{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/ensembles-of-compact-region-specific","title":"Ensembles of Compact, Region-specific & Regularized Spiking Neural Networks for Scalable Place Recognition","arxiv_id":"2209.08723","date":"2022-09-19","proceeding":null,"authors":["Somayeh Hussaini","Michael Milford","Tobias Fischer"],"abstract":"Spiking neural networks have significant potential utility in robotics due to their high energy efficiency on specialized hardware, but proof-of-concept implementations have not yet typically achieved competitive performance or capability with conventional approaches. In this paper, we tackle one of the key practical challenges of scalability by introducing a novel modular ensemble network approach, where compact, localized spiking networks each learn and are solely responsible for recognizing places in a local region of the environment only. This modular approach creates a highly scalable system. However, it comes with a high-performance cost where a lack of global regularization at deployment time leads to hyperactive neurons that erroneously respond to places outside their learned region. Our second contribution introduces a regularization approach that detects and removes these problematic hyperactive neurons during the initial environmental learning phase. We evaluate this new scalable modular system on benchmark localization datasets Nordland and Oxford RobotCar, with comparisons to standard techniques NetVLAD, DenseVLAD, and SAD, and a previous spiking neural network system. Our system substantially outperforms the previous SNN system on its small dataset, but also maintains performance on 27 times larger benchmark datasets where the operation of the previous system is computationally infeasible, and performs competitively with the conventional localization systems.","url_abs":"https://arxiv.org/abs/2209.08723v3","url_pdf":"https://arxiv.org/pdf/2209.08723v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"ensembles-of-compact-region-specific","repo_url":"https://github.com/qvpr/vprsnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2209.08723","atlas_url":"https://app.syntology.ai/?focus=2209.08723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.08723"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/qvpr/vprsnn","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":8,"unverified":1},"by_repo_kind":{"official":{"samples":9,"ran":8,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"a96ffbef241371b2","entry":"get_2d_input_weights","repo":"qvpr/vprsnn","repo_kind":"official","path":"non_modular_snn/snn_model.py","file_url":"https://github.com/qvpr/vprsnn/blob/HEAD/non_modular_snn/snn_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a96ffbef241371b2"}},{"code_sha256_prefix":"50c1a870c63f44ac","entry":"get_current_performance","repo":"qvpr/vprsnn","repo_kind":"official","path":"non_modular_snn/snn_model.py","file_url":"https://github.com/qvpr/vprsnn/blob/HEAD/non_modular_snn/snn_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"50c1a870c63f44ac"}},{"code_sha256_prefix":"a887a1977eac8be7","entry":"get_new_assignments","repo":"qvpr/vprsnn","repo_kind":"official","path":"non_modular_snn/snn_model_evaluation.py","file_url":"https://github.com/qvpr/vprsnn/blob/HEAD/non_modular_snn/snn_model_evaluation.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a887a1977eac8be7"}},{"code_sha256_prefix":"a1a14ab4f98c5898","entry":"get_pred_results","repo":"qvpr/vprsnn","repo_kind":"official","path":"ens_seq/process_ensembles.py","file_url":"https://github.com/qvpr/vprsnn/blob/HEAD/ens_seq/process_ensembles.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a1a14ab4f98c5898"}},{"code_sha256_prefix":"720ef6aa43c99a5c","entry":"get_recognized_number_ranking","repo":"qvpr/vprsnn","repo_kind":"official","path":"non_modular_snn/snn_model_evaluation.py","file_url":"https://github.com/qvpr/vprsnn/blob/HEAD/non_modular_snn/snn_model_evaluation.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"720ef6aa43c99a5c"}},{"code_sha256_prefix":"00c77e9c7b606f8c","entry":"get_training_neuronal_spikes","repo":"qvpr/vprsnn","repo_kind":"official","path":"non_modular_snn/snn_model_evaluation.py","file_url":"https://github.com/qvpr/vprsnn/blob/HEAD/non_modular_snn/snn_model_evaluation.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"00c77e9c7b606f8c"}},{"code_sha256_prefix":"d4c6cb7efff7834e","entry":"ignore_hyperactive_neurons","repo":"qvpr/vprsnn","repo_kind":"official","path":"modular_snn/modular_snn_config_evaluation.py","file_url":"https://github.com/qvpr/vprsnn/blob/HEAD/modular_snn/modular_snn_config_evaluation.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d4c6cb7efff7834e"}},{"code_sha256_prefix":"66c440371d32e993","entry":"plot_initial_performance","repo":"qvpr/vprsnn","repo_kind":"official","path":"non_modular_snn/snn_model.py","file_url":"https://github.com/qvpr/vprsnn/blob/HEAD/non_modular_snn/snn_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"66c440371d32e993"}},{"code_sha256_prefix":"3bab27750d0830f8","entry":"compute_dist_matrix_seqslam","repo":"qvpr/vprsnn","repo_kind":"official","path":"ens_seq/process_seqmatch.py","file_url":"https://github.com/qvpr/vprsnn/blob/HEAD/ens_seq/process_seqmatch.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3bab27750d0830f8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}