Log In Sign Up

Balancing Constraints and Submodularity in Data Subset Selection

by   Srikumar Ramalingam, et al.

Deep learning has yielded extraordinary results in vision and natural language processing, but this achievement comes at a cost. Most deep learning models require enormous resources during training, both in terms of computation and in human labeling effort. In this paper, we show that one can achieve similar accuracy to traditional deep-learning models, while using less training data. Much of the previous work in this area relies on using uncertainty or some form of diversity to select subsets of a larger training set. Submodularity, a discrete analogue of convexity, has been exploited to model diversity in various settings including data subset selection. In contrast to prior methods, we propose a novel diversity driven objective function, and balancing constraints on class labels and decision boundaries using matroids. This allows us to use efficient greedy algorithms with approximation guarantees for subset selection. We outperform baselines on standard image classification datasets such as CIFAR-10, CIFAR-100, and ImageNet. In addition, we also show that the proposed balancing constraints can play a key role in boosting the performance in long-tailed datasets such as CIFAR-100-LT.


page 1

page 2

page 3

page 4


Learning From Less Data: Diversified Subset Selection and Active Learning in Image Classification Tasks

Supervised machine learning based state-of-the-art computer vision techn...

Semantic Redundancies in Image-Classification Datasets: The 10 Don't Need

Large datasets have been crucial to the success of deep learning models ...

Learning From Less Data: A Unified Data Subset Selection and Active Learning Framework for Computer Vision

Supervised machine learning based state-of-the-art computer vision techn...

MEESO: A Multi-objective End-to-End Self-Optimized Approach for Automatically Building Deep Learning Models

Deep learning has been widely used in various applications from differen...

Submodular Mutual Information for Targeted Data Subset Selection

With the rapid growth of data, it is becoming increasingly difficult to ...

EnSyth: A Pruning Approach to Synthesis of Deep Learning Ensembles

Deep neural networks have achieved state-of-art performance in many doma...

Mass Personalization of Deep Learning

We discuss training techniques, objectives and metrics toward mass perso...