Unsupervised Learning of Eye Gaze Representation from the Web

Abstract

Automatic eye gaze estimation has interested researchers for a while now. In this paper, we propose an unsupervised learning based method for estimating the eye gaze region. To train the proposed network "Ize-Net" in selfsupervised manner, we collect a large 'in the wild' dataset containing 1,54,251 images from the web. For the images in the database, we divide the gaze into three regions based on an automatic technique based on pupil-centers localization and then use a feature-based technique to determine the gaze region. The performance is evaluated on the Tablet Gaze and CAVE datasets by fine-tuning results of Ize-Net for the task of eye gaze estimation. The feature representation learned is also used to train traditional machine learning algorithms for eye gaze estimation. The results demonstrate that the proposed method learns a rich data representation, which can be efficiently finetuned for any eye gaze estimation dataset.

Appearance-based Gaze Estimation With Deep Learning: A Review and Benchmark

“…Eye image [26] - [42], [119], [113] [38], [47], [48], [95], [120] [40], [46], [51], [98], [100], [115], [121] [49], [50], [79], [52], [53], [80], [54] -Facial image - [35] [43], [64], [101] [66], [68], [104], [108] [5], [46], [69], [92], [99], [110], [111], [116], [118], [122] [49], [50], [67], [59], [61], [83], [62], [123], [78], [124], [63], [112], [82], [37], [107] [60]…”

“…[43], [64], [42], [101], [113], [119] [38], [47], [66], [68], [95], [104], [108], [120] [5], [36], [40], [46], [70], [71], [72], [98], [99], [100], [115], [116], [118], [121], [122] [82], [50], [49], [37], [59], [61], [83], [62], [123], [78], [79], [124], [52], [53], [80], [63], [125], [107] -Semi-/Self-/Un-Supervised CNN --- [48] [51], [69], [92], [110], [111] [54], [112], [37...…”

“…Single camera [26] [35] [43], [64], [42], [113] [38], [47], [48], [66], [68], [95], [104], [108], [120] [5], [36], [40], [46], [69], [70], [71], [72], [100], [111], [115], [116], [118], [121], [122] [59], [49], [50], [61], [83], [62], [123], [78], [79], [124], [52], [53], [80], [63], [125], [82], [37], [107] [60]…”

Automatic Gaze Analysis: A Survey of Deep Learning based Approaches

“…These methods face several challenges, which include partial occlusion of the iris by the eyelid, illumination condition, head pose, specular reflection in case the user wears glasses, the inability to use standard shape fitting for iris boundary detection, and other effects including motion blur and over saturation of image [72]. To deal with these challenges, most of the existing gaze estimation [23], [25], [48]- [56] [28], [48], [60]- [65] [57]- [59], [70], [74] HMD 2-5 55°-75°I ndependent (Leanback, Sitting, Upright) [31], [33], [75], [76] Automotive 50 40°-60°M obile, Sitting, Upright [39], [77]- [83] Handheld 20-40 5°-12°L eanfwd, Sitting, Standing, Mobile [24], [62], [84]- [87] ET/ FV --Leanfwd, Sitting, Standing, Upright [26], [88] methods have been performed under constrained environments like fixation of head pose, controlled illumination conditions, and camera angle. Such methods require a huge dump of highresolution labeled images.…”

“…Although, the performance enhancement comes with the cost of large scale annotated data, which is expensive to acquire. Recently, deep learning with limited annotation has gained increasing popularity [26]- [28].…”