PropVG: End-to-End Proposal-Driven Visual Grounding with Multi-Granularity Discrimination
This work addresses visual grounding for computer vision applications by introducing a novel method that enhances object identification in complex scenarios, though it is incremental in improving existing paradigms.
The paper tackles the problem of visual grounding by proposing PropVG, an end-to-end proposal-based framework that integrates foreground object proposal generation with referential object comprehension, achieving state-of-the-art results on benchmarks like gRefCOCO and RefCOCO with improved accuracy.
Recent advances in visual grounding have largely shifted away from traditional proposal-based two-stage frameworks due to their inefficiency and high computational complexity, favoring end-to-end direct reference paradigms. However, these methods rely exclusively on the referred target for supervision, overlooking the potential benefits of prominent prospective targets. Moreover, existing approaches often fail to incorporate multi-granularity discrimination, which is crucial for robust object identification in complex scenarios. To address these limitations, we propose PropVG, an end-to-end proposal-based framework that, to the best of our knowledge, is the first to seamlessly integrate foreground object proposal generation with referential object comprehension without requiring additional detectors. Furthermore, we introduce a Contrastive-based Refer Scoring (CRS) module, which employs contrastive learning at both sentence and word levels to enhance the capability in understanding and distinguishing referred objects. Additionally, we design a Multi-granularity Target Discrimination (MTD) module that fuses object- and semantic-level information to improve the recognition of absent targets. Extensive experiments on gRefCOCO (GREC/GRES), Ref-ZOM, R-RefCOCO, and RefCOCO (REC/RES) benchmarks demonstrate the effectiveness of PropVG. The codes and models are available at https://github.com/Dmmm1997/PropVG.