Deep Neural Networks for Object Detection

By Christian Szegedy, Alexander Toshev, Dumitru Erhan. 2013

1,555 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (2015, background): “Several papers have proposedways of using deep networks for predicting object bounding boxes [9], [25], [26], [27].”
Going deeper with convolutions (2014, background): “The biggest gains in object-detection have not come from the utilization of deep networks alone or bigger models, but from the synergy of deep architectures and classical computer vision, like the R-CNN algorithm by Girshick et al [6].”
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition (2014, neutral): “This result is similar to the 50-bin pyramid above (34.98/14.14), but considerably better than the no-SPP counterpart (35.99/14.76).”
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation (2013, methodology): “In brief, our CNN nearly matches the performance of Krizhevsky et al. [25], obtaining a top-1 error rate 2.2 percentage points higher on the ILSVRC2012 classification validation set.”
Rethinking ImageNet Pre-Training (2018, background): “, [31, 38, 45])—a fact that is somewhat overlooked today.”
Learning to decompose for object detection and instance segmentation (2015, methodology): “We adopted a mask based loss function for penalizing activations at the location where there is no object corresponding to the category (Szegedy et al., 2013).”
Scalable Object Detection Using Deep Neural Networks (2013, methodology): “We capitalize on the excellent representation learning abilities of DNNs, as recently exeplified recently in image classification [10] and object detection settings [13], and perform joint learning of representation and predictors.”
Beyond Skip Connections: Top-Down Modulation for Object Detection (2016, methodology): “Convolutional neural networks (ConvNets) have revolutionized the field of object detection [4, 14, 16, 17, 41, 44, 48].”
Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors (2016, background): “While both R-CNN and Fast R-CNN relied on an external proposal generator, recent works have shown that it is possible to generate box proposals using neural networks as well [40, 39, 8, 30].”
R-FCN: Object Detection via Region-based Fully Convolutional Networks (2016, background): “Another family of object detectors resort to fully-connected ( fc ) layers for generating holistic object detection results on an entire image, such as [26, 4, 18].”
Deformable part models are convolutional neural networks (2014, methodology): “A schematic diagram of the model is presented in Figure 1.”
Pix2seq: A Language Modeling Framework for Object Detection (2021, methodology): “For example, the loss function is often based on bounding box regression (Szegedy et al., 2013; Lin et al., 2017b), intersection over union (Rezatoﬁghi et al., 2019), and set-based matching (Erhan et al., 2014; Liu et al., 2016; Redmon et al., 2016; Stewart et al., 2016; Carion et al., 2020).”
Analyzing the Performance of Multilayer Neural Networks for Object Recognition (2014, methodology): “These results can be compared to the 30.5% mAP obtained by DetectorNet [21], a recent detection system based on the same network architecture, which was trained from scratch on VOC 2012 trainval.”
Scalable, High-Quality Object Detection (2014, neutral): “Szegedy et al. [21] demonstrated effective use of deep neural networks for object detection formulated as a regression onto bounding box masks.”
Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019 (2019, neutral): “) [62, 63, 64].”
Deep learning in neural networks: An overview (2014, background): “Compare also CNN-based work on object detection (Szegedy et al., 2013) and scene parsing (Farabet et al.”
Recent advances in convolutional neural networks (2015, background): “Since 2012, the huge success of CNNs in ImageNet challenge [6] rekindles interest in CNN-based object detection [121–127].”
Self-Driving Car Steering Angle Prediction Based on Image Recognition (2019, background): “Recently, more attempts on using deep CNNs and RNNs to tackle the challenges of video classification [9], scene parsing [4], and object detection [17] have stimulated the applications of more complicated CNN architectures in autonomous driving.”
Rule Extraction Algorithm for Deep Neural Networks: A Review (2016, background): “As well as, the significant result has been achieved for object detection [7], [8].”