Results 1 -
7 of
7
Shifting Weights: Adapting Object Detectors from Image to Video
"... Typical object detectors trained on images perform poorly on video, as there is a clear distinction in domain between the two types of data. In this paper, we tackle the problem of adapting object detectors learned from images to work well on videos. We treat the problem as one of unsupervised domai ..."
Abstract
-
Cited by 12 (2 self)
- Add to MetaCart
(Show Context)
Typical object detectors trained on images perform poorly on video, as there is a clear distinction in domain between the two types of data. In this paper, we tackle the problem of adapting object detectors learned from images to work well on videos. We treat the problem as one of unsupervised domain adaptation, in which we are given labeled data from the source domain (image), but only unlabeled data from the target domain (video). Our approach, self-paced domain adaptation, seeks to iteratively adapt the detector by re-training the detector with automatically discovered target domain examples, starting with the easiest first. At each iteration, the algorithm adapts by considering an increased number of target domain examples, and a decreased number of source domain examples. To discover target domain examples from the vast amount of video data, we introduce a simple, robust approach that scores trajectory tracks instead of bounding boxes. We also show how rich and expressive features specific to the target domain can be incorporated under the same framework. We show promising results on the 2011 TRECVID Multimedia Event Detection [1] and LabelMe Video [2] datasets that illustrate the benefit of our approach to adapt object detectors to video. 1
Efficient Optimization for Low-Rank Integrated Bilinear Classifiers
"... Abstract. In pattern classification, it is needed to efficiently treat twoway data (feature matrices) while preserving the two-way structure such as spatio-temporal relationships, etc. The classifier for the feature matrix is generally formulated by multiple bilinear forms which result in a matrix. ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
Abstract. In pattern classification, it is needed to efficiently treat twoway data (feature matrices) while preserving the two-way structure such as spatio-temporal relationships, etc. The classifier for the feature matrix is generally formulated by multiple bilinear forms which result in a matrix. The rank of the matrix, i.e., the number of bilinear forms, should be low from the viewpoint of generalization performance and computational cost. For that purpose, we propose a low-rank bilinear classifier based on the efficient optimization. In the proposed method, the classifier is optimized by minimizing the trace norm of the classifier (matrix), which contributes to the rank reduction for an efficient classifier without any hard constraint on the rank. We formulate the optimization problem in a tractable convex form and propose the procedure to solve it efficiently with the global optimum. In addition, by considering a kernelbased extension of the bilinear method, we induce a novel multiple kernel learning (MKL), called heterogeneous MKL. The method combines both inter kernels between heterogeneous types of features and the ordinary kernels within homogeneous features into a new discriminative kernel in a unified manner using the bilinear model. In the experiments on various classification problems using feature arrays, co-occurrence feature matrices, and multiple kernels, the proposed method exhibits favorable performances compared to the other methods. 1
Efficient Similarity Derived from Kernel-Based Transition Probability
"... Abstract. Semi-supervised learning effectively integrates labeled and unlabeled samples for classification, and most of the methods are founded on the pair-wise similarities between the samples. In this paper, we propose methods to construct similarities from the probabilistic viewpoint, whilst the ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
Abstract. Semi-supervised learning effectively integrates labeled and unlabeled samples for classification, and most of the methods are founded on the pair-wise similarities between the samples. In this paper, we propose methods to construct similarities from the probabilistic viewpoint, whilst the similarities have so far been formulated in a heuristic manner such as by k-NN. We first propose the kernel-based formulation of transition probabilities via considering kernel least squares in the probabilistic framework. The similarities are consequently derived from the kernel-based transition probabilities which are efficiently computed, and the similarities are inherently sparse without applying k-NN. In the case of multiple types of kernel functions, the multiple transition probabilities are also obtained correspondingly. From the probabilistic viewpoint, they can be integrated with prior probabilities, i.e., linear weights, and we propose a computationally efficient method to optimize the weights in a discriminative manner, as in multiple kernel learning. The novel similarity is thereby constructed by the composite transition probability and it benefits the semi-supervised learning methods as well. In the various experiments on semi-supervised learning problems, the proposed methods demonstrate favorable performances, compared to the other methods, in terms of classification performances and computation time. 1
Bayesian Fusion for Multi-Modal Aerial Images
"... Abstract—This paper presents a fusion method to combine aerial images from a low flying Unmanned Aerial Vehicle (UAV) with images of other spectral bands from sources such as satellites or commercial hyperspectral imagers. The proposed method propagates information from high-resolution images into o ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract—This paper presents a fusion method to combine aerial images from a low flying Unmanned Aerial Vehicle (UAV) with images of other spectral bands from sources such as satellites or commercial hyperspectral imagers. The proposed method propagates information from high-resolution images into other low-resolution modalities while allowing the images to have different spectral channels. This means the relationship between the high-resolution and low-resolution channels is expected to be non-deterministic, non-linear and non-stationary. A novel Gaussian Process (GP) framework was developed to define a stochastic prior over the estimated images. Its covariance function is computed to replicate the local structure of the high-resolution image, and allows the model to infer a high-resolution estimate from a low-resolution channel. Results are presented for natural images acquired by a UAV in a farmland mapping application. I.
KHAMIS, LAMPERT: CO-CLASSIFICATION WITH OUTPUT SPACE REGULARIZATION 1 CoConut: Co-Classification with Output Space Regularization
"... In this work we introduce a new approach to co-classification, i.e. the task of jointly classifying multiple, otherwise independent, data samples. The method we present, named CoConut, is based on the idea of adding a regularizer in the label space to en-code certain priors on the resulting labeling ..."
Abstract
- Add to MetaCart
(Show Context)
In this work we introduce a new approach to co-classification, i.e. the task of jointly classifying multiple, otherwise independent, data samples. The method we present, named CoConut, is based on the idea of adding a regularizer in the label space to en-code certain priors on the resulting labelings. A regularizer that encourages labelings that are smooth across the test set, for instance, can be seen as a test-time variant of the cluster assumption, which has been proven useful at training time in semi-supervised learning. A regularizer that introduces a preference for certain class proportions can be regarded as a prior distribution on the class labels. CoConut can build on existing classi-fiers without making any assumptions on how they were obtained and without the need to re-train them. The use of a regularizer adds a new level of flexibility. It allows the in-tegration of potentially new information at test time, even in other modalities than what the classifiers were trained on. We evaluate our framework on six datasets, reporting a clear performance gain in classification accuracy compared to the standard classification setup that predicts labels for each test sample separately. 1
Similarity measure
, 2013
"... transition probability toward similarity measure for semi-supervised learning ..."
Abstract
- Add to MetaCart
(Show Context)
transition probability toward similarity measure for semi-supervised learning
Low-Rank Bilinear Classification: Efficient Convex Optimization and Extensions
, 2013
"... Your article is protected by copyright and all rights are held exclusively by Springer Science +Business Media New York. This e-offprint is for personal use only and shall not be self-archived in electronic repositories. If you wish to self-archive your article, please use the accepted manuscript ve ..."
Abstract
- Add to MetaCart
Your article is protected by copyright and all rights are held exclusively by Springer Science +Business Media New York. This e-offprint is for personal use only and shall not be self-archived in electronic repositories. If you wish to self-archive your article, please use the accepted manuscript version for posting on your own website. You may further deposit the accepted manuscript version in any repository, provided it is only made publicly available 12 months after official publication or later and provided acknowledgement is given to the original source of publication and a link is inserted to the published article on Springer's website. The link must be accompanied by the following text: "The final publication is available at link.springer.com”.
