论文信息
论文标题：CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation
论文作者：Ankit Singh
论文来源：NeurIPS 2021
论文地址：download
论文代码：download
视屏讲解：click
1 简介
解决办法：
- 提出基于质心的对比学习框架；
- 提出基于类级的实例对比学习框架；
2 方法
2.1 整体框架
2.2 源域监督训练
$\mathcal{L}_{\text {sup }}=-\sum_{k=1}^{K}\left(y^{i}\right_{k} \log \left(\mathcal { F } \left(\mathcal{G}\left(\left(x_{l}^{i}\right\right_{k}\right.\right.$
2.3 域间对比对齐
$C_{k}^{s}=\frac{\sum_{i=1}^{i=B} \mathbb{1}_{\left\{y_{i}^{s}=k\right\}} \mathcal{F}\left(\mathcal{G}\left(x_{i}^{s}\right\right}{\sum_{i=1}^{i=B} \mathbb{1}_{\left\{y_{i}^{s}=k\right\}}}$
$C_{k}^{s}=\rho\left(C_{k}^{s}\right_{s t e p}+(1-\rho\left(C_{k}^{s}\right_{s t e p-1}$
$\hat{y_{i}^{t}}=\operatorname{argmax}\left(\left(\mathcal{F}\left(\mathcal{G}\left(x_{i}^{t}\right\right\right\right.$
$\mathcal{L}_{c l u}\left(C_{i}^{t}, C_{i}^{s}\right=-\log \frac{h\left(C_{i}^{t}, C_{i}^{s}\right}{h\left(C_{i}^{t}, C_{i}^{s}\right+\sum_{\substack{r=1 \\ q \in\{s, t\}}}^{K} \mathbb{1}_{\{r \neq i\}} h\left(C_{i}^{t}, C_{r}^{q}\right}$
$h(\mathbf{u}, \mathbf{v}=\exp \left(\frac{\mathbf{u}^{\top} \mathbf{v}}{\|\mathbf{u}\|_{2}\|\mathbf{v}\|_{2}} / \tau\right$
2.4 实例对比对齐
$\tilde{x}_{i}^{t}=\psi\left(x_{i}^{t}\right$
$\mathcal{L}_{i n s}\left(\tilde{x}_{i}^{t}, x_{i}^{t}\right=-\log \frac{h\left(\mathcal{F}\left(\mathcal{G}\left(\tilde{x}_{i}^{t}\right, \mathcal{F}\left(\mathcal{G}\left(x_{i}^{t}\right\right\right\right.}{\sum_{r=1}^{B} h\left(\mathcal{F}\left(\mathcal{G}\left(\tilde{x}_{i}^{t}\right\right, \mathcal{F}\left(\mathcal{G}\left(x_{r}^{t}\right\right\right+\sum_{r=1}^{B} \mathbb{1}_{\{r \neq i\}} h\left(\mathcal{F}\left(\mathcal{G}\left(\tilde{x}_{i}^{t}\right\right, \mathcal{F}\left(\mathcal{G}\left(\tilde{x}_{r}^{t}\right\right\right}$
2.5 训练目标
3 总结
略
编程笔记 » 迁移学习(CLDA)《CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation》