Research map / Image generation / Text-to-image diffusion
Exploring Phrase-Level Grounding with Text-to-Image Diffusion Model
Danni Yang, Ruohan Dong, Jiayi Ji, Yiwei Ma, Haowei Wang, Xiaoshuai Sun, Rongrong Ji
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 Locate-to-Segment Processor (self-attention aggregation from cross-attention anchors) (ablation) | DiffPNG cross-attention baseline · PNG val (zero-shot) | Average Recall overall: 30.24 -> 33.54 | Improved |
| add SAM-based Mask Refinement (ablation) | DiffPNG · PNG val (zero-shot) | Average Recall overall: 33.54 -> 38.49 | Improved |
| add DenseCRF refinement (ablation) | DiffPNG · PNG val (zero-shot) | Average Recall overall: 33.54 -> 23.49 | Hurt |
| select anchors by threshold instead of top-K percentage (ablation) | DiffPNG · PNG val (zero-shot) | Average Recall overall: 30.13 -> 33.54 | Improved |
| use top-K percentage anchors rather than cross-attention alone (ablation) | cross-attention baseline · PNG val (zero-shot) | Average Recall overall: 30.24 -> 30.13 | No clear effect |
| use cross-attention resolution 16 rather than 32 or 64 (ablation) | DiffPNG · PNG val (zero-shot) | Average Recall overall: 16.54 -> 33.54 | Improved |
| use subject-focused aggregator instead of average aggregator (ablation) | DiffPNG · PNG val (zero-shot) | Average Recall overall: 32.40 -> 33.27 | Improved |
| use subject-focused aggregator instead of multiplication aggregator (ablation) | DiffPNG · PNG val (zero-shot) | Average Recall overall: 28.67 -> 33.27 | Improved |
| aggregate cross-attention rather than self-attention-enhanced maps (ablation) | DiffPNG · PNG val (zero-shot) | Average Recall overall: 33.27 -> 33.54 | Improved |
| use DatasetDiffusion or DiffSeg style attention merging instead of cross-attention only (ablation) | cross-attention baseline · PNG val (zero-shot) | Average Recall overall: 30.24 -> 23.46 and 24.08 | Hurt |
| tune binarization threshold alpha to 0.3 instead of 0.5 (ablation) | DiffPNG LSP output · PNG val (zero-shot) | Average Recall overall: 28.20 -> 33.54 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DatasetDiffusion — Dataset Diffusion: Diffusion-based Synthetic Data Generation for Pixel-Level Semantic Segmentation (NeurIPS 2023) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Improving Panoptic Narrative Grounding by Harnessing Semantic Relationships and Visual Confirmation (AAAI 2024 · similarity 0.90)
- Seg4Diff: Unveiling Open-Vocabulary Semantic Segmentation in Text-to-Image Diffusion Transformers (NeurIPS 2025 · similarity 0.89)
- Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding (CVPR 2025 · similarity 0.88)
- Mask Grounding for Referring Image Segmentation (CVPR 2024 · similarity 0.88)
- Connecting the Dots: Training-Free Visual Grounding via Agentic Reasoning (AAAI 2026 · similarity 0.88)
- Improved Visual Grounding through Self-Consistent Explanations (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.
