Training image classifiers using Semi-Weak Label Data

TL;DR

This paper introduces a semi-weak label learning paradigm for image classification, leveraging class counts to improve performance over traditional weakly supervised methods, and demonstrates its effectiveness on CIFAR-10 data.

Contribution

It proposes a novel semi-weak label learning framework that uses class count information, bridging the gap between weak supervision and full supervision in image classification.

Findings

Outperforms MIL-based weakly-supervised and learning from proportion baselines.

Achieves results comparable to fully supervised models.

Effective across various datasets and experimental settings.

Abstract

In Multiple Instance learning (MIL), weak labels are provided at the bag level with only presence/absence information known. However, there is a considerable gap in performance in comparison to a fully supervised model, limiting the practical applicability of MIL approaches. Thus, this paper introduces a novel semi-weak label learning paradigm as a middle ground to mitigate the problem. We define semi-weak label data as data where we know the presence or absence of a given class and the exact count of each class as opposed to knowing the label proportions. We then propose a two-stage framework to address the problem of learning from semi-weak labels. It leverages the fact that counting information is non-negative and discrete. Experiments are conducted on generated samples from CIFAR-10. We compare our model with a fully-supervised setting baseline, a weakly-supervised setting baseline and learning from pro-portion (LLP) baseline. Our framework not only outperforms both baseline models for MIL-based weakly super-vised setting and learning from proportion setting, but also gives comparable results compared to the fully supervised model. Further, we conduct thorough ablation studies to analyze across datasets and variation with batch size, losses architectural changes, bag size and regularization