跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1680新增论文
+1333其中 AI 相关
+187已有论文修订
+59新增 AI 导读

arXiv 最近完成扫描:2026-11-18 04:28 · 全站最近入库:2026-11-17 23:35各信源进度 →

统计口径与数据新鲜度

统计 2026-11-17 09:51 — 2026-11-18 09:51(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-18 04:28最近发现新增版本:2026-11-17 23:35库内论文最新更新时间:2026-11-17 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

25,786 已收录论文21,491 AI 相关7,725 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 1 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
新论文 · v1arXiv:2611.19780

A Threshold-Free Visual-Semantic Matching Metric for Evaluating Consistency in Subject-Driven Image Generation

Bowei Shan, Heng Yin

原文摘要

In subject-driven text-to-image generation, quantitatively evaluating localized visual consistency across varying poses and environments remains a major challenge. Existing metrics either rely on global image embeddings (CLIP, DINO) and Vision-Language Models (VLMs) that pool spatial representations and miss fine-grained textural artifacts, or depend on scalar threshold-gated dense metrics such as Visual-Semantic Matching (VSM) that suffer from point-alignment dropouts, severe threshold sensitivity, and score instability. To overcome these limitations, we propose TF-VSM, a fully continuous, threshold-free visual-consistency metric paired with an extended feature-disentanglement retraining schedule for dual-branch ResNet feature-aggregation networks. Rather than enforcing rigid binary cutoffs $(T_s,T_v)$, TF-VSM weights every object point by a non-linear semantic match confidence $w_j=ReLU(\hat{s}_j)^2$ and continuously integrates visual similarity over all consistency levels $r\in[0,1]$, yielding a closed-form confidence-weighted score without any hand-tuned hyperparameters. On a controlled 100-pair benchmark with ground-truth inpainting oracles, TF-VSM attains Pearson $0.638$ and Spearman $0.674$ oracle correlation, improving over the pretrained VSM baseline ($0.454/0.589$) by $+0.171/+0.116$ after retraining, and drastically outperforming CLIP ($-0.052/-0.004$), DINO ($0.087/0.121$), and VLMs ($0.096/0.003$). Six diagnostic ablations confirm that smooth confidence weighting is the right mechanism, that hard semantic gating is brittle (dropping to $0.533$ Pearson at $T_s{=}0.8$), and that the threshold-free metric is essentially invariant to the training-time loss balance $α$ that the thresholded metric still depends on.

cs.CV