Saket Anand

Semi-Supervised Kernel Mean Shift Clustering

Mean shift clustering is a powerful nonparametric technique that does not require prior knowledge of the number of clusters and does not constrain the shape of the clusters. However, being completely unsupervised, its performance suffers when the original distance metric fails to capture the underlying cluster structure. Despite recent advances in semi-supervised clustering methods, there has been little effort towards incorporating supervision into mean shift. We propose a semi-supervised framework for kernel mean shift clustering (SKMS) that uses only pairwise constraints to guide the clustering procedure. The points are first mapped to a high-dimensional kernel space where the constraints are imposed by a linear transformation of the mapped points. This is achieved by modifying the initial kernel matrix by minimizing a log det divergence-based objective function. We show the advantages of SKMS by evaluating its performance on various synthetic and real datasets while comparing with state-of-the-art semi-supervised clustering algorithms.

Generalized Projection-Based M-Estimator

We propose a novel robust estimation algorithm - the generalized projection-based M-estimator (gpbM), which does not require the user to specify any scale parameters. The algorithm is general and can handle heteroscedastic data with multiple linear constraints for single and multicarrier problems. The gpbM has three distinct stages - scale estimation, robust model estimation, and inlier/outlier dichotomy. In contrast, in its predecessor pbM, each model hypotheses was associated with a different scale estimate. For data containing multiple inlier structures with generally different noise covariances, the estimator iteratively determines one structure at a time. The model estimation can be further optimized by using Grassmann manifold theory. We present several homoscedastic and heteroscedastic synthetic and real-world computer vision problems with single and multiple carriers.

Generalized projection based M-estimator: Theory and applications

We introduce a robust estimator called generalized projection based M-estimator (gpbM) which does not require the user to specify any scale parameters. For multiple inlier structures, with different noise covariances, the estimator iteratively determines one inlier structure at a time. Unlike pbM, where the scale of the inlier noise is estimated simultaneously with the model parameters, gpbM has three distinct stages–scale estimation, robust model estimation and inlier/outlier dichotomy. We evaluate our performance on challenging synthetic data, face image clustering upto ten different faces from Yale Face Database B and multi-body projective motion segmentation problem on Hopkins155 dataset. Results of state-of-the-art methods are presented for comparison.

A New Face Recognition Algorithm using Bijective Mappings

A new face recognition algorithm is proposed which is robust to variations in pose, expression and illumination. The framework is similar to the ubiquitous block matching algorithm used for motion estimation in video compression but has been adapted to compensate for illumination differences. One of the key differentiators of this approach is that unlike traditional face recognition algorithms, the image data representing the face or features extracted from the facial data is not used for classification. Instead, the mapping between the probe and gallery images given by the block matching algorithm is used to classify the faces for recognition. Once the mappings are found for each gallery image, the degree of bijectivity that each mapping produces is used to derive the similarity scores for recognition.

Automatic Detection and Recognition of Individuals in Patterned Species

Visual animal biometrics is rapidly gaining popularity as it enables a non-invasive and cost-effective approach for wildlife monitoring applications. Widespread usage of camera traps has led to large volumes of collected images, making manual processing of visual content hard to manage. In this work, we develop a framework for automatic detection and recognition of individuals in different patterned species like tigers, zebras and jaguars. Most existing systems primarily rely on manual input for localizing the animal, which does not scale well to large datasets. In order to automate the detection process while retaining robustness to blur, partial occlusion, illumination and pose variations, we use the recently proposed Faster-RCNN object detection framework to efficiently detect animals in images. We further extract features from AlexNet of the animals flank and train a logistic regression (or Linear SVM) classifier to recognize the individuals. We primarily test and evaluate our framework on a camera trap tiger image dataset that contains images that vary in overall image quality, animal pose, scale and lighting. We also evaluate our recognition system on zebra and jaguar images to show generalization to other patterned species. Our framework gives perfect detection results in camera trapped tiger images and a similar or better individual recognition performance when compared with state-of-the-art recognition techniques.

