Off-campus UMass Amherst users: To download campus access dissertations, please use the following link to log into our proxy server with your UMass Amherst user name and password.

Non-UMass Amherst users: Please talk to your librarian about requesting this dissertation through interlibrary loan.

Dissertations that have an embargo placed on them will not be available to anyone until the embargo expires.

Author ORCID Identifier


Open Access Dissertation

Document Type


Degree Name

Doctor of Philosophy (PhD)

Degree Program

Computer Science

Year Degree Awarded


Month Degree Awarded


First Advisor

Raghavan Manmatha

Second Advisor

James Allan

Third Advisor

Subhransu Maji

Fourth Advisor

Patrick A. Kelly

Subject Categories

Artificial Intelligence and Robotics


Image classification has been a core topic in the computer vision community. Its recent success with convolutional neural network (CNN) algorithm has led to various real world applications such as large scale management of photos/videos on cloud/social-media, image based search for online retailers, self-driving cars, building robots and healthcare. Image classification can be broadly categorized into binary, multi-class and multi-label classification problems. Binary classification involves assigning one of the two class labels to an instance. In multi-class classification problem, an instance should be categorized into one of more than two classes. Multi-label classification is a generalized version of the multi-class classification problem where each image is assigned multiple labels as opposed to a single label. In this work, we first present various methods that take advantage of deep representations (fully connected layer of pre-trained CNN on the ImageNet dataset) and yield better performance on multi-label classification when compared to methods that use over a dozen conventional visual features. Following the success of deep representations, we intend to build a generic end-to-end deep learning framework to address all three problem categories of image classification. However, there are still no well established guidelines (in terms of choosing the number of layers to go deeper, the number of kernels and the size, the type of regularizer, the choice of non-linear function, etc.) to build an efficient deep neural network and often network architecture design is specific to a problem/dataset. Hence, we present some initial efforts in building a computational framework called Deep Decision Network (DDN) which is completely data-driven. DDN is a tree-like structured built stage-wise. During the learning phase, starting from the root network node, DDN automatically builds a network that splits the data into disjoint clusters of classes which would be handled by the subsequent expert networks. This results in a tree-like structured network driven by the data. The proposed approach provides an insight into the data by identifying the group of classes that are hard to classify and require more attention when compared to others. This feature is crucial for people trying to solve the problem with little or no domain knowledge, especially for applications in medical domain. Initially, we evaluate DDN on a binary classification problem and later extend it to more challenging multi-class and multi-label classification problems. The extension of DDN to multi-class and multi-label involves some changes but they still operate under the same underlying principle. In all the three cases, the proposed approach is tested for its recognition performance and scalability on publicly available datasets providing comparison to other methods.