Research map / Label-efficient and robust learning / Noisy labels
The Devil Is in the Labels: Noisy Label Correction for Robust Scene Graph Generation
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 NICE noisy-label detection and correction | Motifs and VCTree · VG PredCls, SGCls, and SGGen | mR@K: 6.7% ~ 14.5% and 4.7% ~ 14.6% absolute gains on metric mR@100 over Motifs and VCTree, respectively | Helped |
| Add negative noisy sample detection and pseudo-label missing foreground triplets (ablation) | Motifs · VG PredCls | mR@100: 17.8% vs. 25.2% | Helped |
| Add positive noisy sample detection, retaining the clean positive subset (ablation) | Motifs · VG PredCls | mR@100: 17.8% vs. 22.0% | Helped |
| Add positive noisy sample detection and label correction with wKNN (ablation) | Motifs · VG PredCls | mR@100: 22.0% vs. 25.2% | Helped |
| Vary the wKNN neighbor count across K={1,3,5} (ablation) | NICE · VG | SGG performance | No clear effect |
| Vary the Neg-NSD mining thresholds across predicate groups (ablation) | NICE · VG | mR@K and R@K | Mixed |
| Use category-specific cutoff distances for positive noisy sample detection (ablation) | NICE · VG | SGG performance | Helped |
Closest papers by meaning
- TD²-Net: Toward Denoising and Debiasing for Video Scene Graph Generation (AAAI 2024 · similarity 0.88)
- Adaptive Self-training Framework for Fine-grained Scene Graph Generation (ICLR 2024 · similarity 0.88)
- Semi-Supervised Clustering Framework for Fine-grained Scene Graph Generation (AAAI 2025 · similarity 0.87)
- HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation (CVPR 2024 · similarity 0.87)
- RA-SGG: Retrieval-Augmented Scene Graph Generation Framework via Multi-Prototype Learning (AAAI 2025 · similarity 0.86)
- NoisyGL: A Comprehensive Benchmark for Graph Neural Networks under Label Noise (NeurIPS 2024 · similarity 0.86)
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.