{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZUP6YEMJL3DL46DJ7VNLGLMTOH","short_pith_number":"pith:ZUP6YEMJ","schema_version":"1.0","canonical_sha256":"cd1fec11895ec6be7869fd5ab32d9371c224726db64d057270bdbe4dca2974f7","source":{"kind":"arxiv","id":"2106.06988","version":3},"attestation_state":"computed","paper":{"title":"NDPNet: A novel non-linear data projection network for few-shot fine-grained image classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Changming Sun, Weichuan Zhang, Xuefang Liu, Yongsheng Gao, Zhe Xue","submitted_at":"2021-06-13T13:33:09Z","abstract_excerpt":"Metric-based few-shot fine-grained image classification (FSFGIC) aims to learn a transferable feature embedding network by estimating the similarities between query images and support classes from very few examples. In this work, we propose, for the first time, to introduce the non-linear data projection concept into the design of FSFGIC architecture in order to address the limited sample problem in few-shot learning and at the same time to increase the discriminability of the model for fine-grained image classification. Specifically, we first design a feature re-abstraction embedding network "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2106.06988","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-13T13:33:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"549efecacdaf86fdc0bc82d6f2a8e36574f82fba02c2bea7d63dea9778cc924b","abstract_canon_sha256":"a994e83081fa4c77398f90f0605bcd6f9f8a98bc7ee051a3727d235b26eb190b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:56:28.379794Z","signature_b64":"ry+scg50GbvTBV7gRsZFIChZq3TKA2sm72XdraokT7ywcSGrLrb9+/9K7mnL9A9BJQSlYNO2Ntbn/lEgJbrBCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd1fec11895ec6be7869fd5ab32d9371c224726db64d057270bdbe4dca2974f7","last_reissued_at":"2026-07-05T02:56:28.379354Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:56:28.379354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NDPNet: A novel non-linear data projection network for few-shot fine-grained image classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Changming Sun, Weichuan Zhang, Xuefang Liu, Yongsheng Gao, Zhe Xue","submitted_at":"2021-06-13T13:33:09Z","abstract_excerpt":"Metric-based few-shot fine-grained image classification (FSFGIC) aims to learn a transferable feature embedding network by estimating the similarities between query images and support classes from very few examples. In this work, we propose, for the first time, to introduce the non-linear data projection concept into the design of FSFGIC architecture in order to address the limited sample problem in few-shot learning and at the same time to increase the discriminability of the model for fine-grained image classification. Specifically, we first design a feature re-abstraction embedding network "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06988","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.06988/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2106.06988","created_at":"2026-07-05T02:56:28.379409+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.06988v3","created_at":"2026-07-05T02:56:28.379409+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06988","created_at":"2026-07-05T02:56:28.379409+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZUP6YEMJL3DL","created_at":"2026-07-05T02:56:28.379409+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZUP6YEMJL3DL46DJ","created_at":"2026-07-05T02:56:28.379409+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZUP6YEMJ","created_at":"2026-07-05T02:56:28.379409+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02498","citing_title":"GloResNet: A lightweight 3D CNN with global topological features for preterm brain injury prediction","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16936","citing_title":"Adaptive receptive field-based spatial-frequency feature reconstruction network for fine-grained few-shot image classification","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZUP6YEMJL3DL46DJ7VNLGLMTOH","json":"https://pith.science/pith/ZUP6YEMJL3DL46DJ7VNLGLMTOH.json","graph_json":"https://pith.science/api/pith-number/ZUP6YEMJL3DL46DJ7VNLGLMTOH/graph.json","events_json":"https://pith.science/api/pith-number/ZUP6YEMJL3DL46DJ7VNLGLMTOH/events.json","paper":"https://pith.science/paper/ZUP6YEMJ"},"agent_actions":{"view_html":"https://pith.science/pith/ZUP6YEMJL3DL46DJ7VNLGLMTOH","download_json":"https://pith.science/pith/ZUP6YEMJL3DL46DJ7VNLGLMTOH.json","view_paper":"https://pith.science/paper/ZUP6YEMJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.06988&json=true","fetch_graph":"https://pith.science/api/pith-number/ZUP6YEMJL3DL46DJ7VNLGLMTOH/graph.json","fetch_events":"https://pith.science/api/pith-number/ZUP6YEMJL3DL46DJ7VNLGLMTOH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZUP6YEMJL3DL46DJ7VNLGLMTOH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZUP6YEMJL3DL46DJ7VNLGLMTOH/action/storage_attestation","attest_author":"https://pith.science/pith/ZUP6YEMJL3DL46DJ7VNLGLMTOH/action/author_attestation","sign_citation":"https://pith.science/pith/ZUP6YEMJL3DL46DJ7VNLGLMTOH/action/citation_signature","submit_replication":"https://pith.science/pith/ZUP6YEMJL3DL46DJ7VNLGLMTOH/action/replication_record"}},"created_at":"2026-07-05T02:56:28.379409+00:00","updated_at":"2026-07-05T02:56:28.379409+00:00"}