To insert individual citation into a bibliography in a word-processor,
select your preferred citation style below and drag-and-drop it into the document.
The goal of this paper is to discover a set of discriminative patches which can serve as a fully unsupervised mid-level visual representation. The desired patches need to satisfy two requirements: 1) to be representative, they need to occur frequently enough in the visual world; 2) to be discriminative, they need to be different enough from the rest of the visual world. The patches could correspond to parts, objects, “visual phrases”, etc. but are not restricted to be any one of them. We pose this as an unsupervised discriminative clustering problem on a huge dataset of image patches. We use an iterative procedure which alternates between clustering and training discriminative classifiers, while applying careful cross-validation at each step to prevent overfitting. The paper experimentally demonstrates the effectiveness of discriminative patches as an unsupervised mid-level visual representation, suggesting that it could be used in place of visual words for many tasks. Furthermore, discriminative patches can also be used in a supervised regime, such as scene classification, where they demonstrate state-of-the-art performance on the MIT Indoor-67 dataset.
A new approach for building discriminative dictionaries is presented. The core idea is to use discrimiative clustering, which turns out to be a simple algorithm that starts with k-means followed by svm classifiers trained to recognize clusters. Two interesting steps are proposed in this paper to come up with coherent and useful dictionaries: first, the use of cross validation to avoid overfitting. Second, turning classifiers in detectors that operate in the validation set (space and scale) to find new cluster members.
The proposed approach seems simple and promising, though it has several details to be careful about. So, I wonder if there is a more principled way to formulate this algorithm on the first place, and second, how can we extend this idea to learn better object detectors.
CiteULike organises scholarly (or academic) papers or literature and provides bibliographic
(which means it makes bibliographies) for universities and higher education establishments.
It helps undergraduates and postgraduates. People studying for PhDs or in postdoctoral (postdoc) positions.
The service is similar in scope to EndNote or RefWorks or any other reference manager
like BibTeX, but it is a social bookmarking service for scientists and humanities researchers.
Notes for this article
There are no reviews yet
