Simultaneous Detection and Segmentation

@inproceedings{Hariharan2014SimultaneousDA,
  title={Simultaneous Detection and Segmentation},
  author={Bharath Hariharan and Pablo Arbel{\'a}ez and Ross B. Girshick and Jitendra Malik},
  booktitle={ECCV},
  year={2014}
}
  • Bharath Hariharan, Pablo Arbeláez, +1 author Jitendra Malik
  • Published in ECCV 2014
  • Computer Science
  • We aim to detect all instances of a category in an image and, for each instance, mark the pixels that belong to it. [...] Key Method We build on recent work that uses convolutional neural networks to classify category-independent region proposals (R-CNN [16]), introducing a novel architecture tailored for SDS. We then use category-specific, top-down figure-ground predictions to refine our bottom-up proposals. We show a 7 point boost (16% relative) over our baselines on SDS, a 5 point boost (10% relative) over…Expand Abstract

    Paper Mentions

    Region-Based Convolutional Networks for Accurate Object Detection and Segmentation
    • 1,036
    • Open Access
    Shape-aware Instance Segmentation
    • 18
    • Highly Influenced
    • Open Access
    Bridging Category-level and Instance-level Semantic Image Segmentation
    • 87
    • Highly Influenced
    • Open Access
    Beyond Bounding Boxes: Precise Localization of Objects in Images
    • 4
    • Open Access
    Region-Based Semantic Segmentation with End-to-End Training
    • 19
    • Highly Influenced
    • Open Access
    Boundary-Aware Instance Segmentation
    • 73
    • Highly Influenced
    • Open Access
    segDeepM: Exploiting segmentation and context in deep neural networks for object detection
    • 113
    • Open Access
    Deep Variational Instance Segmentation
    Segmentation is All You Need
    • 5
    • Open Access

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 39 REFERENCES
    Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
    • 11,328
    • Open Access
    Bottom-Up Segmentation for Top-Down Detection
    • 127
    • Highly Influential
    • Open Access
    Semantic segmentation using regions and parts
    • 283
    • Open Access
    Learning to localize detected objects
    • 47
    • Open Access
    Learning Hierarchical Features for Scene Labeling
    • 2,055
    • Open Access
    Segmentation as selective search for object recognition
    • 615
    • Highly Influential
    • Open Access
    OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
    • 3,602
    • Open Access
    What, Where and How Many? Combining Object Detectors and CRFs
    • 341
    • Open Access
    Constrained parametric min-cuts for automatic object segmentation
    • 469
    • Open Access
    Layered Object Models for Image Segmentation
    • 131
    • Open Access