[ { "@id": "https://w3id.org/sciencelive/np/RAauQR3eY4NGILF2ei5a6YLbZjT7JDK_tQGYyl2R4DcMk/provenance", "@graph": [ { "@id": "https://w3id.org/sciencelive/np/RAauQR3eY4NGILF2ei5a6YLbZjT7JDK_tQGYyl2R4DcMk/assertion", "http://www.w3.org/ns/prov#wasAttributedTo": [ { "@id": "https://orcid.org/0000-0002-1784-2920" } ] } ] }, { "@id": "https://w3id.org/sciencelive/np/RAauQR3eY4NGILF2ei5a6YLbZjT7JDK_tQGYyl2R4DcMk/pubinfo", "@graph": [ { "@id": "https://orcid.org/0000-0002-1784-2920", "http://xmlns.com/foaf/0.1/name": [ { "@value": "Anne Fouilloux" } ] }, { "@id": "https://w3id.org/sciencelive/np/RAauQR3eY4NGILF2ei5a6YLbZjT7JDK_tQGYyl2R4DcMk", "http://purl.org/dc/terms/created": [ { "@value": "2026-04-26T19:36:55.873Z", "@type": "http://www.w3.org/2001/XMLSchema#dateTime" } ], "http://purl.org/dc/terms/creator": [ { "@id": "https://orcid.org/0000-0002-1784-2920" } ], "http://purl.org/dc/terms/license": [ { "@id": "https://creativecommons.org/licenses/by/4.0/" } ], "http://purl.org/nanopub/x/introduces": [ { "@id": "https://w3id.org/sciencelive/np/RAauQR3eY4NGILF2ei5a6YLbZjT7JDK_tQGYyl2R4DcMk/decrop-2025-cnn-scattering-stacking-study" } ], "http://purl.org/nanopub/x/wasCreatedAt": [ { "@id": "https://platform.sciencelive4all.org" } ], "http://www.w3.org/2000/01/rdf-schema#label": [ { "@value": "NP created using Declaring a replication study design according to FORRT" } ], "https://w3id.org/np/o/ntemplate/wasCreatedFromTemplate": [ { "@id": "https://w3id.org/np/RAuLEjPp-4dTvPwMkfHggTto1CgjIftiGRAgHlyeEonjQ" } ] }, { "@id": "https://w3id.org/sciencelive/np/RAauQR3eY4NGILF2ei5a6YLbZjT7JDK_tQGYyl2R4DcMk/sig", "http://purl.org/nanopub/x/hasAlgorithm": [ { "@value": "RSA" } ], "http://purl.org/nanopub/x/hasPublicKey": [ { "@value": "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" } ], "http://purl.org/nanopub/x/hasSignature": [ { "@value": "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" } ], "http://purl.org/nanopub/x/hasSignatureTarget": [ { "@id": "https://w3id.org/sciencelive/np/RAauQR3eY4NGILF2ei5a6YLbZjT7JDK_tQGYyl2R4DcMk" } ], "http://purl.org/nanopub/x/signedBy": [ { "@id": "https://orcid.org/0000-0002-1784-2920" } ] } ] }, { "@id": "https://w3id.org/sciencelive/np/RAauQR3eY4NGILF2ei5a6YLbZjT7JDK_tQGYyl2R4DcMk/Head", "@graph": [ { "@id": "https://w3id.org/sciencelive/np/RAauQR3eY4NGILF2ei5a6YLbZjT7JDK_tQGYyl2R4DcMk", "http://www.nanopub.org/nschema#hasAssertion": [ { "@id": "https://w3id.org/sciencelive/np/RAauQR3eY4NGILF2ei5a6YLbZjT7JDK_tQGYyl2R4DcMk/assertion" } ], "http://www.nanopub.org/nschema#hasProvenance": [ { "@id": "https://w3id.org/sciencelive/np/RAauQR3eY4NGILF2ei5a6YLbZjT7JDK_tQGYyl2R4DcMk/provenance" } ], "http://www.nanopub.org/nschema#hasPublicationInfo": [ { "@id": "https://w3id.org/sciencelive/np/RAauQR3eY4NGILF2ei5a6YLbZjT7JDK_tQGYyl2R4DcMk/pubinfo" } ], "@type": [ "http://www.nanopub.org/nschema#Nanopublication" ] } ] }, { "@id": "https://w3id.org/sciencelive/np/RAauQR3eY4NGILF2ei5a6YLbZjT7JDK_tQGYyl2R4DcMk/assertion", "@graph": [ { "@id": "https://w3id.org/sciencelive/np/RAauQR3eY4NGILF2ei5a6YLbZjT7JDK_tQGYyl2R4DcMk/decrop-2025-cnn-scattering-stacking-study", "@type": [ "https://w3id.org/sciencelive/o/terms/FORRT-Replication-Study", "https://w3id.org/sciencelive/o/terms/Replication-Study" ], "http://www.w3.org/2000/01/rdf-schema#label": [ { "@value": "CNN + scattering stacking on Decrop 2025's plankton splits" } ], "http://www.w3.org/2004/02/skos/core#related": [ { "@id": "http://www.wikidata.org/entity/Q113009580" }, { "@id": "http://www.wikidata.org/entity/Q17084460" }, { "@id": "http://www.wikidata.org/entity/Q184755" }, { "@id": "http://www.wikidata.org/entity/Q2539" }, { "@id": "http://www.wikidata.org/entity/Q3604063" }, { "@id": "http://www.wikidata.org/entity/Q98526763" } ], "https://w3id.org/sciencelive/o/terms/hasDeviationDescription": [ { "@value": "This is an extension, not a reproduction. Differences from Decrop et al. 2025: (1) we add a stacking meta-classifier on top of the CNN's softmax outputs; the original paper reports CNN-alone metrics. (2) We compute scattering features as additional input — the paper does not use scattering. (3) Reported metrics include mean rare-class recall (computed on the 13 classes with train-set size <200), which the paper does not report; aggregate top-1, top-5, micro/macro/weighted F1 are all from the same test.txt evaluation pipeline. Differences from Delouis et al. 2022 (FOSCAT method paper): we use FOSCAT's 2D scattering operator (scat_cov.funct) on flat RGB images, not the spherical HEALPix variant the paper develops; same library, different operator. As with chains #1–#4, FOSCAT was used via the annefou/FOSCAT@v0.1.0-cpu fork; that CPU patch has since been merged upstream and is included in foscat>=2026.4.1 on PyPI." } ], "https://w3id.org/sciencelive/o/terms/hasDiscipline": [ { "@id": "http://www.wikidata.org/entity/Q7173" } ], "https://w3id.org/sciencelive/o/terms/hasMethodologyDescription": [ { "@value": "Three-stage pipeline. \nStage 1 (01_scattering_features.py): compute multi-scale scattering features on RGB phytoplankton images via FOSCAT scat_cov.funct(NORIENT=8, KERNELSZ=3) at 64×64 pixels, producing 246-dimensional feature vectors per image. Features are computed on (a) a balanced training subset, (b) Decrop's released val.txt (33,829 images), and (c) Decrop's released test.txt (33,718 images). \n\nStage 2 (02_cnn_predictions.py): obtain CNN softmax probabilities for the same val and test images by running Decrop's pretrained EfficientNetV2-B0 via the authors' planktonclas package with 10-crop test-time augmentation. These predictions can equivalently be sourced from the upstream fiesta-decrop-reproduction repository (Zenodo 10.5281/zenodo.19701133), which is the FAIR-archived form of the same computation. \n\nStage 3 (03_stacking.py): fit a class-weighted scikit-learn LogisticRegression on the 246-dim scattering features (StandardScaler + class_weight='balanced') to obtain scattering-derived softmax probabilities; concatenate with CNN softmax probabilities to form 190-dim meta-features; train a second class-weighted LogisticRegression on Decrop's val split as the stacking meta-classifier; evaluate on Decrop's test split. Compute top-1, top-5, and per-class recall against the integer labels in test.txt. Mean rare-class recall is averaged over the 13 'rare' classes defined as those with fewer than 200 training-set examples in Decrop's train.txt. Comparator results: CNN alone, scattering+LR alone, naive 50/50 probability ensemble, and a hard-switch oracle ceiling (perfect choice between CNN and scattering predictions per image) for context." } ], "https://w3id.org/sciencelive/o/terms/hasScopeDescription": [ { "@value": "This study tests whether multi-scale scattering features computed independently of the CNN can be combined with the CNN's softmax probabilities via a class-weighted stacking meta-classifier to lift mean rare-class recall on Decrop et al. 2025's exact 95-class phytoplankton classification benchmark, at acceptable cost to aggregate top-1 accuracy. The chain reuses Decrop's released dataset, pretrained CNN weights, and train.txt/val.txt/test.txt splits, asking whether the rare-species class-imbalance limitation acknowledged in the paper can be partially addressed by complementary feature representations." } ], "https://w3id.org/sciencelive/o/terms/targetsClaim": [ { "@id": "https://w3id.org/sciencelive/np/RAeI2cspabQBUMHiA94jOKjiBypsIFSPPDwH_f5l1sJu4/decrop-2025-cnn-scattering-stacking-claim" } ] } ] } ]