Perch 2.0
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-17.)
Perch 2.0 has 75 facts recorded in Dontopedia across 1 reference, with 14 live disagreements.
75 facts·42 predicates·1 sources·14 in dispute
Mostly:tp:verdict reason(6), rdf:type(5), evaluated on(5)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (17)
Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.
comparedWithCompared With(5)
- Aves Bio
ex:aves-bio - Birdaves
ex:birdaves - Birdnet V2 3
ex:birdnet-v2-3 - Perch 1 0
ex:perch-1-0 - Surfperch
ex:surfperch
usedToEvaluateUsed to Evaluate(3)
- Dclde 2026 Dataset
ex:dclde-2026-dataset - Noaa Pipan Dataset
ex:noaa-pipan-dataset - Reefset Dataset
ex:reefset-dataset
comparesPerformanceOfCompares Performance of(2)
- Comparison Study
ex:comparison-study - Study Comparison
ex:study-comparison
basedOnBased on(1)
- Linear Classifiers
ex:linear-classifiers
generatedByGenerated by(1)
- Perch 2 0 Embeddings
ex:perch-2-0-embeddings
illustratesQualityOfIllustrates Quality of(1)
- Figure 2
ex:figure-2
learnedDuringTrainingOfLearned During Training of(1)
- Bittern Lesson
ex:bittern-lesson
outperformedByOutperformed by(1)
- Alternative Embedding Models
ex:alternative-embedding-models
separatesEcotypeWorseThanSeparates Ecotype Worse Than(1)
- Perch 1 0
ex:perch-1-0
targetModelTarget Model(1)
- Understanding Perch Performance
ex:understanding-perch-performance
Other facts (74)
The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.
74 facts
| Predicate | Value | Ref |
|---|---|---|
| Tp:verdict Reason | The dataset or training/evaluation relationship is grounded in the staged manuscript. | [1] |
| Tp:verdict Reason | The claimed model property matches the parsed model-property table in the staged manuscript. | [1] |
| Tp:verdict Reason | The claim is source-grounded in the manuscript, but the artifact-availability requirement is blocked by missing exact code/model-card/data URLs. | [1] |
| Tp:verdict Reason | The manuscript states the visualization interpretation, but no embeddings or figure-generation data are available for quantitative verification. | [1] |
| Tp:verdict Reason | The claim is source-grounded, but the unit's executable recomputation requirement is blocked by missing experiment artifacts. | [1] |
| Tp:verdict Reason | The claim is grounded in the staged manuscript text. | [1] |
| Rdf:type | Model | [1] |
| Rdf:type | Foundation Model | [1] |
| Rdf:type | Bioacoustics Foundation Model | [1] |
| Rdf:type | Model Version | [1] |
| Rdf:type | Embedding Model | [1] |
| Evaluated on | Noaa Pipan Dataset | [1] |
| Evaluated on | Reefset Dataset | [1] |
| Evaluated on | Dclde 2026 Dataset | [1] |
| Evaluated on | Marine Mammal Audio Task | [1] |
| Evaluated on | Underwater Audio Task | [1] |
| Compares With | Perch 1 0 | [1] |
| Compares With | Surfperch | [1] |
| Compares With | Aves Bio | [1] |
| Compares With | Birdaves | [1] |
| Compares With | Birdnet V2 3 | [1] |
| Includes Taxonomic Group | Bird | [1] |
| Includes Taxonomic Group | Mammal | [1] |
| Includes Taxonomic Group | Amphibian | [1] |
| Includes Taxonomic Group | Insect | [1] |
| Tested on | Wmmsd Dataset | [1] |
| Tested on | Watkins Marine Mammal Sound Database | [1] |
| Tested on | Wmmsd | [1] |
| Is Recommended for | Developing Linear Classifiers | [1] |
| Is Recommended for | Marine Mammal Classification | [1] |
| Is Recommended for | Few Labeled Examples | [1] |
| Also Covers | Insects | [1] |
| Also Covers | Mammals | [1] |
| Also Covers | Amphibians | [1] |
| Has Training Data Deficiency | Marine Mammal Audio | [1] |
| Has Training Data Deficiency | Marine Mammal Classes | [1] |
| Trained on | Labeled Recordings | [1] |
| Trained on | Log Mel Spectrograms | [1] |
| Uses Loss | Classification Loss | [1] |
| Uses Loss | Self Supervised Loss | [1] |
| Generalizes to | Non Species Classification Tasks | [1] |
| Generalizes to | Unseen Species | [1] |
| Has Best Boundary Between | Northern Resident Killer Whale | [1] |
| Has Best Boundary Between | Transient Killer Whale | [1] |
| Tp:simulation Verdict | reproduced | [1] |
| Tp:simulation Verdict | inconclusive | [1] |
| Part of Benchmark | Beans Benchmark | [1] |
| Evaluated for | Underwater Audio Task | [1] |
| Uses Validation Source | Marine Audio Validation Set | [1] |
| Model Selection Reported in | Van Merrienboer Et Al 2025 | [1] |
| Has Sample Rate | 32000 | [1] |
| Has Window Size | 5 | [1] |
| Has Embedding Dimension | 1536 | [1] |
| Has Model Parameter Count | 101.8M | [1] |
| Trained on Taxa | Broad Terrestrial | [1] |
| Learned Lesson | Bittern Lesson | [1] |
| Has Focus | Underwater Transfer Tasks | [1] |
| Is Model Type | Supervised Bioacoustics Foundation Model | [1] |
| Pretrained on Species Count | 14597 | [1] |
| Has Performance Level | state-of-the-art | [1] |
| Via Method | Few Shot Transfer Learning | [1] |
| Generates Embedding | Model Embedding | [1] |
| Has Result Description | Consistently High Performance | [1] |
| Generally Outperforms | Alternative Embedding Models | [1] |
| Transfers to | Underwater Tasks | [1] |
| Strength | strong | [1] |
| Covers Species Count | 14500 | [1] |
| Primarily Covers | Birds | [1] |
| Uses Architecture | Efficientnet B3 | [1] |
| Uses Technique | Self Distillation | [1] |
| Produces | Strong Embeddings | [1] |
| Tested As Part of | Beans Benchmark | [1] |
| Evaluated As Part of | Beans Benchmark | [1] |
| Shows Reasonable Clustering | true | [1] |
Timeline
Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.
—
typetp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:Model
—
labeltp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
Perch 2.0
—
testedOntp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:wmmsd-dataset
—
partOfBenchmarktp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:beans-benchmark
—
