CVPR2019 | 10篇論文速遞（涵蓋全景分割、實例分割和姿態估計等方向）
- 2019 年 12 月 31 日
- 筆記
【導讀】CVPR 2019 接收論文列表已經出來了，但只是一些索引號，所以並沒有完整的論文合集。CVer 最近也在整理收集，今天一文涵蓋10篇 CVPR 2019 論文速遞，內容涵蓋全景分割、實例分割和姿態估計等方向。
之前曾分享：CVPR2019 | 15篇論文速遞（涵蓋目標檢測、語義分割和姿態估計等方向）
特別鳴謝 CV_arXiv_Daily 公眾號提供的部分素材
實例分割
[1] CVPR2019 開源Mask Scoring R-CNN新文
論文題目：Mask Scoring R-CNN
作者：Zhaojin Huang, Lichao Huang, Yongchao Gong, Chang Huang, Xinggang Wang
論文鏈接：https://arxiv.org/abs/1903.00241
代碼鏈接：https://github.com/zjhuang22/maskscoring_rcnn
摘要: Letting a deep network be aware of the quality of its own predictions is an interesting yet important problem. In the task of instance segmentation, the confidence of instance classification is used as mask quality score in most instance segmentation frameworks. However, the mask quality, quantified as the IoU between the instance mask and its ground truth, is usually not well correlated with classification score. In this paper, we study this problem and propose Mask Scoring R-CNN which contains a network block to learn the quality of the predicted instance masks. The proposed network block takes the instance feature and the corresponding predicted mask together to regress the mask IoU. The mask scoring strategy calibrates the misalignment between mask quality and mask score, and improves instance segmentation performance by prioritizing more accurate mask predictions during COCO AP evaluation. By extensive evaluations on the COCO dataset, Mask Scoring R-CNN brings consistent and noticeable gain with different models, and outperforms the state-of-the-art Mask R-CNN. We hope our simple and effective approach will provide a new direction for improving instance segmentation.
3D點雲
[2] CVPR2019 3D Point Clouds新文
論文題目：Octree guided CNN with Spherical Kernels for 3D Point Clouds
作者：Huan Lei, Naveed Akhtar, Ajmal Mian
論文鏈接：https://arxiv.org/abs/1903.00343
摘要: We propose an octree guided neural network architecture and spherical convolutional kernel for machine learning from arbitrary 3D point clouds. The network architecture capitalizes on the sparse nature of irregular point clouds, and hierarchically coarsens the data representation with space partitioning. At the same time, the proposed spherical kernels systematically quantize point neighborhoods to identify local geometric structures in the data, while maintaining the properties of translation-invariance and asymmetry. We specify spherical kernels with the help of network neurons that in turn are associated with spatial locations. We exploit this association to avert dynamic kernel generation during network training that enables efficient learning with high resolution point clouds. The effectiveness of the proposed technique is established on the benchmark tasks of 3D object classification and segmentation, achieving new state-of-the-art on ShapeNet and RueMonge2014 datasets.
聚類
[3] CVPR 2019 聚類新文
論文題目：Efficient Parameter-free Clustering Using First Neighbor Relations
作者：M. Saquib Sarfraz, Vivek Sharma, Rainer Stiefelhagen
論文鏈接：https://arxiv.org/abs/1902.11266
摘要: We present a new clustering method in the form of a single clustering equation that is able to directly discover groupings in the data. The main proposition is that the first neighbor of each sample is all one needs to discover large chains and finding the groups in the data. In contrast to most existing clustering algorithms our method does not require any hyper-parameters, distance thresholds and/or the need to specify the number of clusters. The proposed algorithm belongs to the family of hierarchical agglomerative methods. The technique has a very low computational overhead, is easily scalable and applicable to large practical problems. Evaluation on well known datasets from different domains ranging between 1077 and 8.1 million samples shows substantial performance gains when compared to the existing clustering techniques.
