发表机构
Shenzhen University（深圳大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对测试时二值分割中熵最小化导致的类别坍缩问题，提出平衡锚点提示适配（BAPA），通过类别平衡锚点与动态提示适配实现均衡更新，在四个领域取得最高平均Dice。
AI 中文摘要
熵最小化是测试时适配（TTA）的标准目标，但在不平衡的二值分割中可能失效。与图像分类不同，密集分割聚合了数千个像素预测，使得较大的预测类别主导更新，将少数类别的预测拉向自身，并随着预测饱和及其熵梯度消失而产生退化的掩码。我们在共享偏移模型中从理论上确立了这种坍缩。该分析促使我们提出平衡锚点提示适配（BAPA），它结合了两个互补模块。类别平衡锚点（CBA）模块分别从每个预测类别中选择高置信度锚点，并赋予前景和背景相等的总损失权重，防止较大区域主导更新。动态提示适配（DPA）在每次预测更新后刷新这些锚点，并且仅优化文本侧的提示残差，同时保持视觉-语言编码器冻结。这种仅提示的更新细化了前景-背景决策边界，而不改变预训练的密集视觉表示。在来自四个领域的实验中，BAPA在评估方法中取得了最高的平均Dice分数。分解消融进一步验证了CBA和DPA的互补作用，支持平衡提示适配作为熵最小化在测试时二值分割中的有效替代方案。
英文摘要
Entropy minimization is a standard objective for test-time adaptation (TTA), but it can fail in imbalanced binary segmentation. Unlike image classification, dense segmentation aggregates thousands of pixel predictions, allowing the larger predicted class to dominate the update, pull minority predictions toward itself, and produce a degenerate mask as predictions saturate and their entropy gradients vanish. We theoretically establish this collapse in a shared-shift model. This analysis motivates Balanced-Anchor Prompt Adaptation (BAPA), which combines two complementary modules. The Class-Balanced Anchors (CBA) module selects high-confidence anchors separately from each predicted class and gives foreground and background equal total loss weight, preventing the larger region from dominating the update. Dynamic Prompt Adaptation (DPA) refreshes these anchors after each prediction update and optimizes only text-side prompt residuals while keeping the vision-language encoders frozen. This prompt-only update refines the foreground-background decision boundary without altering the pretrained dense visual representation. Across experiments from four domains, BAPA achieves the highest mean Dice among the evaluated methods. Factorized ablations further validate the complementary roles of CBA and DPA, supporting balanced prompt adaptation as an effective alternative to entropy minimization for test-time binary segmentation.
