Context-Aware Single-Shot Detector

@article{Xiang2018ContextAwareSD,
  title={Context-Aware Single-Shot Detector},
  author={Wei Xiang and Dong-Qing Zhang and Vassilis Athitsos and Hong Heather Yu},
  journal={2018 IEEE Winter Conference on Applications of Computer Vision (WACV)},
  year={2018},
  pages={1784-1793}
}
  • Wei Xiang, Dong-Qing Zhang, H. Yu
  • Published 27 July 2017
  • Computer Science
  • 2018 IEEE Winter Conference on Applications of Computer Vision (WACV)
SSD (Single Shot Detector) is one of the state-of-the-art object detection algorithms, and it combines high detection accuracy with real-time speed. However, it is widely recognized that SSD is less accurate in detecting small objects compared to large objects, because it ignores the context from outside the proposal boxes. In this paper, we present CSSD–a shorthand for context-aware single-shot multibox object detector. CSSD is built on top of SSD, with additional layers modeling multi-scale… 

Figures and Tables from this paper

Detecting Small Objects in Thermal Images Using Single-Shot Detector
TLDR
DDSSD (Dilation and Deconvolution Single Shot Multibox Detector), an enhanced SSD with a novel feature fusion module which can improve the performance over SSD for small object detection, outperforming a lot of state-of theart object detection algorithms in both aspects of accuracy and speed.
Multi-flow Sub-network and Multiple Connections for Single Shot Detection
TLDR
A multi-flow sub-network and multiple connections for single shot detection (MSSD), which is built upon a one-stage strategy to inherit the computational efficiency and improve the detection accuracy.
Weaving Multi-scale Context for Single Shot Detector
TLDR
A novel network topology, called WeaveNet, is proposed that can efficiently fuse multi-scale information and boost the detection accuracy with negligible extra cost and is easy to train without requiring batch normalization and can be further accelerated by the proposed architecture simplification.
StairNet: Top-Down Semantic Aggregation for Accurate One Shot Detection
TLDR
The final model StairNet detector unifies the multi-scale representations and semantic distribution effectively and significantly improves the weakness of SSD and outperforms the other state-of-the-art one-stage detectors.
Gated bidirectional feature pyramid network for accurate one-shot detection
TLDR
The gated bidirectional feature pyramid network (GBFPN), a simple and effective architecture that provides a significant improvement over the baseline model, StairNet, shows state-of-the-art results.
Adaptive Multi-Scale Information Flow for Object Detection
TLDR
A novel module named Adaptive Multi-Scale Information Flow (ASIF) is presented to break the bias and find the proper multi-scale representation for each layer of the feature pyramid to ensure both speed and accuracy.
Better to Follow, Follow to Be Better: Towards Precise Supervision of Feature Super-Resolution for Small Object Detection
TLDR
A novel feature-level super-resolution approach is proposed that not only correctly addresses these two desiderata but also is integrable with any proposal-based detectors with feature pooling and achieves new state-of-the-art performance on Tsinghua-Tencent 100K and highly competitive results on both PASCAL VOC and MS COCO.
Densely convolutional and feature fused object detector
TLDR
The proposed deep convolutional network, DCFF-Net, which is a one-stage object detector from scratch similarly to DSOD has better detection performance by the aid of the fusion of different layers’ feature maps, especially on small objects and occluded objects.
MSF-ACNN: multi-scale feature fusion atrous convolutional neural networks for pedestrian fine-grained attribution detection
TLDR
This paper proposes a novel CNN-based framework for improving the accuracy of small objects detection, dubbed MSF-ACNN, using atrous convolutions in cascade along with multi-scale feature fusion, which can obtain better mean average precision (mAP) than the current state-of-the-art methods.
FHEDN: A based on context modeling Feature Hierarchy Encoder-Decoder Network for face detection
TLDR
A based on context modeling structure named Feature Hierarchy Encoder-Decoder Network for face detection (FHEDN), which can detect small, blur and occluded face with hierarchy by hierarchy from the end to the beginning likes encoder-decoder in a single network.
...
1
2
3
...

References

SHOWING 1-10 OF 37 REFERENCES
DSSD : Deconvolutional Single Shot Detector
TLDR
This paper combines a state-of-the-art classifier with a fast detection framework and augments SSD+Residual-101 with deconvolution layers to introduce additional large-scale context in object detection and improve accuracy, especially for small objects.
SSD: Single Shot MultiBox Detector
TLDR
The approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature map location, which makes SSD easy to train and straightforward to integrate into systems that require a detection component.
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.
R-FCN: Object Detection via Region-based Fully Convolutional Networks
TLDR
This work presents region-based, fully convolutional networks for accurate and efficient object detection, and proposes position-sensitive score maps to address a dilemma between translation-invariance in image classification and translation-variance in object detection.
Feature Pyramid Networks for Object Detection
TLDR
This paper exploits the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost and achieves state-of-the-art single-model results on the COCO detection benchmark without bells and whistles.
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.
Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks
TLDR
The Inside-Outside Net (ION), an object detector that exploits information both inside and outside the region of interest, provides strong evidence that context and multi-scale representations improve small object detection.
Microsoft COCO: Common Objects in Context
We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene
A MultiPath Network for Object Detection
TLDR
Three modifications to the standard Fast R-CNN object detector are tested, including a skip connections that give the detector access to features at multiple network layers, a foveal structure to exploit object context at multiple object resolutions, and an integral loss function and corresponding network adjustment that improve localization.
...
1
2
3
4
...