| 研究課題/領域番号 |
23K11169
|
|---|
| 研究種目 |
基盤研究(C)
|
| 配分区分 | 基金 |
|---|
| 応募区分 | 一般 |
|---|
| 審査区分 |
小区分61010:知覚情報処理関連
|
|---|
| 研究機関 | 岡山大学 |
|---|
研究代表者 |
Yucel Zeynep 岡山大学, 環境生命自然科学学域, 准教授 (20586250)
|
|---|
| 研究期間 (年度) |
2023-04-01 – 2025-03-31
|
| 研究課題ステータス |
中途終了 (2023年度)
|
| 配分額 *注記 |
2,210千円 (直接経費: 1,700千円、間接経費: 510千円)
2025年度: 650千円 (直接経費: 500千円、間接経費: 150千円)
2024年度: 780千円 (直接経費: 600千円、間接経費: 180千円)
2023年度: 780千円 (直接経費: 600千円、間接経費: 180千円)
|
|---|
| キーワード | saliency / affordance / segmentation / gaze / perception / action / intention |
|---|
| 研究開始時の研究の概要 |
[1] After determining strategy of functional segmentation of tool objects according to affordances, we will generation of baseline saliency from tool images. [2] We will collect data from human subjects and and determine the distribution of the gaze bias for each functional segment. [3] We will apply spatial modulation on the baseline saliency computed at [1] by introducing attractors and repellers from the abovementioned models.
|
| 研究実績の概要 |
We examined the performance of four recent saliency models EML-NET, SalGAN, DeepGaze IIE, and DeepGaze on images of hand tools. These objects have distinct segments with various roles, and studies suggest that tool segments inherently attract human attention. We tested the models on a dataset containing both tool and non-tool images, then compared their predictions with human gaze data using six criteria. The results show that the models often struggle to predict saliency accurately for tool images compared to non-tool images. This suggests a need to address this limitation in saliency modeling for tool-specific contexts.
|
| 現在までの達成度 (区分) |
現在までの達成度 (区分)
2: おおむね順調に進展している
理由
We have demonstarted that the existing state-of-the-art saliency models are not as efficient in representing eye gaze patterns over tool images as they are in representing the eye gaze patterns over other images from ordinary daily life scenes. This justifies an effort to improve the existing methods.
|
| 今後の研究の推進方策 |
We focus on the state-of-the-art visual saliency prediction model of DeepGaze IIE and make an effort to refine it to account for this bias. Since the integration of transfer learning into saliency prediction over the last decade has notably enhanced prediction performance, we will initially curate a custom image data set featuring tools, non-tools and ambiguous images and record empirical gaze data from human participants to be used in fine-tuning. In this way, we will improve the model’s performance for this specific stimulus category and evaluate it by IG and NSS metrics.
|
