Codemaps - Segment, Classify and Search Objects Locally
Zhenyang Li, Efstratios Gavves, Koen E. A. van de Sande et al. · IEEE International Conference on Computer Vision (ICCV) · 2013
In this paper we aim for segmentation and classification of objects. We propose codemaps that are a joint formulation of the classification score and the local neighborhood it belongs to in the image. We obtain the codemap by reordering the encoding, pooling and classification steps over lattice elements. Other than existing linear decompositions who emphasize only the efficiency benefits for localized search, we make three novel contributions. As a preliminary, we provide a theoretical generalization of the sufficient mathematical conditions under which image encodings and classification becomes locally decomposable. As first novelty we introduce l2 normalization for arbitrarily shaped image regions, which is fast enough for semantic segmentation using our Fisher codemaps. Second, using the same lattice across images, we propose kernel pooling which embeds nonlinearities into codemaps for object classification by explicit or approximate feature mappings. Results demonstrate that l2 normalized Fisher codemaps improve the state-of-the-art in semantic segmentation for PASCAL VOC. For object classification the addition of nonlinearities brings us on par with the state-of-the-art, but is 3x faster. Because of the codemaps' inherent efficiency, we can reach significant speed-ups for localized search as well. We exploit the efficiency gain for our third novelty: object seg- ment retrieval using a single query image only.
Cited by 15 works. doi:10.1109/iccv.2013.454 Open-access PDF
Authors
References
- ImageNet classification with deep convolutional neural networks
- ImageNet: A large-scale hierarchical image database
- Distinctive Image Features from Scale-Invariant Keypoints
- The Pascal Visual Object Classes (VOC) Challenge
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
- Selective Search for Object Recognition
- Video Google: a text retrieval approach to object matching in videos
- Learning with Kernels
- The Pascal Visual Object Classes Challenge: A Retrospective
- Visual categorization with bags of keypoints