Focal Loss for Dense Object Detection
Reads0
Chats0
TLDR
Focal loss as discussed by the authors focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training, which improves the accuracy of one-stage detectors.Abstract:
The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. In contrast, one-stage detectors that are applied over a regular, dense sampling of possible object locations have the potential to be faster and simpler, but have trailed the accuracy of two-stage detectors thus far. In this paper, we investigate why this is the case. We discover that the extreme foreground-background class imbalance encountered during training of dense detectors is the central cause. We propose to address this class imbalance by reshaping the standard cross entropy loss such that it down-weights the loss assigned to well-classified examples. Our novel Focal Loss focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training. To evaluate the effectiveness of our loss, we design and train a simple dense detector we call RetinaNet. Our results show that when trained with the focal loss, RetinaNet is able to match the speed of previous one-stage detectors while surpassing the accuracy of all existing state-of-the-art two-stage detectors. Code is at: https://github.com/facebookresearch/Detectron .read more
Citations
More filters
Journal ArticleDOI
PBNet: Part-based convolutional neural network for complex composite object detection in remote sensing imagery
TL;DR: A unified part-based convolutional neural network (PBNet), which is specifically designed for composite object detection in remote sensing imagery and surpasses the existing detection algorithms and achieves state-of-the-art accuracy.
Journal ArticleDOI
Deep neural network ensemble for pneumonia localization from a large-scale chest x-ray database
Ilyas Sirazitdinov,Maksym Kholiavchenko,Tamerlan Mustafaev,Yuan Yixuan,Ramil Kuleev,Bulat Ibragimov +5 more
TL;DR: This work developed a reliable solution for automated pneumonia diagnosis and validated it on the largest clinical database publicity available to date and proposed an ensemble of two convolutional neural networks, namely RetinaNet and Mask R-CNN for pneumonia detection and localization.
Journal ArticleDOI
A predictive machine learning application in agriculture: Cassava disease detection and classification with imbalanced dataset using convolutional neural networks
TL;DR: The goal was to counter high-class imbalance so that the model can accurately predict underrepresented classes in multi-class image datasets and achieve an accuracy score of over 93% with class weight, SMOTE and focal loss with deep convolutional neural networks from scratch.
Journal ArticleDOI
Transfer learning using a multi-scale and multi-network ensemble for skin lesion classification.
Amirreza Mahbod,Gerald Schaefer,Chunliang Wang,Georg Dorffner,Rupert Ecker,Isabella Ellinger +5 more
TL;DR: It is confirmed that the image size has an effect on skin lesion classification performance when employing transfer learning of CNNs and it is shown that image cropping results in better performance compared to image resizing.
Journal ArticleDOI
Automated Atrial Fibrillation Detection using a Hybrid CNN-LSTM Network on Imbalanced ECG Datasets
Georgios Petmezas,K. Haris,Leandros Stefanopoulos,Vassilis Kilintzis,Andreas Tzavelis,John A. Rogers,Aggelos K. Katsaggelos,Nicos Maglaveras,Nicos Maglaveras +8 more
TL;DR: A novel hybrid neural model utilizing focal loss, an improved version of cross-entropy loss, to deal with training data imbalance is proposed, which can aid clinicians to detect common atrial fibrillation in real-time on routine screening ECG.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings ArticleDOI
Histograms of oriented gradients for human detection
Navneet Dalal,Bill Triggs +1 more
TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.
Book ChapterDOI
Microsoft COCO: Common Objects in Context
Tsung-Yi Lin,Michael Maire,Serge Belongie,James Hays,Pietro Perona,Deva Ramanan,Piotr Dollár,C. Lawrence Zitnick +7 more
TL;DR: A new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding by gathering images of complex everyday scenes containing common objects in their natural context.
Proceedings ArticleDOI
Fully convolutional networks for semantic segmentation
TL;DR: The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.