{"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/clip-count-towards-text-guided-zero-shot","title":"CLIP-Count: Towards Text-Guided Zero-Shot Object Counting","arxiv_id":"2305.07304","date":"2023-05-12","proceeding":null,"authors":["Ruixiang Jiang","Lingbo Liu","Changwen Chen"],"abstract":"Recent advances in visual-language models have shown remarkable zero-shot text-image matching ability that is transferable to downstream tasks such as object detection and segmentation. Adapting these models for object counting, however, remains a formidable challenge. In this study, we first investigate transferring vision-language models (VLMs) for class-agnostic object counting. Specifically, we propose CLIP-Count, the first end-to-end pipeline that estimates density maps for open-vocabulary objects with text guidance in a zero-shot manner. To align the text embedding with dense visual features, we introduce a patch-text contrastive loss that guides the model to learn informative patch-level visual representations for dense prediction. Moreover, we design a hierarchical patch-text interaction module to propagate semantic information across different resolution levels of visual features. Benefiting from the full exploitation of the rich image-text alignment knowledge of pretrained VLMs, our method effectively generates high-quality density maps for objects-of-interest. Extensive experiments on FSC-147, CARPK, and ShanghaiTech crowd counting datasets demonstrate state-of-the-art accuracy and generalizability of the proposed method. Code is available: https://github.com/songrise/CLIP-Count.","url_abs":"https://arxiv.org/abs/2305.07304v2","url_pdf":"https://arxiv.org/pdf/2305.07304v2.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":"clip-count-towards-text-guided-zero-shot","repo_url":"https://github.com/songrise/clip-count","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"cross-part-crowd-counting","task_name":"Cross-Part Crowd Counting"},{"task_slug":null,"task_name":"Cross-Part Evaluation"},{"task_slug":"crowd-counting","task_name":"Crowd Counting"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-counting","task_name":"Object Counting"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"zero-shot-counting","task_name":"Zero-Shot Counting"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"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":"clip","method_name":"CLIP"},{"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":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2305.07304","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07304"}},"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/songrise/clip-count","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran_fixture":1,"ran":2},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":"bd3578806ecf5ac2","entry":"adjust_learning_rate","repo":"songrise/clip-count","repo_kind":"official","path":"util/lr_sched.py","file_url":"https://github.com/songrise/clip-count/blob/HEAD/util/lr_sched.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd3578806ecf5ac2"}},{"code_sha256_prefix":"e3aa4e8e74369506","entry":"drop_path","repo":"songrise/clip-count","repo_kind":"official","path":"models/models_crossvit.py","file_url":"https://github.com/songrise/clip-count/blob/HEAD/models/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":"89edf5372214b57d","entry":"get_layer_id_for_vit","repo":"songrise/clip-count","repo_kind":"official","path":"util/lr_decay.py","file_url":"https://github.com/songrise/clip-count/blob/HEAD/util/lr_decay.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"89edf5372214b57d"}},{"code_sha256_prefix":"8baf25cef41cba16","entry":"param_groups_lrd","repo":"songrise/clip-count","repo_kind":"official","path":"util/lr_decay.py","file_url":"https://github.com/songrise/clip-count/blob/HEAD/util/lr_decay.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8baf25cef41cba16"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}