Improving object detection with deep convolutional networks via Bayesian optimization and structured prediction

@article{Zhang2015ImprovingOD,
  title={Improving object detection with deep convolutional networks via Bayesian optimization and structured prediction},
  author={Y. Zhang and Kihyuk Sohn and Ruben Villegas and Gang Pan and Honglak Lee},
  journal={2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2015},
  pages={249-258}
}
  • Y. Zhang, Kihyuk Sohn, Honglak Lee
  • Published 13 April 2015
  • Computer Science
  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Object detection systems based on the deep convolutional neural network (CNN) have recently made ground-breaking advances on several object detection benchmarks. While the features learned by these high-capacity neural networks are discriminative for categorization, inaccurate localization is still a major source of error for detection. Building upon high-capacity CNN architectures, we address the localization problem by 1) using a search algorithm based on Bayesian optimization that… 
Improving Region Based CNN Object Detector Using Bayesian Optimization
TLDR
This paper presents a sequential searching algorithm using Bayesian Optimization to propose better bounding boxes hence reducing localization error and demonstrates the state-of-the-art performance on PASCAL VOC 2007 benchmark under the standard localization requirements.
Improving object detection via improving accuracy of object localization
TLDR
This work combines a high-recall algorithm proposing candidate regions for an object bounding box with an algorithm reducing localization bias, and utilizing box alignment which penalizing deviation via taking object boundaries into account, to instruct the procedure of proposing input of CNN.
Improved Object Detection With Iterative Localization Refinement in Convolutional Neural Networks
TLDR
Simulations show that the proposed ILR method can improve the main state-of-the-art works on the PASCAL VOC 2007, 2012 and Youtube-Objects data sets and can be incorporated with many existing CNN-based object detection algorithms to enhance the detection accuracy without changing their configurations.
Object Detection via a Multi-region and Semantic Segmentation-Aware CNN Model
TLDR
An object detection system that relies on a multi-region deep convolutional neural network that also encodes semantic segmentation-aware features that aims at capturing a diverse set of discriminative appearance factors and exhibits localization sensitivity that is essential for accurate object localization.
Adaptive Deep Convolutional Neural Networks for Scene-Specific Object Detection
TLDR
This paper proposes an efficient method to construct a scene-specific regression model based on a generic CNN-based classifier that achieves the best performance on three surveillance data sets for pedestrian detection and one surveillance data set for vehicle detection.
Object Detection With Deep Learning: A Review
TLDR
This paper provides a review of deep learning-based object detection frameworks and focuses on typical generic object detection architectures along with some modifications and useful tricks to improve detection performance further.
Weakly Supervised Localization Using Deep Feature Maps
TLDR
This paper proposes an efficient beam search based approach to detect and localize multiple objects in images and significantly outperforms the state-of-the-art in standard object localization data-sets.
Robust Vehicle Detection in Aerial Images Based on Cascaded Convolutional Neural Networks
TLDR
A CNN-based detection model combining two independent convolutional neural networks, where the first network is applied to generate a set of vehicle-like regions from multi-feature maps of different hierarchies and scales, yields high performance, not only in detection accuracy but also in detection speed.
DeepID-Net: Object Detection with Deformable Part Based Convolutional Neural Networks
TLDR
By changing the net structures, training strategies, adding and removing some key components in the detection pipeline, a set of models with large diversity are obtained, which significantly improves the effectiveness of model averaging.
Object Detection Using Deep Learning
TLDR
This paper proposes an efficient and an accurate object detection system using Deep Learning that makes use of Convolutional Neural Network algorithm to compute the images in a more perfect manner.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 71 REFERENCES
Structured Prediction for Object Detection in Deep Neural Networks
TLDR
This work proposes to adapt a structured loss function for neural network training which directly maximizes overlap of the prediction with ground truth bounding boxes, and shows how this structured loss can be implemented efficiently.
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TLDR
This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%.
Scalable Object Detection Using Deep Neural Networks
TLDR
This work proposes a saliency-inspired neural network model for detection, which predicts a set of class-agnostic bounding boxes along with a single score for each box, corresponding to its likelihood of containing any object of interest.
Deep Neural Networks for Object Detection
TLDR
This paper presents a simple and yet powerful formulation of object detection as a regression problem to object bounding box masks, and defines a multi-scale inference procedure which is able to produce high-resolution object detections at a low cost by a few network applications.
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
TLDR
This integrated framework for using Convolutional Networks for classification, localization and detection is the winner of the localization task of the ImageNet Large Scale Visual Recognition Challenge 2013 and obtained very competitive results for the detection and classifications tasks.
Learning to Localize Objects with Structured Output Regression
TLDR
This work proposes to treat object localization in a principled way by posing it as a problem of predicting structured data: it model the problem not as binary classification, but as the prediction of the bounding box of objects located in images.
Learning to localize detected objects
  • Qieyun Dai, Derek Hoiem
  • Computer Science
    2012 IEEE Conference on Computer Vision and Pattern Recognition
  • 2012
TLDR
This paper describes and evaluates several color models and edge cues for local predictions, and proposes two approaches for localization: learned graph cut segmentation and structural bounding box prediction.
Accurate Object Detection with Joint Classification-Regression Random Forests
TLDR
A novel object detection approach that is capable of regressing the aspect ratio of objects, which results in accurately predicted bounding boxes having high overlap with the ground truth and gives competitive results on standard detection benchmarks.
Very Deep Convolutional Networks for Large-Scale Image Recognition
TLDR
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Object Detection with Discriminatively Trained Part Based Models
We describe an object detection system based on mixtures of multiscale deformable part models. Our system is able to represent highly variable object classes and achieves state-of-the-art results in
...
1
2
3
4
5
...