QR-CLIP: Introducing Explicit Open-World Knowledge for Location and Time Reasoning
This work addresses the challenge of abstract reasoning in AI for applications like image understanding, though it appears incremental as it builds on existing CLIP models with a novel method.
The paper tackles the problem of teaching machines to reason about the location and time from images by introducing explicit open-world knowledge, resulting in an average 10% and 130% relative improvement over previous state-of-the-art methods for location and time reasoning tasks.
Daily images may convey abstract meanings that require us to memorize and infer profound information from them. To encourage such human-like reasoning, in this work, we teach machines to predict where and when it was taken rather than performing basic tasks like traditional segmentation or classification. Inspired by Horn's QR theory, we designed a novel QR-CLIP model consisting of two components: 1) the Quantity module first retrospects more open-world knowledge as the candidate language inputs; 2) the Relevance module carefully estimates vision and language cues and infers the location and time. Experiments show our QR-CLIP's effectiveness, and it outperforms the previous SOTA on each task by an average of about 10% and 130% relative lift in terms of location and time reasoning. This study lays a technical foundation for location and time reasoning and suggests that effectively introducing open-world knowledge is one of the panaceas for the tasks.