Research map / Detection and segmentation / CNN features
Explicit Visual Prompting for Universal Foreground Segmentations
Weihuang Liu, Xi Shen, Chi‐Man Pun, Xiaodong Cun
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 frozen patch-embedding features Fpe as prompt (ablation) | EVPv1 (SegFormer) · CASIA forgery | AUC: .833 -> .862 | Improved |
| add high-frequency features Fhfc as prompt (ablation) | EVPv1 (SegFormer) · CASIA forgery | AUC: .846 -> .862 | Improved |
| add patch-embedding features Fpe as prompt (ablation) | EVPv2 (SegFormer) · ISTD shadow | BER: 1.75 -> 1.35 | Improved |
| add Frequency Enhanced Adaptor instead of two plain MLP blocks (ablation) | EVPv2 (SegFormer) · ISTD shadow | BER: 1.40 -> 1.35 | Improved |
| unshare MLP_tune across adaptors (shared MLP_tune) (ablation) | EVPv1 (SegFormer) · ISTD shadow | BER: 1.77 -> 1.35 | Improved |
| use unshared MLP_up in each adaptor (ablation) | EVPv1 (SegFormer) · ISTD shadow | BER: 1.35 -> 1.33 | No clear effect |
| tune all four SegFormer stages instead of only Stage1 (ablation) | EVPv2 (SegFormer) · ISTD shadow | BER: 3.99 -> 1.35 | Improved |
| tune Stage3 only vs all stages (ablation) | EVPv2 (SegFormer) · ISTD shadow | BER: 1.44 -> 1.35 | Improved |
| reduce scale factor r from 64 to 16 (more tunable parameters) (ablation) | EVPv2 (SegFormer) · ISTD shadow | BER: 1.69 -> 1.35 | Improved |
| reduce scale factor r from 16 to 4 (ablation) | EVPv2 (SegFormer) · ISTD shadow | BER: 1.35 -> 1.53 | Hurt |
| replace full fine-tuning with EVPv2 (frozen backbone) (ablation) | SegFormer · ISTD shadow | BER: 2.42 -> 1.35 | Improved |
| replace full fine-tuning with EVPv2 (frozen backbone) (ablation) | ViT-CLS · CASIA forgery | AUC: .692 -> .784 | Improved |
Closest papers by meaning
- Just a Few Glances: Open-Set Visual Perception with Image Prompt Paradigm (AAAI 2025 · similarity 0.88)
- Visual In-Context Prompting (CVPR 2024 · similarity 0.88)
- Relax Image-Specific Prompt Requirement in SAM: A Single Generic Prompt for Segmenting Camouflaged Objects (AAAI 2024 · similarity 0.88)
- AutoVP: An Automated Visual Prompting Framework and Benchmark (ICLR 2024 · similarity 0.88)
- Segment Anyword: Mask Prompt Inversion for Open-Set Grounded Segmentation (ICML 2025 · similarity 0.87)
- FOCUS: Towards Universal Foreground Segmentation (AAAI 2025 · similarity 0.87)
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.
