Multiple Instance Learning Convolutional Neural Networks for Object Recognition

TL;DR

This paper introduces MILCNN, a weakly supervised CNN framework that addresses labeling challenges in object recognition, achieving state-of-the-art results on multiple benchmark datasets.

Contribution

The paper proposes a novel MIL-based CNN framework for weakly supervised object recognition, reducing reliance on detailed labels and improving performance.

Findings

Achieved state-of-the-art accuracy on CIFAR10, CIFAR100, and ILSVRC2015 datasets.

Demonstrated effectiveness of MILCNN in weakly supervised settings.

Showed robustness against label noise and data augmentation issues.

Abstract

Convolutional Neural Networks (CNN) have demon- strated its successful applications in computer vision, speech recognition, and natural language processing. For object recog- nition, CNNs might be limited by its strict label requirement and an implicit assumption that images are supposed to be target- object-dominated for optimal solutions. However, the labeling procedure, necessitating laying out the locations of target ob- jects, is very tedious, making high-quality large-scale dataset prohibitively expensive. Data augmentation schemes are widely used when deep networks suffer the insufficient training data problem. All the images produced through data augmentation share the same label, which may be problematic since not all data augmentation methods are label-preserving. In this paper, we propose a weakly supervised CNN framework named Multiple Instance Learning Convolutional Neural Networks (MILCNN) to solve this problem. We apply MILCNN framework to object recognition and report state-of-the-art performance on three benchmark datasets: CIFAR10, CIFAR100 and ILSVRC2015 classification dataset.