SLAN: Self-Locator Aided Network for Cross-Modal Understanding
It addresses the problem of fine-grained cross-modal understanding for vision-language tasks, offering a novel approach that is incremental in improving region localization without extra data.
The paper tackles the challenge of extracting key image regions for vision-language alignment without relying on scarce grounding data, proposing SLAN which achieves competitive results, such as 85.7% and 69.2% on COCO retrieval tasks, surpassing previous SOTA methods.
Learning fine-grained interplay between vision and language allows to a more accurate understanding for VisionLanguage tasks. However, it remains challenging to extract key image regions according to the texts for semantic alignments. Most existing works are either limited by textagnostic and redundant regions obtained with the frozen detectors, or failing to scale further due to its heavy reliance on scarce grounding (gold) data to pre-train detectors. To solve these problems, we propose Self-Locator Aided Network (SLAN) for cross-modal understanding tasks without any extra gold data. SLAN consists of a region filter and a region adaptor to localize regions of interest conditioned on different texts. By aggregating cross-modal information, the region filter selects key regions and the region adaptor updates their coordinates with text guidance. With detailed region-word alignments, SLAN can be easily generalized to many downstream tasks. It achieves fairly competitive results on five cross-modal understanding tasks (e.g., 85.7% and 69.2% on COCO image-to-text and text-to-image retrieval, surpassing previous SOTA methods). SLAN also demonstrates strong zero-shot and fine-tuned transferability to two localization tasks.