{"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/magic-tokens-select-diverse-tokens-for-multi","title":"Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification","arxiv_id":"2403.10254","date":"2024-03-15","proceeding":"CVPR 2024 1","authors":["Pingping Zhang","Yuhao Wang","Yang Liu","Zhengzheng Tu","Huchuan Lu"],"abstract":"Single-modal object re-identification (ReID) faces great challenges in maintaining robustness within complex visual scenarios. In contrast, multi-modal object ReID utilizes complementary information from diverse modalities, showing great potentials for practical applications. However, previous methods may be easily affected by irrelevant backgrounds and usually ignore the modality gaps. To address above issues, we propose a novel learning framework named \\textbf{EDITOR} to select diverse tokens from vision Transformers for multi-modal object ReID. We begin with a shared vision Transformer to extract tokenized features from different input modalities. Then, we introduce a Spatial-Frequency Token Selection (SFTS) module to adaptively select object-centric tokens with both spatial and frequency information. Afterwards, we employ a Hierarchical Masked Aggregation (HMA) module to facilitate feature interactions within and across modalities. Finally, to further reduce the effect of backgrounds, we propose a Background Consistency Constraint (BCC) and an Object-Centric Feature Refinement (OCFR). They are formulated as two new loss functions, which improve the feature discrimination with background suppression. As a result, our framework can generate more discriminative features for multi-modal object ReID. Extensive experiments on three multi-modal ReID benchmarks verify the effectiveness of our methods. The code is available at https://github.com/924973292/EDITOR.","url_abs":"https://arxiv.org/abs/2403.10254v1","url_pdf":"https://arxiv.org/pdf/2403.10254v1.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":"magic-tokens-select-diverse-tokens-for-multi","repo_url":"https://github.com/924973292/editor","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"magic-tokens-select-diverse-tokens-for-multi","repo_url":"https://github.com/924973292/fusionreid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"}],"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/2403.10254","atlas_url":"https://app.syntology.ai/?focus=2403.10254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10254"}},"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/924973292/fusionreid","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/924973292/editor","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/924973292/EDITOR","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":1,"repositories":1},"listed":{"samples":7,"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":7,"samples":[{"code_sha256_prefix":"4f2b5c4adcb39a83","entry":"Attention","repo":"924973292/fusionreid","repo_kind":"listed","path":"modeling/fusion_part/fusion.py","file_url":"https://github.com/924973292/fusionreid/blob/HEAD/modeling/fusion_part/fusion.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":"4f2b5c4adcb39a83"}},{"code_sha256_prefix":"4800b901068d9f8f","entry":"Attention_mix","repo":"924973292/fusionreid","repo_kind":"listed","path":"modeling/fusion_part/fusion.py","file_url":"https://github.com/924973292/fusionreid/blob/HEAD/modeling/fusion_part/fusion.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":"4800b901068d9f8f"}},{"code_sha256_prefix":"cd31ba10bfe67622","entry":"Block","repo":"924973292/fusionreid","repo_kind":"listed","path":"modeling/fusion_part/fusion.py","file_url":"https://github.com/924973292/fusionreid/blob/HEAD/modeling/fusion_part/fusion.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":"cd31ba10bfe67622"}},{"code_sha256_prefix":"21b633fce8142a7c","entry":"Block_mix","repo":"924973292/fusionreid","repo_kind":"listed","path":"modeling/fusion_part/fusion.py","file_url":"https://github.com/924973292/fusionreid/blob/HEAD/modeling/fusion_part/fusion.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":"21b633fce8142a7c"}},{"code_sha256_prefix":"74e30c9a44099a4e","entry":"Mutual_Fsuion_Unit","repo":"924973292/fusionreid","repo_kind":"listed","path":"modeling/fusion_part/fusion.py","file_url":"https://github.com/924973292/fusionreid/blob/HEAD/modeling/fusion_part/fusion.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":"74e30c9a44099a4e"}},{"code_sha256_prefix":"ab8e0fc65383467b","entry":"Shared_Encoding_Unit","repo":"924973292/fusionreid","repo_kind":"listed","path":"modeling/fusion_part/fusion.py","file_url":"https://github.com/924973292/fusionreid/blob/HEAD/modeling/fusion_part/fusion.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":"ab8e0fc65383467b"}},{"code_sha256_prefix":"e3b2a83f52101f2d","entry":"normalize","repo":"924973292/EDITOR","repo_kind":"official","path":"layers/triplet_loss.py","file_url":"https://github.com/924973292/EDITOR/blob/HEAD/layers/triplet_loss.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e3b2a83f52101f2d"}},{"code_sha256_prefix":"9558cd4a63752d5e","entry":"Reflection_item","repo":"924973292/fusionreid","repo_kind":"listed","path":"modeling/fusion_part/fusion.py","file_url":"https://github.com/924973292/fusionreid/blob/HEAD/modeling/fusion_part/fusion.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":"9558cd4a63752d5e"}},{"code_sha256_prefix":"71b4e1d375d8fd78","entry":"cosine_dist","repo":"924973292/EDITOR","repo_kind":"official","path":"layers/triplet_loss.py","file_url":"https://github.com/924973292/EDITOR/blob/HEAD/layers/triplet_loss.py","link_basis":"harvester_set","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":"71b4e1d375d8fd78"}},{"code_sha256_prefix":"5315f75bf5367f0a","entry":"euclidean_dist","repo":"924973292/EDITOR","repo_kind":"official","path":"layers/triplet_loss.py","file_url":"https://github.com/924973292/EDITOR/blob/HEAD/layers/triplet_loss.py","link_basis":"harvester_set","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":"5315f75bf5367f0a"}},{"code_sha256_prefix":"2e6109d5214f6e2a","entry":"make_loss","repo":"924973292/EDITOR","repo_kind":"official","path":"layers/make_loss.py","file_url":"https://github.com/924973292/EDITOR/blob/HEAD/layers/make_loss.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":"2e6109d5214f6e2a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}