为验证-free少样本CLIP适配器设计的Hold-One-Shot-Out (HOSO)
Hold-One-Shot-Out (HOSO) for Validation-Free Few-Shot CLIP Adapters
AI总结：
HOSO-Adapter通过无需验证的少样本设置，提升CLIP适配器性能，平均高出4个百分点
摘要：
在许多CLIP适应方法中，一个混合比率超参数控制预训练CLIP知识与有限的、数据集特定的监督之间的平衡。大多数少样本CLIP适应技术通过在测试集上对混合比率进行消融实验或需要额外的验证集来选择每个数据集的混合比率，因此不是严格意义上的少样本。我们提出了一种简单、无需验证的方法来学习CLIP适应中的混合比率。Hold-One-Shot-Out (HOSO)为CLIP-Adapter式方法提供了一种新的方法，以在新建立的无需验证的环境下竞争。CLIP-Adapter与HOSO (HOSO-Adapter)使用一个样本的保留集来学习混合比率，而适配器则在剩余的少样本支持示例上进行训练。在无需验证的少样本协议下，HOSO-Adapter在11个标准少样本数据集上平均比CLIP-Adapter基准高出超过4个百分点。有趣的是，在8-和16-样本设置中，即使在测试集上选择了最优的混合比率，HOSO-Adapter仍优于CLIP-Adapter。消融研究验证了使用单次保留机制、解耦训练以及对简单学习混合比率基准的改进。代码已在此发布：https://github.com/chris-vorster/HOSO-Adapter
英文摘要：
In many CLIP adaptation methods, a blending ratio hyperparameter controls the trade-off between general pretrained CLIP knowledge and the limited, dataset-specific supervision from the few-shot cases. Most few-shot CLIP adaptation techniques report results by ablation of the blending ratio on the test set or require additional validation sets to select the blending ratio per dataset, and thus are not strictly few-shot. We present a simple, validation-free method for learning the blending ratio in CLIP adaptation. Hold-One-Shot-Out (HOSO) presents a novel approach for CLIP-Adapter-style methods to compete in the newly established validation-free setting. CLIP-Adapter with HOSO (HOSO-Adapter) learns the blending ratio using a one-shot, hold-out set, while the adapter trains on the remaining few-shot support examples. Under the validation-free few-shot protocol, HOSO-Adapter outperforms the CLIP-Adapter baseline by more than 4 percentage points on average across 11 standard few-shot datasets. Interestingly, in the 8- and 16-shot settings, HOSO-Adapter outperforms CLIP-Adapter even with the optimal blending ratio selected on the test set. Ablation studies validate the use of a one-shot hold-out mechanism, decoupled training, and improvements over the naively learnt blending ratio baseline. Code is released here: https://github.com/chris-vorster/HOSO-Adapter
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
