accuracy with human accuracy. We conclude with lessons learned in the 5 years of the challenge, and propose future directions and improvements.

/pdf/imagenet-large-scale-visual-recognition-challenge-caky5nmmix.pdf

ImageNet Large Scale Visual Recognition Challenge

The central building block of convolutional neural networks (CNNs) is the convolution operator, which enables networks to construct informative features by fusing both spatial and channel-wise information within local receptive fields at each layer. A broad range of prior research has investigated the spatial component of this relationship, seeking to strengthen the representational power of a CNN by enhancing the quality of spatial encodings throughout its feature hierarchy. In this work, we focus instead on the channel relationship and propose a novel architectural unit, which we term the “Squeeze-and-Excitation” (SE) block, that adaptively recalibrates channel-wise feature responses by explicitly modelling interdependencies between channels. We show that these blocks can be stacked together to form SENet architectures that generalise extremely effectively across different datasets. We further demonstrate that SE blocks bring significant improvements in performance for existing state-of-the-art CNNs at slight additional computational cost. Squeeze-and-Excitation Networks formed the foundation of our ILSVRC 2017 classification submission which won first place and reduced the top-5 error to 2.251 percent, surpassing the winning entry of 2016 by a relative improvement of ${\sim }$ ∼ 25 percent. Models and code are available at https://github.com/hujie-frank/SENet .

/pdf/squeeze-and-excitation-networks-50icgwqgeu.pdf

Squeeze-and-Excitation Networks

We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep convolutional neural network (CNN) that takes the low-resolution image as the input and outputs the high-resolution one. We further show that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network. But unlike traditional methods that handle each component separately, our method jointly optimizes all layers. Our deep CNN has a lightweight structure, yet demonstrates state-of-the-art restoration quality, and achieves fast speed for practical on-line usage. We explore different network structures and parameter settings to achieve trade-offs between performance and speed. Moreover, we extend our network to cope with three color channels simultaneously, and show better overall reconstruction quality.

Image Super-Resolution Using Deep Convolutional Networks

We propose Convolutional Block Attention Module (CBAM), a simple yet effective attention module for feed-forward convolutional neural networks. Given an intermediate feature map, our module sequentially infers attention maps along two separate dimensions, channel and spatial, then the attention maps are multiplied to the input feature map for adaptive feature refinement. Because CBAM is a lightweight and general module, it can be integrated into any CNN architectures seamlessly with negligible overheads and is end-to-end trainable along with base CNNs. We validate our CBAM through extensive experiments on ImageNet-1K, MS~COCO detection, and VOC~2007 detection datasets. Our experiments show consistent improvements in classification and detection performances with various models, demonstrating the wide applicability of CBAM. The code and models will be publicly available.

CBAM: Convolutional Block Attention Module

Synthetic data has emerged as a promising source for 3D human research as it offers low-cost access to large-scale human datasets. To advance the diversity and annotation quality of human models, we introduce a new synthetic dataset, Synbody, with three appealing features: 1) a clothed parametric human model that can generate a diverse range of subjects; 2) the layered human representation that naturally offers high-quality 3D annotations to support multiple tasks; 3) a scalable system for producing realistic data to facilitate real-world tasks. The dataset comprises 1.7M images with corresponding accurate 3D annotations, covering 10,000 human body models, 1000 actions, and various viewpoints. The dataset includes two subsets for human mesh recovery as well as human neural rendering. Extensive experiments on SynBody indicate that it substantially enhances both SMPL and SMPL-X estimation. Furthermore, the incorporation of layered annotations offers a valuable training resource for investigating the Human Neural Radiance Fields (NeRF).

SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling

In this study, we propose a novel method of surface stretch forming, named the Surface Stretch Forming based on Collaborative Control of Sheet Metal Deformation and Die Contact State (SF-CCDC). By controlling the motion paths of the discrete clamps, the contact process with the die, and the deformation process of the sheet metal can be changed. The processes of conventional stretch forming (SF-C) and SF-CCDC were numerically simulated. The results show that in SF-CCDC, the shearing effect of the die edge on the sheet metal can be reduced through the collaborative control of sheet metal deformation and contact with the die. Compared to SF-C, the maximum thinning rate is reduced by 50%, and the risk of stretch cracking is lower in SF-CCDC. Furthermore, both the center and edge areas of the sheet make contact with the die simultaneously, ensuring adequate deformation constraints and preventing wrinkling defects. Experiments were conducted to demonstrate the reliability and adaptability of the SF-CCDC method for forming double-curved surfaces.

Surface stretch forming process based on collaborative control of sheet metal deformation and die contact state

An image processing method and apparatus, and a computer storage medium are provided. The method includes: obtaining a first image, recognizing a target object in the first image, acquiring a first target area of the target object, and acquiring a second target area associated with the first target area; and performing image deformation processing on the first target area and simultaneously performing image deformation processing on the second target area, to generate a second image.

Image processing method and apparatus, and computer storage medium

Provided are a method and apparatus for creating a facial model, and an electronic device. The method comprises: carrying out keypoint detection on a current facial image to obtain at least one keypoint feature of the current facial image; acquiring, according to the at least one keypoint feature, a target skeleton parameter matching the current facial image; and creating, according to the target skeleton parameter and a standard three-dimensional facial model, a virtual three-dimensional facial model corresponding to the current facial image.

Method and apparatus for creating facial model, electronic device, and computer-readable storage medium

/pdf/learning-with-privileged-tasks-50esu3kf4d.pdf

Chen Qian

Papers

SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling

Surface stretch forming process based on collaborative control of sheet metal deformation and die contact state

Image processing method and apparatus, and computer storage medium

Method and apparatus for creating facial model, electronic device, and computer-readable storage medium

Learning With Privileged Tasks