Multi-Teacher Multi-Objective Meta-Learning for Zero-Shot Hyperspectral Band Selection

TL;DR

This paper introduces a multi-teacher multi-objective meta-learning framework for zero-shot hyperspectral band selection, enabling generalization across datasets without retraining.

Contribution

The proposed M$^3$BS method leverages a graph convolution network and multiple teachers to extract dataset-agnostic meta-knowledge for zero-shot band selection.

Findings

Achieves comparable performance to state-of-the-art methods on unseen datasets.

Effectively extracts transferable meta-knowledge for diverse hyperspectral datasets.

Demonstrates efficiency and generalizability in zero-shot band selection tasks.

Abstract

Band selection plays a crucial role in hyperspectral image classification by removing redundant and noisy bands and retaining discriminative ones. However, most existing deep learning-based methods are aimed at dealing with a specific band selection dataset, and need to retrain parameters for new datasets, which significantly limits their generalizability.To address this issue, a novel multi-teacher multi-objective meta-learning network (M$^3$BS) is proposed for zero-shot hyperspectral band selection. In M$^3$BS, a generalizable graph convolution network (GCN) is constructed to generate dataset-agnostic base, and extract compatible meta-knowledge from multiple band selection tasks. To enhance the ability of meta-knowledge extraction, multiple band selection teachers are introduced to provide diverse high-quality experiences.strategy Finally, subsequent classification tasks are attached and jointly optimized with multi-teacher band selection tasks through multi-objective meta-learning in an end-to-end trainable way. Multi-objective meta-learning guarantees to coordinate diverse optimization objectives automatically and adapt to various datasets simultaneously. Once the optimization is accomplished, the acquired meta-knowledge can be directly transferred to unseen datasets without any retraining or fine-tuning. Experimental results demonstrate the effectiveness and efficiency of our proposed method on par with state-of-the-art baselines for zero-shot hyperspectral band selection.