表示學習
[4] CVPR 2019 表示學習新文
論文題目：End-to-End Efficient Representation Learning via Cascading Combinatorial Optimization
作者：Yeonwoo Jeong, Yoonsuing Kim, Hyun Oh Song
論文鏈接：https://arxiv.org/abs/1902.10990
摘要: We develop hierarchically quantized efficient embedding representations for similarity-based search and show that this representation provides not only the state of the art performance on the search accuracy but also provides several orders of speed up during inference. The idea is to hierarchically quantize the representation so that the quantization granularity is greatly increased while maintaining the accuracy and keeping the computational complexity low. We also show that the problem of finding the optimal sparse compound hash code respecting the hierarchical structure can be optimized in polynomial time via minimum cost flow in an equivalent flow network. This allows us to train the method end-to-end in a mini-batch stochastic gradient descent setting. Our experiments on Cifar100 and ImageNet datasets show the state of the art search accuracy while providing several orders of magnitude search speedup respectively over exhaustive linear search over the dataset.
Text-to-Image
[5] CVPR 2019 Text-to-Image新文
論文題目：Object-driven Text-to-Image Synthesis via Adversarial Training
作者：Wenbo Li, Pengchuan Zhang, Lei Zhang, Qiuyuan Huang, Xiaodong He, Siwei Lyu, Jianfeng Gao
論文鏈接：https://arxiv.org/abs/1902.10740
摘要: In this paper, we propose Object-driven Attentive Generative Adversarial Newtorks (Obj-GANs) that allow object-centered text-to-image synthesis for complex scenes. Following the two-step (layout-image) generation process, a novel object-driven attentive image generator is proposed to synthesize salient objects by paying attention to the most relevant words in the text description and the pre-generated semantic layout. In addition, a new Fast R-CNN based object-wise discriminator is proposed to provide rich object-wise discrimination signals on whether the synthesized object matches the text description and the pre-generated layout. The proposed Obj-GAN significantly outperforms the previous state of the art in various metrics on the large-scale COCO benchmark, increasing the Inception score by 27% and decreasing the FID score by 11%. A thorough comparison between the traditional grid attention and the new object-driven attention is provided through analyzing their mechanisms and visualizing their attention layers, showing insights of how the proposed model generates complex scenes in high quality.
人臉
[6] CVPR 2019 人臉新文
論文題目：Joint Face Detection and Facial Motion Retargeting for Multiple Faces
作者：Bindita Chaudhuri, Noranart Vesdapunt, Baoyuan Wang
論文鏈接：https://arxiv.org/abs/1902.10744
摘要: Facial motion retargeting is an important problem in both computer graphics and vision, which involves capturing the performance of a human face and transferring it to another 3D character. Learning 3D morphable model (3DMM) parameters from 2D face images using convolutional neural networks is common in 2D face alignment, 3D face reconstruction etc. However, existing methods either require an additional face detection step before retargeting or use a cascade of separate networks to perform detection followed by retargeting in a sequence. In this paper, we present a single end-to-end network to jointly predict the bounding box locations and 3DMM parameters for multiple faces. First, we design a novel multitask learning framework that learns a disentangled representation of 3DMM parameters for a single face. Then, we leverage the trained single face model to generate ground truth 3DMM parameters for multiple faces to train another network that performs joint face detection and motion retargeting for images with multiple faces. Experimental results show that our joint detection and retargeting network has high face detection accuracy and is robust to extreme expressions and poses while being faster than state-of-the-art methods.
CNN訓練
[7] CVPR 2019 CNN訓練新文
論文題目：RePr: Improved Training of Convolutional Filters
作者：Aaditya Prakash, James Storer, Dinei Florencio, Cha Zhang
論文鏈接：https://arxiv.org/abs/1811.07275
摘要: A well-trained Convolutional Neural Network can easily be pruned without significant loss of performance. This is because of unnecessary overlap in the features captured by the network's filters. Innovations in network architecture such as skip/dense connections and Inception units have mitigated this problem to some extent, but these improvements come with increased computation and memory requirements at run-time. We attempt to address this problem from another angle – not by changing the network structure but by altering the training method. We show that by temporarily pruning and then restoring a subset of the model's filters, and repeating this process cyclically, overlap in the learned features is reduced, producing improved generalization. We show that the existing model-pruning criteria are not optimal for selecting filters to prune in this context and introduce inter-filter orthogonality as the ranking criteria to determine under-expressive filters. Our method is applicable both to vanilla convolutional networks and more complex modern architectures, and improves the performance across a variety of tasks, especially when applied to smaller networks.
