Research map / Detection and segmentation / Weakly supervised detection and segmentation
APL: Anchor-based Prompt Learning for One-stage Weakly Supervised Referring Expression Comprehension
Yaxin Luo, Jiayi Ji, Xiaofu Chen, Yuxin Zhang, Tianhe Ren, Gen Luo
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 anchor-based prompt encoder (position, color, category prompts) (ablation) | RefCLIP-style baseline · RefCOCO val | accuracy (%): 60.36 -> 62.89 | Improved |
| add text reconstruction loss (ablation) | APL · RefCOCO+ val | accuracy (%): 41.54 -> 42.31 | Improved |
| add visual alignment loss (ablation) | APL · RefCOCO val | accuracy (%): 63.01 -> 64.51 | Improved |
| use APL instead of RefCLIP | one-stage weakly supervised REC · RefCOCO val | accuracy (%): 60.36 -> 64.51 | Improved |
| use APL instead of RefCLIP | inference speed · inference speed | fps: 31.3fps -> 26.7fps | Hurt |
| use APL pseudo-labels instead of RefCLIP pseudo-labels to train SimREC | SimREC student · ReferIt test | accuracy (%): 42.33 -> 45.22 | Improved |
| use APL pseudo-labels instead of RefCLIP pseudo-labels to train TransVG | TransVG student · RefCOCO val | accuracy (%): 64.08 -> 64.86 | No clear effect |
| use text description instead of positional function for spatial prompt (ablation) | APE · RefCOCO | accuracy (%): -6.63% | Hurt |
| use BLIP-generated region captions as text prompts (ablation) | APE · RefCOCO | accuracy (%) | Hurt |
| extend APL to weakly supervised referring segmentation with YOLOv5-Seg | APL · RefCOCO val (RES) | mask accuracy (%): 31.17 -> 55.92 | 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.
- RefCLIP — RefCLIP: A Universal Teacher for Weakly Supervised Referring Expression Comprehension (CVPR 2023) · better on 6 of 7 shared results
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
- Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks (ICLR 2026 · similarity 0.89)
- RefDetector: A Simple Yet Effective Matching-based Method for Referring Expression Comprehension (AAAI 2025 · similarity 0.89)
- DViN: Dynamic Visual Routing Network for Weakly Supervised Referring Expression Comprehension (CVPR 2025 · similarity 0.87)
- Rethinking Two-Stage Referring Expression Comprehension: A Novel Grounding and Segmentation Method Modulated by Point (AAAI 2024 · similarity 0.87)
- A Large-Scale Human-Centric Benchmark for Referring Expression Comprehension in the LMM Era (NeurIPS 2024 · similarity 0.87)
- ScanFormer: Referring Expression Comprehension by Iteratively Scanning (CVPR 2024 · 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.
