From 63bb67d77aaf5b291a405ad55e19ea2d19b60f6b Mon Sep 17 00:00:00 2001
From: lukas-heiligenbrunner <lukas.heiligenbrunner@gmail.com>
Date: Fri, 24 Mar 2023 14:17:21 +0100
Subject: [PATCH] finish presentation

---
 presentation/main.tex | 33 ++++++++++++++++++++-------------
 1 file changed, 20 insertions(+), 13 deletions(-)

diff --git a/presentation/main.tex b/presentation/main.tex
index 2a664e7..d2ab206 100644
--- a/presentation/main.tex
+++ b/presentation/main.tex
@@ -64,6 +64,7 @@
 %----------------------------------------------------------------------------------------
 % todo pic of action
 
+
     \section{The Goal}
     \begin{frame}{The goal}
         \begin{itemize}
@@ -105,7 +106,7 @@
             \begin{itemize}
                 \item YouTube
             \end{itemize}
-            \item using semi-supervised learning might be benefitial
+            \item Using semi-supervised learning might be benefitial
         \end{itemize}
     \end{frame}
 
@@ -143,11 +144,10 @@
             \item Pseudo-labeling
             \item Train model on labeled data
             \begin{itemize}
-                \item Eg. 1\% of data labeled
+                \item Eg. 1\%/10\% of data labeled
             \end{itemize}
-            \item Confidence of prediction
-            \item If high enough
-            \item Use to predict unlabeled data
+            \item Confidence of prediction [Threshold]
+            \item Use pseudo-labels to predict unlabeled data
         \end{itemize}
 
         \framebreak
@@ -174,11 +174,13 @@
             \begin{itemize}
                 \item lower capacity
                 \item better captures temporal dynamics in recognizing actions
+                \item scene changes/motion over time
             \end{itemize}
             \item Large model
             \begin{itemize}
                 \item better learns spatial semantics
                 \item to distinguish different action instances
+                \item localize/identify objects in specific scene
             \end{itemize}
         \end{itemize}
 
@@ -190,7 +192,7 @@
             \item Supplemented by lightweight auxiliary network
             \begin{itemize}
                 \item Different structure
-                \item Fewer channels
+                \item Fewer channels (smaller)
             \end{itemize}
             \item Different representation of data complements primary backbone
         \end{itemize}
@@ -201,6 +203,10 @@
     \end{frame}
 
     \begin{frame}{Performance Perspectives}
+        \begin{itemize}
+            \item 1\% labeled data + 400 Labels
+            \item Kinetics-400 dataset
+        \end{itemize}
         \includegraphics[scale=.205]{rsc/performance_comparison}
     \end{frame}
 
@@ -219,24 +225,24 @@
 
     \begin{frame}[allowframebreaks]{How existing method \textit{FixMatch} works}
         \begin{itemize}
-            \item $\mathbbm{1} \coloneqq \text{Indicator Function}$
             \item $B_u \coloneqq \text{Batchsize}$
-            \item $\mathcal{T} \coloneqq \text{Confidence Threshold}$
+            \item $\tau \coloneqq \text{Confidence Threshold (Hyperparameter)}$
             \item $F(\mathcal{T}_{\text{strong}}(u_i)) \coloneqq \text{Class distribution}$
             \item $p_i \coloneqq F(\mathcal{T}_{\text{weak}}(u_i))$
             \item $\hat{y}_i \coloneqq \arg \max(p_i) \coloneqq \text{Pseudo Label}$
             \item $\mathcal{H} \coloneqq \text{Cross-entropy loss}$
             \item $\mathcal{L}_u \coloneqq \text{Loss on the unlabeled data}$
-            \item $\mathcal{F} \coloneqq \text{Model}$
+            \item $F \coloneqq \text{Model}$
+            \item $\mathbbm{1} \coloneqq \text{Indicator Function}$
         \end{itemize}
         \begin{align*}
-            \mathcal{L}_u = \frac{1}{B_u} \sum_{i=1}^{B_u} \mathbbm{1}(\max(p_i) \geq \mathcal{T}) \mathcal{H}(\hat{y}_i,F(\mathcal{T}_{\text{strong}}(u_i)))
+            \mathcal{L}_u = \frac{1}{B_u} \sum_{i=1}^{B_u} \mathbbm{1}(\max(p_i) \geq \tau) \mathcal{H}(\hat{y}_i,F(\mathcal{T}_{\text{strong}}(u_i)))
         \end{align*}
 
         \framebreak
 
         \begin{itemize}
-            \item $\mathbbm{1}(\max(p_i) \geq \mathcal{T})$
+            \item $\mathbbm{1}(\max(p_i) \geq \tau)$
             \begin{itemize}
                 \item 'confidence-based masking'
                 \item retain label only if largest probability is above threshold
@@ -268,8 +274,8 @@
         \begin{itemize}
             \item Learning on unlabeled data
             \begin{align*}
-                \mathcal{L}_u^F &= \frac{1}{B_u} \sum_{i=1}^{B_u} \mathbbm{1}(\max(p_i^A) \geq \mathcal{T}) \mathcal{H}(\hat{y}_i^A,F(\mathcal{T}_{\text{strong}}(u_i)))\\
-                \mathcal{L}_u^A &= \frac{1}{B_u} \sum_{i=1}^{B_u} \mathbbm{1}(\max(p_i^F) \geq \mathcal{T}) \mathcal{H}(\hat{y}_i^F,A(\mathcal{T}_{\text{strong}}(u_i)))\\
+                \mathcal{L}_u^F &= \frac{1}{B_u} \sum_{i=1}^{B_u} \mathbbm{1}(\max(p_i^A) \geq \tau) \mathcal{H}(\hat{y}_i^A,F(\mathcal{T}_{\text{strong}}(u_i)))\\
+                \mathcal{L}_u^A &= \frac{1}{B_u} \sum_{i=1}^{B_u} \mathbbm{1}(\max(p_i^F) \geq \tau) \mathcal{H}(\hat{y}_i^F,A(\mathcal{T}_{\text{strong}}(u_i)))\\
             \end{align*}
             \item Complete training objective
             \begin{align*}
@@ -279,6 +285,7 @@
         \end{itemize}
     \end{frame}
 
+
     \section{Implementation}
 
     \begin{frame}{Networks}