MUNIN
Lightweight few-shot learning for acoustic individual identification in birds. A ResNet18 encoder trained from scratch on mel spectrograms using episodic prototypical learning.
Source du modèle
- Type
- Other
- Taille du fichier
- 42,7 MB
- Version
- vRevision 6cf140c
- Mis à jour
- 22 sept. 2026
- Téléchargements
- 0
- Source
- Hugging Face
Description de la source
MUNIN: Metric-learning Unit for Non-invasive Individual Naming
Lightweight few-shot learning for acoustic individual identification in birds. A ResNet18 encoder trained from scratch on mel spectrograms using episodic prototypical learning.
Key Result
MUNIN (11M parameters, 512-d embeddings) achieves parity with BirdNET (pretrained on 6,000+ species, 1024-d) for individual bird identification:
| Setting | MUNIN | BirdNET | Perch |
|---|---|---|---|
| 1-shot | 85.0% | 81.4% | 80.4% |
| 3-shot | 89.9% | 91.5% | 90.8% |
| 5-shot | 93.9% | 94.1% | 92.8% |
TOST equivalence at 5-shot within +/-2pp margin (p=0.0013). Evaluated on 9 held-out individuals across 3 species.
Checkpoints
| File | Description |
|---|---|
| MUNIN flagship -- best 5-shot model (93.9%) | |
| 3-shot variant (89.9%) | |
| 1-shot variant (85.0%, leads BirdNET) |
Usage
Input Format
- Mono audio at 22050 Hz
- Mel spectrogram: 128 bins, 1.5s clips (65 frames)
- Shape:
Training
- Episodic prototypical learning (5-way 5-shot)
- 27 training individuals across 3 species (cockatoo, penguin, little owl)
- 50 epochs, 200 episodes/epoch, cosine annealing LR
- Trained on consumer GPU (RTX 4070, ~15 min)
Paper
Citation
Sources
1 source
Sources
1 sourceVérifié 6 sept.
Download files
Artefacts du modèle
3 artefacts
Artefacts du modèle
3 artefactsExtraits de sources
2 extraits
Extraits de sources
2 extraits--- license: mit tags: - bioacoustics - few-shot-learning - prototypical-networks - bird-identification - individual-identification - audio - mel-spectrogram datasets: - custom language: - en pipeline_tag: audio-classification --- # MUNIN: Metric-learning Unit for Non-invasive Individual Naming Lightweight few-shot learning for acoustic individual identification in birds. A ResNet18 encoder trained from scratch on mel spectrograms using episodic prototypical learning. ## Key Result MUNIN (11M parameters, 512-d embeddings) achieves parity with BirdNET (pretrained on 6,000+ species, 1024-d) for individual bird identification: | Setting | MUNIN | BirdNET | Perch | |---------|-------|---------|-------| | 1-shot | **85.0%** | 81.4% | 80.4% | | 3-shot | 89.9% | **91.5%** | 90.8% | | 5-shot | 93.9% | **94.1%** | 92.8% | TOST equivalence at 5-shot within +/-2pp margin (p=0.0013). Evaluated on 9 held-out individuals across 3 species. ## Checkpoints | File | Description | |------|-------------| | | **MUNIN flagship** -- best 5-shot model (93.9%) | | | 3-shot variant (89.9%) | | | 1-shot variant (85.0%, leads BirdNET) | ## Usage ## Input Format - Mono audio at 22050 Hz - Mel spectrogram: 128 bins, 1.5s clips (65 frames) - Shape: ## Training - Episodic prototypical learning (5-way 5-shot) - 27 training individuals across 3 species (cockatoo, penguin, little owl) - 50 epochs, 200 episodes/epoch, cosine annealing LR - Trained on consumer GPU (RTX 4070, ~15 min) ## Paper Preprint: [MUNIN: Lightweight few-shot learning achieves parity with large pretrained encoders for acoustic individual identification in birds](https://github.com/j8ckfi/MUNIN) ## Citation
Source context: 0 downloads · 0 likes · Pipeline audio-classification · Repo potteryrage/MUNIN
