CRAFT Objects from Images

@article{Yang2016CRAFTOF,
  title={CRAFT Objects from Images},
  author={Bin Yang and Junjie Yan and Zhen Lei and S. Li},
  journal={2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2016},
  pages={6043-6051}
}
  • Bin Yang, Junjie Yan, S. Li
  • Published 12 April 2016
  • Computer Science
  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Object detection is a fundamental problem in image understanding. One popular solution is the R-CNN framework [15] and its fast versions [14, 27]. They decompose the object detection problem into two cascaded easier tasks: 1) generating object proposals from images, 2) classifying proposals into various object categories. Despite that we are handling with two relatively easier tasks, they are not solved perfectly and there's still room for improvement. In this paper, we push the "divide and… 

Figures and Tables from this paper

C-FCN: Corners-based fully convolutional network for visual object detection
TLDR
An anchor-free proposal generator named corner region proposal network (CRPN) which is based on a pair of key-points, including top-left corner and bottom-right corner of an object bounding box is proposed, achieving an end-to-end object detection.
A Region-Based Efficient Network for Accurate Object Detection
TLDR
A region-baed efficient network for accurate object detection in images that achieved robust overall detection efficiency over existing approaches using fewer or more proposals, in terms of recall, mean average best overlap (MABO), and mean average precision (mAP).
Revisiting Faster R-CNN: A Deeper Look at Region Proposal Network
TLDR
A novel object detection network is proposed to address problems in Faster R-CNN, including coarseness of feature maps for accurate localization, fixed-window feature extraction in RPN and insensitivity for small scale objects.
Crafting GBD-Net for Object Detection
TLDR
This paper proposes a gated bi-directional CNN (GBD-Net) to pass messages among features from different support regions during both feature learning and feature extraction, and shows the effectiveness of different network structures and existing techniques for object detection.
Learning Open-World Object Proposals Without Learning to Classify
TLDR
A classification-free Object Localization Network (OLN) which estimates the objectness of each region purely by how well the location and shape of a region overlap with any ground-truth object (e.g., centerness and IoU).
Dual Refinement Network for Single-Shot Object Detection
TLDR
A dual refinement network (DRN) is proposed to boost the performance of the single-stage detector and a multi-deformable head is designed, in which multiple detection paths with different receptive field sizes devote themselves to detecting objects.
Object Recognition with Videos Student :
TLDR
This project attempts to address temporal information at the feature and proposal level, as well as improving the post-processing efficiency of ImageNet VID task to increase the mean Average Precision under the setting of Image net VID task.
COMP 4801 – Interim Report Object Recognition with Videos
TLDR
This project attempts to address two issues through three proposed modifications, with an objective to increase the mean Average Precision for on ImageNet VID task.
Learning to Separate: Detecting Heavily-Occluded Objects in Urban Scenes
TLDR
A Non-Maximum-Suppression algorithm is proposed that dramatically improves the detection recall while maintaining high precision in scenes with heavy occlusions, derived from a novel embedding mechanism, in which the semantic and geometric features of the detected boxes are jointly exploited.
...
...

References

SHOWING 1-10 OF 49 REFERENCES
Object detection by labeling superpixels
TLDR
This paper takes object detection as a multi-label superpixel labeling problem by minimizing an energy function and uses the data cost term to capture the appearance, smooth cost terms to encode the spatial context and label costterm to favor compact detection.
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%.
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.
Instance-Aware Semantic Segmentation via Multi-task Network Cascades
  • Jifeng Dai, Kaiming He, Jian Sun
  • Computer Science
    2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
TLDR
This paper presents Multitask Network Cascades for instance-aware semantic segmentation, which consists of three networks, respectively differentiating instances, estimating masks, and categorizing objects, and develops an algorithm for the nontrivial end-to-end training of this causal, cascaded structure.
DeepID-Net: Deformable deep convolutional neural networks for object detection
TLDR
The proposed approach improves the mean averaged precision obtained by RCNN, which was the state-of-the-art, from 31% to 50.3% on the ILSVRC2014 detection test set.
DeepBox: Learning Objectness with Convolutional Networks
TLDR
This work argues for a data-driven, semantic approach for ranking object proposals, which uses convolutional neural networks to rerank proposals from a bottom-up method, and uses a novel four-layer CNN architecture that is as good as much larger networks on the task of evaluating objectness while being much faster.
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.
DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection
TLDR
A set of models with large diversity are obtained, which significantly improves the effectiveness of modeling averaging, and improves the mean averaged precision obtained by RCNN, which is the state of the art of object detection, from31% to 45%.
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.
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.
...
...