ELF-UA: Efficient Label-Free User Adaptation in Gaze Estimation

Authors: Yong Wu, Yang Wang, Sanqing Qu, Zhijun Li, Guang Chen

IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments validate the effectiveness of our method on several challenging benchmarks.
Researcher Affiliation Academia 1Tongji University 2Concordia University
Pseudocode Yes Algorithm 1 Training for ELF-UA
Open Source Code No The paper does not provide any explicit statement about releasing the source code or a link to a code repository.
Open Datasets Yes We re-purpose several existing gaze datasets for our problem, including ETH-XGaze [Zhang et al., 2020], Gaze360 [Kellnhofer et al., 2019], Gaze Capture [Krafka et al., 2016] and MPIIGaze [Zhang et al., 2019].
Dataset Splits Yes During offline training (called meta-training using metalearning terminology), we are given a labeled source dataset S = {(xi, yi)}Ns i=1... In addition to the source dataset S, we also have access to an unlabeled person-specific dataset T. This person-specific dataset contains unlabeled images of K persons, where each person has multiple images, i.e. T = {D1, D2, ...DK}... We select 993 persons with over 400 samples per person as the unlabeled person-specific dataset for training. We select 109 persons with over 1000 samples per person are used for testing. For each task, we construct a task with a support set Dtr and query set Dval. The support set Dtr is used to update the model parameter ψ to obtain a user-adapted model ψ . The query set Dval is used to measure the performance of the adapted model ψ .
Hardware Specification Yes All experiments are performed on a single RTX 3090 GPU.
Software Dependencies No The paper mentions 'Py Torch' but does not specify a version number or other software dependencies with version numbers.
Experiment Setup Yes We use SGD for the meta-optimization with a fixed learning rate of β = 10 4. The inner optimization is done using 3 gradient steps with an adaptation learning rate of α = 10 2. During meta-testing, we use the same fixed learning rate and 3 gradient steps as meta-optimization to keep consistent with training. We set the weight of the distance between source and target data to γ = 0.1 (Eq. 4). The meta-batch size is set to n = 10 (Eq. 5) and each task consists of K = 5 face images. All images are cropped to the resolution of 224 224.