English

A dual contrastive framework

Computer Vision and Pattern Recognition 2024-12-16 v1 Artificial Intelligence

Abstract

In current multimodal tasks, models typically freeze the encoder and decoder while adapting intermediate layers to task-specific goals, such as region captioning. Region-level visual understanding presents significant challenges for large-scale vision-language models. While limited spatial awareness is a known issue, coarse-grained pretraining, in particular, exacerbates the difficulty of optimizing latent representations for effective encoder-decoder alignment. We propose AlignCap, a framework designed to enhance region-level understanding through fine-grained alignment of latent spaces. Our approach introduces a novel latent feature refinement module that enhances conditioned latent space representations to improve region-level captioning performance. We also propose an innovative alignment strategy, the semantic space alignment module, which boosts the quality of multimodal representations. Additionally, we incorporate contrastive learning in a novel manner within both modules to further enhance region-level captioning performance. To address spatial limitations, we employ a General Object Detection (GOD) method as a data preprocessing pipeline that enhances spatial reasoning at the regional level. Extensive experiments demonstrate that our approach significantly improves region-level captioning performance across various tasks

Keywords

Cite

@article{arxiv.2412.10348,
  title  = {A dual contrastive framework},
  author = {Yuan Sun and Zhao Zhang and Jorge Ortiz},
  journal= {arXiv preprint arXiv:2412.10348},
  year   = {2024}
}
R2 v1 2026-06-28T20:34:28.644Z