Continual testing time domain adaptive image classification method
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
目的持续测试时适应（continual test-time adaption， CTTA）旨在不使用任何源数据情况下，使源预训练模型适应持续变化的目标域。目前持续测试时适应主要依赖于自训练方法，在基于平均教师模型框架下将数据增强后样本的预测值作为伪标签，构建一致性损失函数实现模型的自训练。然而，现有方法中使用随机数据增强策略忽视了域间差异的重要性，导致模型稳定性和泛化性失衡等问题，使得在某些域间进行知识转移变得更具挑战性。为此，提出一种面向域间差异的持续测试时适应方法，聚焦于计算机视觉领域中的图像分类任务，探讨如何通过持续测试时适应技术提升模型对新域的适应能力。方法首先，提出一种基于域间差异的弹性数据增强策略。通过构建表示域间特征风格的Gram矩阵，计算相邻域间的差异，选取合适的弹性因子控制数据增强的强度，在数据预处理层面考虑域间差异性，使模型能更好地适应域复杂多变的情况。其次，提出一种全局弹性对称交叉熵损失函数。将基于域间差异计算取得的弹性因子应用于伪标签生成以及一致性损失函数的构建中，在模型优化层面考虑域间差异性，增强模型对不同域变化下的理解和适应能力。最后，提出一种基于置信度的伪标签自纠错策略。在弹性数据增强下，强数据增强通过对原始数据进行较大程度的变换来实现，模型在预测过程中可能面临预测偏差的问题，而弱数据增强涉及较小程度的变换，不会显著改变基本特征，模型对其预测的置信度较高。该策略利用高置信度的弱数据增强预测值对强数据增强的预测值进行自纠错，减少误差积累现象。结果在CIFAR10-C、CIFAR100-C和ImageNet-C 3个数据集上与多种先进算法进行比较，相较于基线方法CoTTA，错误率分别降低了约2.3%、2.7%和3.6%。在CIFAR10-C数据集中进行了消融实验，进一步验证了各个模块的有效性。为了符合更实际的域变化场景，在CIFAR100-C设计了域随机输入实验，结果显示本文方法在域随机输入的情况下错误率低于现有方法，对比基线平均错误率降低了3.9%，证明了本文方法可以有效地评估域间关系，并部署灵活策略以提升模型对持续变化目标域的适应能力。结论本文算法平衡了模型在持续测试时适应场景中的泛化性和稳定性，有效减少了误差积累现象。
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it