論文閱讀:CVPR2016 Paper list
在過幾天CVPR2016就要召開了,先放個list。
ORAL SESSION
Image Captioning and Question Answering
Monday, June 27th, 9:00AM - 10:05AM.
These papers will also be presented at the following poster session
-
1 Deep Compositional Captioning: Describing Novel Object Categories Without Paired Training Data.
Lisa Anne Hendricks, Subhashini Venugopalan, Marcus Rohrbach, Raymond Mooney, Kate Saenko, Trevor Darrell
-
2 Generation and Comprehension of Unambiguous Object Descriptions.
Junhua Mao, Jonathan Huang, Alexander Toshev, Oana Camburu, Alan L. Yuille, Kevin Murphy
-
3 Stacked Attention Networks for Image Question Answering.
Zichao Yang, Xiaodong He, Jianfeng Gao, Li Deng, Alex Smola
-
4 Image Question Answering Using Convolutional Neural Network With Dynamic Parameter Prediction.
Hyeonwoo Noh, Paul Hongsuck Seo, Bohyung Han
-
5 Neural Module Networks.
Jacob Andreas, Marcus Rohrbach, Trevor Darrell, Dan Klein
SPOTLIGHT SESSION
Language and Vision
Monday, June 27th, 10:05AM - 10:30AM.
These papers will also be presented at the following
-
6 Learning Deep Representations of Fine-Grained Visual Descriptions.
Scott Reed, Zeynep Akata, Honglak Lee , Bernt Schiele
-
7 Multi-Cue Zero-Shot Learning With Strong Supervision.
Zeynep Akata, Mateusz Malinowski, Mario Fritz, Bernt Schiele
-
8 Latent Embeddings for Zero-Shot Classification.
Yongqin Xian, Zeynep Akata, Gaurav Sharma, Quynh Nguyen, Matthias Hein, Bernt Schiele
-
9 One-Shot Learning of Scene Locations via Feature Trajectory Transfer.
Roland Kwitt, Sebastian Hegenbart, Marc Niethammer
-
10 Learning Attributes Equals Multi-Source Domain Generalization.
Chuang Gan, Tianbao Yang, Boqing Gong
-
11 Anticipating Visual Representations From Unlabeled Video.
Carl Vondrick, Hamed Pirsiavash, Antonio Torralba
ORAL SESSION
Matching and Alignment
Monday, June 27th, 9:00AM - 10:05AM.
These papers will also be presented at the following poster session
-
12 Learning to Assign Orientations to Feature Points.
Kwang Moo Yi, Yannick Verdie, Pascal Fua, Vincent Lepetit
-
13 Learning Dense Correspondence via 3D-Guided Cycle Consistency.
Tinghui Zhou, Philipp Krähenbuhl, Mathieu Aubry, Qixing Huang, Alexei A. Efros
-
14 The Global Patch Collider.
Shenlong Wang, Sean Ryan Fanello, Christoph Rhemann, Shahram Izadi, Pushmeet Kohli
-
15 Joint Probabilistic Matching Using m-Best Solutions.
Seyed Hamid Rezatofighi, Anton Milan, Zhen Zhang, Qinfeng Shi, Anthony Dick, Ian Reid
-
16 Face Alignment Across Large Poses: A 3D Solution.
Xiangyu Zhu, Zhen Lei, Xiaoming Liu, Hailin Shi, Stan Z. Li
SPOTLIGHT SESSION
Segmentation and Contour Detection
Monday, June 27th, 10:05AM - 10:30AM.
These papers will also be presented at the following poster session
-
17 Interactive Segmentation on RGBD Images via Cue Selection.
Jie Feng, Brian Price, Scott Cohen, Shih-Fu Chang
-
18 Layered Scene Decomposition via the Occlusion-CRF.
Chen Liu, Pushmeet Kohli, Yasutaka Furukawa
-
19 Affinity CNN: Learning Pixel-Centric Pairwise Relations for Figure/Ground Embedding.
Michael Maire, Takuya Narihira, Stella X. Yu
-
20 Weakly Supervised Object Boundaries.
Anna Khoreva, Rodrigo Benenson, Mohamed Omran, Matthias Hein, Bernt Schiele
-
21 Object Contour Detection With a Fully Convolutional Encoder-Decoder Network.
Jimei Yang, Brian Price, Scott Cohen, Honglak Lee , Ming-Hsuan Yang
POSTER SESSION
Poster Session 1-1. Monday, June 27th, 10:30AM - 12:30PM.
