{"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/a-cat-is-a-cat-not-a-dog-unraveling","title":"A Cat Is A Cat (Not A Dog!): Unraveling Information Mix-ups in Text-to-Image Encoders through Causal Analysis and Embedding Optimization","arxiv_id":"2410.00321","date":"2024-10-01","proceeding":null,"authors":["Chieh-Yun Chen","Chiang Tseng","Li-Wu Tsao","Hong-Han Shuai"],"abstract":"This paper analyzes the impact of causal manner in the text encoder of text-to-image (T2I) diffusion models, which can lead to information bias and loss. Previous works have focused on addressing the issues through the denoising process. However, there is no research discussing how text embedding contributes to T2I models, especially when generating more than one object. In this paper, we share a comprehensive analysis of text embedding: i) how text embedding contributes to the generated images and ii) why information gets lost and biases towards the first-mentioned object. Accordingly, we propose a simple but effective text embedding balance optimization method, which is training-free, with an improvement of 125.42% on information balance in stable diffusion. Furthermore, we propose a new automatic evaluation metric that quantifies information loss more accurately than existing methods, achieving 81% concordance with human assessments. This metric effectively measures the presence and accuracy of objects, addressing the limitations of current distribution scores like CLIP's text-image similarities.","url_abs":"https://arxiv.org/abs/2410.00321v5","url_pdf":"https://arxiv.org/pdf/2410.00321v5.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":"a-cat-is-a-cat-not-a-dog-unraveling","repo_url":"https://github.com/basiclab/unraveling-information-mix-ups","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.00321","atlas_url":"https://app.syntology.ai/?focus=2410.00321","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00321"}},"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":"deterministic:regex_extraction","url":"https://github.com/basiclab/Unraveling-Information-Mix-ups","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/basiclab/unraveling-information-mix-ups","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":"4f1fe3d1f6b89580","entry":"attn_map_tr2np","repo":"basiclab/Unraveling-Information-Mix-ups","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/basiclab/Unraveling-Information-Mix-ups/blob/HEAD/utils/utils.py","link_basis":"first_harvest_node","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":"4f1fe3d1f6b89580"}},{"code_sha256_prefix":"99fc8c88c6520b92","entry":"check_mixture","repo":"basiclab/Unraveling-Information-Mix-ups","repo_kind":"official","path":"eval_metrics/owlv2.py","file_url":"https://github.com/basiclab/Unraveling-Information-Mix-ups/blob/HEAD/eval_metrics/owlv2.py","link_basis":"first_harvest_node","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":"99fc8c88c6520b92"}},{"code_sha256_prefix":"5feb9e1dddda5062","entry":"load_animals","repo":"basiclab/unraveling-information-mix-ups","repo_kind":"official","path":"data/gen_prompt.py","file_url":"https://github.com/basiclab/unraveling-information-mix-ups/blob/HEAD/data/gen_prompt.py","link_basis":"first_harvest_node","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":"5feb9e1dddda5062"}},{"code_sha256_prefix":"abb4ecbad6e0555f","entry":"resize_net_attn_map","repo":"basiclab/Unraveling-Information-Mix-ups","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/basiclab/Unraveling-Information-Mix-ups/blob/HEAD/utils/utils.py","link_basis":"first_harvest_node","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":"abb4ecbad6e0555f"}},{"code_sha256_prefix":"dad22709a45ad4ab","entry":"seed_everything","repo":"basiclab/Unraveling-Information-Mix-ups","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/basiclab/Unraveling-Information-Mix-ups/blob/HEAD/utils/utils.py","link_basis":"first_harvest_node","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":"dad22709a45ad4ab"}},{"code_sha256_prefix":"346d093f84857a6b","entry":"owlv2_eval","repo":"basiclab/Unraveling-Information-Mix-ups","repo_kind":"official","path":"eval_metrics/owlv2.py","file_url":"https://github.com/basiclab/Unraveling-Information-Mix-ups/blob/HEAD/eval_metrics/owlv2.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":"346d093f84857a6b"}},{"code_sha256_prefix":"ff0f7c7f0e3e3086","entry":"register_attention_control","repo":"basiclab/Unraveling-Information-Mix-ups","repo_kind":"official","path":"model/attentions_utils.py","file_url":"https://github.com/basiclab/Unraveling-Information-Mix-ups/blob/HEAD/model/attentions_utils.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":"ff0f7c7f0e3e3086"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}