Simultaneous Detection and Segmentation
Bharath Hariharan, Pablo Arbeláez, Ross Girshick et al. · arXiv (Cornell University) · 2014
We aim to detect all instances of a category in an image and, for each instance, mark the pixels that belong to it. We call this task Simultaneous Detection and Segmentation (SDS). Unlike classical bounding box detection, SDS requires a segmentation and not just a box. Unlike classical semantic segmentation, we require individual object instances. 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 state-of-the-art on semantic segmentation, and state-of-the-art performance in object detection. Finally, we provide diagnostic tools that unpack performance and provide directions for future work.
Cited by 161 works. doi:10.48550/arxiv.1407.1808 Open-access PDF
Authors
References
- Distinctive Image Features from Scale-Invariant Keypoints
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
- Backpropagation Applied to Handwritten Zip Code Recognition
- Histograms of Oriented Gradients for Human Detection
- The Pascal Visual Object Classes (VOC) Challenge
- Object Detection with Discriminatively Trained Part-Based Models
- Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position
- DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
- Learning Hierarchical Features for Scene Labeling
- Segmentation as selective search for object recognition