English

SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive Decoding

Computer Vision and Pattern Recognition 2026-03-31 v1

Abstract

Despite significant advancements in Vision-Language Models (VLMs), the performance of existing VLMs remains hindered by object hallucination, a critical challenge to achieving accurate visual understanding. To address this issue, we propose SECOND: Selective and Contrastive Decoding, a novel approach that enables VLMs to effectively leverage multi-scale visual information with an object-centric manner, closely aligning with human visual perception. SECOND progressively selects and integrates multi-scale visual information, facilitating a more precise interpretation of images. By contrasting these visual information iteratively, SECOND significantly reduces perceptual hallucinations and outperforms a wide range of benchmarks. Our theoretical analysis and experiments highlight the largely unexplored potential of multi-scale application in VLMs, showing that prioritizing and contrasting across scales outperforms existing methods.

Keywords

Cite

@article{arxiv.2506.08391,
  title  = {SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive Decoding},
  author = {Woohyeon Park and Woojin Kim and Jaeik Kim and Jaeyoung Do},
  journal= {arXiv preprint arXiv:2506.08391},
  year   = {2026}
}
R2 v1 2026-07-01T03:08:16.424Z