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

Abstract

Supervised machine learning based state-of-the-art computer vision techniques are in general data hungry and pose the challenges of not having adequate computing resources and of high costs involved in human labeling efforts. Training data subset selection and active learning techniques have been proposed as possible solutions to these challenges respectively. A special class of subset selection functions naturally model notions of diversity, coverage and representation and they can be used to eliminate redundancy and thus lend themselves well for training data subset selection. They can also help improve the efficiency of active learning in further reducing human labeling efforts by selecting a subset of the examples obtained using the conventional uncertainty sampling based techniques. In this work we empirically demonstrate the effectiveness of two diversity models, namely the Facility-Location and Disparity-Min models for training-data subset selection and reducing labeling effort. We do this for a variety of computer vision tasks including Gender Recognition, Scene Recognition and Object Recognition. Our results show that subset selection done in the right way can add 2-3% in accuracy on existing baselines, particularly in the case of less training data. This allows the training of complex machine learning models (like Convolutional Neural Networks) with much less training data while incurring minimal performance loss.

On Training Instance Selection for Few-Shot Neural Text Generation

“…Choosing data points farthest to the cluster centers leads to the worst performance. This is consistent with previous findings (Kaushal et al, 2018;Birodkar et al, 2019) that data points farthest from cluster centers are usually outliers and less representative. Selecting them might mislead the model to capture non-generic patterns and thereby generalize poorly.…”

“…This naturally matches the objectives of k-means clustering which minimizes the within-cluster variances while maximizing the between-cluster variances to encourage the diversity and representativeness of each cluster (Krishna and Murty, 1999;Kanungo et al, 2002). As has been shown in image classification tasks, data points closer to the cluster centroids are usually most important, while other faraway points can even be safely removed without hurting model performance (Kaushal et al, 2018;Birodkar et al, 2019). Inspired by this, we propose a simple selection strategy which first clusters the whole unlabeled dataset with the K-means algorithm, and then from each cluster, selects the data point that is closest to the cluster centroid.…”

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

“…[ Wei et al, 2015] pose the problem of subset selection as a constrained sub-modular maximization problem and use it to propose an active learning algorithm. The proposed techniques are used by [Kaushal et al, 2018] in the context of image recognition tasks. These drawback however, is that when used with deep-neural networks, simple uncertainty based strategies out-perform the mentioned algorithm.…”

“…We train a 32-layer ResNet for the CIFAR-10 and CIFAR-100 [Krizhevsky and Hinton, 2009] datasets. The semantic representation obtained was a 64dimensional vector.…”

“…Large datasets have played a central role in the recent success of deep learning. In fact, the performance of AlexNet [Krizhevsky et al, 2012] trained on ImageNet [Deng et al, 2009] in 2012 is often considered as the starting point of the current deep learning era. Undoubtedly, prominent datasets of ImageNet, CI-FAR, and CIFAR-100 [Krizhevsky and Hinton, 2009] have had a crucial role in the evolution of deep learning methods since then; with even bigger datasets like OpenImages [Kuznetsova et al, 2018] and Tencent ML-images [Wu et al, 2019] recently emerging.…”