Gaze Embeddings for Zero-Shot Image Classification
This provides a more accessible alternative to expert annotations for fine-grained image classification, though it is incremental in leveraging gaze data for zero-shot learning.
The paper tackles the problem of zero-shot image classification by using human gaze data as auxiliary information instead of expert-annotated attributes, showing that gaze data is class-discriminative and outperforms baselines in this task.
Zero-shot image classification using auxiliary information, such as attributes describing discriminative object properties, requires time-consuming annotation by domain experts. We instead propose a method that relies on human gaze as auxiliary information, exploiting that even non-expert users have a natural ability to judge class membership. We present a data collection paradigm that involves a discrimination task to increase the information content obtained from gaze data. Our method extracts discriminative descriptors from the data and learns a compatibility function between image and gaze using three novel gaze embeddings: Gaze Histograms (GH), Gaze Features with Grid (GFG) and Gaze Features with Sequence (GFS). We introduce two new gaze-annotated datasets for fine-grained image classification and show that human gaze data is indeed class discriminative, provides a competitive alternative to expert-annotated attributes, and outperforms other baselines for zero-shot image classification.