Research map / Detection and segmentation / Weakly supervised detection and segmentation
Weakly Supervised Visual Semantic Parsing
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 |
|---|---|---|---|
| Use VSPNet instead of PPR-FCN under weak supervision | VG preprocessed · SGGen | R@50: 1.5 -> 3.1 | Helped |
| Use VSPNet instead of PPR-FCN under weak supervision | VG preprocessed · PhrDet | R@50: 2.4 -> 17.6 | Helped |
| Use VSPNet instead of S-PPR-FCN under full supervision | VG preprocessed · SGGen | R@50: 6.0 -> 8.9 | Helped |
| Use VSPNet instead of Graph R-CNN | VG, full supervision · SGGen | R@50: 11.4 -> 12.6 | Helped |
| Use VSPNet instead of Assoc. Emb. | VG, full supervision · PredCls | R@50: 68.0 -> 67.4 | Hurt |
| Use VSPNet instead of Graph R-CNN | VG, full supervision · inference time | seconds per image: 0.83 -> 0.11 | Helped |
| Add iterative graph alignment rather than independent one-step alignments (ablation) | VSPNet on VG preprocessed · weak supervision, SGGen | R@50: 1.3 -> 3.1 | Helped |
| Use 3 alignment steps rather than 1 (ablation) | VSPNet on VG preprocessed · weak supervision, SGGen | R@50: 1.8 -> 3.1 | Helped |
| Add three-stage message aggregation rather than average pooling (ablation) | VSPNet on VG preprocessed · weak supervision, PhrDet | R@50: 16.7 -> 17.6 | Helped |
| Add role-driven attention rather than uniform attention (ablation) | VSPNet on VG preprocessed · weak supervision, PhrDet | R@50: 15.7 -> 17.6 | Helped |
| Use 3 message-passing steps rather than 1 (ablation) | VSPNet on VG preprocessed · weak supervision, PhrDet | R@50: 15.5 -> 17.6 | Helped |
Closest papers by meaning
- LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation (CVPR 2024 · similarity 0.90)
- Scene Graph Generation with Role-Playing Large Language Models (NeurIPS 2024 · similarity 0.89)
- From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models (CVPR 2024 · similarity 0.89)
- RA-SGG: Retrieval-Augmented Scene Graph Generation Framework via Multi-Prototype Learning (AAAI 2025 · similarity 0.89)
- Leveraging Predicate and Triplet Learning for Scene Graph Generation (CVPR 2024 · similarity 0.89)
- DSGG: Dense Relation Transformer for an End-to-end Scene Graph Generation (CVPR 2024 · similarity 0.88)
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.