evaluatedFortp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:underwater-audio-task
—
evaluatedOntp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:noaa-pipan-dataset
—
evaluatedOntp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:reefset-dataset
—
evaluatedOntp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:dclde-2026-dataset
—
usesValidationSourcetp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:marine-audio-validation-set
—
modelSelectionReportedIntp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:van-merrienboer-et-al-2025
—
hasSampleRatetp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
32000
—
hasWindowSizetp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
5
—
hasEmbeddingDimensiontp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
1536
—
hasModelParameterCounttp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
101.8M
—
trainedOnTaxatp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:broad-terrestrial
—
learnedLessontp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:bittern-lesson
—
hasFocustp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:underwater-transfer-tasks
—
typetp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:FoundationModel
—
isModelTypetp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:SupervisedBioacousticsFoundationModel
—
pretrainedOnSpeciesCounttp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
14597
—
includesTaxonomicGrouptp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:bird
—
includesTaxonomicGrouptp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:mammal
—
includesTaxonomicGrouptp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:amphibian
—
includesTaxonomicGrouptp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:insect
—
hasPerformanceLeveltp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
state-of-the-art
—
evaluatedOntp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:marine-mammal-audio-task
—
evaluatedOntp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:underwater-audio-task
—
viaMethodtp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:few-shot-transfer-learning
—
hasTrainingDataDeficiencytp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:marine-mammal-audio
—
hasTrainingDataDeficiencytp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:marine-mammal-classes
—
generatesEmbeddingtp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:model-embedding
—
comparesWithtp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:perch-1-0
—
comparesWithtp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:surfperch
—
comparesWithtp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:aves-bio
—
comparesWithtp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:birdaves
—
comparesWithtp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:birdnet-v2-3
—
hasResultDescriptiontp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:consistently-high-performance
—
generallyOutperformstp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:alternative-embedding-models
—
isRecommendedFortp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:developing-linear-classifiers
—
isRecommendedFortp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:marine-mammal-classification
—
isRecommendedFortp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:few-labeled-examples
—
transfersTotp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:underwater-tasks
—
typetp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:bioacoustics-foundation-model
—
strengthtp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
strong
—
trainedOntp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:labeled-recordings
—
coversSpeciesCounttp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
14500
—
primarilyCoverstp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:birds
—
alsoCoverstp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:insects
—
alsoCoverstp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:mammals
—
alsoCoverstp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:amphibians
—
usesArchitecturetp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:efficientnet-b3
—
trainedOntp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:log-mel-spectrograms
—
usesLosstp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:classification-loss
—
usesTechniquetp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:self-distillation
—
usesLosstp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:self-supervised-loss
—
producestp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:strong-embeddings
—
generalizesTotp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:non-species-classification-tasks
—
generalizesTotp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:unseen-species
—
testedOntp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:watkins-marine-mammal-sound-database
—
testedAsPartOftp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:beans-benchmark
—
typetp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:ModelVersion
—
testedOntp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:wmmsd
—
evaluatedAsPartOftp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:beans-benchmark
—
typetp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:EmbeddingModel
—
showsReasonableClusteringtp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
true
—
hasBestBoundaryBetweentp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:northern-resident-killer-whale
—
hasBestBoundaryBetweentp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
ex:transient-killer-whale
—
simulationVerdicttp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
reproduced
—
verdictReasontp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
The dataset or training/evaluation relationship is grounded in the staged manuscript.
