【计算机视觉论文速递】2019-03-12
- 2019-03-12
本文分享共10篇论文（含5篇CVPR 2019），涉及目标检测、人脸检测和语义分割等方向。
[TOC]
《ScratchDet: Exploring to Train Single-Shot Object Detectors from Scratch》
Date：20190309
Author：京东等(CVPR 2019)
Abstract：Current state-of-the-art object objectors are fine-tuned from the off-the-shelf networks pretrained on large-scale classification dataset ImageNet, which incurs some additional problems: 1) T he classification and detection have different degrees of sensitivity to translation, resulting in the learning objective bias; 2) The architecture is limited by the classification network, leading to the inconvenience of modification. To cope with these problems, training detectors from scratch is a feasible solution. However, the detectors trained from scratch generally perform worse than the pretrained ones, even suffer from the convergence issue in training. In this paper, we explore to train object detectors from scratch robustly. By analysing the previous work on optimization landscape, we find that one of the overlooked points in current trained-from-scratch detector is the BatchNorm. Resorting to the stable and predictable gradient brought by BatchNorm, detectors can be trained from scratch stably while keeping the favourable performance independent to the network architecture. Taking this advantage, we are able to explore various types of networks for object detection, without suffering from the poor convergence. By extensive experiments and analysis on downsampling factor, we propose the Root-ResNet backbone network, which makes full use of the information from original images. Our ScratchDet achieves the state-of-the-art accuracy on PASCAL VOC 2007, 2012 and MS COCO among all the train-from-scratch detectors and even performs better than several one-stage pretrained methods.
arXiv：https://arxiv.org/abs/1810.08425v3
github：https://github.com/KimSoybean/ScratchDet
《MSFD:Multi-Scale Receptive Field Face Detector》(ICPR 2018)
Date：20190311
Author：北京邮电大学
Abstract：We aim to study the multi-scale receptive fields of a single convolutional neural network to detect faces of varied scales. This paper presents our Multi-Scale Receptive Field Face Detector (MSFD), which has superior performance on detecting faces at different scales and enjoys real-time inference speed. MSFD agglomerates context and texture by hierarchical structure. More additional information and rich receptive field bring significant improvement but generate marginal time consumption. We simultaneously propose an anchor assignment strategy which can cover faces with a wide range of scales to improve the recall rate of small faces and rotated faces. To reduce the false positive rate, we train our detector with focal loss which keeps the easy samples from overwhelming. As a result, MSFD reaches superior results on the FDDB, Pascal-Faces and WIDER FACE datasets, and can run at 31 FPS on GPU for VGA-resolution images.
ariXiv：https://arxiv.org/abs/1903.04147
《Structured Knowledge Distillation for Semantic Segmentation》(CVPR 2019)
Date：20190311
Author：阿德莱德大学 & 微软亚洲研究院 & 北航
Abstract：In this paper, we investigate the knowledge distillation strategy for training small semantic segmentation networks by making use of large networks. We start from the straightforward scheme, pixel-wise distillation, which applies the distillation scheme adopted for image classification and performs knowledge distillation for each pixel separately. We further propose to distill the structured knowledge from large networks to small networks, which is motivated by that semantic segmentation is a structured prediction problem. We study two structured distillation schemes: (i) pair-wise distillation that distills the pairwise similarities, and (ii) holistic distillation that uses GAN to distill holistic knowledge. The effectiveness of our knowledge distillation approaches is demonstrated by extensive experiments on three scene parsing datasets: Cityscapes, Camvid and ADE20K.
ariXiv：https://arxiv.org/abs/1903.04197
《Group-wise Correlation Stereo Network》(CVPR 2019)
Date：20190310
Author：香港中文大学 & 商汤科技
Abstract：Stereo matching estimates the disparity between a rectified image pair, which is of great importance to depth sensing, autonomous driving, and other related tasks. Previous works built cost volumes with cross-correlation or concatenation of left and right features across all disparity levels, and then a 2D or 3D convolutional neural network is utilized to regress the disparity maps. In this paper, we propose to construct the cost volume by group-wise correlation. The left features and the right features are divided into groups along the channel dimension, and correlation maps are computed among each group to obtain multiple matching cost proposals, which are then packed into a cost volume. Group-wise correlation provides efficient representations for measuring feature similarities and will not lose too much information like full correlation. It also preserves better performance when reducing parameters compared with previous methods. The 3D stacked hourglass network proposed in previous works is improved to boost the performance and decrease the inference computational cost. Experiment results show that our method outperforms previous methods on Scene Flow, KITTI 2012, and KITTI 2015 datasets.
ariXiv：https://arxiv.org/abs/1903.04025 github：https://github.com/xy-guo/GwcNet
《Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimation》(CVPR 2019)
Date：20190311
Author：意大利特伦托大学 & 华为技术爱尔兰公司
Abstract：Nowadays, the majority of state of the art monocular depth estimation techniques are based on supervised deep learning models. However, collecting RGB images with associated depth maps is a very time consuming procedure. Therefore, recent works have proposed deep architectures for addressing the monocular depth prediction task as a reconstruction problem, thus avoiding the need of collecting ground-truth depth. Following these works, we propose a novel self-supervised deep model for estimating depth maps. Our framework exploits two main strategies: refinement via cycle-inconsistency and distillation. Specifically, first a \emph{student} network is trained to predict a disparity map such as to recover from a frame in a camera view the associated image in the opposite view. Then, a backward cycle network is applied to the generated image to re-synthesize back the input image, estimating the opposite disparity. A third network exploits the inconsistency between the original and the reconstructed input frame in order to output a refined depth map. Finally, knowledge distillation is exploited, such as to transfer information from the refinement network to the student. Our extensive experimental evaluation demonstrate the effectiveness of the proposed framework which outperforms state of the art unsupervised methods on the KITTI benchmark.
