{"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/lemevit-efficient-vision-transformer-with","title":"LeMeViT: Efficient Vision Transformer with Learnable Meta Tokens for Remote Sensing Image Interpretation","arxiv_id":"2405.09789","date":"2024-05-16","proceeding":null,"authors":["Wentao Jiang","Jing Zhang","Di Wang","Qiming Zhang","Zengmao Wang","Bo Du"],"abstract":"Due to spatial redundancy in remote sensing images, sparse tokens containing rich information are usually involved in self-attention (SA) to reduce the overall token numbers within the calculation, avoiding the high computational cost issue in Vision Transformers. However, such methods usually obtain sparse tokens by hand-crafted or parallel-unfriendly designs, posing a challenge to reach a better balance between efficiency and performance. Different from them, this paper proposes to use learnable meta tokens to formulate sparse tokens, which effectively learn key information meanwhile improving the inference speed. Technically, the meta tokens are first initialized from image tokens via cross-attention. Then, we propose Dual Cross-Attention (DCA) to promote information exchange between image tokens and meta tokens, where they serve as query and key (value) tokens alternatively in a dual-branch structure, significantly reducing the computational complexity compared to self-attention. By employing DCA in the early stages with dense visual tokens, we obtain the hierarchical architecture LeMeViT with various sizes. Experimental results in classification and dense prediction tasks show that LeMeViT has a significant $1.7 \\times$ speedup, fewer parameters, and competitive performance compared to the baseline models, and achieves a better trade-off between efficiency and performance.","url_abs":"https://arxiv.org/abs/2405.09789v1","url_pdf":"https://arxiv.org/pdf/2405.09789v1.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":"lemevit-efficient-vision-transformer-with","repo_url":"https://github.com/vitae-transformer/lemevit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.09789","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.09789"}},"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/ViTAE-Transformer/LeMeViT","reach":null}],"summary":{"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"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":2,"samples":[{"code_sha256_prefix":"1a1001adc58b631f","entry":"scaled_dot_product_attention","repo":"ViTAE-Transformer/LeMeViT","repo_kind":"official","path":"models/lemevit.py","file_url":"https://github.com/ViTAE-Transformer/LeMeViT/blob/HEAD/models/lemevit.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1a1001adc58b631f"}},{"code_sha256_prefix":"3cfb0aff817efb9b","entry":"DualCrossAttention","repo":"ViTAE-Transformer/LeMeViT","repo_kind":"official","path":"models/lemevit.py","file_url":"https://github.com/ViTAE-Transformer/LeMeViT/blob/HEAD/models/lemevit.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":"3cfb0aff817efb9b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}