—
verdictReasontp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
The claimed model property matches the parsed model-property table in the staged manuscript.
—
simulationVerdicttp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
inconclusive
—
verdictReasontp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
The claim is source-grounded in the manuscript, but the artifact-availability requirement is blocked by missing exact code/model-card/data URLs.
—
verdictReasontp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
The manuscript states the visualization interpretation, but no embeddings or figure-generation data are available for quantitative verification.
—
verdictReasontp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
The claim is source-grounded, but the unit's executable recomputation requirement is blocked by missing experiment artifacts.
—
verdictReasontp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims
The claim is grounded in the staged manuscript text.
References (1)
1 references
tp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9:claims- full textchunk-009text/plain3 KB
doc:agent/chunk-009/f33235ee-7e4c-40ec-b809-de198012fc5fShow excerpt
nighan, T. B. Brown, B. Chess, R. Child, S. Gray, A. Radford, J. Wu, and D. Amodei. Scaling laws for neural language models. arXiv [cs.LG], Jan. 2020. E. Mercado and S. Handel. Understanding the structure of humpback whale songs (l). The Jo…
- full textchunk-008text/plain3 KB
doc:agent/chunk-008/5506d265-7ff5-434b-b60e-b755c8a596d6Show excerpt
Marine Science, 11:1394695, 2024. J. A. Allen, E. C. Garland, C. Garrigue, R. A. Dunlop, and M. J. Noad. Song complexity is maintained during inter-population cultural transmission of humpback whale songs. Scientific reports, 12(1): 8999, 2…
- full textchunk-007text/plain3 KB
doc:agent/chunk-007/04710b2a-ba75-48cb-94b5-13d951854faaShow excerpt
atasets with thousands of classes can be high performing, even on out-of-domain down- stream tasks. Next, the ‘bittern lesson’ learned when training Perch 2.0 was that bird species classification in particular is a challenging su- pervision…
- full textchunk-006text/plain3 KB
doc:agent/chunk-006/44f49039-e92d-4aae-a989-a3343ce76194Show excerpt
= 8k = 16k = 8 k = 16k = 8 k = 16 GMWM0.8900.9140.7640.8210.9360.9540.868* 0.917*0.8230.855 SurfPerch 0.9320.9470.8590.9030.9810.9840.7960.8990.982* 0.986* Perch 1.0 0.9580.9680.9010.9310.9770.9810.8360.9050.9580.970 Perch 2.0 0.9…
- full textchunk-005text/plain3 KB
doc:agent/chunk-005/31b9995b-056a-4dab-a3da-ede4fabae094Show excerpt
V2.348 kHz3.0102420.0MBirds, Frogs AVES-bio16 kHzVariable768 2 94.4MGeneral Audio BirdAVES (large)16 kHzVariable1024 3 315.4MGeneral Audio + Birds 4 Comparison models. As our goal is to provide guidance on which pretrained embedding models …
- full textchunk-004text/plain3 KB
doc:agent/chunk-004/2ce1467e-29e9-40e4-a12c-ee1e34601ebcShow excerpt
ludes new classes unseen by the models. The classes used in the NOAA PIPAN evaluation set include anthropomorphic noise, unknown whale species, and the following baleen whale species: common minke whale, humpback whale, sei whale, blue whal…
- full textchunk-003text/plain3 KB
doc:agent/chunk-003/05e7df2c-afdb-4b38-8576-118d1c22e948Show excerpt
ained on log-mel spectrograms using a classification loss. Additionally, the model used a form of self-distillation and a self-supervised loss (in the form of source recording prediction) with the goal of producing strong embeddings that ar…
- full textchunk-002text/plain3 KB
doc:agent/chunk-002/6ad8a5fa-2898-42fc-95e1-ea78861375f7Show excerpt
ion as new sounds are discovered while not having large amounts of human labeled data. Despite these challenges, passive acoustic monitoring is a critical tool for marine conservation and ecology (Fleishman et al., 2023), and discoveries ab…
