Poster: Time-Efficient Sparse and Lightweight Adaptation for Real-Time Mobile Applications
We propose TESLA Time-Efficient Sparse and Lightweight Adaptation strategy for real-time mobile applications, which skips adaptation for specific batches to increase the inference sample rate. Our method balances model accuracy and inference speed by accumulating domain-informative samples from non-adapted batches and sparsely adapting them.
Jun 3, 2024
On-device Efficient DNN Adaptation Framework for Real-time Applications
Exploring model adaptation methods that enable real-time inference on extremely resource-constrained devices
Apr 27, 2024
Sherlock: Automated Hidden Camera Detection with Shutter Speed Adaptation
With the rapid advancements in surveillance camera technology, there has been a surge in crimes involving illegal filming using hidden cameras. However, current solutions necessitate slow manual scanning processes that require thousands ofworkers within a city to ensure coverage. To address this challenge, we introduce Sherlock, a fully automated hidden camera detection system that utilizes a drone in combination with a flickering flashlight. To expedite the scanning process and accommodate the irregular movements of the drone, Sherlock leverages the rolling shutter effect to capture images when the flashlight is turned on and off within a single frame. This methodology enables Sherlock to efficiently identify reflective objects and detect hidden camera lenses among them. To demonstrate the feasibility of Sherlock, we present a proof-of-concept evaluation by deploying a drone in various environments to detect and locate hidden cameras.
Oct 25, 2023
Drone/Smartphone based Hidden Camera Detection System
Exploring mobile system that uses a flickering flashlight and the rolling shutter effect to quickly detect hidden cameras amidst rising illegal filming crimess
Oct 25, 2023
Domain-aware Contrastive Federated Learning in Extreme Non-iid Conditions
Addressed the extreme noniid scenario, where the classification label and features are simultaneously non-iid via Domain-aware Contrastive Federated Learning with Major Domain Group Selection
Oct 23, 2023