Generalization and Hallucination of Large Vision-Language Models through a Camouflaged Lens
Preprint
Abstract
Large Vision-Language Model (LVLM) has seen burgeoning development and increasing attention recently. In this paper, we propose a novel framework, camo-perceptive vision-language framework (CPVLF), to explore whether LVLM can generalize to the challenging camouflaged object detection (COD) scenario in a training-free manner. During the process of generalization, we find that due to hallucination issues within LVLM, it can erroneously perceive objects in camouflaged scenes, producing counterfactual concepts. Moreover, as LVLM is not specifically trained for the precise localization of camouflaged objects, it exhibits a degree of uncertainty in accurately pinpointing these objects. Therefore, we propose chain of visual perception, which enhances LVLM's perception of camouflaged scenes from both linguistic and visual perspectives, reducing the hallucination issue and improving its capability in accurately locating camouflaged objects. We validate the effectiveness of CPVLF on three widely used COD datasets, and the experiments show the potential of LVLM in the COD task.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest2025
- Feature Shrinkage Pyramid for Camouflaged Object Detection with Transformers2023
- Deep Gradient Learning for Efficient Camouflaged Object DetectionMachine Intelligence Research, 2023
- Detecting Camouflaged Object in Frequency Domain2022
- Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection2022
- Camouflaged object detection via Neighbor Connection and Hierarchical Information TransferComputer Vision and Image Understanding, 2022
- Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration NetworkPattern Recognition, 2022
- Simultaneously Localize, Segment and Rank the Camouflaged Objects2021
- Anabranch network for camouflaged object segmentationComputer Vision and Image Understanding, 2019
- Microsoft COCO: Common Objects in Context2014