Notice！

~~Continuous update.~~
~~On vacation...~~
Busy with recent things , I'll update without day.

CV--PaperDaily

创建人	知乎论文阅读专栏	个人博客	其他
ming71	论文笔记入口	chaser	CSDN

Update CV papers here everday .
The content includes but is not limited to Object detection , Semantic segmentation , and other papers about deep learning . Most of papers are published in recent two years
Your comments are welcome , and you can e-mail me by mq_chaser@126.com .

Paper reading divided by Conference & Journal

AAAI

M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid
Weakly Supervised Semantic Segmentation Using Superpixel Pooling Network

CVPR

Assisted Excitation of Activations: A Learning Technique to Improve Object
Borrow from Anywhere Pseudo Multi-modal Object Detection in Thermal Imagery
Cascade R-CNN: Delving into High Quality Object Detection
Feature Pyramid Networks for Object Detection
Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade
Path Aggregation Network for Instance Segmentation
Region Proposal by Guided Anchoring
Scale-Transferable Object Detection
DOTA: A Large-scale Dataset for Object Detection in Aerial Images
R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection
Pseudo Mask Augmented Object Detection
Single-Shot Object Detection with Enriched Semantics
Weakly Supervised Instance Segmentation using Class Peak Response
Learning Deep Features for Discriminative Localization
Simple Does It: Weakly Supervised Instance and Semantic Segmentation
Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations
Panoptic Segmentation
Learning Instance Activation Maps for Weakly Supervised Instance Segmentation

ECCV

DetNet: A Backbone network for Object Detection
Receptive Field Block Net for Accurate and Fast Object Detection
Modeling Visual Context is Key to Augmenting Object Detection Datasets
Contextual Priming and Feedback for Faster R-CNN
Learning to Segment via Cut-and-Paste

ICCV

Focal Loss for Dense Object Detection
InstaBoost: Boosting Instance Segmentation via Probability Map Guided
Scale-Aware Trident Networks for Object Detection
EGNet: Edge Guidance Network for Salient Object Detection
ThunderNet: Towards Real-time Generic Object Detection
Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection

ICML

Making Convolutional Networks Shift-Invariant Again

ICLR

Why do deep convolutional networks generalize so poorly to small image transformations?
Dataset Augmentationin In Feature Space
ImageNet-trained CNNs are biased towards texture: increasing shape bias improves accuracy and robustness
Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet

ArXiv

FSSD: Feature Fusion Single Shot Multibox Detector
MDSSD: Multi-scale Deconvolutional Single Shot Detector for Small Objects
MMDetection: Open MMLab Detection Toolbox and Benchmark
Double-Head RCNN: Rethinking Classification and Localization for Object Detection
Learning Data Augmentation Strategies for Object Detection
A Preliminary Study on Data Augmentation of Deep Learning for Image Classification
Improved Regularization of Convolutional Neural Networks with Cutout
Data Augmentation by Pairing Samples for Images Classification
How much real data do we actually need: Analyzing object detection performance using synthetic and real data
Bag of Freebies for Training Object Detection Neural Networks
The Effectiveness of Data Augmentation in Image Classification using Deep Learning
Natural Adversarial Examples
Recent Advances in Deep Learning for Object Detection
Matrix Nets: A New Deep Architecture for Object Detection
Needles in Haystacks: On Classifying Tiny Objects in Large Images
CBNet: A Novel Composite Backbone Network Architecture for Object Detection
Light-Head R-CNN: In Defense of Two-Stage Object Detector
R3Det Refined Single-Stage Detector with Feature Refinement for Rotating Object

Others

(Acess) Smart Augmentation: Learning an Optimal Data Augmentation Strategy
(ICANN) Further advantages of data augmentation on convolutional neural networks
(WACV) Understanding Convolution for Semantic Segmentation
(BMCV) Enhancement of SSD by concatenating feature maps for object detection
(Big Data) A survey on Image Data Augmentation for Deep Learning
(DICTA) Understanding data augmentation for classification: when to warp?
(IJCV) What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?
(ACCV) Reverse Densely Connected Feature Pyramid Network for Object Detection
(IJAC) An Overview of Contour Detection Approaches
(ICIP) SSSDET: Simple Short and Shallow Network for Resource Efficient Vehicle Detection in Aerial Scenes
(Remote Sensing) Automatic Ship Detection of Remote Sensing Images from Google Earth in Complex Scenes Based on Multi-Scale Rotation Dense Feature Pyramid Networks
(Multimedia) Arbitrary-oriented scene text detection via rotation proposals
(NIPS) R-FCN： Object Detection via Region-based Fully Convolutional Networks

munian-ustc / CV_PaperDaily