Stacked Robust Autoencoder for Classification

In this work we propose an l p -norm data fidelity constraint for training the autoencoder. Usually the Euclidean distance is used for this purpose; we generalize the l 2 -norm to the l p -norm; smaller values of p make the problem robust to outliers. The ensuing optimization problem is solved using the Augmented Lagrangian approach. The proposed l p -norm Autoencoder has been tested on benchmark deep learning datasets – MNIST, CIFAR-10 and SVHN. We have seen that the proposed robust autoencoder yields better results than the standard autoencoder (l 2 -norm) and deep belief network for all of these problems.

Fast hypothesis filtering for multi-structure geometric model fitting

We propose a fast and efficient two-stage hypothesis filtering technique that can improve performance of clustering based robust multi-model fitting algorithms. Sampling based hypothesis generation is nondeterministic and permits little control over generating poor model hypotheses, often leading to a significant proportion of bad hypotheses. Our novel filtering approach leverages the asymmetry in the distributions of points around the inlier/outlier boundary via the sample skewness computed in the residual space. The output is a set of promising hypotheses which aid multi-model fitting algorithms in improving accuracy as well as running time. We validate our approach on the AdelaideRMF dataset and show favorable results along with comparisons to state-of-the-art.

Metric learning based automatic segmentation of patterned species

Many species in the wild exhibit a visual pattern that can be used to uniquely identify an individual. This observation has recently led to visual animal biometrics become a rapidly growing application area of computer vision. Customized software tools for animal biometrics already employ vision based techniques to recognize individuals in images taken in uncontrolled environments. However, most existing tools require the user to localize the animals for accurate identification. In this work, we propose a figure/ground segmentation method that automatically extracts out the animal in an image. Our method relies on a semi-supervised metric learning algorithm that uses a small amount of training data without compromising generalization performance. We design a simple pipeline comprising of superpixel segmentation, texture based feature extraction followed by mean shift clustering using the learned metric. We show that our approach can yield competitive results for figure/ground segmentation of patterned animals in images taken in the wild, often under extreme illumination conditions.

Distance Metric Learning by Optimization on the Stiefel Manifold

Distance metric learning has proven to be very successful in various problem domains. Most techniques learn a global metric in the form of a n× n symmetric positive semidefinite (PSD) Mahalanobis distance matrix, which has O(n2) unknowns. The PSD constraint makes solving the metric learning problem even harder making it computationally intractable for high dimensions. In this work, we propose a flexible formulation that can employ different regularization functions, while implicitly maintaining the positive semidefiniteness constraint. We achieve this by eigendecomposition of the rank p Mahalanobis distance matrix followed by a joint optimization on the Stiefel manifold Sn,p and the positive orthant R +. The resulting nonconvex optimization problem is solved by employing an alternating strategy. We use a recently proposed projection free approach for efficient optimization over the Stiefel manifold. Even though the problem is nonconvex, we empirically show competitive classification accuracy on UCI and USPS digits datasets.

Robust Multi-Model Fitting Using Density and Preference Analysis

Robust multi-model fitting problems are often solved using consensus based or preference based methods, each of which captures largely independent information from the data. However, most existing techniques still adhere to either of these approaches. In this paper, we bring these two paradigms together and present a novel robust method for discovering multiple structures from noisy, outlier corrupted data. Our method adopts a random sampling based hypothesis generation and works on the premise that inliers are densely packed around the structure, while the outliers are sparsely spread out. We leverage consensus maximization by defining the residual density, which is a simple and efficient measure of density in the 1-D residual space. We locate the inlier-outlier boundary by using preference based point correlations together with the disparity in residual density of inliers and outliers. Finally, we employ a simple strategy that uses preference based hypothesis correlation and residual density to identify one hypothesis representing each structure and their corresponding inliers. The strength of the proposed approach is evaluated empirically by comparing with state-of-the-art techniques over synthetic data and the AdelaideRMF dataset.