Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks

@article{Bell2016InsideOutsideND,
  title={Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks},
  author={Sean Bell and C. L. Zitnick and K. Bala and Ross B. Girshick},
  journal={2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2016},
  pages={2874-2883}
}
  • Sean Bell, C. L. Zitnick, +1 author Ross B. Girshick
  • Published 2016
  • Computer Science
  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • It is well known that contextual and multi-scale representations are important for accurate visual recognition. In this paper we present the Inside-Outside Net (ION), an object detector that exploits information both inside and outside the region of interest. Contextual information outside the region of interest is integrated using spatial recurrent neural networks. Inside, we use skip pooling to extract information at multiple scales and levels of abstraction. Through extensive experiments we… CONTINUE READING
    688 Citations
    Learning to detect and localize many objects from few examples
    • 5
    • Highly Influenced
    • PDF
    Combining the Best of Convolutional Layers and Recurrent Layers: A Hybrid Network for Semantic Segmentation
    • 28
    • PDF
    Region average pooling for context-aware object detection
    • 7
    • PDF
    Learning Object Detectors from Scratch with Gated Recurrent Feature Pyramids
    • 27
    • PDF
    Context Learning Network for Object Detection
    • 1
    • Highly Influenced
    Attentive Contexts for Object Detection
    • 108
    • PDF
    RON: Reverse Connection with Objectness Prior Networks for Object Detection
    • 227
    • PDF
    Multi-scale Fusion with Context-aware Network for Object Detection
    • 2
    • Highly Influenced
    Pyramid context learning for object detection
    Revisiting Faster R-CNN: A Deeper Look at Region Proposal Network
    • 5

    References

    SHOWING 1-10 OF 52 REFERENCES
    ParseNet: Looking Wider to See Better
    • 634
    • Highly Influential
    • PDF
    Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
    • 11,946
    • PDF
    Fully Convolutional Networks for Semantic Segmentation
    • 7,734
    • Highly Influential
    • PDF
    Return of the Devil in the Details: Delving Deep into Convolutional Nets
    • 2,662
    • PDF
    Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
    • 19,581
    • PDF
    You Only Look Once: Unified, Real-Time Object Detection
    • 9,378
    • PDF
    HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection
    • 460
    • PDF
    Object Detection via a Multi-region and Semantic Segmentation-Aware CNN Model
    • 473
    • PDF
    Microsoft COCO: Common Objects in Context
    • 10,912
    • PDF