Images and Language
-
22 What Value Do Explicit High Level Concepts Have in Vision to Language Problems?.
Qi Wu, Chunhua Shen, Lingqiao Liu, Anthony Dick, Anton van den Hengel
Edge Contour Detection
-
23 Fast Detection of Curved Edges at Low SNR.
Nati Ofir, Meirav Galun, Boaz Nadler, Ronen Basri
-
24 Object Skeleton Extraction in Natural Images by Fusing Scale-Associated Deep Side Outputs.
Wei Shen, Kai Zhao, Yuan Jiang, Yan Wang, Zhijiang Zhang, Xiang Bai
-
25 Learning Relaxed Deep Supervision for Better Edge Detection.
Yu Liu, Michael S. Lew
-
26 Occlusion Boundary Detection via Deep Exploration of Context.
Huan Fu, Chaohui Wang, Dacheng Tao, Michael J. Black
-
27 SemiContour: A Semi-Supervised Learning Approach for Contour Detection.
Zizhao Zhang, Fuyong Xing, Xiaoshuang Shi, Lin Yang
Feature Extraction and Description
-
28 Learning to Localize Little Landmarks.
Saurabh Singh, Derek Hoiem, David Forsyth
-
29 InterActive: Inter-Layer Activeness Propagation.
Lingxi Xie, Liang Zheng, Jingdong Wang, Alan L. Yuille, Qi Tian
-
30 Exploit Bounding Box Annotations for Multi-Label Object Recognition.
Hao Yang, Joey Tianyi Zhou, Yu Zhang, Bin-Bin Gao, Jianxin Wu, Jianfei Cai
-
31 TI-POOLING: Transformation-Invariant Pooling for Feature Learning in Convolutional Neural Networks.
Dmitry Laptev, Nikolay Savinov, Joachim M. Buhmann, Marc Pollefeys
-
32 Fashion Style in 128 Floats: Joint Ranking and Classification Using Weak Data for Feature Extraction.
Edgar Simo-Serra, Hiroshi Ishikawa
-
33 Equiangular Kernel Dictionary Learning With Applications to Dynamic Texture Analysis.
Yuhui Quan, Chenglong Bao, Hui Ji
-
34 Compact Bilinear Pooling.
Yang Gao, Oscar Beijbom, Ning Zhang, Trevor Darrell
Feature Extraction and Matching
-
35 Accumulated Stability Voting: A Robust Descriptor From Descriptors of Multiple Scales.
Tsun-Yi Yang, Yen-Yu Lin, Yung-Yu Chuang
-
36 CoMaL: Good Features to Match on Object Boundaries.
Swarna K. Ravindran, Anurag Mittal
-
37 Progressive Feature Matching With Alternate Descriptor Selection and Correspondence Enrichment.
Yuan-Ting Hu, Yen-Yu Lin
Image Segmentation
-
38 A New Finsler Minimal Path Model With Curvature Penalization for Image Segmentation and Closed Contour Detection.
Da Chen, Jean-Marie Mirebeau, Laurent D. Cohen
-
39 Scale-Aware Alignment of Hierarchical Image Segmentation.
Yuhua Chen, Dengxin Dai, Jordi Pont-Tuset, Luc Van Gool
-
40 Deep Interactive Object Selection.
Ning Xu, Brian Price, Scott Cohen, Jimei Yang, Thomas S. Huang
-
41 Pull the Plug? Predicting If Computers or Humans Should Segment Images.
Danna Gurari, Suyog Jain, Margrit Betke, Kristen Grauman
-
42 In the Shadows, Shape Priors Shine: Using Occlusion to Improve Multi-Region Segmentation.
Yuka Kihara, Matvey Soloviev, Tsuhan Chen
