{"ID":2892606,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.14959","arxiv_id":"2507.14959","title":"Polymorph: Energy-Efficient Multi-Label Classification for Video Streams on Embedded Devices","abstract":"Real-time multi-label video classification on embedded devices is constrained by limited compute and energy budgets. Yet, video streams exhibit structural properties such as label sparsity, temporal continuity, and label co-occurrence that can be leveraged for more efficient inference. We introduce Polymorph, a context-aware framework that activates a minimal set of lightweight Low Rank Adapters (LoRA) per frame. Each adapter specializes in a subset of classes derived from co-occurrence patterns and is implemented as a LoRA weight over a shared backbone. At runtime, Polymorph dynamically selects and composes only the adapters needed to cover the active labels, avoiding full-model switching and weight merging. This modular strategy improves scalability while reducing latency and energy overhead. Polymorph achieves 40% lower energy consumption and improves mAP by 9 points over strong baselines on the TAO dataset. Polymorph is open source at https://github.com/inference-serving/polymorph/.","short_abstract":"Real-time multi-label video classification on embedded devices is constrained by limited compute and energy budgets. Yet, video streams exhibit structural properties such as label sparsity, temporal continuity, and label co-occurrence that can be leveraged for more efficient inference. We introduce Polymorph, a context...","url_abs":"https://arxiv.org/abs/2507.14959","url_pdf":"https://arxiv.org/pdf/2507.14959v3","authors":"[\"Saeid Ghafouri\",\"Mohsen Fayyaz\",\"Xiangchen Li\",\"Deepu John\",\"Bo Ji\",\"Dimitrios Nikolopoulos\",\"Hans Vandierendonck\"]","published":"2025-07-20T13:39:50Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.PF\"]","methods":"[\"LoRA\"]","has_code":false,"code_links":[{"ID":612003,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2892606,"paper_url":"https://arxiv.org/abs/2507.14959","paper_title":"Polymorph: Energy-Efficient Multi-Label Classification for Video Streams on Embedded Devices","repo_url":"https://github.com/inference-serving/polymorph","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}