Summary of Fine-grained Classification For Poisonous Fungi Identification with Transfer Learning, by Christopher Chiu et al.
Fine-Grained Classification for Poisonous Fungi Identification with Transfer Learning
by Christopher Chiu, Maximilian Heil, Teresa Kim, Anthony Miyaguchi
First submitted to arxiv on: 10 Jul 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes a solution to the fine-grained visual categorization (FGVC) of fungi species, focusing on identifying poisonous species. The task is challenging due to dataset size and class imbalance, subtle inter-class variations, and significant intra-class variability. To address this challenge, the authors employ ensemble classifier heads on pre-computed image embeddings. State-of-the-art self-supervised vision models are used as robust feature extractors for downstream computer vision tasks without fine-tuning. The approach achieves best scores in Track 3 (0.345), accuracy (78.4%), and macro-F1 (0.577) on the private test set. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary FungiCLEF 2024 is a special task that helps identify poisonous fungi species. This is hard because there are many similar-looking fungi, some are poisonous, and others are not. To make it easier, scientists used special computer models to recognize patterns in images of fungi. These models can learn from looking at lots of pictures without needing specific training for each type of fungus. This paper shows how this approach worked best on a private test set. |
Keywords
* Artificial intelligence * Fine tuning * Self supervised
