CVLGJul 10, 2024

Fine-Grained Classification for Poisonous Fungi Identification with Transfer Learning

arXiv:2407.07492v16 citationsh-index: 4Has Code
Originality Synthesis-oriented
AI Analysis

This work addresses the problem of identifying poisonous fungi for applications like safety and biodiversity, but it is incremental as it applies existing methods to a new dataset.

The paper tackled the fine-grained visual categorization of poisonous fungi species using ensemble classifier heads on pre-computed image embeddings from self-supervised vision models, achieving a best Track 3 score of 0.345, accuracy of 78.4%, and macro-F1 of 0.577 on the private test set.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes