diff --git a/finetuning.tex b/finetuning.tex index 68ca9bd009a33d4ba442c3db0127785e3b87efd1..b2ea0de130fd4472ea7954784c8e17ff03336961 100644 --- a/finetuning.tex +++ b/finetuning.tex @@ -1,20 +1,26 @@ -\begin{minipage}[c]{0.55\textwidth} - \textbf{Setting:} +\vspace{0.45cm} +\begin{minipage}[c]{0.46\textwidth} + \textbf{Problem Formulation:} \begin{itemize} - \item classes appear sequentially (or in batches) % $c_1,c_2,\dots,c_T$ - \item each class $y$ has training images $X^y=\{x^y_1,\dots,x^y_{n_y}\}$ - \end{itemize} + \item Pretrained model $M$ for task $T: X \rightarrow Y$ + \item How to most efficiently fine-tune $M$ for new task $T': X' \rightarrow Y$ where $\mathcal{P}(X) \neq \mathcal{P}(X')$ + \item \textbf{Baseline:} Fine-tuning + \begin{itemize} + \item slow for large models + \item overfitting (small $X'$, many parameters) + \end{itemize} + \end{itemize} \end{minipage} -~ -\begin{minipage}[c]{0.4\textwidth} +% +\begin{minipage}[c]{0.49\textwidth} \begin{center} \newcommand{\pacsheight}{2.5cm} \textbf{Example (PACS~\blue{[1]} dataset and variants)} - \begin{minipage}[c]{0.14\textwidth} + \begin{minipage}[c]{0.16\textwidth} \centering \includegraphics[height=\pacsheight]{pacs_1.png} - \centering \scriptsize Photo - \end{minipage}~ + \centering \scriptsize \blue{Photo (base)} + \end{minipage}~~~ \begin{minipage}[c]{0.14\textwidth} \centering \includegraphics[height=\pacsheight]{pacs_2.png}