ming71/cv_paperdaily

CV 论文笔记

CV--PaperDaily

Updated at irregular intervals. Notes are attached to PDF files.

Archive

2022

• [TMM] Latent Feature Pyramid Network for Object Detection

---

2021

• [AAAI] Learning Modulated Loss for Rotated Object Detection
• [AAAI] R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object
• [ICCV] Reconcile Prediction Consistency for Balanced Object Detection
• [CVPR] You Only Look One-level Feature
• [CVPR] Boundary IoU: Improving Object-Centric Image Segmentation Evaluation
• [CVPR] Coordinate Attention for Efficient Mobile Network Design
• [CVPR] Dot Distance for Tiny Object Detection in Aerial Images
• [CVPR] IQDet: Instance-wise Quality Distribution Sampling for Object Detection
• [ICML] Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss
• [ICLR] Deformable DETR: Deformable Transformers for End-to-End Object Detection
• [WACV] Disentangled Contour Learning for Quadrilateral Text Detection
• [BMVC] Mask-aware IoU for Anchor Assignment in Real-time Instance Segmentation
• [NeurIPS] Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression
• [NeurIPS] Dynamic Resolution Network
• [IROS] Object-to-Scene: Learning to Transfer Object Knowledge to Indoor Scene Recognition
• [ACM MM] Decoupled IoU Regression for Object Detection
• [JSTARS] Arbitrary-Oriented Ship Detection through Center-Head Point Extraction
• [TIP] GSDet: Object Detection in Aerial Images Based on Scale Reasoning
• [TIP] HCE: Hierarchical Context Embedding for Region-Based Object Detection
• [TGRS] SKNet: Detecting Rotated Ships as Keypoints in Optical Remote Sensing Images
• [TGRS] Laplacian Feature Pyramid Network for Object Detection in VHR Optical Remote Sensing Images
• [NCAA] Hilbert sEMG data scanning for hand gesture recognition based on deep learning
• [IVC] Weighted boxes fusion: Ensembling boxes from different object detection models
• [Knowledge-Based Systems] PRPN: Progressive region prediction network for natural scene text detection
• Confidence Propagation Cluster: Unleash Full Potential of Object Detectors
• FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery
• Object Detection in Aerial Images A Large-Scale Benchmark and Challenges
• Gaussian Guided IoU: A Better Metric for Balanced Learning on Object Detection
• MOD: Benchmark for Military Object Detection
• Location-Sensitive Visual Recognition with Cross-IOU Loss
• Anchor Pruning for Object Detection
• SCALoss: Side and Corner Aligned Loss for Bounding Box Regression

