# Motif Mining and Unsupervised Representation Learning for BirdCLEF 2022

arXiv: https://arxiv.org/abs/2206.04805 · HTML: https://mlsanity.com/paper/2206.04805/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 11 references that are in the map.
- First posted on arXiv 8 Jun 2022.

## Builds on (most cited first, 2 of 2)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Tile2Vec: Unsupervised representation learning for spatially distributed data](https://mlsanity.com/paper/1805.02855/) (2018)

## Built on by (most cited first, 3 of 3)

- [Few-shot Long-Tailed Bird Audio Recognition](https://mlsanity.com/paper/2206.11260/) (2022)
- [Automated Bioacoustic Monitoring for South African Bird Species on Unlabeled Data](https://mlsanity.com/paper/2406.13579/) (2024)
- [Can Tokens Compete? Token Representations against Supervised CNN Backbones for BirdCLEF+ 2026](https://mlsanity.com/paper/2607.14474/) (2026)

## Abstract (arXiv)

We build a classification model for the BirdCLEF 2022 challenge using unsupervised methods. We implement an unsupervised representation of the training dataset using a triplet loss on spectrogram representation of audio motifs. Our best model performs with a score of 0.48 on the public leaderboard.