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
Proceedings ArticleDOI
Prime Sample Attention in Object Detection
TL;DR: The notion of Prime Samples, those that play a key role in driving the detection performance are proposed, and a simple yet effective sampling and learning strategy called PrIme Sample Attention (PISA) is developed that directs the focus of the training process towards such samples.
Posted Content
SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud
TL;DR: This work introduces a new model SqueezeSegV2, which is more robust against dropout noises in LiDAR point cloud and therefore achieves significant accuracy improvement, and a domain-adaptation training pipeline consisting of three major components: learned intensity rendering, geodesic correlation alignment, and progressive domain calibration.
Journal ArticleDOI
DeepSTORM3D: dense 3D localization microscopy and PSF design by deep learning
Elias Nehme,Daniel Freedman,Racheli Gordon,Boris Ferdman,Lucien E. Weiss,Onit Alalouf,Tal Naor,Reut Orange,Tomer Michaeli,Yoav Shechtman +9 more
TL;DR: DeepSTORM3D uses deep learning for accurate localization of point emitters in densely labeled samples in three dimensions for volumetric localization microscopy with high temporal resolution, as well as for optimal point-spread function design.
Proceedings ArticleDOI
D2Det: Towards High Quality Object Detection and Instance Segmentation
TL;DR: A novel two-stage detection method, D2Det, that collectively addresses both precise localization and accurate classification is proposed and a discriminative RoI pooling scheme that samples from various sub-regions of a proposal and performs adaptive weighting to obtain discriminating features is introduced.
Proceedings ArticleDOI
AugFPN: Improving Multi-Scale Feature Learning for Object Detection
TL;DR: Guo et al. as discussed by the authors proposed a new feature pyramid architecture named AugFPN, which consists of three components: Consistent Supervision, Residual Feature Augmentation, and Soft RoI Selection.
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.