-
43 Convexity Shape Constraints for Image Segmentation.
Loic A. Royer, David L. Richmond, Carsten Rother, Bjoern Andres, Dagmar Kainmueller
-
44 MCMC Shape Sampling for Image Segmentation With Nonparametric Shape Priors.
Ertunc Erdil, Sinan Yildirim, Müjdat Cetin, Tolga Tasdizen
Low-Level Vision
-
45 From Noise Modeling to Blind Image Denoising.
Fengyuan Zhu, Guangyong Chen, Pheng-Ann Heng
-
46 Efficient and Robust Color Consistency for Community Photo Collections.
Jaesik Park, Yu-Wing Tai, Sudipta N. Sinha, In So Kweon
-
47 Needle-Match: Reliable Patch Matching Under High Uncertainty.
Or Lotan, Michal Irani
-
48 ReconNet: Non-Iterative Reconstruction of Images From Compressively Sensed Measurements.
Kuldeep Kulkarni, Suhas Lohit, Pavan Turaga, Ronan Kerviche, Amit Ashok
-
49 Soft-Segmentation Guided Object Motion Deblurring.
Jinshan Pan, Zhe Hu, Zhixun Su, Hsin-Ying Lee, Ming-Hsuan Yang
-
50 Two Illuminant Estimation and User Correction Preference.
Dongliang Cheng, Abdelrahman Abdelhamed, Brian Price, Scott Cohen, Michael S. Brown
-
51 Deep Contrast Learning for Salient Object Detection.
Guanbin Li, Yizhou Yu
-
52 Multiview Image Completion With Space Structure Propagation.
Seung-Hwan Baek, Inchang Choi, Min H. Kim
-
53 Composition-Preserving Deep Photo Aesthetics Assessment.
Long Mai, Hailin Jin, Feng Liu
-
54 Automatic Image Cropping : A Computational Complexity Study.
Jiansheng Chen, Gaocheng Bai, Shaoheng Liang, Zhengqin Li
-
55 A Deeper Look at Saliency: Feature Contrast, Semantics, and Beyond.
Neil D. B. Bruce, Christopher Catton, Sasa Janjic
-
56 Spatially Binned ROC: A Comprehensive Saliency Metric.
Calden Wloka, John Tsotsos
-
57 GraB: Visual Saliency via Novel Graph Model and Background Priors.
Qiaosong Wang, Wen Zheng, Robinson Piramuthu
-
58 Predicting When Saliency Maps Are Accurate and Eye Fixations Consistent.
Anna Volokitin, Michael Gygli, Xavier Boix
-
59 Split and Match: Example-Based Adaptive Patch Sampling for Unsupervised Style Transfer.
Oriel Frigo, Neus Sabater, Julie Delon, Pierre Hellier
-
60 Detection and Accurate Localization of Circular Fiducials Under Highly Challenging Conditions.
Lilian Calvet, Pierre Gurdjos, Carsten Griwodz, Simone Gasparini
Scene Understanding
-
61 Scene Recognition With CNNs: Objects, Scales and Dataset Bias.
Luis Herranz, Shuqiang Jiang, Xiangyang Li
-
62 Learning Action Maps of Large Environments via First-Person Vision.
Nicholas Rhinehart, Kris M. Kitani
-
63 Single-Image Crowd Counting via Multi-Column Convolutional Neural Network.
Yingying Zhang, Desen Zhou, Siqin Chen, Shenghua Gao, Yi Ma
-
64 Shallow and Deep Convolutional Networks for Saliency Prediction.
Junting Pan, Elisa Sayrol, Xavier Giro-i-Nieto, Kevin McGuinness, Noel E. O'Connor
