{"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/lum-vit-learnable-under-sampling-mask-vision","title":"LUM-ViT: Learnable Under-sampling Mask Vision Transformer for Bandwidth Limited Optical Signal Acquisition","arxiv_id":"2403.01412","date":"2024-03-03","proceeding":null,"authors":["Lingfeng Liu","Dong Ni","Hangjie Yuan"],"abstract":"Bandwidth constraints during signal acquisition frequently impede real-time detection applications. Hyperspectral data is a notable example, whose vast volume compromises real-time hyperspectral detection. To tackle this hurdle, we introduce a novel approach leveraging pre-acquisition modulation to reduce the acquisition volume. This modulation process is governed by a deep learning model, utilizing prior information. Central to our approach is LUM-ViT, a Vision Transformer variant. Uniquely, LUM-ViT incorporates a learnable under-sampling mask tailored for pre-acquisition modulation. To further optimize for optical calculations, we propose a kernel-level weight binarization technique and a three-stage fine-tuning strategy. Our evaluations reveal that, by sampling a mere 10% of the original image pixels, LUM-ViT maintains the accuracy loss within 1.8% on the ImageNet classification task. The method sustains near-original accuracy when implemented on real-world optical hardware, demonstrating its practicality. Code will be available at https://github.com/MaxLLF/LUM-ViT.","url_abs":"https://arxiv.org/abs/2403.01412v1","url_pdf":"https://arxiv.org/pdf/2403.01412v1.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":"lum-vit-learnable-under-sampling-mask-vision","repo_url":"https://github.com/maxllf/lum-vit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"binarization","task_name":"Binarization"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2403.01412","atlas_url":"https://app.syntology.ai/?focus=2403.01412","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01412"}},"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/MaxLLF/LUM-ViT","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/maxllf/lum-vit","reach":{"status":"ok"}}],"summary":{"ran":4,"ran_violates":1,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":7,"samples":[{"code_sha256_prefix":"71f6284d7ea766a7","entry":"Attention","repo":"maxllf/lum-vit","repo_kind":"official","path":"LUM-ViT.py","file_url":"https://github.com/maxllf/lum-vit/blob/HEAD/LUM-ViT.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":"71f6284d7ea766a7"}},{"code_sha256_prefix":"552fc396d62c3313","entry":"Block","repo":"maxllf/lum-vit","repo_kind":"official","path":"LUM-ViT.py","file_url":"https://github.com/maxllf/lum-vit/blob/HEAD/LUM-ViT.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"552fc396d62c3313"}},{"code_sha256_prefix":"b55b079ace7d9330","entry":"TokenChannelMask","repo":"maxllf/lum-vit","repo_kind":"official","path":"LUM-ViT.py","file_url":"https://github.com/maxllf/lum-vit/blob/HEAD/LUM-ViT.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b55b079ace7d9330"}},{"code_sha256_prefix":"d2434fa3227589c0","entry":"VisionTransformer","repo":"maxllf/lum-vit","repo_kind":"official","path":"LUM-ViT.py","file_url":"https://github.com/maxllf/lum-vit/blob/HEAD/LUM-ViT.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d2434fa3227589c0"}},{"code_sha256_prefix":"ef2325b4dcee1c65","entry":"unravel_index","repo":"maxllf/lum-vit","repo_kind":"official","path":"LUM-ViT.py","file_url":"https://github.com/maxllf/lum-vit/blob/HEAD/LUM-ViT.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ef2325b4dcee1c65"}},{"code_sha256_prefix":"93357c8bf33ed47c","entry":"LUM_ViT","repo":"maxllf/lum-vit","repo_kind":"official","path":"LUM-ViT.py","file_url":"https://github.com/maxllf/lum-vit/blob/HEAD/LUM-ViT.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":"93357c8bf33ed47c"}},{"code_sha256_prefix":"a18f2cd4db02fee5","entry":"_init_vit_weights","repo":"maxllf/lum-vit","repo_kind":"official","path":"LUM-ViT.py","file_url":"https://github.com/maxllf/lum-vit/blob/HEAD/LUM-ViT.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":"a18f2cd4db02fee5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}