---

2020

• [AAAI] Arbitrary-Oriented Object Detection with Circular Smooth Label
• [AAAI] CBNet: A Novel Composite Backbone Network Architecture for Object Detection
• [AAAI] Distance-IoU
• [AAAI] Progressive Feature Polishing Network for Salient Object Detection
• [BMVC] Cascade RetinaNet: Maintaining Consistency for Single-Stage Object Detection
• [CVPR] AugFPN: Improving Multi-scale Feature Learning for Object Detection
• [CVPR] ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection
• [CVPR] Delving into Online High-quality Anchors Mining for Detecting Outer Faces
• [CVPR] Detection in Crowded Scenes One Proposal, Multiple Predictions
• [CVPR] Learning from Noisy Anchors for One-stage Object Detection
• [CVPR] Multiple Anchor Learning for Visual Object Detection
• [CVPR] PolarMask: Single Shot Instance Segmentation with Polar Representation
• [CVPR] Revisiting the Sibling Head in Object Detector
• [ECCV] Dynamic R-CNN : Towards High Quality Object Detection via Dynamic Training
• [ECCV] PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments
• [ECCV] Probabilistic Anchor Assignment with IoU Prediction for Object Detection
• [ECCV] Rotation-robust Intersection over Union for 3D Object Detection
• [ECCV] End-to-End Object Detection with Transformers
• [ECCV] Side-Aware Boundary Localization for More Precise Object Detection
• [JSTARS] Learning Point-guided Localization for Detection in Remote Sensing Images
• [TGRS] Adaptive Period Embedding for Representing Oriented Objects in Aerial Images
• [TCSVT] Joint Anchor-Feature Refinement for Real-Time Accurate Object Detection in Images and Videos
• [Neurocomputing] Recent Advances in Deep Learning for Object Detection
• [Neurocomputing] Single-Shot Bidirectional Pyramid Networks for High-Quality Object Detection
• [Remote Sens.] EFN: Field-based Object Detection for Aerial Images
• [Remote Sens.] Single-Stage Rotation-Decoupled Detector for Oriented Object
• [Remote Sens.] A2S-Det: Efficiency Anchor Matching in Aerial Image Oriented Object Detection
• [WACV] Improving Object Detection with Inverted Attention
• [WACV] Propose-and-Attend Single Shot Detector
• Align Deep Features for Oriented Object Detection
• AMRNet: Chips Augmentation in Areial Images Object Detection
• BBRefinement: An universal scheme to improve precision of box object detectors
• Conditional Convolutions for Instance Segmentation
• Cross-layer Feature Pyramid Network for Salient Object Detection
• EAGLE: Large-scale Vehicle Detection Dataset inReal-World Scenarios using Aerial Imagery
• Extended Feature Pyramid Network for Small Object Detection
• FeatureNMS: Non-Maximum Suppression by Learning Feature Embeddings
• Feature Pyramid Grids
• IterDet: Iterative Scheme for ObjectDetection in Crowded Environments
• Location-Aware Feature Selection for Scene Text Detection
• Objects detection for remote sensing images based on polar coordinates
• Scale-Invariant Multi-Oriented Text Detection in Wild Scene Images
• Scaled-YOLOv4: Scaling Cross Stage Partial Network

---

2019

• [AAAI] Gradient Harmonized Single-stage Detector
• [AAAI] M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid
• [BMVC] Rethinking Classification and Localization for Cascade R-CNN
• [CVPR] Assisted Excitation of Activations: A Learning Technique to Improve Object
• [CVPR] Borrow from Anywhere Pseudo Multi-modal Object Detection in Thermal Imagery
• [CVPR] Dual Attention Network for Scene Segmentation
• [CVPR] Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression
• [CVPR] Learning RoI Transformer for Detecting Oriented Objects in Aerial Images
• [CVPR] Learning Instance Activation Maps for Weakly Supervised Instance Segmentation
• [CVPR] Libra R-CNN: Towards Balanced Learning for Object Detection
• [CVPR] Panoptic Segmentation
• [CVPR] Region Proposal by Guided Anchoring
• [CVPR] ScratchDet : Training Single-Shot Object Detectors
• [CVPR] Softer-NMS: Rethinking Bounding Box Regression for Accurate Object Detection
• [CVPR] Spatial-aware Graph Relation Network for Large-scale Object Detection
• [CVPR] Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations
• [ICCV] Dynamic Multi-scale Filters for Semantic Segmentation
• [ICCV] EGNet: Edge Guidance Network for Salient Object Detection
• [ICCV] FCOS: Fully Convolutional One-Stage Object Detection
• [ICCV] InstaBoost: Boosting Instance Segmentation via Probability Map Guided
• [ICCV] Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving
• [ICCV] Matrix Nets: A New Deep Architecture for Object Detection
• [ICCV] ThunderNet: Towards Real-time Generic Object Detection
• [ICCV] Towards More Robust Detection for Small, Cluttered and Rotated Objects
• [ICCV] Scale-Aware Trident Networks for Object Detection
• [ICCV] SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects
• [ICIP] SSSDET: Simple Short and Shallow Network for Resource Efficient Vehicle Detection in Aerial Scenes
• [ICLR] Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet
• [ICLR] ImageNet-trained CNNs are biased towards texture: increasing shape bias improves accuracy and robustness
• [ICLR] Why do deep convolutional networks generalize so poorly to small image transformations?
• [ICML] How much real data do we actually need: Analyzing object detection performance using synthetic and real data
• [ICML] Making Convolutional Networks Shift-Invariant Again
• [ICTAI] Twin Feature Pyramid Networks for Object Detection
• [IEEE Access] A Real-Time Scene Text Detector with Learned Anchor
• [IEEE Trans Geosci Remote Sens] CAD-Net: A Context-Aware Detection Network for Objects in Remote Sensing Imagery
• [IJCAI] Omnidirectional Scene Text Detection with Sequential-free Box Discretization
• [J. Big Data] A survey on Image Data Augmentation for Deep Learning
• [NeurIPS] Cascade RPN Delving into High-Quality Region Proposal Network with Adaptive Convolution
• [NeurIPS] FreeAnchor Learning to Match Anchors for Visual Object Detection
• A Preliminary Study on Data Augmentation of Deep Learning for Image Classification
• Bag of Freebies for Training Object Detection Neural Networks
• Consistent Optimization for Single-Shot Object Detection
• Deep Learning for 2D and 3D Rotatable Data An Overview of Methods
• Double-Head RCNN: Rethinking Classification and Localization for Object Detection
• IENet: Interacting Embranchment One Stage Anchor Free Detector for Orientation Aerial Object Detection
• IoU-uniform R-CNN: Breaking Through the Limitations of RPN
• Is Sampling Heuristics Necessary in Training Deep Object Detectors
• Learning Data Augmentation Strategies for Object Detection
• Learning from Noisy Anchors for One-stage Object Detection
• Light-Head R-CNN: In Defense of Two-Stage Object Detector
• MMDetection: Open MMLab Detection Toolbox and Benchmark
• Multi-Scale Attention Network for Crowd Counting
• Natural Adversarial Examples
• Needles in Haystacks: On Classifying Tiny Objects in Large Images
• Revisiting Feature Alignment for One-stage Object Detection
• Ship Detection: An Improved YOLOv3 Method

