Vikas K. Garg

DEEP-CARVING: Discovering visual attributes by carving deep neural nets

Most of the approaches for discovering visual attributes in images demand significant supervision, which is cumbersome to obtain. In this paper, we aim to discover visual attributes in a weakly supervised setting that is commonly encountered with contemporary image search engines. For instance, given a noun (say forest) and its associated attributes (say dense, sunlit, autumn), search engines can now generate many valid images for any attribute-noun pair (dense forests, autumn forests, etc). However, images for an attributenoun pair do not contain any information about other attributes (like which forests in the autumn are dense too). Thus, a weakly supervised scenario occurs: each of the M attributes corresponds to a class such that a training image in class m ∈ {1, . . . , M} contains a single label that indicates the presence of the mth attribute only. The task is to discover all the attributes present in a test image. Deep Convolutional Neural Networks (CNNs) [20] have enjoyed remarkable success in vision applications recently. However, in a weakly supervised scenario, widely used CNN training procedures do not learn a robust modelfor predicting multiple attribute labels simultaneously. The primary reason is that the attributes highly co-occur within the training data, and unlike objects, do not generally exist as well-defined spatial boundaries within the image. To ameliorate this limitation, we propose Deep-Carving, a novel training procedure with CNNs, that helps the net efficiently carve itselffor the task of multiple attribute prediction. During training, the responses of the feature maps are exploited in an ingenious way to provide the net with multiple pseudo-labels (for training images) for subsequent iterations. The process is repeated periodically after a fixed number of iterations, and enables the net carve itself iteratively for efficiently disentangling features. Additionally, we contribute a noun-adjective pairing inspired Natural Scenes Attributes Dataset to the research community, CAMITNSAD, containing a number of co-occurring attributes within a noun category. We describe, in detail, salient aspects of this dataset. Our experiments on CAMITNSAD and the SUN Attributes Dataset [29], with weak supervision, clearly demonstrate that the Deep-Carved CNNs consistently achieve considerable improvement in the precision of attribute prediction over popular baseline methods.

Novel Biobjective Clustering (BiGC) Based on Cooperative Game Theory

We propose a new approach to clustering. Our idea is to map cluster formation to coalition formation in cooperative games, and to use the Shapley value of the patterns to identify clusters and cluster representatives. We show that the underlying game is convex and this leads to an efficient biobjective clustering algorithm that we call BiGC. The algorithm yields high-quality clustering with respect to average point-to-center distance (potential) as well as average intracluster point-to-point distance (scatter). We demonstrate the superiority of BiGC over state-of-the-art clustering algorithms (including the center based and the multiobjective techniques) through a detailed experimentation using standard cluster validity criteria on several benchmark data sets. We also show that BiGC satisfies key clustering properties such as order independence, scale invariance, and richness.

Multi-regularization for Fuzzy Co-clustering

Co-clustering is a powerful technique with varied applications in text clustering and recommender systems. For large scale high dimensional and sparse real world data, there is a strong need to provide an overlapped co-clustering algorithm that mitigates the effect of noise and non-discriminative information, generalizes well to the unseen data, and performs well with respect to several quality measures. In this paper, we introduce a novel fuzzy co-clustering algorithm that incorporates multiple regularizers to address these important issues. Specifically, we propose MRegFC that considers terms corresponding to Entropy, Gini Index, and Joint Entropy simultaneously. We demonstrate that MRegFC generates significantly higher quality results compared to many existing approaches on several real world benchmark datasets.