AL-GTD: Deep Active Learning for Gaze Target Detection
Francesco Tonini, Nicola Dall'Asen, Lorenzo Vaquero, Cigdem Beyan, Elisa Ricci
Abstract
Gaze target detection aims at determining the image location where a person is looking. While existing studies have made significant progress in this area by regressing accurate gaze heatmaps, these achievements have largely relied on access to extensive labeled datasets, which demands substantial human labor. In this paper, our goal is to reduce the reliance on the size of labeled training data for gaze target detection. To achieve this, we propose AL-GTD, an innovative approach that integrates supervised and self-supervised losses within a novel sample acquisition function to perform active learning (AL). Additionally, it utilizes pseudo-labeling to mitigate distribution shifts during the training phase. AL-GTD achieves the best of all AUC results by utilizing only 40-50% of the training data, in contrast to state-of-the-art (SOTA) gaze target detectors requiring the entire training dataset to achieve the same performance. Importantly, AL-GTD quickly reaches satisfactory performance with 10-20% of the training data, showing the effectiveness of our acquisition function, which is able to acquire the most informative samples. We provide a comprehensive experimental analysis by adapting several AL methods for the task. AL-GTD outperforms AL competitors, simultaneously exhibiting superior performance compared to SOTA gaze target detectors when all are trained within a low-data regime. Code is available at: https://github.com/francescotonini/al-gtd.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers1
Builds on21
- Deformable DETR: Deformable Transformers for End-to-End Object DetectionXizhou Zhu, Weijie Su, Lewei Lu, Bin Li et al.ICLR 2021 · 7,353 citations
- Variational Adversarial Active LearningSamarth Sinha, Sayna Ebrahimi, Trevor DarrellICCV 2019 · 662 citations
- Gaze360: Physically Unconstrained Gaze Estimation in the WildPetr Kellnhofer, Adrià Recasens, Simon Stent, Wojciech Matusik et al.ICCV 2019 · 469 citations
- Active Learning for Deep Detection Neural NetworksHamed H. Aghdam, Abel Gonzalez-Garcia, Antonio M. López, Joost van de WeijerICCV 2019 · 155 citations
- Active Learning for Deep Object Detection via Probabilistic ModelingJiwoong Choi, Ismail Elezi, Hyuk-Jae Lee, Clément Farabet et al.ICCV 2021 · 144 citations
Related papers
- ALWOD: Active Learning for Weakly-Supervised Object DetectionYuting Wang, Velibor Ilic, Jiatong Li, Branislav Kisacanin et al.ICCV 2023 · 15 citations
- Not All Labels Are Equal: Rationalizing The Labeling Costs for Training Object DetectionIsmail Elezi, Zhiding Yu, Anima Anandkumar, Laura Leal-Taixé et al.CVPR 2022 · 45 citations
- End-to-End Human-Gaze-Target Detection with TransformersDanyang Tu, Xiongkuo Min, Huiyu Duan, Guodong Guo et al.CVPR 2022 · 69 citations
- Self-Training for Sample-Efficient Active Learning for Text Classification with Pre-Trained Language ModelsChristopher Schröder, Gerhard HeyerEMNLP 2024 · 2 citations
- Boosting Image-based Mutual Gaze Detection using Pseudo 3D GazeBardia Doosti, Ching-Hui Chen, Raviteja Vemulapalli, Xuhui Jia et al.AAAI 2021 · 17 citations
