{"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/lates-latent-space-distillation-for-teacher","title":"SAM: Squeeze-and-Mimic Networks for Conditional Visual Driving Policy Learning","arxiv_id":"1912.02973","date":"2019-12-06","proceeding":null,"authors":["Albert Zhao","Tong He","Yitao Liang","Haibin Huang","Guy Van Den Broeck","Stefano Soatto"],"abstract":"We describe a policy learning approach to map visual inputs to driving controls conditioned on turning command that leverages side tasks on semantics and object affordances via a learned representation trained for driving. To learn this representation, we train a squeeze network to drive using annotations for the side task as input. This representation encodes the driving-relevant information associated with the side task while ideally throwing out side task-relevant but driving-irrelevant nuisances. We then train a mimic network to drive using only images as input and use the squeeze network's latent representation to supervise the mimic network via a mimicking loss. Notably, we do not aim to achieve the side task nor to learn features for it; instead, we aim to learn, via the mimicking loss, a representation of the side task annotations directly useful for driving. We test our approach using the CARLA simulator. In addition, we introduce a more challenging but realistic evaluation protocol that considers a run that reaches the destination successful only if it does not violate common traffic rules. A video summarizing this work is available at https://youtu.be/ipKAMzmJpMs , and code is available at https://github.com/twsq/sam-driving .","url_abs":"https://arxiv.org/abs/1912.02973v2","url_pdf":"https://arxiv.org/pdf/1912.02973v2.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":"lates-latent-space-distillation-for-teacher","repo_url":"https://github.com/twsq/sam-driving","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"carla","method_name":"CARLA"},{"method_slug":"entropy-regularization","method_name":"Entropy Regularization"},{"method_slug":"ppo","method_name":"PPO"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1912.02973","atlas_url":"https://app.syntology.ai/?focus=1912.02973","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}