1. |
- Afkham, Heydar Maboudi, et al.
(författare)
-
A topological framework for training latent variable models
- 2014
-
Ingår i: Proceedings - International Conference on Pattern Recognition. - 9781479952083 ; , s. 2471-2476
-
Konferensbidrag (refereegranskat)abstract
- We discuss the properties of a class of latent variable models that assumes each labeled sample is associated with a set of different features, with no prior knowledge of which feature is the most relevant feature to be used. Deformable-Part Models (DPM) can be seen as good examples of such models. These models are usually considered to be expensive to train and very sensitive to the initialization. In this paper, we focus on the learning of such models by introducing a topological framework and show how it is possible to both reduce the learning complexity and produce more robust decision boundaries. We will also argue how our framework can be used for producing robust decision boundaries without exploiting the dataset bias or relying on accurate annotations. To experimentally evaluate our method and compare with previously published frameworks, we focus on the problem of image classification with object localization. In this problem, the correct location of the objects is unknown, during both training and testing stages, and is considered as a latent variable.
|
|
2. |
- Afkham, Heydar Maboudi, et al.
(författare)
-
Gradual improvement of image descriptor quality
- 2014
-
Ingår i: ICPRAM 2014 - Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods. - : SCITEPRESS - Science and and Technology Publications. - 9789897580185 ; , s. 233-238
-
Konferensbidrag (refereegranskat)abstract
- In this paper, we propose a framework for gradually improving the quality of an already existing image descriptor. The descriptor used in this paper (Afkham et al., 2013) uses the response of a series of discriminative components for summarizing each image. As we will show, this descriptor has an ideal form in which all categories become linearly separable. While, reaching this form is not feasible, we will argue how by replacing a small fraction of these components, it is possible to obtain a descriptor which is, on average, closer to this ideal form. To do so, we initially identify which components do not contribute to the quality of the descriptor and replace them with more robust components. Here, a joint feature selection method is used to find improved components. As our experiments show, this change directly reflects in the capability of the resulting descriptor in discriminating between different categories.
|
|
3. |
- Afkham, Heydar Maboudi, et al.
(författare)
-
Initialization framework for latent variable models
- 2014
-
Ingår i: ICPRAM 2014 - Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods. - : SCITEPRESS - Science and and Technology Publications. - 9789897580185 ; , s. 227-232
-
Konferensbidrag (refereegranskat)abstract
- In this paper, we discuss the properties of a class of latent variable models that assumes each labeled sample is associated with set of different features, with no prior knowledge of which feature is the most relevant feature to be used. Deformable-Part Models (DPM) can be seen as good example of such models. While Latent SVM framework (LSVM) has proven to be an efficient tool for solving these models, we will argue that the solution found by this tool is very sensitive to the initialization. To decrease this dependency, we propose a novel clustering procedure, for these problems, to find cluster centers that are shared by several sample sets while ignoring the rest of the cluster centers. As we will show, these cluster centers will provide a robust initialization for the LSVM framework.
|
|
4. |
- Afkham, Heydar Maboudi, et al.
(författare)
-
Uncertainty estimation of predictions of peptides' chromatographic retention times in shotgun proteomics
- 2017
-
Ingår i: Bioinformatics. - : OXFORD UNIV PRESS. - 1367-4803 .- 1367-4811. ; 33:4, s. 508-513
-
Tidskriftsartikel (refereegranskat)abstract
- Motivation: Liquid chromatography is frequently used as a means to reduce the complexity of peptide-mixtures in shotgun proteomics. For such systems, the time when a peptide is released from a chromatography column and registered in the mass spectrometer is referred to as the peptide's retention time. Using heuristics or machine learning techniques, previous studies have demonstrated that it is possible to predict the retention time of a peptide from its amino acid sequence. In this paper, we are applying Gaussian Process Regression to the feature representation of a previously described predictor ELUDE. Using this framework, we demonstrate that it is possible to estimate the uncertainty of the prediction made by the model. Here we show how this uncertainty relates to the actual error of the prediction. Results: In our experiments, we observe a strong correlation between the estimated uncertainty provided by Gaussian Process Regression and the actual prediction error. This relation provides us with new means for assessment of the predictions. We demonstrate how a subset of the peptides can be selected with lower prediction error compared to the whole set. We also demonstrate how such predicted standard deviations can be used for designing adaptive windowing strategies.
|
|
5. |
- Maboudi Afkham, Heydar, et al.
