Polymorph: Energy-Efficient Multi-Label Classification for Video Streams on Embedded Devices

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ghafouri, Saeid, Fayyaz, Mohsen, Li, Xiangchen, John, Deepu, Ji, Bo, Nikolopoulos, Dimitrios, Vandierendonck, Hans
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915721727967232
author Ghafouri, Saeid
Fayyaz, Mohsen
Li, Xiangchen
John, Deepu
Ji, Bo
Nikolopoulos, Dimitrios
Vandierendonck, Hans
author_facet Ghafouri, Saeid
Fayyaz, Mohsen
Li, Xiangchen
John, Deepu
Ji, Bo
Nikolopoulos, Dimitrios
Vandierendonck, Hans
contents 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/.
format Preprint
id arxiv_https___arxiv_org_abs_2507_14959
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Polymorph: Energy-Efficient Multi-Label Classification for Video Streams on Embedded Devices
Ghafouri, Saeid
Fayyaz, Mohsen
Li, Xiangchen
John, Deepu
Ji, Bo
Nikolopoulos, Dimitrios
Vandierendonck, Hans
Computer Vision and Pattern Recognition
Performance
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/.
title Polymorph: Energy-Efficient Multi-Label Classification for Video Streams on Embedded Devices
topic Computer Vision and Pattern Recognition
Performance
url https://arxiv.org/abs/2507.14959