-
65 Sample and Filter: Nonparametric Scene Parsing via Efficient Filtering.
Mohammad Najafi, Sarah Taghavi Namin, Mathieu Salzmann, Lars Petersson
-
66 DeLay: Robust Spatial Layout Estimation for Cluttered Indoor Scenes.
Saumitro Dasgupta, Kuan Fang, Kevin Chen, Silvio Savarese
-
67 A Text Detection System for Natural Scenes With Convolutional Feature Learning and Cascaded Classification.
Siyu Zhu, Richard Zanibbi
Segmentation and Saliency
-
68 Reversible Recursive Instance-Level Object Segmentation.
Xiaodan Liang, Yunchao Wei, Xiaohui Shen, Zequn Jie, Jiashi Feng, Liang Lin, Shuicheng Yan
-
69 Coherent Parametric Contours for Interactive Video Object Segmentation.
Yao Lu, Xue Bai, Linda Shapiro, Jue Wang
-
70 Manifold SLIC: A Fast Method to Compute Content-Sensitive Superpixels.
Yong-Jin Liu, Cheng-Chi Yu, Min-Jing Yu, Ying He
-
71 Deep Saliency With Encoded Low Level Distance Map and High Level Features.
Gayoung Lee, Yu-Wing Tai, Junmo Kim
-
72 Instance-Level Segmentation for Autonomous Driving With Deep Densely Connected MRFs.
Ziyu Zhang, Sanja Fidler, Raquel Urtasun
-
73 DHSNet: Deep Hierarchical Saliency Network for Salient Object Detection.
Nian Liu, Junwei Han
-
74 Object Co-Segmentation via Graph Optimized-Flexible Manifold Ranking.
Rong Quan, Junwei Han, Dingwen Zhang, Feiping Nie
Video Segmentation
-
75 Primary Object Segmentation in Videos via Alternate Convex Optimization of Foreground and Background Distributions.
Won-Dong Jang, Chulwoo Lee, Chang-Su Kim
-
76 Automatic Fence Segmentation in Videos of Dynamic Scenes.
Renjiao Yi, Jue Wang, Ping Tan
-
77 Discovering the Physical Parts of an Articulated Object Class From Multiple Videos.
Luca Del Pero, Susanna Ricco, Rahul Sukthankar, Vittorio Ferrari
-
78 A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation.
Federico Perazzi, Jordi Pont-Tuset, Brian McWilliams, Luc Van Gool, Markus Gross, Alexander Sorkine-Hornung
-
79 Learning Temporal Regularity in Video Sequences.
Mahmudul Hasan, Jonghyun Choi, Jan Neumann, Amit K. Roy-Chowdhury, Larry S. Davis
-
80 Bilateral Space Video Segmentation.
Nicolas Maerki, Federico Perazzi, Oliver Wang, Alexander Sorkine-Hornung
-
81 ReD-SFA: Relation Discovery Based Slow Feature Analysis for Trajectory Clustering.
Zhang Zhang, Kaiqi Huang, Tieniu Tan, Peipei Yang, Jun Li
ORAL SESSION
Object Recognition and Detection
Monday, June 27th, 1:45PM - 2:50PM.
These papers will also be presented at the following poster session
-
1 Training Region-Based Object Detectors With Online Hard Example Mining.
Abhinav Shrivastava, Abhinav Gupta, Ross Girshick
-
2 Deep Residual Learning for Image Recognition.
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
-
3 You Only Look Once: Unified, Real-Time Object Detection.
Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi
-
4 LocNet: Improving Localization Accuracy for Object Detection.
Spyros Gidaris, Nikos Komodakis
-
5 Sketch Me That Shoe.
Qian Yu, Feng Liu, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales, Chen-Change Loy
SPOTLIGHT SESSION
Object Detection 1
Monday, June 27th, 2:50PM - 3:20PM.
These papers will also be presented at the following poster session
-
6 Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images.
Shuran Song, Jianxiong Xiao
-
7 Object Detection From Video Tubelets With Convolutional Neural Networks.
Kai Kang, Wanli Ouyang, Hongsheng Li, Xiaogang Wang
-
8 Learning With Side Information Through Modality Hallucination.
Judy Hoffman, Saurabh Gupta, Trevor Darrell
-
9 Object-Proposal Evaluation Protocol is ‘Gameable’.
Neelima Chavali, Harsh Agrawal, Aroma Mahendru, Dhruv Batra
-
10 HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection.
Tao Kong, Anbang Yao, Yurong Chen, Fuchun Sun
-
11 We Don't Need No Bounding-Boxes: Training Object Class Detectors Using Only Human Verification.
Dim P. Papadopoulos, Jasper R. R. Uijlings, Frank Keller, Vittorio Ferrari
-
12 Factors in Finetuning Deep Model for Object Detection With Long-Tail Distribution.
Wanli Ouyang, Xiaogang Wang, Cong Zhang, Xiaokang Yang
ORAL SESSION
Vision With Alternative Sensors
Monday, June 27th, 1:45PM - 2:50PM.