視覺語音導航
[8] CVPR 2019 視覺語音導航新文
論文題目：Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation
作者：Xin Wang, Qiuyuan Huang, Asli Celikyilmaz, Jianfeng Gao, Dinghan Shen, Yuan-Fang Wang, William Yang Wang, Lei Zhang
論文鏈接：https://arxiv.org/abs/1811.10092
摘要: Vision-language navigation (VLN) is the task of navigating an embodied agent to carry out natural language instructions inside real 3D environments. In this paper, we study how to address three critical challenges for this task: the cross-modal grounding, the ill-posed feedback, and the generalization problems. First, we propose a novel Reinforced Cross-Modal Matching (RCM) approach that enforces cross-modal grounding both locally and globally via reinforcement learning (RL). Particularly, a matching critic is used to provide an intrinsic reward to encourage global matching between instructions and trajectories, and a reasoning navigator is employed to perform cross-modal grounding in the local visual scene. Evaluation on a VLN benchmark dataset shows that our RCM model significantly outperforms existing methods by 10% on SPL and achieves the new state-of-the-art performance. To improve the generalizability of the learned policy, we further introduce a Self-Supervised Imitation Learning (SIL) method to explore unseen environments by imitating its own past, good decisions. We demonstrate that SIL can approximate a better and more efficient policy, which tremendously minimizes the success rate performance gap between seen and unseen environments (from 30.7% to 11.7%).
6D 目標姿態估計
[9] CVPR 2019 6D目標姿態估計新文
論文題目：DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion
作者：Chen Wang, Danfei Xu, Yuke Zhu, Roberto Martín-Martín, Cewu Lu, Li Fei-Fei, Silvio Savarese
論文鏈接：https://arxiv.org/abs/1901.04780
摘要: A key technical challenge in performing 6D object pose estimation from RGB-D image is to fully leverage the two complementary data sources. Prior works either extract information from the RGB image and depth separately or use costly post-processing steps, limiting their performances in highly cluttered scenes and real-time applications. In this work, we present DenseFusion, a generic framework for estimating 6D pose of a set of known objects from RGB-D images. DenseFusion is a heterogeneous architecture that processes the two data sources individually and uses a novel dense fusion network to extract pixel-wise dense feature embedding, from which the pose is estimated. Furthermore, we integrate an end-to-end iterative pose refinement procedure that further improves the pose estimation while achieving near real-time inference. Our experiments show that our method outperforms state-of-the-art approaches in two datasets, YCB-Video and LineMOD. We also deploy our proposed method to a real robot to grasp and manipulate objects based on the estimated pose.
全景分割
[10] CVPR 2019 全景分割新文
論文題目：Attention-guided Unified Network for Panoptic Segmentation
作者：Yanwei Li, Xinze Chen, Zheng Zhu, Lingxi Xie, Guan Huang, Dalong Du, Xingang Wang
論文鏈接：https://arxiv.org/abs/1812.03904
摘要: This paper studies panoptic segmentation, a recently proposed task which segments foreground (FG) objects at the instance level as well as background (BG) contents at the semantic level. Existing methods mostly dealt with these two problems separately, but in this paper, we reveal the underlying relationship between them, in particular, FG objects provide complementary cues to assist BG understanding. Our approach, named the Attention-guided Unified Network (AUNet), is an unified framework with two branches for FG and BG segmentation simultaneously. Two sources of attentions are added to the BG branch, namely, RPN and FG segmentation mask to provide object-level and pixel-level attentions, respectively. Our approach is generalized to different backbones with consistent accuracy gain in both FG and BG segmentation, and also sets new state-of-the-arts in the MS-COCO (46.5% PQ) benchmarks.
—End—