(författare)
-
Improving feature level likelihoods using cloud features
- 2012
-
Ingår i: ICPRAM - Proc. Int. Conf. Pattern Recogn. Appl. Methods. - 9789898425980 ; , s. 431-437
-
Konferensbidrag (refereegranskat)abstract
- The performance of many computer vision methods depends on the quality of the local features extracted from the images. For most methods the local features are extracted independently of the task and they remain constant through the whole process. To make features more dynamic and give models a choice in the features they can use, this work introduces a set of intermediate features referred as cloud features. These features take advantage of part-based models at the feature level by combining each extracted local feature with its close by local feature creating a cloud of different representations for each local features. These representations capture the local variations around the local feature. At classification time, the best possible representation is pulled out of the cloud and used in the calculations. This selection is done based on several latent variables encoded within the cloud features. The goal of this paper is to test how the cloud features can improve the feature level likelihoods. The focus of the experiments of this paper is on feature level inference and showing how replacing single features with equivalent cloud features improves the likelihoods obtained from them. The experiments of this paper are conducted on several classes of MSRCv1 dataset.
|
|
6. |
- Maboudi Afkham, Heydar, 1983-
(författare)
-
Improving Image Classification Performance using Joint Feature Selection
- 2014
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- In this thesis, we focus on the problem of image classification and investigate how its performance can be systematically improved. Improving the performance of different computer vision methods has been the subject of many studies. While different studies take different approaches to achieve this improvement, in this thesis we address this problem by investigating the relevance of the statistics collected from the image.We propose a framework for gradually improving the quality of an already existing image descriptor. In our studies, we employ a descriptor which is composed the response of a series of discriminative components for summarizing each image. As we will show, this descriptor has an ideal form in which all categories become linearly separable. While, reaching this form is not possible, we will argue how by replacing a small fraction of these components, it is possible to obtain a descriptor which is, on average, closer to this ideal form. To do so, we initially identify which components do not contribute to the quality of the descriptor and replace them with more robust components. As we will show, this replacement has a positive effect on the quality of the descriptor.While there are many ways of obtaining more robust components, we introduce a joint feature selection problem to obtain image features that retains class discriminative properties while simultaneously generalising between within class variations. Our approach is based on the concept of a joint feature where several small features are combined in a spatial structure. The proposed framework automatically learns the structure of the joint constellations in a class dependent manner improving the generalisation and discrimination capabilities of the local descriptor while still retaining a low-dimensional representations.The joint feature selection problem discussed in this thesis belongs to a specific class of latent variable models that assumes each labeled sample is associated with a set of different features, with no prior knowledge of which feature is the most relevant feature to be used. Deformable-Part Models (DPM) can be seen as good examples of such models. These models are usually considered to be expensive to train and very sensitive to the initialization. Here, we focus on the learning of such models by introducing a topological framework and show how it is possible to both reduce the learning complexity and produce more robust decision boundaries. We will also argue how our framework can be used for producing robust decision boundaries without exploiting the dataset bias or relying on accurate annotations.To examine the hypothesis of this thesis, we evaluate different parts of our framework on several challenging datasets and demonstrate how our framework is capable of gradually improving the performance of image classification by collecting more robust statistics from the image and improving the quality of the descriptor.
|
|
7. |
- Maboudi Afkham, Heydar, et al.
(författare)
-
Joint Visual Vocabulary For Animal Classification
- 2008
-
Ingår i: 19TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOLS 1-6. - 9781424421749 ; , s. 2019-2022
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a method for visual object categorization based on encoding the joint textural information in objects and the surrounding back-ground, and requiring no segmentation during recognition. The framework can be used together with various learning techniques and model representations. Here we use this framework with simple probabilistic models and more complex representations obtained using Support Vector Machines. We prove that our approach provides good recognition performance for complex problems for which some of the existing methods have difficulties. Additionally, we introduce a new extensive database containing realistic images of animals in complex natural environments. We asses the database in a set of experiments in which we compare the performance of our approach with a recently proposed method.
|
|
8. |
- Maboudi Afkham, Heydar, et al.
(författare)
-
Qualitative vocabulary based descriptor
- 2013
-
Ingår i: ICPRAM 2013. - 9789898565419 ; , s. 188-193
-
Konferensbidrag (refereegranskat)abstract
- Creating a single feature descriptors from a collection of feature responses is an often occurring task. As such the bag-of-words descriptors have been very successful and applied to data from a large range of different domains. Central to this approach is making an association of features to words. In this paper we present a new and novel approach to feature to word association problem. The proposed method creates a more robust representation when data is noisy and requires less words compared to the traditional methods while retaining similar performance. We experimentally evaluate the method on a challenging image classification data-set and show significant improvement to the state of the art.
|
|
9. |
- Madry, Marianna, et al.
(författare)
-
Extracting essential local object characteristics for 3D object categorization
- 2013
-
Ingår i: 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). - : IEEE conference proceedings. - 9781467363587 ; , s. 2240-2247
-
Konferensbidrag (refereegranskat)abstract
- Most object classes share a considerable amount of local appearance and often only a small number of features are discriminative. The traditional approach to represent an object is based on a summarization of the local characteristics by counting the number of feature occurrences. In this paper we propose the use of a recently developed technique for summarizations that, rather than looking into the quantity of features, encodes their quality to learn a description of an object. Our approach is based on extracting and aggregating only the essential characteristics of an object class for a task. We show how the proposed method significantly improves on previous work in 3D object categorization. We discuss the benefits of the method in other scenarios such as robot grasping. We provide extensive quantitative and qualitative experiments comparing our approach to the state of the art to justify the described approach.
|
|