These papers will also be presented at the following poster session
-
13 Information-Driven Adaptive Structured-Light Scanners.
Guy Rosman, Daniela Rus, John W. Fisher III
-
14 Simultaneous Optical Flow and Intensity Estimation From an Event Camera.
Patrick Bardow, Andrew J. Davison, Stefan Leutenegger
-
15 Macroscopic Interferometry: Rethinking Depth Estimation With Frequency-Domain Time-Of-Flight.
Achuta Kadambi, Jamie Schiel, Ramesh Raskar
-
16 ASP Vision: Optically Computing the First Layer of Convolutional Neural Networks Using Angle Sensitive Pixels.
Huaijin G. Chen, Suren Jayasuriya, Jiyue Yang, Judy Stephen, Sriram Sivaramakrishnan, Ashok Veeraraghavan, Alyosha Molnar
-
17 Computational Imaging for VLBI Image Reconstruction.
Katherine L. Bouman, Michael D. Johnson, Daniel Zoran, Vincent L. Fish, Sheperd S. Doeleman, William T. Freeman
SPOTLIGHT SESSION
Video Analysis 1
Monday, June 27th, 2:50PM - 3:20PM.
These papers will also be presented at the following poster session
-
18 You Lead, We Exceed: Labor-Free Video Concept Learning by Jointly Exploiting Web Videos and Images.
Chuang Gan, Ting Yao, Kuiyuan Yang, Yi Yang, Tao Mei
-
19 Track and Segment: An Iterative Unsupervised Approach for Video Object Proposals.
Fanyi Xiao, Yong Jae Lee
-
20 Beyond Local Search: Tracking Objects Everywhere With Instance-Specific Proposals.
Gao Zhu, Fatih Porikli, Hongdong Li
-
21 Groupwise Tracking of Crowded Similar-Appearance Targets From Low-Continuity Image Sequences.
Hongkai Yu, Youjie Zhou, Jeff Simmons, Craig P. Przybyla, Yuewei Lin, Xiaochuan Fan, Yang Mi, Song Wang
-
22 Social LSTM: Human Trajectory Prediction in Crowded Spaces.
Alexandre Alahi, Kratarth Goel, Vignesh Ramanathan, Alexandre Robicquet, Li Fei-Fei, Silvio Savarese
-
23 What Players Do With the Ball: A Physically Constrained Interaction Modeling.
Andrii Maksai, Xinchao Wang, Pascal Fua
-
24 Highlight Detection With Pairwise Deep Ranking for First-Person Video Summarization.
Ting Yao, Tao Mei, Yong Rui
POSTER SESSION
Poster Session 1-2. Monday, June 27th, 4:45PM - 6:45PM.
Events, Activities, and Surveillance
-
25 Direct Prediction of 3D Body Poses From Motion Compensated Sequences.
Bugra Tekin, Artem Rozantsev, Vincent Lepetit, Pascal Fua
-
26 Video2GIF: Automatic Generation of Animated GIFs From Video.
Michael Gygli, Yale Song, Liangliang Cao
-
27 NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis.
Amir Shahroudy, Jun Liu, Tian-Tsong Ng, Gang Wang
-
28 Progressively Parsing Interactional Objects for Fine Grained Action Detection.
Bingbing Ni, Xiaokang Yang, Shenghua Gao
-
29 Hierarchical Recurrent Neural Encoder for Video Representation With Application to Captioning.
Pingbo Pan, Zhongwen Xu, Yi Yang, Fei Wu, Yueting Zhuang
-
30 From Keyframes to Key Objects: Video Summarization by Representative Object Proposal Selection.
Jingjing Meng, Hongxing Wang, Junsong Yuan, Yap-Peng Tan
-
31 Temporal Action Localization in Untrimmed Videos via Multi-Stage CNNs.
Zheng Shou, Dongang Wang, Shih-Fu Chang
-
32 Summary Transfer: Exemplar-Based Subset Selection for Video Summarization.
Ke Zhang, Wei-Lun Chao, Fei Sha, Kristen Grauman
-
33 POD: Discovering Primary Objects in Videos Based on Evolutionary Refinement of Object Recurrence, Background, and Primary Object Models.
