{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OII7AS6WUK5ZEAGU5APCALDQ6Y","short_pith_number":"pith:OII7AS6W","schema_version":"1.0","canonical_sha256":"7211f04bd6a2bb9200d4e81e202c70f604d3bd1788c14b88b82bbf498a89187d","source":{"kind":"arxiv","id":"1801.05787","version":2},"attestation_state":"computed","paper":{"title":"Faster gaze prediction with dense networks and Fisher pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Alykhan Tejani, Ferenc Husz\\'ar, Iryna Korshunova, Lucas Theis","submitted_at":"2018-01-17T18:34:33Z","abstract_excerpt":"Predicting human fixations from images has recently seen large improvements by leveraging deep representations which were pretrained for object recognition. However, as we show in this paper, these networks are highly overparameterized for the task of fixation prediction. We first present a simple yet principled greedy pruning method which we call Fisher pruning. Through a combination of knowledge distillation and Fisher pruning, we obtain much more runtime-efficient architectures for saliency prediction, achieving a 10x speedup for the same AUC performance as a state of the art network on the"},"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":"1801.05787","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-17T18:34:33Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9ed395032509fbf816dd543ebb865b66e16edc23c9183be2104f83d2dd13d3cd","abstract_canon_sha256":"6c3f53d9fdaf81b46b982e4c01d52d8ad40690729e7001c65aac7d7f2450f613"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:18.098129Z","signature_b64":"eLNjQkoJCF+1QftyFnI6Xn2nTDRvZJXi8Dk8F0NYqFeBLB1iklcGU3XvzfHj7tS1wnFjb0K6kPIMyAk7YQW7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7211f04bd6a2bb9200d4e81e202c70f604d3bd1788c14b88b82bbf498a89187d","last_reissued_at":"2026-05-18T00:11:18.097398Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:18.097398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Faster gaze prediction with dense networks and Fisher pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Alykhan Tejani, Ferenc Husz\\'ar, Iryna Korshunova, Lucas Theis","submitted_at":"2018-01-17T18:34:33Z","abstract_excerpt":"Predicting human fixations from images has recently seen large improvements by leveraging deep representations which were pretrained for object recognition. However, as we show in this paper, these networks are highly overparameterized for the task of fixation prediction. We first present a simple yet principled greedy pruning method which we call Fisher pruning. Through a combination of knowledge distillation and Fisher pruning, we obtain much more runtime-efficient architectures for saliency prediction, achieving a 10x speedup for the same AUC performance as a state of the art network on the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.05787","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1801.05787","created_at":"2026-05-18T00:11:18.097524+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.05787v2","created_at":"2026-05-18T00:11:18.097524+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.05787","created_at":"2026-05-18T00:11:18.097524+00:00"},{"alias_kind":"pith_short_12","alias_value":"OII7AS6WUK5Z","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OII7AS6WUK5ZEAGU","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OII7AS6W","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.10771","citing_title":"Importance Estimation for Neural Network Pruning","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13688","citing_title":"MedCore: Boundary-Preserving Medical Core Pruning for MedSAM","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18264","citing_title":"Universally Empowering Zeroth-Order Optimization via Adaptive Layer-wise Sampling","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OII7AS6WUK5ZEAGU5APCALDQ6Y","json":"https://pith.science/pith/OII7AS6WUK5ZEAGU5APCALDQ6Y.json","graph_json":"https://pith.science/api/pith-number/OII7AS6WUK5ZEAGU5APCALDQ6Y/graph.json","events_json":"https://pith.science/api/pith-number/OII7AS6WUK5ZEAGU5APCALDQ6Y/events.json","paper":"https://pith.science/paper/OII7AS6W"},"agent_actions":{"view_html":"https://pith.science/pith/OII7AS6WUK5ZEAGU5APCALDQ6Y","download_json":"https://pith.science/pith/OII7AS6WUK5ZEAGU5APCALDQ6Y.json","view_paper":"https://pith.science/paper/OII7AS6W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.05787&json=true","fetch_graph":"https://pith.science/api/pith-number/OII7AS6WUK5ZEAGU5APCALDQ6Y/graph.json","fetch_events":"https://pith.science/api/pith-number/OII7AS6WUK5ZEAGU5APCALDQ6Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OII7AS6WUK5ZEAGU5APCALDQ6Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OII7AS6WUK5ZEAGU5APCALDQ6Y/action/storage_attestation","attest_author":"https://pith.science/pith/OII7AS6WUK5ZEAGU5APCALDQ6Y/action/author_attestation","sign_citation":"https://pith.science/pith/OII7AS6WUK5ZEAGU5APCALDQ6Y/action/citation_signature","submit_replication":"https://pith.science/pith/OII7AS6WUK5ZEAGU5APCALDQ6Y/action/replication_record"}},"created_at":"2026-05-18T00:11:18.097524+00:00","updated_at":"2026-05-18T00:11:18.097524+00:00"}