---

2018

• [ACCV] Reverse Densely Connected Feature Pyramid Network for Object Detection
• [BMVC] Enhancement of SSD by concatenating feature maps for object detection
• [CVPR] An Analysis of Scale Invariance in Object Detection
• [CVPR] Cascade R-CNN: Delving into High Quality Object Detection
• [CVPR] DOTA: A Large-scale Dataset for Object Detection in Aerial Images
• [CVPR] Path Aggregation Network for Instance Segmentation
• [CVPR] Pseudo Mask Augmented Object Detection
• [CVPR] Rotation Sensitive Regression for Oriented Scene Text Detection
• [CVPR] Scale-Transferable Object Detection
• [CVPR] Single-Shot Object Detection with Enriched Semantics
• [CVPR] Single-Shot Refinement Neural Network for Object Detection
• [CVPR] Squeeze-and-Excitation Networks
• [CVPR] Weakly Supervised Instance Segmentation using Class Peak Response
• [ECCV] Acquisition of Localization Confidence for Accurate Object Detection
• [ECCV] Deep Feature Pyramid Reconfiguration for Object Detection
• [ECCV] DetNet: A Backbone network for Object Detection
• [ECCV] Learning to Segment via Cut-and-Paste
• [ECCV] Modeling Visual Context is Key to Augmenting Object Detection Datasets
• [ECCV] Receptive Field Block Net for Accurate and Fast Object Detection
• [ICLR] Multi-Scale Dense Convolutional Networks for Efficient Prediction
• [ICANN] Further advantages of data augmentation on convolutional neural networks
• [ISBI] A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation
• [TIP] TextBoxes++: A single-shot oriented scene text detector
• [TMM] Arbitrary-oriented scene text detection via rotation proposals
• [IJAC] An Overview of Contour Detection Approaches
• [IJCV] What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?
• [J Mach Learn Res] Neural Architecture Search: A Survey
• [Remote Sens.] Automatic Ship Detection of Remote Sensing Images from Google Earth in Complex Scenes Based on Multi-Scale Rotation Dense Feature Pyramid Networks
• [VISIGRAPP] Learning Transformation Invariant Representations with Weak Supervision
• [WACV] Understanding Convolution for Semantic Segmentation
• Data Augmentation by Pairing Samples for Images Classification
• MDSSD: Multi-scale Deconvolutional Single Shot Detector for Small Objects
• RAM: Residual Attention Module for Single Image Super-Resolution
• R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection

---

2017

• [AAAI] Weakly Supervised Semantic Segmentation Using Superpixel Pooling Network
• [CVPR] Feature Pyramid Networks for Object Detection
• [CVPR] Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade
• [CVPR] Oriented Response Networks
• [CVPR] Simple Does It: Weakly Supervised Instance and Semantic Segmentation
• [ICCV] Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection
• [ICCV] Focal Loss for Dense Object Detection
• [ICCV] Grad-CAM Visual Explanations From Deep Networks via Gradient-Based Localization
• [ICCV] Single shot scale-invariant face detector
• [ICCV] Single Shot Text Detector with Regional Attention
• [ICIP] Rotated region based CNN for ship detection
• [ICLR] Dataset Augmentationin In Feature Space
• [ICPRAM] A High Resolution Optical Satellite Image Dataset for Ship Recognition and Some New Baselines
• [IEEE Acess] Smart Augmentation: Learning an Optimal Data Augmentation Strategy
• FSSD: Feature Fusion Single Shot Multibox Detector
• Improved Regularization of Convolutional Neural Networks with Cutout
• The Effectiveness of Data Augmentation in Image Classification using Deep Learning
• Tversky loss function for image segmentation using 3D fully convolutional deep networks

---

2016

• [CVPR] Learning Deep Features for Discriminative Localization
• [DICTA] Understanding data augmentation for classification: when to warp?
• [ECCV] Contextual Priming and Feedback for Faster R-CNN
• [NIPS] R-FCN: Object Detection via Region-based Fully Convolutional Networks
• [GRSL] Ship Rotated Bounding Box Space for Ship Extraction From High-Resolution Optical Satellite Images With Complex Backgrounds
• Beyond Skip Connections: Top-Down Modulation for Object Detection

---

2015

• [ICDAR] ICDAR 2015 competition on Robust Reading

---

2014

• [CVPR] Scalable Object Detection Using Deep Neural Networks

---

2012

• [PAMI] Measuring the Objectness of Image Windows

---

2009

• [ICML] Curriculum learning

---

2000

• [IJCV] The earth mover's distance as a metric for image retrieval

cv_paperdaily's Issues

请问使用哪个PDF阅读器打开可以看到你的笔记？

我使用浏览器打开pdf，但看不到你的笔记，请问哪个PDF阅读器可以呢？

YOLO v3+: Assisted Excitation of Activations中alph

这个max_iteration一般是多少呢？如果几十万会不会就没什么效果了？

请问有没有准确率和帧率都比较高的分割算法推荐？

看了CBNet的论文，感觉帧率有点低了，如果能做到20fps就好了。请问有没有20fps准确率又不错的物体分割算法推荐一下，谢谢！

基于bounding boxes的弱监督分割算法

请问一下，基于bounding boxes的弱监督分割算法最新的论文（Semi-Supervised Semantic Image Segmentation with Self-correcting Networks）有没有？我只找到了18年的还没有代码？谢谢！

关于YOLOV3+: Assisted Excitation of Activations的一个疑问

5. Discussion
   Excite object regions vs suppress non-object regions?
     （这一点我的理解不一定对，看原文）作者认为两种机制不同。如果是直接进行不含目标样本的抑制，那么在检测阶段无法获知哪些样本（bbox）是不含样本的，需要进行打分判断（也就是conf置信）；而AE激励响应是直接通过逐步的减少让最终结果只关注到少量的正样本上，这一点学习起来更加容易。

您好，很感谢您的分享，让我也从中了解了这篇文献的**。有一个问题想跟您讨论下，您在结论时提出：”AE激励响应是直接通过逐步的减少让最终结果只关注到少量的正样本上“，但是我看文中的公式，实际上是一个示性函数乘以1个α因子，而这个因子是逐渐衰减的，训练到最后衰减为0，这时示性函数也就发挥不了作用了，也就是正样本的mask不起作用了，所以到最后不应该是关注所有样本（既有正样本，也包括负样本）才对吗，您能帮忙解释一下吗，或者我的理解有问题？谢谢！