{"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/introspective-learning-a-two-stage-approach-1","title":"Introspective Learning : A Two-Stage Approach for Inference in Neural Networks","arxiv_id":"2209.08425","date":"2022-09-17","proceeding":null,"authors":["Mohit Prabhushankar","Ghassan AlRegib"],"abstract":"In this paper, we advocate for two stages in a neural network's decision making process. The first is the existing feed-forward inference framework where patterns in given data are sensed and associated with previously learned patterns. The second stage is a slower reflection stage where we ask the network to reflect on its feed-forward decision by considering and evaluating all available choices. Together, we term the two stages as introspective learning. We use gradients of trained neural networks as a measurement of this reflection. A simple three-layered Multi Layer Perceptron is used as the second stage that predicts based on all extracted gradient features. We perceptually visualize the post-hoc explanations from both stages to provide a visual grounding to introspection. For the application of recognition, we show that an introspective network is 4% more robust and 42% less prone to calibration errors when generalizing to noisy data. We also illustrate the value of introspective networks in downstream tasks that require generalizability and calibration including active learning, out-of-distribution detection, and uncertainty estimation. Finally, we ground the proposed machine introspection to human introspection for the application of image quality assessment.","url_abs":"https://arxiv.org/abs/2209.08425v1","url_pdf":"https://arxiv.org/pdf/2209.08425v1.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":"introspective-learning-a-two-stage-approach-1","repo_url":"https://github.com/olivesgatech/introspective-learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"},{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"image-quality-assessment","task_name":"Image Quality Assessment"},{"task_slug":"out-of-distribution-detection","task_name":"Out-of-Distribution Detection"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"},{"task_slug":"two","task_name":"Vocal Bursts Valence Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2209.08425","atlas_url":"https://app.syntology.ai/?focus=2209.08425","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.08425"}},"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":"deterministic:regex_extraction","url":"https://github.com/markus93/NN_calibration","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/jfc43/robust-ood-detection","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/JordanAsh/badge","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/adityac94/Grad_CAM_plus_plus","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/olivesgatech/introspective-learning","reach":null}],"summary":{"ran":1,"ran_honours":1,"ran_fixture":1,"unverified":1},"by_repo_kind":{"found_in_text":{"samples":2,"ran":1,"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":4,"samples":[{"code_sha256_prefix":"6ddce4b6345c6b85","entry":"Strategy","repo":"JordanAsh/badge","repo_kind":"found_in_text","path":"query_strategies/badge_sampling.py","file_url":"https://github.com/JordanAsh/badge/blob/HEAD/query_strategies/badge_sampling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6ddce4b6345c6b85"}},{"code_sha256_prefix":"81e261e3bc5ae477","entry":"distance","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"81e261e3bc5ae477"}},{"code_sha256_prefix":"28cc855e066f5ccd","entry":"init_centers","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"28cc855e066f5ccd"}},{"code_sha256_prefix":"0c39991686b6770f","entry":"BadgeSampling","repo":"JordanAsh/badge","repo_kind":"found_in_text","path":"query_strategies/badge_sampling.py","file_url":"https://github.com/JordanAsh/badge/blob/HEAD/query_strategies/badge_sampling.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0c39991686b6770f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}