Feature generation for long-tail classification

Vigneswaran, Rahul and Law, Marc T. and Balasubramanian, Vineeth N. and Tapaswi, Makarand (2021) Feature generation for long-tail classification. In: 12th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2021, 20 December 2021 through 22 December 2021, Virtual, Online.

Text
ACM_International.pdf - Published Version
Available under License Creative Commons Attribution.
Download (1MB)

Abstract

The visual world naturally exhibits an imbalance in the number of object or scene instances resulting in a long-tailed distribution. This imbalance poses significant challenges for classification models based on deep learning. Oversampling instances of the tail classes attempts to solve this imbalance. However, the limited visual diversity results in a network with poor representation ability. A simple counter to this is decoupling the representation and classifier networks and using oversampling only to train the classifier. In this paper, instead of repeatedly re-sampling the same image (and thereby features), we explore a direction that attempts to generate meaningful features by estimating the tail category's distribution. Inspired by ideas from recent work on few-shot learning [53], we create calibrated distributions to sample additional features that are subsequently used to train the classifier. Through several experiments on the CIFAR-100-LT (long-tail) dataset with varying imbalance factors and on mini-ImageNet-LT (long-tail), we show the efficacy of our approach and establish a new state-of-the-art. We also present a qualitative analysis of generated features using t-SNE visualizations and analyze the nearest neighbors used to calibrate the tail class distributions. Our code is available at https://github.com/rahulvigneswaran/TailCalibX. © 2021 ACM.

[error in script]

IITH Creators: