Research map / Detection and segmentation / Open-set and few-shot detection
SIXray: A Large-Scale Security Inspection X-Ray Benchmark for Prohibited Item Discovery in Overlapping Images
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add CHR to DenseNet | DenseNet · SIXray100 | localization accuracy: 50.31% vs 44.70% | Helped |
| add CHR to DenseNet | DenseNet · SIXray1000 | mAP: 39.28 -> 48.36 | Helped |
| add CHR to DenseNet | DenseNet · SIXray1000 | localization accuracy: 43.87% vs 34.61% | Helped |
| add CHR to DenseNet | DenseNet · SIXray10 | mAP: 77.36 -> 79.56 | Helped |
| add CHR to DenseNet | DenseNet · SIXray10 | localization accuracy: 62.46 -> 65.62 | Helped |
| add direct hierarchical fusion (H) (ablation) | ResNet34 · SIXray10 | localization accuracy: 51.45 -> 49.91 | Hurt |
| add direct hierarchical fusion (H) (ablation) | ResNet34 · SIXray100 | mAP: 52.74 -> 53.59 | Helped |
| add class-balanced loss (CH) (ablation) | ResNet34 · SIXray1000 | mAP: 33.26 -> 37.87 | Helped |
| add class-balanced loss (CH) (ablation) | ResNet34 · SIXray10 | localization accuracy: 51.45 -> 48.01 | Hurt |
| add hierarchical refinement (HR) (ablation) | ResNet34 · SIXray100 | localization accuracy: 35.05 -> 41.57 | Helped |
| add hierarchical refinement (HR) (ablation) | ResNet34 · SIXray10 | mAP: 74.83 -> 75.87 | Helped |
| add hierarchical refinement and class-balanced loss (CHR) (ablation) | ResNet34 · SIXray1000 | mAP: 33.26 -> 38.74 | Helped |
Closest papers by meaning
- CSPCL: Category Semantic Prior Contrastive Learning for Deformable DETR-Based Prohibited Item Detectors (NeurIPS 2025 · similarity 0.87)
- Dual-view X-ray Detection: Can AI Detect Prohibited Items from Dual-view X-ray Images like Humans? (CVPR 2025 · similarity 0.87)
- STING-BEE: Towards Vision-Language Model for Real-World X-ray Baggage Security Inspection (CVPR 2025 · similarity 0.84)
- ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization (NeurIPS 2025 · similarity 0.81)
- Weak-to-Strong 3D Object Detection with X-Ray Distillation (CVPR 2024 · similarity 0.81)
- Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection (AAAI 2024 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.