- full textchunk-001text/plain3 KB
doc:agent/chunk-001/2b871fa0-4034-4d77-a1ce-b818711dd372Show excerpt
Perch 2.0 transfers ‘whale’ to underwater tasks Andrea Burns ∗ Google DeepMind Lauren Harrell ∗ Google Research Bart van Merriënboer Google DeepMind Vincent Dumoulin Google DeepMind Jenny Hamer Google DeepMind Tom Denton Google DeepMind Abs…
- full textchunk-005text/plain3 KB
doc:agent/chunk-005/84c4d25d-a6fb-4da9-95ec-773c6e223fa2Show excerpt
monitoring. Ecol. Inform., 61(101236):101236, Mar. 2021. 6 J. Kaplan, S. McCandlish, T. Henighan, T. B. Brown, B. Chess, R. Child, S. Gray, A. Radford, J. Wu, and D. Amodei. Scaling laws for neural language models. arXiv [cs.LG], Jan. 2020…
- full textchunk-004text/plain6 KB
doc:agent/chunk-004/597f88dd-b871-4083-99cd-a9a4484853abShow excerpt
e datasets with thousands of classes can be high performing, even on out-of-domain down- stream tasks. Next, the ‘bittern lesson’ learned when training Perch 2.0 was that bird species classification in particular is a challenging su- pervis…
- full textchunk-003text/plain6 KB
doc:agent/chunk-003/e23b9efa-8e61-4312-a564-68c6956429b2Show excerpt
ce on which pretrained embedding models should be used for agile modeling and transfer learning (with existing tools), we limit our comparisons to models supported in the Perch Hoplite Github repository 5 . We compare the performance of the…
- full textchunk-002text/plain6 KB
doc:agent/chunk-002/f0b400dc-caae-4eca-b34a-d5598b9eddf0Show excerpt
l of producing strong embeddings that are linearly separable for a wide range of bioacoustics tasks. Embeddings from the Perch model have shown successful generalization to tasks other than species classification (e.g., individual identific…
- full textchunk-001text/plain6 KB
doc:agent/chunk-001/ae1f6e1d-0812-43e1-93c6-1e7778c77d74Show excerpt
Perch 2.0 transfers ‘whale’ to underwater tasks Andrea Burns ∗ Google DeepMind Lauren Harrell ∗ Google Research Bart van Merriënboer Google DeepMind Vincent Dumoulin Google DeepMind Jenny Hamer Google DeepMind Tom Denton Google DeepMind Abs…
- full texttoiletpaper-smoke-paperapplication/pdf24 KB
tp:paper:c75b96b4-5c8e-4a8f-bf4c-2af6ba7423d9Show excerpt
Perch 2.0 transfers ‘whale’ to underwater tasks Andrea Burns ∗ Google DeepMind Lauren Harrell ∗ Google Research Bart van Merriënboer Google DeepMind Vincent Dumoulin Google DeepMind Jenny Hamer Google DeepMind Tom Denton Google DeepMind A…
See also
- Model
- Wmmsd Dataset
- Beans Benchmark
- Underwater Audio Task
- Noaa Pipan Dataset
- Reefset Dataset
- Dclde 2026 Dataset
- Marine Audio Validation Set
- Van Merrienboer Et Al 2025
- Broad Terrestrial
- Bittern Lesson
- Underwater Transfer Tasks
- Foundation Model
- Supervised Bioacoustics Foundation Model
- Bird
- Mammal
- Amphibian
- Insect
- Marine Mammal Audio Task
- Few Shot Transfer Learning
- Marine Mammal Audio
- Marine Mammal Classes
- Model Embedding
- Perch 1 0
- Surfperch
- Aves Bio
- Birdaves
- Birdnet V2 3
- Consistently High Performance
- Alternative Embedding Models
- Developing Linear Classifiers
- Marine Mammal Classification
- Few Labeled Examples
- Underwater Tasks
- Bioacoustics Foundation Model
- Labeled Recordings
- Birds
- Insects
- Mammals
- Amphibians
- Efficientnet B3
- Log Mel Spectrograms
- Classification Loss
- Self Distillation
- Self Supervised Loss
- Strong Embeddings
- Non Species Classification Tasks
- Unseen Species
- Watkins Marine Mammal Sound Database
- Model Version
- Wmmsd
- Embedding Model
- Northern Resident Killer Whale
- Transient Killer Whale
Keep researching
Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.