홈 › Papers

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

2025-07-20 · Saeid Ghafouri, Mohsen Fayyaz, Xiangchen Li, Deepu John, Bo Ji, Dimitrios Nikolopoulos, Hans Vandierendonck arxiv

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/.

📄 PDF Abstract BibTeX arXiv:2507.14959

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Label Classification Video Classification

High-Speed and Energy-Efficient Non-Binary Computing with Polymorphic Electro-Optic Circuits and Architectures

2023-04-15 · Ishan Thakkar, Sairam Sri Vatsavai, Venkata Sai Praneeth Karempudi

In this paper, we present microring resonator (MRR) based polymorphic E-O circuits and architectures that can be employed for high-speed and energy-efficient non-binary reconfigurable computing. Our polymorphic E-O circu…

FastCSP: Accelerated Molecular Crystal Structure Prediction with Universal Model for Atoms

2025-08-04 · Vahe Gharakhanyan, Yi Yang, Luis Barroso-Luque, Daniel S. Levine 외 arxiv

Molecular crystal structure prediction (CSP) is essential for applications in pharmaceuticals and organic electronics. However, CSP remains challenging and computationally intensive due to the need to explore a large sea…

Energy-based Out-of-distribution Detection for Multi-label Classification

2021-01-01 · Haoran Wang, Weitang Liu, Alex Bocchieri, Yixuan Li

Out-of-distribution (OOD) detection is essential to prevent anomalous inputs from causing a model to fail during deployment. Improved methods for OOD detection in multi-class classification have emerged, while OOD detect…

Classification General Classification Multi-class Classification Multi-Label Classification+3

Can multi-label classification networks know what they don’t know?

2021-05-21 · NeurIPS 2021 12 · Haoran Wang, Weitang Liu, Alex Bocchieri, Yixuan Li

Estimating out-of-distribution (OOD) uncertainty is a major challenge for safely deploying machine learning models in the open-world environment. Improved methods for OOD detection in multi-class classification have emer…

Classification Multi-class Classification Multi-Label Classification MUlTI-LABEL-ClASSIFICATION+1

Can multi-label classification networks know what they don't know?

2021-09-29 · NeurIPS 2021 12 · Haoran Wang, Weitang Liu, Alex Bocchieri, Yixuan Li

Estimating out-of-distribution (OOD) uncertainty is a central challenge for safely deploying machine learning models in the open-world environment. Improved methods for OOD detection in multi-class classification have em…