{"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/enhancing-large-vision-language-models-with","title":"Enhancing Large Vision Language Models with Self-Training on Image Comprehension","arxiv_id":"2405.19716","date":"2024-05-30","proceeding":null,"authors":["Yihe Deng","Pan Lu","Fan Yin","Ziniu Hu","Sheng Shen","Quanquan Gu","James Zou","Kai-Wei Chang","Wei Wang"],"abstract":"Large vision language models (LVLMs) integrate large language models (LLMs) with pre-trained vision encoders, thereby activating the perception capability of the model to understand image inputs for different queries and conduct subsequent reasoning. Improving this capability requires high-quality vision-language data, which is costly and labor-intensive to acquire. Self-training approaches have been effective in single-modal settings to alleviate the need for labeled data by leveraging model's own generation. However, effective self-training remains a challenge regarding the unique visual perception and reasoning capability of LVLMs. To address this, we introduce Self-Training on Image Comprehension (STIC), which emphasizes a self-training approach specifically for image comprehension. First, the model self-constructs a preference dataset for image descriptions using unlabeled images. Preferred responses are generated through a step-by-step prompt, while dis-preferred responses are generated from either corrupted images or misleading prompts. To further self-improve reasoning on the extracted visual information, we let the model reuse a small portion of existing instruction-tuning data and append its self-generated image descriptions to the prompts. We validate the effectiveness of STIC across seven different benchmarks, demonstrating substantial performance gains of 4.0% on average while using 70% less supervised fine-tuning data than the current method. Further studies investigate various components of STIC and highlight its potential to leverage vast quantities of unlabeled images for self-training. Code and data are made publicly available.","url_abs":"https://arxiv.org/abs/2405.19716v2","url_pdf":"https://arxiv.org/pdf/2405.19716v2.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":"enhancing-large-vision-language-models-with","repo_url":"https://github.com/yihedeng9/stic","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-comprehension","task_name":"Image Comprehension"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"LLaVA-v1.6 (7B, w/ STIC)","rank_in_archive_order":83,"of":231,"metrics":{"GPT-4 score":"45.0","Params":"7B"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"LLaVA-v1.5 (7B, w/ STIC)","rank_in_archive_order":180,"of":231,"metrics":{"GPT-4 score":"32.6","Params":"7B"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.19716","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19716"}},"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/yihedeng9/stic","reach":null}],"summary":{"ran_draft_wrong":3,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":1,"samples":[{"code_sha256_prefix":"7d2672b31e9aa80e","entry":"get_file_names","repo":"yihedeng9/stic","repo_kind":"official","path":"llava/eval/eval_mm_vet.py","file_url":"https://github.com/yihedeng9/stic/blob/HEAD/llava/eval/eval_mm_vet.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7d2672b31e9aa80e"}},{"code_sha256_prefix":"a7bee88c1c7fd6a3","entry":"image_parser","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"a7bee88c1c7fd6a3"}},{"code_sha256_prefix":"969f70cdb9e7b42d","entry":"load_metadata","repo":"yihedeng9/stic","repo_kind":"official","path":"llava/eval/eval_mm_vet.py","file_url":"https://github.com/yihedeng9/stic/blob/HEAD/llava/eval/eval_mm_vet.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"969f70cdb9e7b42d"}},{"code_sha256_prefix":"4edc6079065ecd0f","entry":"arg_parser","repo":"yihedeng9/stic","repo_kind":"official","path":"llava/eval/eval_mm_vet.py","file_url":"https://github.com/yihedeng9/stic/blob/HEAD/llava/eval/eval_mm_vet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4edc6079065ecd0f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}