ariXiv：https://arxiv.org/abs/1903.04202
《Instance- and Category-level 6D Object Pose Estimation》
Date：20190311
Author：帝国理工学院
Abstract：6D object pose estimation is an important task that determines the 3D position and 3D rotation of an object in camera-centred coordinates. By utilizing such a task, one can propose promising solutions for various problems related to scene understanding, augmented reality, control and navigation of robotics. Recent developments on visual depth sensors and low-cost availability of depth data significantly facilitate object pose estimation. Using depth information from RGB-D sensors, substantial progress has been made in the last decade by the methods addressing the challenges such as viewpoint variability, occlusion and clutter, and similar looking distractors. Particularly, with the recent advent of convolutional neural networks, RGB-only based solutions have been presented. However, improved results have only been reported for recovering the pose of known instances, i.e., for the instance-level object pose estimation tasks. More recently, state-of-the-art approaches target to solve object pose estimation problem at the level of categories, recovering the 6D pose of unknown instances. To this end, they address the challenges of the category-level tasks such as distribution shift among source and target domains, high intra-class variations, and shape discrepancies between objects.
ariXiv：https://arxiv.org/abs/1903.04229
《Video Generation from Single Semantic Label Map》(CVPR 2019)
Date：20190311
Author：商汤科技
Abstract：This paper proposes the novel task of video generation conditioned on a SINGLE semantic label map, which provides a good balance between flexibility and quality in the generation process. Different from typical end-to-end approaches, which model both scene content and dynamics in a single step, we propose to decompose this difficult task into two sub-problems. As current image generation methods do better than video generation in terms of detail, we synthesize high quality content by only generating the first frame. Then we animate the scene based on its semantic meaning to obtain the temporally coherent video, giving us excellent results overall. We employ a cVAE for predicting optical flow as a beneficial intermediate step to generate a video sequence conditioned on the initial single frame. A semantic label map is integrated into the flow prediction module to achieve major improvements in the image-to-video generation process. Extensive experiments on the Cityscapes dataset show that our method outperforms all competing methods.
ariXiv：https://arxiv.org/abs/1903.04480 github：https://github.com/junting/seg2vid
《MTRNet: A Generic Scene Text Eraser》
Date：20190311
Author：昆士兰科技大学
Abstract：Text removal algorithms have been proposed for uni-lingual scripts with regular shapes and layouts. However, to the best of our knowledge, a generic text removal method which is able to remove all or user-specified text regions regardless of font, script, language or shape is not available. Developing such a generic text eraser for real scenes is a challenging task, since it inherits all the challenges of multi-lingual and curved text detection and inpainting. To fill this gap, we propose a mask-based text removal network (MTRNet). MTRNet is a conditional adversarial generative network (cGAN) with an auxiliary mask. The introduced auxiliary mask not only makes the cGAN a generic text eraser, but also enables stable training and early convergence on a challenging large-scale synthetic dataset, initially proposed for text detection in real scenes. What's more, MTRNet achieves state-of-the-art results on several real-world datasets including ICDAR 2013, ICDAR 2017 MLT, and CTW1500, without being explicitly trained on this data, outperforming previous state-of-the-art methods trained directly on these datasets.
ariXiv：https://arxiv.org/abs/1903.04092
《Spatial-Aware Non-Local Attention for Fashion Landmark Detection》
Date：20190311
Author：北京大学 & 西安交通大学 & 京东
Abstract：Fashion landmark detection is a challenging task even using the current deep learning techniques, due to the large variation and non-rigid deformation of clothes. In order to tackle these problems, we propose Spatial-Aware Non-Local (SANL) block, an attentive module in deep neural network which can utilize spatial information while capturing global dependency. Actually, the SANL block is constructed from the non-local block in the residual manner which can learn the spatial related representation by taking a spatial attention map from Grad-CAM. We then establish our fashion landmark detection framework on feature pyramid network, equipped with four SANL blocks in the backbone. It is demonstrated by the experimental results on two large-scale fashion datasets that our proposed fashion landmark detection approach with the SANL blocks outperforms the current state-of-the-art methods considerably. Some supplementary experiments on fine-grained image classification also show the effectiveness of the proposed SANL block.
ariXiv：https://arxiv.org/abs/1903.04104
《The Unconstrained Ear Recognition Challenge 2019》
Date：20190311
Author：University of Ljubljana等
Abstract：This paper presents a summary of the 2019 Unconstrained Ear Recognition Challenge (UERC), the second in a series of group benchmarking efforts centered around the problem of person recognition from ear images captured in uncontrolled settings. The goal of the challenge is to assess the performance of existing ear recognition techniques on a challenging large-scale ear dataset and to analyze performance of the technology from various viewpoints, such as generalization abilities to unseen data characteristics, sensitivity to rotations, occlusions and image resolution and performance bias on sub-groups of subjects, selected based on demographic criteria, i.e. gender and ethnicity. Research groups from 12 institutions entered the competition and submitted a total of 13 recognition approaches ranging from descriptor-based methods to deep-learning models. The majority of submissions focused on deep learning approaches and hybrid techniques combining hand-crafted and learned image descriptors. Our analysis shows that hybrid and deep-learning-based approaches significantly outperform traditional hand-crafted approaches. We argue that this is a good indicator of where ear recognition will be heading in the future. Furthermore, the results in general improve upon the UERC 2017 and display the steady advancement of the ear recognition.