Proceedings ArticleDOI
BiCoS: A Bi-level co-segmentation method for image classification
Yuning Chai,Victor Lempitsky,Andrew Zisserman +2 more
- pp 2579-2586
TLDR
A new scalable, alternation-based algorithm for co-segmentation, BiCoS, is introduced, which is simpler than many of its predecessors, and yet has superior performance on standard benchmark image datasets.Abstract:
The objective of this paper is the unsupervised segmentation of image training sets into foreground and background in order to improve image classification performance. To this end we introduce a new scalable, alternation-based algorithm for co-segmentation, BiCoS, which is simpler than many of its predecessors, and yet has superior performance on standard benchmark image datasets.read more
Citations
More filters
Posted Content
CNN Features off-the-shelf: an Astounding Baseline for Recognition
TL;DR: A series of experiments conducted for different recognition tasks using the publicly available code and model of the OverFeat network which was trained to perform object classification on ILSVRC13 suggest that features obtained from deep learning with convolutional nets should be the primary candidate in most visual recognition tasks.
Proceedings ArticleDOI
Cats and dogs
TL;DR: These models are very good: they beat all previously published results on the challenging ASIRRA test (cat vs dog discrimination) when applied to the task of discriminating the 37 different breeds of pets, and obtain an average accuracy of about 59%, a very encouraging result considering the difficulty of the problem.
Book ChapterDOI
What’s the Point: Semantic Segmentation with Point Supervision
TL;DR: This work takes a natural step from image-level annotation towards stronger supervision: it asks annotators to point to an object if one exists, and incorporates this point supervision along with a novel objectness potential in the training loss function of a CNN model.
Book ChapterDOI
Segmentation propagation in imagenet
TL;DR: This paper proposes to automatically populate ImageNet with pixelwise segmentations, by leveraging existing manual annotations in the form of class labels and bounding-boxes, and effectively exploits the hierarchical structure of ImageNet.
Proceedings ArticleDOI
Fine-grained recognition without part annotations
TL;DR: This work proposes a method for fine-grained recognition that uses no part annotations, based on generating parts using co-segmentation and alignment, which is combined in a discriminative mixture.
References
More filters
Proceedings ArticleDOI
Object recognition from local scale-invariant features
TL;DR: Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.
Journal ArticleDOI
Efficient Graph-Based Image Segmentation
TL;DR: An efficient segmentation algorithm is developed based on a predicate for measuring the evidence for a boundary between two regions using a graph-based representation of the image and it is shown that although this algorithm makes greedy decisions it produces segmentations that satisfy global properties.
Journal ArticleDOI
"GrabCut": interactive foreground extraction using iterated graph cuts
TL;DR: A more powerful, iterative version of the optimisation of the graph-cut approach is developed and the power of the iterative algorithm is used to simplify substantially the user interaction needed for a given quality of result.
Proceedings ArticleDOI
Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images
Yuri Boykov,Marie-Pierre Jolly +1 more
TL;DR: In this paper, the user marks certain pixels as "object" or "background" to provide hard constraints for segmentation, and additional soft constraints incorporate both boundary and region information.
Proceedings ArticleDOI
Vlfeat: an open and portable library of computer vision algorithms
Andrea Vedaldi,Brian Fulkerson +1 more
TL;DR: VLFeat is an open and portable library of computer vision algorithms that includes rigorous implementations of common building blocks such as feature detectors, feature extractors, (hierarchical) k-means clustering, randomized kd-tree matching, and super-pixelization.
Related Papers (5)
Automated Flower Classification over a Large Number of Classes
M.-E. Nilsback,Andrew Zisserman +1 more