3 papers
cs.CV2026
Scout: Open-World Species Recognition on the Edge
Mohammad Mehdi Rastikerdar, Hui Guan, Deepak Ganesan
Large vision-language models (VLMs) enable recognition beyond a fixed class set, but their computational demands prevent them from running on many edge devices. Cloud offload makes…
cs.CV2024
WildFit: Autonomous In-situ Model Adaptation for Resource-Constrained IoT Systems
Mohammad Mehdi Rastikerdar, Jin Huang, Hui Guan +1
Resource-constrained IoT devices increasingly rely on deep learning models, however, these models experience significant accuracy drops due to domain shifts when encountering varia…
cs.CV2023
Efficient IoT Inference via Context-Awareness
Mohammad Mehdi Rastikerdar, Jin Huang, Shiwei Fang +2
While existing strategies to execute deep learning-based classification on low-power platforms assume the models are trained on all classes of interest, this paper posits that adop…