{"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/countr-transformer-based-generalised-visual","title":"CounTR: Transformer-based Generalised Visual Counting","arxiv_id":"2208.13721","date":"2022-08-29","proceeding":null,"authors":["Chang Liu","Yujie Zhong","Andrew Zisserman","Weidi Xie"],"abstract":"In this paper, we consider the problem of generalised visual object counting, with the goal of developing a computational model for counting the number of objects from arbitrary semantic categories, using arbitrary number of \"exemplars\", i.e. zero-shot or few-shot counting. To this end, we make the following four contributions: (1) We introduce a novel transformer-based architecture for generalised visual object counting, termed as Counting Transformer (CounTR), which explicitly capture the similarity between image patches or with given \"exemplars\" with the attention mechanism;(2) We adopt a two-stage training regime, that first pre-trains the model with self-supervised learning, and followed by supervised fine-tuning;(3) We propose a simple, scalable pipeline for synthesizing training images with a large number of instances or that from different semantic categories, explicitly forcing the model to make use of the given \"exemplars\";(4) We conduct thorough ablation studies on the large-scale counting benchmark, e.g. FSC-147, and demonstrate state-of-the-art performance on both zero and few-shot settings.","url_abs":"https://arxiv.org/abs/2208.13721v3","url_pdf":"https://arxiv.org/pdf/2208.13721v3.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":"countr-transformer-based-generalised-visual","repo_url":"https://github.com/Verg-Avesta/CounTR","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"exemplar-free-counting","task_name":"Exemplar-Free Counting"},{"task_slug":"object-counting","task_name":"Object Counting"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"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"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/exemplar-free-counting-on-fsc147","task":"Exemplar-Free Counting","dataset":"FSC147","model":"CounTR","rank_in_archive_order":4,"of":9,"metrics":{"MAE(test)":"14.71","MAE(val)":"18.07","RMSE(test)":"106.87","RMSE(val)":"71.84"},"uses_additional_data":false},{"leaderboard":"/sota/object-counting-on-carpk","task":"Object Counting","dataset":"CARPK","model":"CounTR","rank_in_archive_order":4,"of":15,"metrics":{"MAE":"5.75","RMSE":"7.45"},"uses_additional_data":false},{"leaderboard":"/sota/object-counting-on-fsc147","task":"Object Counting","dataset":"FSC147","model":"CounTR","rank_in_archive_order":8,"of":19,"metrics":{"MAE(test)":"11.95","MAE(val)":"13.13","RMSE(test)":"91.23","RMSE(val)":"49.83"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2208.13721","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.13721"}},"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/Verg-Avesta/CounTR","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"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":"e3aa4e8e74369506","entry":"drop_path","repo":"Verg-Avesta/CounTR","repo_kind":"official","path":"models_crossvit.py","file_url":"https://github.com/Verg-Avesta/CounTR/blob/HEAD/models_crossvit.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e3aa4e8e74369506"}},{"code_sha256_prefix":"1f53c50f46429972","entry":"load_image","repo":"Verg-Avesta/CounTR","repo_kind":"official","path":"demo_zero.py","file_url":"https://github.com/Verg-Avesta/CounTR/blob/HEAD/demo_zero.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":"1f53c50f46429972"}},{"code_sha256_prefix":"b3dfc95b707288c3","entry":"transform_pre_train","repo":"Verg-Avesta/CounTR","repo_kind":"official","path":"util/FSC147.py","file_url":"https://github.com/Verg-Avesta/CounTR/blob/HEAD/util/FSC147.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":"b3dfc95b707288c3"}},{"code_sha256_prefix":"75f6c7e715903362","entry":"transform_val","repo":"Verg-Avesta/CounTR","repo_kind":"official","path":"util/FSC147.py","file_url":"https://github.com/Verg-Avesta/CounTR/blob/HEAD/util/FSC147.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":"75f6c7e715903362"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}