No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Solving Class Imbalance Problem in Target Detection with a Squared Cross Entropy Based Method
Abstract
The foreground-background class imbalance in target detection is inevitable, which is caused by the training data set. Specifically, the number of targets contained in any image of the training data set is generally very small, that is, the number of positive examples is small, while the number of the negative examples from the background is large. Therefore, the ability of the algorithm to detect the negatives is stronger than that of positive examples. The Focal Loss algorithm solves this problem by improving the classification loss function. However, Focal Loss brings additional hyper-parameters, which remains to be further adjusted. This paper refers to the idea of Focal Loss from the classification loss function, and proposes new a classification loss function SCE that is similar to Focal Loss but does not contain any extra hyper-parameters. Experiments in the paper prove that SCE can obtain performance equivalent to Focal Loss without introducing hyper-parameters.KeywordsTarget detectionCross entropyLoss functionClass Imbalance
ResearchGate has not been able to resolve any citations for this publication.
In this paper, we present a comprehensive review of the imbalance problems in object detection. To analyze the problems in a systematic manner, we introduce a problem-based taxonomy. Following this taxonomy, we discuss each problem in depth and present a unifying yet critical perspective on the solutions in the literature. In addition, we identify major open issues regarding the existing imbalance problems as well as imbalance problems that have not been discussed before. Moreover, in order to keep our review up to date, we provide an accompanying webpage which catalogs papers addressing imbalance problems, according to our problem-based taxonomy. Researchers can track newer studies on this webpage available at: https://github.com/kemaloksuz/ObjectDetectionImbalance.
The state-of-the-art performance for object detection has been significantly improved over the past two years. Besides the introduction of powerful deep neural networks such as GoogleNet and VGG, novel object detection frameworks such as R-CNN and its successors, Fast R-CNN and Faster R-CNN, play an essential role in improving the state-of-the-art. Despite their effectiveness on still images, those frameworks are not specifically designed for object detection from videos. Temporal and contextual information of videos are not fully investigated and utilized. In this work, we propose a deep learning framework that incorporates temporal and contextual information from tubelets obtained in videos, which dramatically improves the baseline performance of existing still-image detection frameworks when they are applied to videos. It is called T-CNN, i.e. tubelets with convolutional neueral networks. The proposed framework won the recently introduced object-detection-from-video (VID) task with provided data in the ImageNet Large-Scale Visual Recognition Challenge 2015 (ILSVRC2015).
Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.
We aim to detect all instances of a category in an image and, for each
instance, mark the pixels that belong to it. We call this task Simultaneous
Detection and Segmentation (SDS). Unlike classical bounding box detection, SDS
requires a segmentation and not just a box. Unlike classical semantic
segmentation, we require individual object instances. We build on recent work
that uses convolutional neural networks to classify category-independent region
proposals (R-CNN [16]), introducing a novel architecture tailored for SDS. We
then use category-specific, top- down figure-ground predictions to refine our
bottom-up proposals. We show a 7 point boost (16% relative) over our baselines
on SDS, a 5 point boost (10% relative) over state-of-the-art on semantic
segmentation, and state-of-the-art performance in object detection. Finally, we
provide diagnostic tools that unpack performance and provide directions for
future work.
Object detection is a fundamental visual recognition problem in computer vision and has been widely studied in the past decades. Visual object detection aims to find objects of certain target classes with precise localization in a given image and assign each object instance a corresponding class label. Due to the tremendous successes of deep learning based image classification, object detection techniques using deep learning have been actively studied in recent years. In this paper, we give a comprehensive survey of recent advances in visual object detection with deep learning. By reviewing a large body of recent related work in literature, we systematically analyze the existing object detection frameworks and organize the survey into three major parts: (i) detection components, (ii) learning strategies, and (iii) applications & benchmarks. In the survey, we cover a variety of factors affecting the detection performance in detail, such as detector architectures, feature learning, proposal generation, sampling strategies, etc. Finally, we discuss several future directions to facilitate and spur future research for visual object detection with deep learning.
High resolution remote sensing image data is veritable big data. It is not only massive, multi-source, and heterogeneous, but also high-dimensional, multi-scale, and non-stationary. In order to overcome the reduction of classification accuracy and redundancy of spatial data when dealing with high resolution remote sensing images using traditional classification methods, this paper improves the traditional Convolution Neural Network (CNN) from the aspects of both the network structure and the training method, and the improved CNN is used in the classification and recognition of high resolution remote sensing images. The experiments show that the classification accuracy of the improved CNN is better than that of the traditional CNN. Furthermore, the classification accuracy of the improved CNN is better than the Deep Belief Network (DBN), Support Vector Machine (SVM), and traditional BP.
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.
Object detection performance, as measured on the canonical PASCAL VOC Challenge datasets, plateaued in the final years of the competition. The best-performing methods were complex ensemble systems that typically combined multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 50% relative to the previous best result on VOC 2012—achieving a mAP of 62.4%. Our approach combines two ideas: (1) one can apply high-capacity convolutional networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data are scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, boosts performance significantly. Since we combine region proposals with CNNs, we call the resulting model an R-CNN or Region-based Convolutional Network. Source code for the complete system is available at http://www.cs.berkeley.edu/rbg/rcnn.
We present a model that generates free-form natural language descriptions of
image regions. Our model leverages datasets of images and their sentence
descriptions to learn about the inter-modal correspondences between text and
visual data. Our approach is based on a novel combination of Convolutional
Neural Networks over image regions, bidirectional Recurrent Neural Networks
over sentences, and a structured objective that aligns the two modalities
through a multimodal embedding. We then describe a Recurrent Neural Network
architecture that uses the inferred alignments to learn to generate novel
descriptions of image regions. We demonstrate the effectiveness of our
alignment model with ranking experiments on Flickr8K, Flickr30K and MSCOCO
datasets, where we substantially improve on the state of the art. We then show
that the sentences created by our generative model outperform retrieval
baselines on the three aforementioned datasets and a new dataset of
region-level annotations.
Moving objects detection in automatic driving based on YOLOv3
- Y Li
- L Hou
- C Wang
Improved YOLOv2 vehicle real-time detection algorithm combined with multi-scale features
- Y Jin
- N Luo
YOLOv3 network based on improved loss function
- S Lyu
- X Cai
- R Feng