{"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/edtformer-an-efficient-decoder-transformer","title":"EDTformer: An Efficient Decoder Transformer for Visual Place Recognition","arxiv_id":"2412.00784","date":"2024-12-01","proceeding":null,"authors":["Tong Jin","Feng Lu","Shuyu Hu","Chun Yuan","Yunpeng Liu"],"abstract":"Visual place recognition (VPR) aims to determine the general geographical location of a query image by retrieving visually similar images from a large geo-tagged database. To obtain a global representation for each place image, most approaches typically focus on the aggregation of deep features extracted from a backbone through using current prominent architectures (e.g., CNNs, MLPs, pooling layer and transformer encoder), giving little attention to the transformer decoder. However, we argue that its strong capability in capturing contextual dependencies and generating accurate features holds considerable potential for the VPR task. To this end, we propose an Efficient Decoder Transformer (EDTformer) for feature aggregation, which consists of several stacked simplified decoder blocks followed by two linear layers to directly generate robust and discriminative global representations for VPR. Specifically, we do this by formulating deep features as the keys and values, as well as a set of independent learnable parameters as the queries. EDTformer can fully utilize the contextual information within deep features, then gradually decode and aggregate the effective features into the learnable queries to form the final global representations. Moreover, to provide powerful deep features for EDTformer and further facilitate the robustness, we use the foundation model DINOv2 as the backbone and propose a Low-Rank Parallel Adaptation (LoPA) method to enhance it, which can refine the intermediate features of the backbone progressively in a memory- and parameter-efficient way. As a result, our method not only outperforms single-stage VPR methods on multiple benchmark datasets, but also outperforms two-stage VPR methods which add a re-ranking with considerable cost. Code will be available at https://github.com/Tong-Jin01/EDTformer.","url_abs":"https://arxiv.org/abs/2412.00784v1","url_pdf":"https://arxiv.org/pdf/2412.00784v1.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":"edtformer-an-efficient-decoder-transformer","repo_url":"https://github.com/tong-jin01/edtformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"re-ranking","task_name":"Re-Ranking"},{"task_slug":"visual-place-recognition","task_name":"Visual Place Recognition"}],"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":"focus","method_name":"Focus"},{"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":"set","method_name":"SET"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2412.00784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.00784"}},"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/tong-jin01/edtformer","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"official":{"samples":5,"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":0,"samples":[{"code_sha256_prefix":"e7fcb6d9ac9deaf4","entry":"named_apply","repo":"tong-jin01/edtformer","repo_kind":"official","path":"backbone/vision_transformer.py","file_url":"https://github.com/tong-jin01/edtformer/blob/HEAD/backbone/vision_transformer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e7fcb6d9ac9deaf4"}},{"code_sha256_prefix":"c160834241fc1797","entry":"collate_fn","repo":"tong-jin01/edtformer","repo_kind":"official","path":"datasets_ws.py","file_url":"https://github.com/tong-jin01/edtformer/blob/HEAD/datasets_ws.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":"c160834241fc1797"}},{"code_sha256_prefix":"f0db6d80ebf12bfa","entry":"path_to_pil_img","repo":"tong-jin01/edtformer","repo_kind":"official","path":"datasets_ws.py","file_url":"https://github.com/tong-jin01/edtformer/blob/HEAD/datasets_ws.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":"f0db6d80ebf12bfa"}},{"code_sha256_prefix":"69d14231085af9e1","entry":"resume_model","repo":"tong-jin01/edtformer","repo_kind":"official","path":"util.py","file_url":"https://github.com/tong-jin01/edtformer/blob/HEAD/util.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":"69d14231085af9e1"}},{"code_sha256_prefix":"e9c2f9f6cf885627","entry":"resume_train","repo":"tong-jin01/edtformer","repo_kind":"official","path":"util.py","file_url":"https://github.com/tong-jin01/edtformer/blob/HEAD/util.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":"e9c2f9f6cf885627"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}