Yeong Jun Koh, Won-Dong Jang, Chang-Su Kim
-
34 What If We Do Not Have Multiple Videos of the Same Action? — Video Action Localization Using Web Images.
Waqas Sultani, Mubarak Shah
-
35 Beyond F-Formations: Determining Social Involvement in Free Standing Conversing Groups From Static Images.
Lu Zhang, Hayley Hung
Fine Grained Categorization
-
36 DeepFashion: Powering Robust Clothes Recognition and Retrieval With Rich Annotations.
Ziwei Liu, Ping Luo, Shi Qiu, Xiaogang Wang, Xiaoou Tang
-
37 SketchNet: Sketch Classification With Web Images.
Hua Zhang, Si Liu, Changqing Zhang, Wenqi Ren, Rui Wang, Xiaochun Cao
-
38 Embedding Label Structures for Fine-Grained Feature Representation.
Xiaofan Zhang, Feng Zhou, Yuanqing Lin, Shaoting Zhang
相關推薦
論文閱讀:CVPR2016 Paper list
在過幾天CVPR2016就要召開了,先放個list。 ORAL SESSION Image Captioning and Question Answering Monday, June 27th, 9:00AM - 10:05AM. These
論文閱讀:Memory Networks
users 方式 article div local 網絡 ava auto data- 一、論文所解決的問題 實現長期記憶(大量的記憶),而且實現怎樣從長期記憶中讀取和寫入,此外還增加了推理功能 為什麽長期記憶非常重要:由於傳統的RNN連復制任務都不行,LST
論文閱讀:A Primer on Neural Network Models for Natural Language Processing(1)
選擇 works embed 負責 距離 feature 結構 tran put 前言 2017.10.2博客園的第一篇文章,Mark。 由於實驗室做的是NLP和醫療相關的內容,因此開始啃NLP這個硬骨頭,希望能學有所成。後續將關註知識圖譜,深度強化學習等內
論文閱讀:Disentangled Representation Learning GAN for Pose-Invariant Face Recognition
ICCV2017的文章,主要使用multi-task的GAN網路來提取pose-invariant特徵,同時生成指定pose的人臉。 下載連結: 作者: Motivation: 對於大pose的人臉識別,現在大家都是兩種方案:1 先轉正再人臉識別。2 直接學習
論文閱讀:You Only Look Once: Unified, Real-Time Object Detection
Preface 注:這篇今年 CVPR 2016 年的檢測文章 YOLO,我之前寫過這篇文章的解讀。但因為不小心在 Markdown 編輯器中編輯時刪除了。幸好同組的夥伴轉載了我的,我就直
目標檢測論文閱讀:Relation Networks for Object Detection
Relation Networks for Object Detection 論文連結:https://arxiv.org/abs/1711.11575 程式碼連結:暫無,尚不清楚是否會公開 這個是CVPR 2018的文章,雖然並沒有什麼巧妙的設
論文閱讀:Deep MANTA: A Coarse-to-fine Many-Task Network for joint 2D and 3D vehicle analysis
這篇論文是在2017年3月22日發表在CVPR上的,作者在這篇論文中提出了一個叫做深度從粗糙到精細化的多工卷積神經網路(Deep MANTA),該模型可以用於對一張圖片中的車輛進行多工的分析。該網路同時執行的多工包括:車輛檢測、部件定位、可見性描述和三維形
論文閱讀:Multiple Object Tracking Using K-Shortest Paths Optimization, PAMI2011
引文: 多目標跟蹤問題通常分為兩步:第一步是與時間無關的目標檢測,即針對每一視訊幀檢測出目標出現的位置,以及在這些位置上出現的置信度;第二步是在時間軸上連線候選目標形成軌跡,在生成軌跡時要儘可能保證同一條軌跡上的所有目標對應同一個真實物體,軌跡數量對應目標
