Research map / Detection and segmentation / Open-set and few-shot detection
OVID: Open-Vocabulary Intrusion Detection
Fujun Han, Jingqi Ye, Chenglong Zhang, Peng Ye
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 Dynamic Memory-Gated module (DMG) (ablation) | OVIDNet baseline · Cityintrusion-OpenV | Acc: 29.36 -> 30.72 | Improved |
| add Multi-Distributed Noise Mixing (MDNM) (ablation) | OVIDNet baseline · Cityintrusion-OpenV | Acc: 29.36 -> 31.75 | Improved |
| add both DMG and MDNM (ablation) | OVIDNet baseline · Cityintrusion-OpenV | Acc: 29.36 -> 32.79 | Improved |
| add both DMG and MDNM (ablation) | OVIDNet baseline · Cityscape zero-shot | PQ: 14.03 -> 16.22 | Improved |
| set noise mixing weights to 0.5, 0.1, 0.4 (vs 0.5, 0.4, 0.1) (ablation) | MDNM · Cityintrusion-OpenV | Acc: 30.28 -> 31.75 | Improved |
| set memory units to M=40 (vs 30 or 50) (ablation) | DMG · Cityintrusion-OpenV | Acc: 30.31, 30.72, 30.34 | Mixed |
| add Geometric Constraint Reclassification (GCRS) (ablation) | OVIDNet · Cityintrusion-OpenV | Rider Acc: 0 -> 23.56 | Improved |
| add GCRS (ablation) | OVIDNet · Cityintrusion-OpenV | Acc: 32.79 -> 33.55 | Improved |
| add DMG and MDNM (ablation) | OVIDNet baseline · Cityintrusion-OpenV-BDD | Acc: 18.69 -> 23.27 | Improved |
| use end-to-end OVIDNet instead of YOLO-World-L+Clipseg | OVIDNet · Cityintrusion-OpenV | Acc: 2.71% (normal), 3.49% (foggy) | Improved |
| use OVIDNet instead of OpenSeeD under foggy coefficients | OVIDNet · Normal->Foggy Cityintrusion-OpenV | Acc: 2.96%, 3.22%, 3.45% | Improved |
Closest papers by meaning
- OW-OVD: Unified Open World and Open Vocabulary Object Detection (CVPR 2025 · similarity 0.87)
- Open-Vocabulary Video Anomaly Detection (CVPR 2024 · similarity 0.85)
- OVT-B: A New Large-Scale Benchmark for Open-Vocabulary Multi-Object Tracking (NeurIPS 2024 · similarity 0.84)
- Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection (CVPR 2024 · similarity 0.84)
- Simple Image-Level Classification Improves Open-Vocabulary Object Detection (AAAI 2024 · similarity 0.83)
- COUNTS: Benchmarking Object Detectors and Multimodal Large Language Models under Distribution Shifts (CVPR 2025 · similarity 0.83)
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.
