Transfer Learning with Self-Supervised Vision Transformers for Snake Identification

Anthony Miyaguchi; Austin Fischer; Murilo Gustineli; Ryan Lundqvist

RECORD

Transfer Learning with Self-Supervised Vision Transformers for Snake Identification

Anthony Miyaguchi, Murilo Gustineli, Austin Fischer, Ryan Lundqvist

Computer Vision and Pattern Recognition · Submitted 8 Jul 2024

abstract compiled · 2026-09-23 · no language-model review

The authors' main claim Despite achieving a score of 39.69, our results show promise for DINOv2 embeddings in snake identification.

how it is stated · asserted 0.79 read the record →

Comment (0) Read on arXiv ↗

Cite ▾

arXiv ID2407.06178 (version 1)

Pith IDXI4K4KNG, Pith's permanent record of this paper and its review

CitationAnthony Miyaguchi, Austin Fischer, Murilo Gustineli, Ryan Lundqvist. "Transfer Learning with Self-Supervised Vision Transformers for Snake Identification." arXiv:2407.06178 (2024). https://pith.science/paper/XI4K4KNG

Claim paper

The compiled record

The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.

Open the compiled record

Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-09-23: 1 request, 4,231 input tokens.

What the abstract itself states, as probabilities: claims first 0.03 · states limitation 0.86 · human participants 0.03 · controlled comparison 0.04 · randomized assignment 0.02 · states quantitative result 0.99 · compares with prior results 0.08 · mentions code or data availability 0.97.

The abstract, sentence by sentence

arXiv listing abstract v1. Results and the main claim are underlined; show every role.

We present our approach for the SnakeCLEF 2024 competition to predict snake species from images. We explore and use Meta's DINOv2 vision transformer model for feature extraction to tackle species' high variability and visual similarity in a dataset of 182,261 images. We perform exploratory analysis on embeddings to understand their structure, and train a linear classifier on the embeddings to predict species. Despite achieving a score of 39.69, our results show promise for DINOv2 embeddings in snake identification. All code for this project is available at https://github.com/dsgt-kaggle-clef/snakeclef-2024.

background contribution method result interpretation main claim

What the classifier reports for each sentence. The number is the probability it gave the label.
#	sentence	role	the authors' own work	states the main conclusion	strength
s0	We present our approach for the SnakeCLEF 2024 competition to predict snake species from images.	contribution 0.94	0.86	0.03	asserted 0.75
s1	We explore and use Meta's DINOv2 vision transformer model for feature extraction to tackle species' high variability and visual similarity in a dataset of 182,261 images.	method 0.98	0.91	0.05	asserted 0.99
s2	We perform exploratory analysis on embeddings to understand their structure, and train a linear classifier on the embeddings to predict species.	method 1.00	0.96	0.04	asserted 0.98
s3	Despite achieving a score of 39.69, our results show promise for DINOv2 embeddings in snake identification.	result 0.70	0.96	0.62	asserted 0.79
s4	All code for this project is available at https://github.com/dsgt-kaggle-clef/snakeclef-2024.	contribution 0.83	0.45	0.02	asserted 0.98

What kind of paper the classifier reports this is: empirical study 0.59 · evidence from observation or experiment 0.70.

What was examined, and what was not

sources read

arXiv listing abstract v1

not examined

full text
figures and tables
references and citing sentences
relations to other papers

levels run

P abstract

not run

S sections
T body sentences
C citations
R cross-paper relations

Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. Every number in the measurements table is the authors', checked by code. Record as JSON

The paper

Original abstract

We present our approach for the SnakeCLEF 2024 competition to predict snake species from images. We explore and use Meta's DINOv2 vision transformer model for feature extraction to tackle species' high variability and visual similarity in a dataset of 182,261 images. We perform exploratory analysis on embeddings to understand their structure, and train a linear classifier on the embeddings to predict species. Despite achieving a score of 39.69, our results show promise for DINOv2 embeddings in snake identification. All code for this project is available at https://github.com/dsgt-kaggle-clef/snakeclef-2024.

Human review

How Pith checks papers → · Full audit of this paper →

How the literature uses it

What this paper does with the arXiv papers it cites

Each citing sentence is taken from the citing paper's LaTeX source and typed by Pith's classifier. A label appears at probability 0.8 or more (0.95 for support), a contest at 0.7 or more; the quoted words are the citing authors'. How each label was checked · JSON

What it cites · 3 sentences without a confident label

Uses the method or tool of 1 paper

In Figure [ref] we plot UMAP [ref] projections of these embeddings, both their [CLS] tokens and the DCT coefficients of the patch tokens.

UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction · Exploratory Data Analysis · 1.00

Cites as background 1 paper

DINOv2 [ref] is a self-supervised vision transformer developed by Meta.

DINOv2: Learning Robust Visual Features without Supervision · Self-Supervised Vision Transformers · 0.80

Discussion

Know something about this paper? Leave a comment, or highlight any passage above to comment on it.