目標檢測論文閱讀:Cascade R-CNN: Delving into High Quality Object Detection
Cascade R-CNN: Delving into High Quality Object Detection 樣本減少引發的過擬合 在train和inference使用不一樣的閾值很容易導致mismatch(這一點在下面會有解釋) 作者為
論文閱讀:Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
論文首先提出了神經網路訓練的一個不好的現象:batch size的增大到一定程度,ResNet的分類準確率會下降。這個現象推翻了我以前的一個直覺:覺得batch size大,訓練的效果會更好。 為了加快訓練的速度(增大batch size)同時保證準確率,論文
目標檢測論文閱讀:Deformable Convolutional Networks
ans 過程 上層 適合 其他 簡易 基礎上 可能 代碼 https://blog.csdn.net/qq_21949357/article/details/80538255 這篇論文其實讀起來還是比較難懂的,主要是細節部分很需要推敲,尤其是deformable的卷積如何實
論文閱讀:Attention to Scale: Scale-aware Semantic Image Segmentation
注意力機制其實就是對feature map做加權,且加權的權重在訓練的時候學習的。 很多語義分割網路融合了多尺度(多解析度)的特徵,但方法不盡相同。一種常見的結構是SPP(Spatial Pooling Pyramid),另一種方法則是使用不同解析度的分
RefineDet論文閱讀:Single-Shot Refinement Neural Network for Object Detection
裁剪 部分 損失函數 過程 bject sin 關聯 增加 問題 摘要 RefineDet是CVPR 2018的一篇論文,文中提出了一個新的single-shot檢測器RefineDet,實現了比二階段方法更高的準確率而且具有與一階段方法相當的效率。RefineDet包括兩
論文閱讀:《Human Parsing with Contextualized Convolutional Neural Network》ICCV 2015
概述 論文主要是提出了一個local-to-global-to-local 的框架結構,主要目的是從低層加入情境化的資訊,這個框架是將交叉層內容(cross-layer context),全域性影
論文閱讀:Deep Relative Distance Learning: Tell the Difference Between Similar Vehicles
Preface 這是我參加今年智慧城市比賽的任務:車輛精確檢索,看的論文。 Abstract 這篇文章所提出的,網路整體架構為: Deep Relative Distance Learning Triplet Loss 在
論文閱讀:Automatic Tooth Region Separation for Dental CT Images
【論文資訊】 Automatic Tooth Region Separation for Dental CT Images Hui Gao 2008 年發表的會議論文 【背景】 提出了該領域研究內容:In order to reconstruct eac
目標檢測論文閱讀:RFB Net
Receptive Field Block Net for Accurate and Fast Object Detection 1. Background 這篇論文要解決的問題很簡單,作為單階段的檢測方法,它試圖尋找速度和精度之間的平衡,就像之前很多sing
[論文閱讀]:Focal Loss for dense Object Detection
在2D的影象檢測的任務中,一種有一個比較明顯的問題就是前後景數量上巨大的不平衡,背景一般遠遠多餘前景(也就是目標),這就導致一個問題,就是背景相關的梯度幾乎統治了梯度的傳播過程,本文提出的Focal Loss 就是試圖對損失函式的形態進行更改,從而達到平衡前後景
論文閱讀:SSD: Single Shot MultiBox Detector
Preface 有幾點更新: 1. 看到一篇 blog 對檢測做了一個總結、收集,強烈推薦: Object Detection 2. 還有,今天在微博上看到 VOC2012 的榜單又被重新整理了,微博原地址為:這裡,如下圖: 3. 目前 voc
論文閱讀:《Convolutional Pose Machines》CVPR 2016
概述 本文使用CNN進行人體姿態估計,它的主要貢獻在於使用順序化的卷積架構來表達空間資訊和紋理資訊。順序化的卷積架構表現在網路分為多個階段,每一個階段都有監督訓練的部分。前面的階段使用原始圖片作為輸入