Supervised Multilabel Image Classification Using Residual Networks with Probabilistic Reasoning

TL;DR

This paper presents a novel multilabel image classification method using a modified ResNet-101 with probabilistic reasoning, achieving state-of-the-art results on the COCO-2014 dataset by modeling label dependencies and uncertainties.

Contribution

It introduces a new approach that integrates probabilistic reasoning into deep residual networks for improved multilabel image classification.

Findings

Achieved 0.794 mAP on COCO-2014 dataset.

Outperformed ResNet-SRN and Vision Transformer baselines.

Demonstrated effective modeling of label dependencies and uncertainties.

Abstract

Multilabel image categorization has drawn interest recently because of its numerous computer vision applications. The proposed work introduces a novel method for classifying multilabel images using the COCO-2014 dataset and a modified ResNet-101 architecture. By simulating label dependencies and uncertainties, the approach uses probabilistic reasoning to improve prediction accuracy. Extensive tests show that the model outperforms earlier techniques and approaches to state-of-the-art outcomes in multilabel categorization. The work also thoroughly assesses the model's performance using metrics like precision-recall score and achieves 0.794 mAP on COCO-2014, outperforming ResNet-SRN (0.771) and Vision Transformer baselines (0.785). The novelty of the work lies in integrating probabilistic reasoning into deep learning models to effectively address the challenges presented by multilabel scenarios.