View article

Learning fine-grained interplay between vision and language contributes to a more accurate understanding for Vision-Language tasks. However, it remains challenging to extract key image regions according to the texts for semantic alignments. Most existing works are either limited by text-agnostic and redundant regions obtained with the frozen detectors, or failing to scale further due to their heavy reliance on scarce grounding (gold) data to pre-train detectors. To solve these problems, we propose Self-Locator Aided Network (SLAN) for vision-language 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 vision-language 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 vision-language understanding tasks (eg, 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.