您當前的位置:首頁 > 攝影

[計算機視覺論文速遞] 2018-11-26 共計46篇論文分享

作者:由 Amusi 發表于 攝影時間:2018-11-26

編輯: Amusi

校稿: Amusi

時間: 2018-11-26

連結:最新的46篇CV論文

本文分享共計46篇論文,涉及CNN、Face、影象分類、目標檢測、影象分割、GAN、Re-Id、SLAM和遷移學習等方向。

更多最新的CV論文可訪問:

今天的文章原本篇幅很長,已經超過50000字,因為Amusi把摘要也放進來了,結果知乎告訴我:正文已超過42703個字,於是就砍掉了大多摘要,如果你像看完整版,可以點選daily-paper-cv

[計算機視覺論文速遞] 2018-11-26 共計46篇論文分享

論文類別目錄

CNN

Face

影象分類

目標檢測

Saliency Detection

場景文字檢測

影象分割

目標跟蹤

GAN

3D

Re-ID

SLAM

遷移學習

風格遷移

Image Caption

Few-Shot Learning

資料集

Other

CNN

《Deeper Interpretability of Deep Networks》

arXiv:

https://

arxiv。org/abs/1811。0780

7

Deep Convolutional Neural Networks (CNNs) have been one of the most influential recent developments in computer vision, particularly for categorization。 There is an increasing demand for explainable AI as these systems are deployed in the real world。 However, understanding the information represented and processed in CNNs remains in most cases challenging。 Within this paper, we explore the use of new information theoretic techniques developed in the field of neuroscience to enable novel understanding of how a CNN represents information。 We trained a 10-layer ResNet architecture to identify 2,000 face identities from 26M images generated using a rigorously controlled 3D face rendering model that produced variations of intrinsic (i。e。 face morphology, gender, age, expression and ethnicity) and extrinsic factors (i。e。 3D pose, illumination, scale and 2D translation)。 With our methodology, we demonstrate that unlike human‘s network overgeneralizes face identities even with extreme changes of face shape, but it is more sensitive to changes of texture。 To understand the processing of information underlying these counterintuitive properties, we visualize the features of shape and texture that the network processes to identify faces。 Then, we shed a light into the inner workings of the black box and reveal how hidden layers represent these features and whether the representations are invariant to pose。 We hope that our methodology will provide an additional valuable tool for interpretability of CNNs。

《Deep Shape-from-Template: Wide-Baseline, Dense and Fast Registration and Deformable Reconstruction from a Single Image》

arXiv:

https://

arxiv。org/abs/1811。0779

1

《Do Normalization Layers in a Deep ConvNet Really Need to Be Distinct?》

arXiv:

https://

arxiv。org/abs/1811。0772

7

《Self-Referenced Deep Learning》

arXiv:

https://

arxiv。org/abs/1811。0759

8

《Multimodal Densenet》

arXiv:

https://

arxiv。org/abs/1811。0740

7

《RePr: Improved Training of Convolutional Filters》

arXiv:

https://

arxiv。org/abs/1811。0727

5

《PydMobileNet: Improved Version of MobileNets with Pyramid Depthwise Separable Convolution》

arXiv:

https://

arxiv。org/abs/1811。0708

3

Face

《Aff-Wild2: Extending the Aff-Wild Database for Affect Recognition》

arXiv:

https://

arxiv。org/abs/1811。0777

0

影象分類

《High Order Neural Networks for Video Classification》

arXiv:

https://

arxiv。org/abs/1811。0751

9

《DeepConsensus: using the consensus of features from multiple layers to attain robust image classification》

arXiv:

https://

arxiv。org/abs/1811。0726

6

目標檢測

《Weakly Supervised Soft-detection-based Aggregation Method for Image Retrieval》

arXiv:

https://

arxiv。org/abs/1811。0761

9

《Fast Efficient Object Detection Using Selective Attention》

arXiv:

https://

arxiv。org/abs/1811。0750

2

《FotonNet: A HW-Efficient Object Detection System Using 3D-Depth Segmentation and 2D-DNN Classifier》

arXiv:

https://

arxiv。org/abs/1811。0749

3

《R2CNN++: Multi-Dimensional Attention Based Rotation Invariant Detector with Robust Anchor Strategy》

arXiv:

https://

arxiv。org/abs/1811。0712

6

Saliency Detection

《Global and Local Sensitivity Guided Key Salient Object Re-augmentation for Video Saliency Detection》

arXiv:

https://

arxiv。org/abs/1811。0748

0

場景文字檢測

《Pixel-Anchor: A Fast Oriented Scene Text Detector with Combined Networks》

arXiv:

https://

arxiv。org/abs/1811。0743

2

《Improving Rotated Text Detection with Rotation Region Proposal Networks》

arXiv:

