PointRefiner: per-instance evaluation results and supplementary checkpoints

Supplementary artifacts for the paper "PointRefiner: Sub-Million Parameter Point-Prompted Instance Segmentation" by Bulzan and Cernăzanu-Glăvan (under review at Neurocomputing, 2026). ▎ Contents: ▎ ▎ 1. Per-instance evaluation result JSONs (11 files) for the LVIS v1 val benchmark (187,447 instances, single-click ▎ protocol). Each file contains a summary block (mean IoU, success-at-IoU rates, mean box IoU, timing) and per-sample ▎ ious / box_ious arrays, indexed in the order of the shared click list (clicks_lvis_val_min10_seed0.json, distributed ▎ via the project repository). Methods covered: ▎ - PointRefiner-Large (paper headline) and PointRefiner-Base ▎ - PointRefiner-Large with the v2 inference recipe (hflip TTA, ScaleNet top-2 fallback, selective auto-refinement) ▎ - SAM 1 ViT-B, SAM 2.1-Tiny, SAM 2.1-Large, MobileSAM, EdgeSAM, EfficientSAM-Ti ▎ 2. Smaller-variant ScaleNet checkpoints used in the development-history experiments described in ▎ experiments/README.md of the project repository (not the canonical paper checkpoints — those ship in the repo ▎ itself). ▎ ▎ The trained model weights for the canonical paper system (PointRefiner-Large + ScaleNet-Base, 5.2 MB total) are ▎ released directly in the source repository: https://github.com/AndreiBulzan/pointrefiner. This Zenodo record ▎ complements the repository with the larger per-instance result arrays. ▎ ▎ All evaluations use the LVIS v1 val annotations on top of COCO 2017 images. The shared click list and full ▎ reproduction commands are in the source repository.本数据集为Bulzan与Cernăzanu-Glăvan所著论文《"PointRefiner: 亚百万参数点提示实例分割（Point-Prompted Instance Segmentation）"》（2026年投稿于Neurocomputing，目前处于审稿阶段）的配套补充材料。 ▎ 内容清单： ▎ 1. 针对LVIS v1验证集基准（共187,447个实例，采用单点点击协议）的逐实例评估结果JSON文件（共11个）。每个文件包含统计摘要模块（平均交并比（Intersection over Union, IoU）、指定交并比阈值下的成功率、平均框交并比、运行时长）以及逐样本的IoU/box_iou数组，索引顺序与共享点击列表（clicks_lvis_val_min10_seed0.json，已通过项目仓库发布）保持一致。涵盖的方法包括： - PointRefiner-Large（论文核心方法）与PointRefiner-Base - 采用v2推理流程的PointRefiner-Large（含水平翻转测试时增强（Test Time Augmentation, TTA）、ScaleNet前2候选回退、选择性自动优化） - SAM 1 ViT-B、SAM 2.1-Tiny、SAM 2.1-Large、MobileSAM、EdgeSAM、EfficientSAM-Ti ▎ 2. 项目仓库experiments/README.md中所述开发历史实验所用的轻量化ScaleNet模型权重（非论文正式权重——正式权重已随仓库本身发布）。 本论文标准系统（PointRefiner-Large + ScaleNet-Base，总大小5.2 MB）的训练模型权重已直接在源代码仓库https://github.com/AndreiBulzan/pointrefiner中发布。本Zenodo数据集仅作为该仓库的补充，提供更大体积的逐实例结果数组。 所有评估均基于COCO 2017图像搭配LVIS v1验证集标注完成。共享点击列表与完整复现命令均已收录于源代码仓库中。