{"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/cris-clip-driven-referring-image-segmentation","title":"CRIS: CLIP-Driven Referring Image Segmentation","arxiv_id":"2111.15174","date":"2021-11-30","proceeding":"CVPR 2022 1","authors":["Zhaoqing Wang","Yu Lu","Qiang Li","Xunqiang Tao","Yandong Guo","Mingming Gong","Tongliang Liu"],"abstract":"Referring image segmentation aims to segment a referent via a natural linguistic expression.Due to the distinct data properties between text and image, it is challenging for a network to well align text and pixel-level features. Existing approaches use pretrained models to facilitate learning, yet separately transfer the language/vision knowledge from pretrained models, ignoring the multi-modal corresponding information. Inspired by the recent advance in Contrastive Language-Image Pretraining (CLIP), in this paper, we propose an end-to-end CLIP-Driven Referring Image Segmentation framework (CRIS). To transfer the multi-modal knowledge effectively, CRIS resorts to vision-language decoding and contrastive learning for achieving the text-to-pixel alignment. More specifically, we design a vision-language decoder to propagate fine-grained semantic information from textual representations to each pixel-level activation, which promotes consistency between the two modalities. In addition, we present text-to-pixel contrastive learning to explicitly enforce the text feature similar to the related pixel-level features and dissimilar to the irrelevances. The experimental results on three benchmark datasets demonstrate that our proposed framework significantly outperforms the state-of-the-art performance without any post-processing. The code will be released.","url_abs":"https://arxiv.org/abs/2111.15174v2","url_pdf":"https://arxiv.org/pdf/2111.15174v2.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":"cris-clip-driven-referring-image-segmentation","repo_url":"https://github.com/DerrickWang005/CRIS.pytorch","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"generalized-referring-expression-segmentation","task_name":"Generalized Referring Expression Segmentation"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"referring-expression-segmentation","task_name":"Referring Expression Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/generalized-referring-expression-segmentation","task":"Generalized Referring Expression Segmentation","dataset":"gRefCOCO","model":"CRIS","rank_in_archive_order":10,"of":13,"metrics":{"cIoU":"55.34","gIoU":"56.27"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-5","task":"Referring Expression Segmentation","dataset":"RefCOCO+ test B","model":"CRIS","rank_in_archive_order":20,"of":30,"metrics":{"Overall IoU":"53.68"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-4","task":"Referring Expression Segmentation","dataset":"RefCOCO+ testA","model":"CRIS","rank_in_archive_order":20,"of":30,"metrics":{"Overall IoU":"68.08"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-3","task":"Referring Expression Segmentation","dataset":"RefCOCO+ val","model":"CRIS","rank_in_archive_order":22,"of":33,"metrics":{"Overall IoU":"62.27"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco","task":"Referring Expression Segmentation","dataset":"RefCoCo val","model":"CRIS","rank_in_archive_order":25,"of":37,"metrics":{"Overall IoU":"70.47"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.15174","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.15174"}},"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/DerrickWang005/CRIS.pytorch","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":4,"ran":3,"unverified":5},"by_repo_kind":{"official":{"samples":12,"ran":7,"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":"98f385d847636a3e","entry":"basic_clean","repo":"DerrickWang005/CRIS.pytorch","repo_kind":"official","path":"utils/simple_tokenizer.py","file_url":"https://github.com/DerrickWang005/CRIS.pytorch/blob/HEAD/utils/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98f385d847636a3e"}},{"code_sha256_prefix":"dbfe3357dc25ca5f","entry":"conv_layer","repo":"DerrickWang005/CRIS.pytorch","repo_kind":"official","path":"model/layers.py","file_url":"https://github.com/DerrickWang005/CRIS.pytorch/blob/HEAD/model/layers.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dbfe3357dc25ca5f"}},{"code_sha256_prefix":"d919ae32e5e4e616","entry":"get_pairs","repo":"DerrickWang005/CRIS.pytorch","repo_kind":"official","path":"utils/simple_tokenizer.py","file_url":"https://github.com/DerrickWang005/CRIS.pytorch/blob/HEAD/utils/simple_tokenizer.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":"d919ae32e5e4e616"}},{"code_sha256_prefix":"539cbfa1328eb51b","entry":"init_random_seed","repo":"DerrickWang005/CRIS.pytorch","repo_kind":"official","path":"utils/misc.py","file_url":"https://github.com/DerrickWang005/CRIS.pytorch/blob/HEAD/utils/misc.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":"539cbfa1328eb51b"}},{"code_sha256_prefix":"89f9fd49ddec76ba","entry":"linear_layer","repo":"DerrickWang005/CRIS.pytorch","repo_kind":"official","path":"model/layers.py","file_url":"https://github.com/DerrickWang005/CRIS.pytorch/blob/HEAD/model/layers.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":"89f9fd49ddec76ba"}},{"code_sha256_prefix":"78241a45492d6667","entry":"trainMetricGPU","repo":"DerrickWang005/CRIS.pytorch","repo_kind":"official","path":"utils/misc.py","file_url":"https://github.com/DerrickWang005/CRIS.pytorch/blob/HEAD/utils/misc.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":"78241a45492d6667"}},{"code_sha256_prefix":"9542161e9640b858","entry":"whitespace_clean","repo":"DerrickWang005/CRIS.pytorch","repo_kind":"official","path":"utils/simple_tokenizer.py","file_url":"https://github.com/DerrickWang005/CRIS.pytorch/blob/HEAD/utils/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9542161e9640b858"}},{"code_sha256_prefix":"d761a6dca9831c24","entry":"build_model","repo":"DerrickWang005/CRIS.pytorch","repo_kind":"official","path":"model/clip.py","file_url":"https://github.com/DerrickWang005/CRIS.pytorch/blob/HEAD/model/clip.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":"d761a6dca9831c24"}},{"code_sha256_prefix":"73cecca9f3575f09","entry":"concat_all_gather","repo":"DerrickWang005/CRIS.pytorch","repo_kind":"official","path":"utils/misc.py","file_url":"https://github.com/DerrickWang005/CRIS.pytorch/blob/HEAD/utils/misc.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":"73cecca9f3575f09"}},{"code_sha256_prefix":"cc23416cff396c39","entry":"load_cfg_from_cfg_file","repo":"DerrickWang005/CRIS.pytorch","repo_kind":"official","path":"utils/config.py","file_url":"https://github.com/DerrickWang005/CRIS.pytorch/blob/HEAD/utils/config.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":"cc23416cff396c39"}},{"code_sha256_prefix":"b4c154b6f0568b6b","entry":"loads_pyarrow","repo":"DerrickWang005/CRIS.pytorch","repo_kind":"official","path":"utils/dataset.py","file_url":"https://github.com/DerrickWang005/CRIS.pytorch/blob/HEAD/utils/dataset.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":"b4c154b6f0568b6b"}},{"code_sha256_prefix":"022883c7911679b3","entry":"merge_cfg_from_list","repo":"DerrickWang005/CRIS.pytorch","repo_kind":"official","path":"utils/config.py","file_url":"https://github.com/DerrickWang005/CRIS.pytorch/blob/HEAD/utils/config.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":"022883c7911679b3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}