Transferable Decoding with Visual Entities for Zero-Shot Image Captioning, ICCV 2023
-
Updated
Sep 9, 2024 - Python
Transferable Decoding with Visual Entities for Zero-Shot Image Captioning, ICCV 2023
[NeurIPS 2024] Official Repository of Multi-Object Hallucination in Vision-Language Models
DASH: Detection and Assessment of Systematic Hallucinations of VLMs
Relabeling of the POPE benchmark
Object Hallucination Benchmark for Vision Language Models
[CVPR 2026] Self-Critical Inference (SCI) & DRBench: multi-round counterfactual inference that scales the test-time robustness of vision-language models against language bias, object hallucination and prompt sensitivity. Official code.
To associate your repository with the object-hallucination topic, visit your repo's landing page and select "manage topics."