https://

arxiv。org/abs/1811。0703

1

影象分割

《OrthoSeg: A Deep Multimodal Convolutional Neural Network for Semantic Segmentation of Orthoimagery》

arXiv:

https://

arxiv。org/abs/1811。0785

9

《M2U-Net: Effective and Efficient Retinal Vessel Segmentation for Resource-Constrained Environments》

arXiv:

https://

arxiv。org/abs/1811。0773

8

目標跟蹤

《Robust Visual Tracking using Multi-Frame Multi-Feature Joint Modeling》

arXiv:

https://

arxiv。org/abs/1811。0749

8

《Deep Siamese Networks with Bayesian non-Parametrics for Video Object Tracking》

arXiv:

https://

arxiv。org/abs/1811。0738

6

《Exploit the Connectivity: Multi-Object Tracking with TrackletNet》

arXiv:

https://

arxiv。org/abs/1811。0725

8

GAN

《Injecting and removing malignant features in mammography with CycleGAN: Investigation of an automated adversarial attack using neural networks》

arXiv:

https://

arxiv。org/abs/1811。0776

7

《SEIGAN: Towards Compositional Image Generation by Simultaneously Learning to Segment, Enhance, and Inpaint》

arXiv:

https://

arxiv。org/abs/1811。0763

0

《GAN-QP: A Novel GAN Framework without Gradient Vanishing and Lipschitz Constraint》

arXiv:

https://

arxiv。org/abs/1811。0729

6

3D

《Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN》

arXiv:

https://

arxiv。org/abs/1811。0778

2

《PointConv: Deep Convolutional Networks on 3D Point Clouds》

arXiv:

https://

arxiv。org/abs/1811。0724

6

《Topology-Aware Non-Rigid Point Cloud Registration》

arXiv:

https://

arxiv。org/abs/1811。0701

4

Re-ID

《Past, Present, and Future Approaches Using Computer Vision for Animal Re-Identification from Camera Trap Data》

arXiv:

https://

arxiv。org/abs/1811。0774

9

《CA3Net: Contextual-Attentional Attribute-Appearance Network for Person Re-Identification》

arXiv:

https://

arxiv。org/abs/1811。0754

4

《Re-Identification with Consistent Attentive Siamese Networks》

arXiv:

https://

arxiv。org/abs/1811。0748

7

SLAM

《Collaborative Dense SLAM》

arXiv:

https://

arxiv。org/abs/1811。0763

2

遷移學習

《An Efficient Transfer Learning Technique by Using Final Fully-Connected Layer Output Features of Deep Networks》

arXiv:

https://

arxiv。org/abs/1811。0745

9

《Transfer Learning with Deep CNNs for Gender Recognition and Age Estimation》

arXiv:

https://

arxiv。org/abs/1811。0734

4

風格遷移

《GLStyleNet: Higher Quality Style Transfer Combining Global and Local Pyramid Features》

arXiv:

https://

arxiv。org/abs/1811。0726

0

Image Caption

《Intention Oriented Image Captions with Guiding Objects》

arXiv:

https://

arxiv。org/abs/1811。0766

2

Few-Shot Learning

《Deep Comparison: Relation Columns for Few-Shot Learning》

arXiv:

https://

arxiv。org/abs/1811。0710

0

資料集

《iQIYI-VID: A Large Dataset for Multi-modal Person Identification》

arXiv:

https://

arxiv。org/abs/1811。0754

8

Other

《Addressing the Invisible: Street Address Generation for Developing Countries with Deep Learning》

NIPS 2018 Workshop

arXiv:

https://

arxiv。org/abs/1811。0776

9

《Handwriting Recognition of Historical Documents with few labeled data》

arXiv:

https://

arxiv。org/abs/1811。0776

8

《GroundNet: Segmentation-Aware Monocular Ground Plane Estimation with Geometric Consistency》

arXiv:

https://

arxiv。org/abs/1811。0722

2

《Image-to-GPS Verification Through A Bottom-Up Pattern Matching Network》

arXiv:

https://

arxiv。org/abs/1811。0728

8

《Matching RGB Images to CAD Models for Object Pose Estimation》

arXiv:

https://

arxiv。org/abs/1811。0724

9

《Optical Flow Dataset and Benchmark for Visual Crowd Analysis》

arXiv:

https://

arxiv。org/abs/1811。0717

0

《Simulating LIDAR Point Cloud for Autonomous Driving using Real-world Scenes and Traffic Flows》

arXiv:

https://

arxiv。org/abs/1811。0711

2

《DSCnet: Replicating Lidar Point Clouds with Deep Sensor Cloning》

arXiv:

https://

arxiv。org/abs/1811。0707

0

標簽: https  arxiv  org  ABS  1811