{"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/admn-a-layer-wise-adaptive-multimodal-network","title":"ADMN: A Layer-Wise Adaptive Multimodal Network for Dynamic Input Noise and Compute Resources","arxiv_id":"2502.07862","date":"2025-02-11","proceeding":null,"authors":["Jason Wu","Kang Yang","Lance Kaplan","Mani Srivastava"],"abstract":"Multimodal deep learning systems are deployed in dynamic scenarios due to the robustness afforded by multiple sensing modalities. Nevertheless, they struggle with varying compute resource availability (due to multi-tenancy, device heterogeneity, etc.) and fluctuating quality of inputs (from sensor feed corruption, environmental noise, etc.). Current multimodal systems employ static resource provisioning and cannot easily adapt when compute resources change over time. Additionally, their reliance on processing sensor data with fixed feature extractors is ill-equipped to handle variations in modality quality. Consequently, uninformative modalities, such as those with high noise, needlessly consume resources better allocated towards other modalities. We propose ADMN, a layer-wise Adaptive Depth Multimodal Network capable of tackling both challenges - it adjusts the total number of active layers across all modalities to meet compute resource constraints, and continually reallocates layers across input modalities according to their modality quality. Our evaluations showcase ADMN can match the accuracy of state-of-the-art networks while reducing up to 75% of their floating-point operations.","url_abs":"https://arxiv.org/abs/2502.07862v1","url_pdf":"https://arxiv.org/pdf/2502.07862v1.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":[],"tasks":[{"task_slug":"multimodal-deep-learning","task_name":"Multimodal Deep Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.07862","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.07862"}},"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":"deterministic:regex_extraction","url":"https://github.com/nesl/ADMN","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"unverified":4},"by_repo_kind":{"found_in_text":{"samples":4,"ran":0,"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":"f7488488e3fc3231","entry":"computeDist","repo":"nesl/ADMN","repo_kind":"found_in_text","path":"AVE_Custom/batch_test_scratch.py","file_url":"https://github.com/nesl/ADMN/blob/HEAD/AVE_Custom/batch_test_scratch.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"f7488488e3fc3231"}},{"code_sha256_prefix":"d7cf2dfd56ace872","entry":"mseloss","repo":"nesl/ADMN","repo_kind":"found_in_text","path":"GTDM_Blur/train_adamml_subnets.py","file_url":"https://github.com/nesl/ADMN/blob/HEAD/GTDM_Blur/train_adamml_subnets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"d7cf2dfd56ace872"}},{"code_sha256_prefix":"a5d43bddf5bcc327","entry":"mseloss","repo":"nesl/ADMN","repo_kind":"found_in_text","path":"GTDM_Reconfigurable_3_Mods/finetune_layers.py","file_url":"https://github.com/nesl/ADMN/blob/HEAD/GTDM_Reconfigurable_3_Mods/finetune_layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"a5d43bddf5bcc327"}},{"code_sha256_prefix":"2bb6109e47bd4aae","entry":"str2bool","repo":"nesl/ADMN","repo_kind":"found_in_text","path":"GTDM_Blur/train_adamml_subnets.py","file_url":"https://github.com/nesl/ADMN/blob/HEAD/GTDM_Blur/train_adamml_subnets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"2bb6109e47bd4aae"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}