{"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/towards-a-multi-agent-vision-language-system","title":"Towards a Multi-Agent Vision-Language System for Zero-Shot Novel Hazardous Object Detection for Autonomous Driving Safety","arxiv_id":"2504.13399","date":"2025-04-18","proceeding":null,"authors":["Shashank Shriram","Srinivasa Perisetla","Aryan Keskar","Harsha Krishnaswamy","Tonko Emil Westerhof Bossen","Andreas Møgelmose","Ross Greer"],"abstract":"Detecting anomalous hazards in visual data, particularly in video streams, is a critical challenge in autonomous driving. Existing models often struggle with unpredictable, out-of-label hazards due to their reliance on predefined object categories. In this paper, we propose a multimodal approach that integrates vision-language reasoning with zero-shot object detection to improve hazard identification and explanation. Our pipeline consists of a Vision-Language Model (VLM), a Large Language Model (LLM), in order to detect hazardous objects within a traffic scene. We refine object detection by incorporating OpenAI's CLIP model to match predicted hazards with bounding box annotations, improving localization accuracy. To assess model performance, we create a ground truth dataset by denoising and extending the foundational COOOL (Challenge-of-Out-of-Label) anomaly detection benchmark dataset with complete natural language descriptions for hazard annotations. We define a means of hazard detection and labeling evaluation on the extended dataset using cosine similarity. This evaluation considers the semantic similarity between the predicted hazard description and the annotated ground truth for each video. Additionally, we release a set of tools for structuring and managing large-scale hazard detection datasets. Our findings highlight the strengths and limitations of current vision-language-based approaches, offering insights into future improvements in autonomous hazard detection systems. Our models, scripts, and data can be found at https://github.com/mi3labucm/COOOLER.git","url_abs":"https://arxiv.org/abs/2504.13399v1","url_pdf":"https://arxiv.org/pdf/2504.13399v1.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":"towards-a-multi-agent-vision-language-system","repo_url":"https://github.com/mi3labucm/coooler","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"zero-shot-object-detection","task_name":"Zero-Shot Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2504.13399","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.13399"}},"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/mi3labucm/coooler","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"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":"8c98a9c32e1c1bff","entry":"process_video_folders","repo":"mi3labucm/coooler","repo_kind":"official","path":"run_omnivlm.py","file_url":"https://github.com/mi3labucm/coooler/blob/HEAD/run_omnivlm.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":"8c98a9c32e1c1bff"}},{"code_sha256_prefix":"a9af049c0346ac95","entry":"run_omnivlm","repo":"mi3labucm/coooler","repo_kind":"official","path":"run_omnivlm.py","file_url":"https://github.com/mi3labucm/coooler/blob/HEAD/run_omnivlm.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":"a9af049c0346ac95"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}