Benchmarking Transferability: A Framework for Fair and Robust Evaluation

Transferability scores aim to quantify how well a model trained on one domain generalizes to a target domain. Despite numerous methods proposed for measuring transferability, their reliability and practical usefulness remain inconclusive, often due to differing experimental setups, datasets, and assumptions. In this paper, we introduce a comprehensive benchmarking framework designed to systematically evaluate transferability scores across diverse settings. Through extensive experiments, we observe variations in how different metrics perform under various scenarios, suggesting that current evaluation practices may not fully capture each method's strengths and limitations. Our findings underscore the value of standardized assessment protocols, paving the way for more reliable transferability measures and better-informed model selection in cross-domain applications. Additionally, we achieved a 3.5\% improvement using our proposed metric for the head-training fine-tuning experimental setup. Our code is available in this repository: https://github.com/alizkzm/pert_robust_platform.

AGISim, An Open Source Airborne Gimbal Mounted IMU Signal Simulator Considering Flight Dynamics Model

In this work we present more comprehensive evaluations on our airborne Gimbal mounted inertial measurement unit (IMU) signal simulator which also considers flight dynamic model (FDM). A flexible IMU signal simulator is an enabling tool in design, development, improvement, test and verification of aided inertial navigation systems (INS). Efforts by other researchers had been concentrated on simulation of the strapdown INS (SINS) with the IMU rigidly attached to the moving body frame. However custom airborne surveying/mapping applications that need pointing and stabilizing camera or any other surveying sensor, require mounting the IMU beside the sensor on a Gimbal onboard the airframe. Hence the proposed Gimbal mounted IMU signal simulator is of interest whilst itself requires further analysis and verifications. Extended evaluation results in terms of both unit tests and functional/integration tests (using aided inertial navigation algorithms with variable/dynamic lever arms), verifies the simulator and its applicability for the mentioned tasks. We have further packaged and published our MATLAB code for the proposed simulator as an open source GitHub repository.