{"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/transductive-information-maximization-for-few","title":"Transductive Information Maximization For Few-Shot Learning","arxiv_id":"2008.11297","date":"2020-08-25","proceeding":null,"authors":["Malik Boudiaf","Ziko Imtiaz Masud","Jérôme Rony","José Dolz","Pablo Piantanida","Ismail Ben Ayed"],"abstract":"We introduce Transductive Infomation Maximization (TIM) for few-shot learning. Our method maximizes the mutual information between the query features and their label predictions for a given few-shot task, in conjunction with a supervision loss based on the support set. Furthermore, we propose a new alternating-direction solver for our mutual-information loss, which substantially speeds up transductive-inference convergence over gradient-based optimization, while yielding similar accuracy. TIM inference is modular: it can be used on top of any base-training feature extractor. Following standard transductive few-shot settings, our comprehensive experiments demonstrate that TIM outperforms state-of-the-art methods significantly across various datasets and networks, while used on top of a fixed feature extractor trained with simple cross-entropy on the base classes, without resorting to complex meta-learning schemes. It consistently brings between 2% and 5% improvement in accuracy over the best performing method, not only on all the well-established few-shot benchmarks but also on more challenging scenarios,with domain shifts and larger numbers of classes.","url_abs":"https://arxiv.org/abs/2008.11297v3","url_pdf":"https://arxiv.org/pdf/2008.11297v3.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":"transductive-information-maximization-for-few","repo_url":"https://github.com/mboudiaf/TIM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"transductive-information-maximization-for-few","repo_url":"https://github.com/sicara/easy-few-shot-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-5-1","task":"Few-Shot Image Classification","dataset":"CUB 200 5-way 1-shot","model":"TIM-GD","rank_in_archive_order":17,"of":36,"metrics":{"Accuracy":"82.2%"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-5","task":"Few-Shot Image Classification","dataset":"CUB 200 5-way 5-shot","model":"TIM-GD","rank_in_archive_order":19,"of":32,"metrics":{"Accuracy":"90.8"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-10","task":"Few-Shot Image Classification","dataset":"Mini-ImageNet to CUB - 5 shot learning","model":"TIM-GD","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"71"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-12","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 10-way (1-shot)","model":"TIM-GD","rank_in_archive_order":3,"of":14,"metrics":{"Accuracy":"56.1"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-13","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 10-way (5-shot)","model":"TIM-GD","rank_in_archive_order":3,"of":14,"metrics":{"Accuracy":"72.8"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-7","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 20-way (1-shot)","model":"TIM-GD","rank_in_archive_order":1,"of":6,"metrics":{"Accuracy":"39.3"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-8","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 20-way (5-shot)","model":"TIM-GD","rank_in_archive_order":1,"of":6,"metrics":{"Accuracy":"59.5"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-2","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (1-shot)","model":"TIM-GD","rank_in_archive_order":18,"of":105,"metrics":{"Accuracy":"77.80"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-tiered","task":"Few-Shot Image Classification","dataset":"Tiered ImageNet 5-way (1-shot)","model":"TIM-GD","rank_in_archive_order":9,"of":49,"metrics":{"Accuracy":"82.1"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-tiered-1","task":"Few-Shot Image Classification","dataset":"Tiered ImageNet 5-way (5-shot)","model":"TIM-GD","rank_in_archive_order":8,"of":51,"metrics":{"Accuracy":"89.8"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-learning-on-mini-imagenet-5-shot","task":"Few-Shot Learning","dataset":"Mini-ImageNet - 5-Shot Learning","model":"TIM-GD","rank_in_archive_order":2,"of":3,"metrics":{"Accuracy":"87.4%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2008.11297","atlas_url":"https://app.syntology.ai/?focus=2008.11297","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.11297"}},"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/mboudiaf/TIM","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sicara/easy-few-shot-learning","reach":null}],"summary":{"ran":2,"ran_draft_wrong":2,"unverified":6},"by_repo_kind":{"official":{"samples":7,"ran":1,"repositories":1},"listed":{"samples":3,"ran":3,"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":"637e871cf76bfc10","entry":"FewShotClassifier","repo":"sicara/easy-few-shot-learning","repo_kind":"listed","path":"easyfsl/methods/tim.py","file_url":"https://github.com/sicara/easy-few-shot-learning/blob/HEAD/easyfsl/methods/tim.py","link_basis":"first_harvest_node","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":"637e871cf76bfc10"}},{"code_sha256_prefix":"c46ba9a1cacbe109","entry":"TIM","repo":"sicara/easy-few-shot-learning","repo_kind":"listed","path":"easyfsl/methods/tim.py","file_url":"https://github.com/sicara/easy-few-shot-learning/blob/HEAD/easyfsl/methods/tim.py","link_basis":"first_harvest_node","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":"c46ba9a1cacbe109"}},{"code_sha256_prefix":"31e41d7e676cb492","entry":"compute_prototypes","repo":"sicara/easy-few-shot-learning","repo_kind":"listed","path":"easyfsl/methods/tim.py","file_url":"https://github.com/sicara/easy-few-shot-learning/blob/HEAD/easyfsl/methods/tim.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"31e41d7e676cb492"}},{"code_sha256_prefix":"a03c85ae21c3b667","entry":"get_one_hot","repo":"mboudiaf/TIM","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/mboudiaf/TIM/blob/HEAD/src/utils.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a03c85ae21c3b667"}},{"code_sha256_prefix":"02652b1ac1a54dda","entry":"conv_block","repo":"mboudiaf/TIM","repo_kind":"official","path":"src/models/Conv4.py","file_url":"https://github.com/mboudiaf/TIM/blob/HEAD/src/models/Conv4.py","link_basis":"first_harvest_node","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":"02652b1ac1a54dda"}},{"code_sha256_prefix":"12cbd4d101797d30","entry":"get_features","repo":"mboudiaf/TIM","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/mboudiaf/TIM/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","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":"12cbd4d101797d30"}},{"code_sha256_prefix":"e232226ad7c9556f","entry":"get_logs_path","repo":"mboudiaf/TIM","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/mboudiaf/TIM/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","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":"e232226ad7c9556f"}},{"code_sha256_prefix":"235da783eeb0573f","entry":"get_metric","repo":"mboudiaf/TIM","repo_kind":"official","path":"src/models/ProtoNet.py","file_url":"https://github.com/mboudiaf/TIM/blob/HEAD/src/models/ProtoNet.py","link_basis":"first_harvest_node","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":"235da783eeb0573f"}},{"code_sha256_prefix":"97533e04cdf4da7e","entry":"with_augment","repo":"mboudiaf/TIM","repo_kind":"official","path":"src/datasets/transform.py","file_url":"https://github.com/mboudiaf/TIM/blob/HEAD/src/datasets/transform.py","link_basis":"first_harvest_node","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":"97533e04cdf4da7e"}},{"code_sha256_prefix":"e1f7a44f9ac823d7","entry":"without_augment","repo":"mboudiaf/TIM","repo_kind":"official","path":"src/datasets/transform.py","file_url":"https://github.com/mboudiaf/TIM/blob/HEAD/src/datasets/transform.py","link_basis":"first_harvest_node","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":"e1f7a44f9ac823d7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}