{"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/class-incremental-grouping-network-for","title":"Class-Incremental Grouping Network for Continual Audio-Visual Learning","arxiv_id":"2309.05281","date":"2023-09-11","proceeding":"ICCV 2023 1","authors":["Shentong Mo","Weiguo Pian","Yapeng Tian"],"abstract":"Continual learning is a challenging problem in which models need to be trained on non-stationary data across sequential tasks for class-incremental learning. While previous methods have focused on using either regularization or rehearsal-based frameworks to alleviate catastrophic forgetting in image classification, they are limited to a single modality and cannot learn compact class-aware cross-modal representations for continual audio-visual learning. To address this gap, we propose a novel class-incremental grouping network (CIGN) that can learn category-wise semantic features to achieve continual audio-visual learning. Our CIGN leverages learnable audio-visual class tokens and audio-visual grouping to continually aggregate class-aware features. Additionally, it utilizes class tokens distillation and continual grouping to prevent forgetting parameters learned from previous tasks, thereby improving the model's ability to capture discriminative audio-visual categories. We conduct extensive experiments on VGGSound-Instruments, VGGSound-100, and VGG-Sound Sources benchmarks. Our experimental results demonstrate that the CIGN achieves state-of-the-art audio-visual class-incremental learning performance. Code is available at https://github.com/stoneMo/CIGN.","url_abs":"https://arxiv.org/abs/2309.05281v1","url_pdf":"https://arxiv.org/pdf/2309.05281v1.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":"class-incremental-grouping-network-for","repo_url":"https://github.com/stonemo/cign","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"class-incremental-learning","task_name":"Class Incremental Learning"},{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"audio-visual-learning","task_name":"audio-visual learning"},{"task_slug":"class-incremental-learning-1","task_name":"class-incremental learning"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.05281","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.05281"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/stonemo/cign","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/stoneMo/CIGN","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":2,"ran":4,"unverified":2},"by_repo_kind":{"official":{"samples":8,"ran":6,"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":"7f29142583965575","entry":"gumbel_softmax","repo":"stonemo/cign","repo_kind":"official","path":"grouping.py","file_url":"https://github.com/stonemo/cign/blob/HEAD/grouping.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7f29142583965575"}},{"code_sha256_prefix":"cb0acca1ea9ead1e","entry":"hard_softmax","repo":"stonemo/cign","repo_kind":"official","path":"grouping.py","file_url":"https://github.com/stonemo/cign/blob/HEAD/grouping.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cb0acca1ea9ead1e"}},{"code_sha256_prefix":"989269e62e59af83","entry":"load_image","repo":"stonemo/cign","repo_kind":"official","path":"datasets.py","file_url":"https://github.com/stonemo/cign/blob/HEAD/datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"989269e62e59af83"}},{"code_sha256_prefix":"d9a3275a90eeb0c1","entry":"log_mel_spectrogram","repo":"stonemo/cign","repo_kind":"official","path":"datasets.py","file_url":"https://github.com/stonemo/cign/blob/HEAD/datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d9a3275a90eeb0c1"}},{"code_sha256_prefix":"e7357eb51f7bea31","entry":"normalize_img","repo":"stonemo/cign","repo_kind":"official","path":"utils.py","file_url":"https://github.com/stonemo/cign/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e7357eb51f7bea31"}},{"code_sha256_prefix":"548ea444cb942399","entry":"visualize","repo":"stonemo/cign","repo_kind":"official","path":"utils.py","file_url":"https://github.com/stonemo/cign/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"548ea444cb942399"}},{"code_sha256_prefix":"51b6f8f92fd22dbd","entry":"CIGN","repo":"stoneMo/CIGN","repo_kind":"official","path":"model.py","file_url":"https://github.com/stoneMo/CIGN/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"51b6f8f92fd22dbd"}},{"code_sha256_prefix":"e3ffe91745bebb04","entry":"build_optimizer_and_scheduler_adam_v2","repo":"stonemo/cign","repo_kind":"official","path":"utils.py","file_url":"https://github.com/stonemo/cign/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e3ffe91745bebb04"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}