Image-Guided Zero-Shot Object Detection in Video Games : Using Images as Prompts for Detection of Unseen 2D Icons

Sammanfattning: Object detection deals with localization and classification of objects in images, where the task is to propose bounding boxes and predict their respective classes. Challenges in object detection include large-scale annotated datasets and re-training of models for specific tasks. Motivated by these problems, we propose a zero-shot object detection (ZSD) model in the setting of user interface icons in video games. Allowing to quickly and accurately analyze the state of a game, with potentially millions of people watching, would greatly benefit the large and fast-growing video game sector. Our resulting model is a modification of YOLOv8, which, at inference time, is prompted with the specific object to detect in an image. Many existing ZSD models exploit semantic embeddings and high-dimensional word vectors to generalize to novel classes. We hypothesize that using only visual representations is sufficient for the detection of unseen classes. To train and evaluate our model, we create synthetic data to reflect the nature of video game icons and in-game frames. Our method achieves similar performance as YOLOv8 on bounding box prediction and detection of seen classes while retaining the same average precision and recall for unseen classes, where the number of unseen classes is in the order of thousands.