Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.00721 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908935323123712 |
|---|---|
| author | Yang, Tianze Jordan, Tyson Sun, Ruitong Liu, Ninghao Sun, Jin |
| author_facet | Yang, Tianze Jordan, Tyson Sun, Ruitong Liu, Ninghao Sun, Jin |
| contents | We present Common Inpainted Objects In-N-Out of Context (COinCO), a novel dataset addressing the scarcity of out-of-context examples in existing vision datasets. By systematically replacing objects in COCO images through diffusion-based inpainting, we create 97,722 unique images featuring both contextually coherent and inconsistent scenes, enabling effective context learning. Each inpainted object is meticulously verified and categorized as in- or out-of-context through Large Vision Language Model assessments. We demonstrate three key tasks enabled by COinCO: (1) a fine-grained context reasoning approach that classifies objects as in- or out-of-context based on three criteria; (2) a novel Objects-from-Context prediction task that determines which new objects naturally belong in given scenes at both instance and clique level semantics, and (3) context-enhanced fake detection on state-of-the-art methods without fine-tuning. COinCO provides a controlled testbed with contextual variations, establishing a foundation for advancing context-aware visual understanding in computer vision, including image forensics. Code and dataset are available at https://co-in-co.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_00721 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Common Inpainted Objects In-N-Out of Context Yang, Tianze Jordan, Tyson Sun, Ruitong Liu, Ninghao Sun, Jin Computer Vision and Pattern Recognition Machine Learning We present Common Inpainted Objects In-N-Out of Context (COinCO), a novel dataset addressing the scarcity of out-of-context examples in existing vision datasets. By systematically replacing objects in COCO images through diffusion-based inpainting, we create 97,722 unique images featuring both contextually coherent and inconsistent scenes, enabling effective context learning. Each inpainted object is meticulously verified and categorized as in- or out-of-context through Large Vision Language Model assessments. We demonstrate three key tasks enabled by COinCO: (1) a fine-grained context reasoning approach that classifies objects as in- or out-of-context based on three criteria; (2) a novel Objects-from-Context prediction task that determines which new objects naturally belong in given scenes at both instance and clique level semantics, and (3) context-enhanced fake detection on state-of-the-art methods without fine-tuning. COinCO provides a controlled testbed with contextual variations, establishing a foundation for advancing context-aware visual understanding in computer vision, including image forensics. Code and dataset are available at https://co-in-co.github.io/. |
| title | Common Inpainted Objects In-N-Out of Context |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2506.00721 |