Reinforcement Learning Based Multi-modal Feature Fusion Network for Novel Class Discovery

TL;DR

This paper introduces a reinforcement learning-based multi-modal feature fusion network designed for discovering novel classes in unlabeled data, combining multi-agent feature extraction, self-supervised learning, and iterative clustering to improve open-set recognition.

Contribution

It proposes a novel multi-modal fusion framework with reinforcement learning and self-supervised clustering for effective novel class discovery in open-set scenarios.

Findings

Achieves competitive results on 3D and 2D datasets

Effectively incorporates self-supervised learning for better feature understanding

Utilizes a multi-agent framework for comprehensive feature fusion

Abstract

With the development of deep learning techniques, supervised learning has achieved performances surpassing those of humans. Researchers have designed numerous corresponding models for different data modalities, achieving excellent results in supervised tasks. However, with the exponential increase of data in multiple fields, the recognition and classification of unlabeled data have gradually become a hot topic. In this paper, we employed a Reinforcement Learning framework to simulate the cognitive processes of humans for effectively addressing novel class discovery in the Open-set domain. We deployed a Member-to-Leader Multi-Agent framework to extract and fuse features from multi-modal information, aiming to acquire a more comprehensive understanding of the feature space. Furthermore, this approach facilitated the incorporation of self-supervised learning to enhance model training. We employed a clustering method with varying constraint conditions, ranging from strict to loose, allowing for the generation of dependable labels for a subset of unlabeled data during the training phase. This iterative process is similar to human exploratory learning of unknown data. These mechanisms collectively update the network parameters based on rewards received from environmental feedback. This process enables effective control over the extent of exploration learning, ensuring the accuracy of learning in unknown data categories. We demonstrate the performance of our approach in both the 3D and 2D domains by employing the OS-MN40, OS-MN40-Miss, and Cifar10 datasets. Our approach achieves competitive competitive results.