m-hood-dataset

M-Hood Dataset: Out-of-Distribution Evaluation Collection This dataset collection contains out-of-distribution (OOD) image datasets specifically curated for evaluating the robustness of object detection models, particularly those trained to mitigate hallucination on out-of-distribution data. 🎯 Purpose These datasets are designed to address limitations in existing OOD benchmarks and enable fine-grained analysis of hallucination suppression. They test how well object… See the full description on the dataset page:

Source: Hugging Face Hub (HugoHE/m-hood-dataset). Metadata imported from the dataset’s Hub tags.