G-CNN: An Iterative Grid Based Object Detector

@article{Najibi2016GCNNAI,
  title={G-CNN: An Iterative Grid Based Object Detector},
  author={Mahyar Najibi and Mohammad Rastegari and Larry S. Davis},
  journal={2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2016},
  pages={2369-2377}
}
We introduce G-CNN, an object detection technique based on CNNs which works without proposal algorithms. [] Key Method We train a regressor to move and scale elements of the grid towards objects iteratively. G-CNN models the problem of object detection as finding a path from a fixed grid to boxes tightly surrounding the objects. G-CNN with around 180 boxes in a multi-scale grid performs comparably to Fast R-CNN which uses around 2K bounding boxes generated with a proposal technique. This strategy makes…

Figures and Tables from this paper

Flow R-CNN: Flow-Enhanced Object Detection
This work addresses the problem of multi-task object detection in an efficient, generic but at the same time simple way, following the recent and highly promising studies in the computer vision
Improvement for Fast Object Detection Based on Regression Method
TLDR
Object detection for 2D image based on convolutional neural networks(CNN) has witnessed a conspicuous development in recent five years, and Fully Convolution Network (FCN), not only demonstrated effective on semantic segmentation task, but also more efficient in computing.
PBG-Net: Object detection with a multi-feature and iterative CNN model
TLDR
PBG-Net, an object detection system based on an elaborately designed multi-feature deep CNN which works without proposal algorithms, is introduced and an iterative regression localization model based on a novel overlap loss function and online hard boxes selection is exploited.
A detection method for low-pixel ratio object
TLDR
This framework improves Faster R-CNN by combining multiple level feature map and optimizing anchor size for bounding box recognition and outperforms other state-of-the-art detection methods on low-pixel ratio object detection.
Attend Refine Repeat: Active Box Proposal Generation via In-Out Localization
TLDR
This work proposes a new approach to tackle the problem of computing category agnostic bounding box proposals based on an active strategy for generating box proposals that starts from a set of seed boxes, which are uniformly distributed on the image, and then progressively moves its attention on the promising image areas where it is more likely to discover well localized boundingbox proposals.
Improving Object Detection with Convolutional Neural Network via Iterative Mechanism
TLDR
This paper trains an iterative version of Faster RCNN to show the application of the iterative mechanism in improving the localization accuracy and presents a prototype CNN model that iteratively searches for objects on a very simple dataset to generate proposals.
Acquisition of Localization Confidence for Accurate Object Detection
TLDR
IoU-Net learning to predict the IoU between each detected bounding box and the matched ground-truth is proposed, which improves the NMS procedure by preserving accurately localized bounding boxes.
Towards the Success Rate of One: Real-Time Unconstrained Salient Object Detection
TLDR
This work proposes an efficient and effective approach for unconstrained salient object detection in images using deep convolutional neural networks, which performs saliency map prediction without pixel-level annotations, salient object Detection without object proposals, and salient object subitizing simultaneously, all in a single pass within a unified framework.
Multistage Object Detection With Group Recursive Learning
TLDR
A new EM-like group recursive learning approach to iteratively refine object proposals by incorporating such context of surrounding proposals and provide an optimal spatial configuration of object detections is proposed.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 31 REFERENCES
AttentionNet: Aggregating Weak Directions for Accurate Object Detection
TLDR
AttentionNet is presented, a novel detection method using a deep convolutional neural network, named AttentionNet, which detects objects without any separated models from the object proposal to the post bounding-box regression.
R-CNN minus R
TLDR
This paper designs and evaluates a detector that uses a trivial region generation scheme, constant for each image, and results in an excellent and fast detector that does not require to process an image with algorithms other than the CNN itself.
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TLDR
This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.
Region-Based Convolutional Networks for Accurate Object Detection and Segmentation
TLDR
A simple and scalable detection algorithm that improves mean average precision (mAP) by more than 50 percent relative to the previous best result on VOC 2012-achieving a mAP of 62.4 percent.
Fast R-CNN
  • Ross B. Girshick
  • Computer Science, Environmental Science
    2015 IEEE International Conference on Computer Vision (ICCV)
  • 2015
This paper proposes a Fast Region-based Convolutional Network method (Fast R-CNN) for object detection. Fast R-CNN builds on previous work to efficiently classify object proposals using deep
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.
Contextual Models for Object Detection Using Boosted Random Fields
TLDR
This work introduces Boosted Random Fields (BRFs), which uses Boosting to learn the graph structure and local evidence of a conditional random field (CRF) and applies it to detect stuff and things in office and street scenes.
Object Detection Using Strongly-Supervised Deformable Part Models
TLDR
This method is able to deal with sub-optimal and incomplete annotations of object parts and is shown to benefit from semi-supervised learning setups where part-level annotation is provided for a fraction of positive examples only.
You Only Look Once: Unified, Real-Time Object Detection
TLDR
Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.
...
1
2
3
4
...