用测试集自身结构提升音频零样本分类准确率，效果显著且计算极轻。
Transductive Zero-Shot Audio Classification with Audio-Language Models
- 利用测试集音频嵌入统计信息，通过无梯度迭代优化后验概率
- 在多个数据集上提升4.6至9.2个百分点，最高达96.2%准确率
- 适合资源受限场景，对长尾分布仍有正向收益
对比语言-音频预训练（CLAP）实现了零样本音频分类，但标准推理将每段音频独立处理，忽略了未标注测试集的结构。本文首次系统研究基于CLAP的类TransCLIP的归纳推理：一种文本锚定的球面高斯混合EM方法，利用测试批的音频嵌入统计信息，在无标签、无梯度、计算开销极小（2000个片段约15毫秒）的前提下优化零样本后验概率。在ESC-50、UrbanSound8K和VocalSound上，该方法一致提升顶1准确率4.6至9.2个百分点（如ESC-50从89.1%提升至94.8%，UrbanSound8K从73.8%提升至81.8%）。进一步发现：(i) 效果受简单判据约束——每类每批约需2.5个样本，超过5个后增益递减；(ii) 与熵引导提示加权互补，组合后在ESC-50上达96.2%；(iii) 在长尾分布下仍保持正收益（20:1不平衡时由+4.9降至+3.1点），此为明确局限。另报告一负面结果：在TUT Urban Acoustic Scenes 2018上，零样本CLAP接近随机，归纳推理无法放大信号。
原文摘要 · Abstract (English)
Contrastive language-audio pretraining (CLAP) enables zero-shot audio classification, but standard inference classifies each clip in isolation and ignores the structure of the unlabeled test set. We present the first systematic study of TransCLIP-style transductive inference for CLAP: a text-anchored spherical Gaussian-mixture EM that refines zero-shot posteriors using the audio-embedding statistics of the test batch, with no labels, no gradients, and negligible compute (about 15 ms on one CPU core for 2,000 clips). Across ESC-50, UrbanSound8K, and VocalSound, this consistently improves top-1 accuracy by +4.6 to +9.2 points over the zero-shot baseline (e.g., 89.1 -> 94.8% on ESC-50, 73.8 -> 81.8% on UrbanSound8K). We further show that the gain (i) is governed by a simple operating boundary -- roughly 2.5 test samples per class per batch are required, with diminishing returns beyond ~5; (ii) is complementary to entropy-guided prompt weighting, with the combination reaching 96.2% on ESC-50; and (iii) attenuates but remains positive under long-tailed batches (+4.9 -> +3.1 points at a 20:1 imbalance), which we report as an explicit limitation. We also document a negative result: on TUT Urban Acoustic Scenes 2018, where zero-shot CLAP is near chance, transduction has no signal to amplify.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。