{"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/fixing-overconfidence-in-dynamic-neural","title":"Fixing Overconfidence in Dynamic Neural Networks","arxiv_id":"2302.06359","date":"2023-02-13","proceeding":null,"authors":["Lassi Meronen","Martin Trapp","Andrea Pilzer","Le Yang","Arno Solin"],"abstract":"Dynamic neural networks are a recent technique that promises a remedy for the increasing size of modern deep learning models by dynamically adapting their computational cost to the difficulty of the inputs. In this way, the model can adjust to a limited computational budget. However, the poor quality of uncertainty estimates in deep learning models makes it difficult to distinguish between hard and easy samples. To address this challenge, we present a computationally efficient approach for post-hoc uncertainty quantification in dynamic neural networks. We show that adequately quantifying and accounting for both aleatoric and epistemic uncertainty through a probabilistic treatment of the last layers improves the predictive performance and aids decision-making when determining the computational budget. In the experiments, we show improvements on CIFAR-100, ImageNet, and Caltech-256 in terms of accuracy, capturing uncertainty, and calibration error.","url_abs":"https://arxiv.org/abs/2302.06359v4","url_pdf":"https://arxiv.org/pdf/2302.06359v4.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":"fixing-overconfidence-in-dynamic-neural","repo_url":"https://github.com/aaltoml/calibrated-dnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"dynamic-neural-networks","task_name":"Dynamic neural networks"},{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2302.06359","atlas_url":"https://app.syntology.ai/?focus=2302.06359","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.06359"}},"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/aaltoml/calibrated-dnn","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"unverified":5},"by_repo_kind":{"official":{"samples":9,"ran":4,"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":"045fc85256f7d946","entry":"Entropy","repo":"aaltoml/calibrated-dnn","repo_kind":"official","path":"adaptive_inference.py","file_url":"https://github.com/aaltoml/calibrated-dnn/blob/HEAD/adaptive_inference.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":"045fc85256f7d946"}},{"code_sha256_prefix":"e6844a563cce4871","entry":"accuracy","repo":"aaltoml/calibrated-dnn","repo_kind":"official","path":"adaptive_inference.py","file_url":"https://github.com/aaltoml/calibrated-dnn/blob/HEAD/adaptive_inference.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":"e6844a563cce4871"}},{"code_sha256_prefix":"ad7b29a67bdb8524","entry":"calc_ensemble_logits","repo":"aaltoml/calibrated-dnn","repo_kind":"official","path":"adaptive_inference.py","file_url":"https://github.com/aaltoml/calibrated-dnn/blob/HEAD/adaptive_inference.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":"ad7b29a67bdb8524"}},{"code_sha256_prefix":"cac21f2c1e3022d0","entry":"norm","repo":"aaltoml/calibrated-dnn","repo_kind":"official","path":"laplace.py","file_url":"https://github.com/aaltoml/calibrated-dnn/blob/HEAD/laplace.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":"cac21f2c1e3022d0"}},{"code_sha256_prefix":"5af8b8b09515bd4b","entry":"estimate_variance_efficient","repo":"aaltoml/calibrated-dnn","repo_kind":"official","path":"laplace.py","file_url":"https://github.com/aaltoml/calibrated-dnn/blob/HEAD/laplace.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":"5af8b8b09515bd4b"}},{"code_sha256_prefix":"6ab6ac3cf72849e7","entry":"get_dataloaders","repo":"aaltoml/calibrated-dnn","repo_kind":"official","path":"dataloader.py","file_url":"https://github.com/aaltoml/calibrated-dnn/blob/HEAD/dataloader.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":"6ab6ac3cf72849e7"}},{"code_sha256_prefix":"35a5cf7271901d9c","entry":"get_layer_info","repo":"aaltoml/calibrated-dnn","repo_kind":"official","path":"op_counter.py","file_url":"https://github.com/aaltoml/calibrated-dnn/blob/HEAD/op_counter.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":"35a5cf7271901d9c"}},{"code_sha256_prefix":"76cc74efee42ba21","entry":"get_num_gen","repo":"aaltoml/calibrated-dnn","repo_kind":"official","path":"op_counter.py","file_url":"https://github.com/aaltoml/calibrated-dnn/blob/HEAD/op_counter.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":"76cc74efee42ba21"}},{"code_sha256_prefix":"26ff085b343fa39e","entry":"is_leaf","repo":"aaltoml/calibrated-dnn","repo_kind":"official","path":"op_counter.py","file_url":"https://github.com/aaltoml/calibrated-dnn/blob/HEAD/op_counter.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":"26ff085b343fa39e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}