Exemplar SVM Research Articles

Multi-spectral template matching based object detection in a few-shot learning manner

Multi-spectral template matching (MSTM) based object detection approaches can be widely used in robotics and aerospace systems for fine-grained object discovery. However, the performance of existing nearest neighbor search based nonparametric paradigms (e.g., correlation coefficient and lp-norm) turns out to be unsatisfactory. These paradigms tend to suffer from two defects: 1) they fail to select from the raw features the discriminative ones that can help distinguish between the target and background; 2) the domain shift between the template and search spectra has not been well addressed within the feature space. In this work, we propose a data-driven MSTM method to address these two issues. First, Exemplar-SVM (E-SVM) is applied to execute feature selection and target/background categorization jointly, which is facilitated by its max-margin mechanism. To enable the learning process where the template is regarded as a single positive sample, knowledge transfer is executed to attain negative samples from other domains, e.g., large-scale public datasets. Then, the hard negative samples are mined to help train a discriminative classifier. Concerning practical applications, we also augment the template with different image degradations and extend E-SVM from the original one-shot learning approach to its few-shot version. Second, a multi-domain adaptation approach via unsupervised multi-domain subspace alignment is proposed to tackle multi-domain shift problem. Here the multiple domains relate to template, search, and negative ones considering both offline learning and online matching. The wide-range experimental results on two multi-spectral datasets demonstrate the effectiveness of our method. The tailored dataset and code will be released publicly.

Domain Generalization and Adaptation Using Low Rank Exemplar SVMs.

Domain adaptation between diverse source and target domains is challenging, especially in the real-world visual recognition tasks where the images and videos consist of significant variations in viewpoints, illuminations, qualities, etc. In this paper, we propose a new approach for domain generalization and domain adaptation based on exemplar SVMs. Specifically, we decompose the source domain into many subdomains, each of which contains only one positive training sample and all negative samples. Each subdomain is relatively less diverse, and is expected to have a simpler distribution. By training one exemplar SVM for each subdomain, we obtain a set of exemplar SVMs. To further exploit the inherent structure of source domain, we introduce a nuclear-norm based regularizer into the objective function in order to enforce the exemplar SVMs to produce a low-rank output on training samples. In the prediction process, the confident exemplar SVM classifiers are selected and reweigted according to the distribution mismatch between each subdomain and the test sample in the target domain. We formulate our approach based on the logistic regression and least square SVM algorithms, which are referred to as low rank exemplar SVMs (LRE-SVMs) and low rank exemplar least square SVMs (LRE-LSSVMs), respectively. A fast algorithm is also developed for accelerating the training of LRE-LSSVMs. We further extend Domain Adaptation Machine (DAM) to learn an optimal target classifier for domain adaptation, and show that our approach can also be applied to domain adaptation with evolving target domain, where the target data distribution is gradually changing. The comprehensive experiments for object recognition and action recognition demonstrate the effectiveness of our approach for domain generalization and domain adaptation with fixed and evolving target domains.

Outfit of Exemplar-SVMs for Object Detection and Beyond

Objectives: The main objective is the development of an efficient method in the recognition of vehicles in real world. Methods: The system relies on setting up of an alternate direct SVM classifier for every model in the planning set. Each of these Exemplar-SVMs is subsequently defined by a singular positive event and a large number negatives. While each discoverer is altogether specific to its model, we precisely watch that a troupe of such Exemplar-SVMs offers shockingly awesome theory. Our execution on the PASCAL VOC revelation errand is keeping pace with the altogether all the more bewildering idle part-based model of Felzenszwalb et al., at only a humble computational cost increase. But the central benefit of our approach is that it makes an unequivocal relationship between each acknowledgment and a singular get ready model. Findings: Since most revelations show incredible course of action to their related model, it is possible to trade any open model meta-data (segmentation, geometric structure, 3D model, etc.) clearly onto the recognizable pieces of proof, which can then be used as an element of general scene understanding. The current methods are taking negative information and processing them. They use the information mining to filter out the negative values, since the classifier is direct SVM the values are represented parametrically. However this system depends on an exceptionally basic thought. We use every model utilizing unending HOG template. The use of exemplar SVM will make the number of examples in the dataset more and the efficient way of processing the objects and identifying them. Applications: This system can be used for Indian roads scenario since there is no proper lane marking system and there is always a chance to get many disturbances in the images. This system can be more developed into a constant evolving model where the processed objects can be stored within and keeps on integrating the data set.

Contour Detection-Based Discovery of Mid-Level Discriminative Patches for Scene Classification

Feature extraction and representation is a key step in scene classification. In this paper, a contour detection-based mid-level features learning method is proposed for scene classification. First, a sketch tokens-based contour detection scheme is proposed to initialize seed blocks for learning mid-level patches and the patches with more contour pixels are selected as seed blocks. The procedure is demonstrated to be helpful for scene classification. Next, the seed blocks are employed to train an exemplar SVM to discover other similar occurrences and an entropy-rank criterion is utilized to mine the discriminative patches. Finally, scene categories are identified by matching the discriminative patches and testing images. Extensive experiments on the MIT Indoor-67 dataset, the 15-scene dataset and the UIUC-sports dataset show that the proposed approach yields better performance than other state-of-the-art counterparts.

Segmentation-free word spotting with exemplar SVMs

In this paper we propose an unsupervised segmentation-free method for word spotting in document images. Documents are represented with a grid of HOG descriptors, and a sliding-window approach is used to locate the document regions that are most similar to the query. We use the Exemplar SVM framework to produce a better representation of the query in an unsupervised way. Then, we use a more discriminative representation based on Fisher Vector to rerank the best regions retrieved, and the most promising ones are used to expand the Exemplar SVM training set and improve the query representation. Finally, the document descriptors are precomputed and compressed with Product Quantization. This offers two advantages: first, a large number of documents can be kept in RAM memory at the same time. Second, the sliding window becomes significantly faster since distances between quantized HOG descriptors can be precomputed. Our results significantly outperform other segmentation-free methods in the literature, both in accuracy and in speed and memory usage.