Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

@article{Girshick2014RichFH,
  title={Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation},
  author={Ross B. Girshick and Jeff Donahue and Trevor Darrell and Jitendra Malik},
  journal={2014 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2014},
  pages={580-587}
}
Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. [...] Key Method Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost.Expand
View on IEEE
arxiv.org
15,286 Citations
Highly Influential Citations
2,065
Background Citations
5,110
Methods Citations
5,718
Results Citations
137

15,286 Citations

Citation Type

Citation Type

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. Expand
Improve object detection via a multi-feature and multi-task CNN model
TLDR
An object detection system based on standard Fast R-CNN object detection branch and DeepLap semantic segmentation branch that multi-feature aggregates hierarchical features for more finer feature maps to detect objects at multiple scales and a novel overlap loss function is used for bounding box regression to improve localization. Expand
Boosting Convolutional Features for Robust Object Proposals
TLDR
A boosting approach is proposed which directly takes advantage of hierarchical CNN features for detecting regions of interest fast and is demonstrated on ImageNet 2013 detection benchmark and compared with state-of-the-art methods. Expand
CNN based region proposals for efficient object detection
TLDR
A high-confidence region-based object detection framework that boosts up the classification performance with less computational burden, and significantly reduces the computational complexity and improves the performance in object detection. Expand
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. Expand
Simultaneous Detection and Segmentation
TLDR
This work builds on recent work that uses convolutional neural networks to classify category-independent region proposals (R-CNN), introducing a novel architecture tailored for SDS, and uses category-specific, top-down figure-ground predictions to refine the bottom-up proposals. Expand
Object proposals using CNN-based edge filtering
TLDR
This paper proposes a novel idea of filtering irrelevant edges using semantic image filtering and true objectness learnt within convolutional layers of CNN, and localizes well proposals by producing highly accurate bounding boxes and reduces the number of proposals. Expand
Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks
TLDR
Convolutional Oriented Boundaries gives a significant leap in performance over the state-of-the-art, and generalizes very well to unseen categories and datasets, and learning to estimate not only contour strength but also orientation provides more accurate results. Expand
Exploit Bounding Box Annotations for Multi-Label Object Recognition
TLDR
This paper first extracts object proposals from each image, then proposes to make use of ground-truth bounding box annotations (strong labels) to add another level of local information by using nearest-neighbor relationships of local regions to form a multi-view pipeline. Expand
Semi-supervised exemplar learning for object detection in aerial imagery
TLDR
A semi-supervised approach that combines the strengths of CNN structures with pre-processing steps borrowed from exemplar learning is employed, which combines the ability to use generically-learned class-relatedness with CNN-based detectors. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 64 REFERENCES
Learning Hierarchical Features for Scene Labeling
TLDR
A method that uses a multiscale convolutional network trained from raw pixels to extract dense feature vectors that encode regions of multiple sizes centered on each pixel, alleviates the need for engineered features, and produces a powerful representation that captures texture, shape, and contextual information. Expand
Regionlets for Generic Object Detection
TLDR
This work proposes to model an object class by a cascaded boosting classifier which integrates various types of features from competing local regions, named as region lets, which significantly outperforms the state-of-the-art on popular multi-class detection benchmark datasets with a single method. Expand
Bottom-Up Segmentation for Top-Down Detection
TLDR
A novel deformable part-based model which exploits region-based segmentation algorithms that compute candidate object regions by bottom-up clustering followed by ranking of those regions that outperform the previous state-of-the-art on VOC 2010 test by 4%. Expand
Semantic segmentation using regions and parts
TLDR
A novel design for region-based object detectors that integrates efficiently top-down information from scanning-windows part models and global appearance cues is proposed that produces class-specific scores for bottom-up regions, and then aggregate the votes of multiple overlapping candidates through pixel classification. Expand
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. Expand
Boosted local structured HOG-LBP for object localization
TLDR
This paper proposes a boosted Local Structured HOG-LBP based object detector to capture the object's local structure, and develop the descriptors from shape and texture information, respectively, and presents a boosted feature selection and fusion scheme for part based object detectors. Expand
Measuring the Objectness of Image Windows
TLDR
A generic objectness measure, quantifying how likely it is for an image window to contain an object of any class, and uses objectness as a complementary score in addition to the class-specific model, which leads to fewer false positives. Expand
CPMC: Automatic Object Segmentation Using Constrained Parametric Min-Cuts
TLDR
A novel framework to generate and rank plausible hypotheses for the spatial extent of objects in images using bottom-up computational processes and mid-level selection cues and it is shown that the algorithm can be used, successfully, in a segmentation-based visual object category recognition pipeline. Expand
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. Expand
The Pascal Visual Object Classes (VOC) Challenge
TLDR
The state-of-the-art in evaluated methods for both classification and detection are reviewed, whether the methods are statistically different, what they are learning from the images, and what the methods find easy or confuse. Expand
...
1
2
3
4
5
...