Fine-Grained Classification for Poisonous Fungi Identification with Transfer Learning

TL;DR

This paper presents a transfer learning approach using ensemble classifiers on pre-trained vision models for fine-grained poisonous fungi identification, achieving top performance in the FungiCLEF 2024 challenge.

Contribution

It demonstrates that self-supervised vision models can be effectively used as feature extractors for fungi classification without task-specific fine-tuning.

Findings

Achieved 78.4% accuracy on the private test set.

Secured the best Track 3 score of 0.345.

Macro-F1 score of 0.577.

Abstract

FungiCLEF 2024 addresses the fine-grained visual categorization (FGVC) of fungi species, with a focus on identifying poisonous species. This task is challenging due to the size and class imbalance of the dataset, subtle inter-class variations, and significant intra-class variability amongst samples. In this paper, we document our approach in tackling this challenge through the use of ensemble classifier heads on pre-computed image embeddings. Our team (DS@GT) demonstrate that state-of-the-art self-supervised vision models can be utilized as robust feature extractors for downstream application of computer vision tasks without the need for task-specific fine-tuning on the vision backbone. Our approach achieved the best Track 3 score (0.345), accuracy (78.4%) and macro-F1 (0.577) on the private test set in post competition evaluation. Our code is available at https://github.com/dsgt-kaggle-clef/fungiclef-2024.