diff --git a/src/year2/machine-learning-for-computer-vision/sections/_object_detection.tex b/src/year2/machine-learning-for-computer-vision/sections/_object_detection.tex
index 12a0448..0375cd8 100644
--- a/src/year2/machine-learning-for-computer-vision/sections/_object_detection.tex
+++ b/src/year2/machine-learning-for-computer-vision/sections/_object_detection.tex
@@ -84,7 +84,7 @@
 
             \indenttbox
             \begin{remark}
-                Recall is monotonically decreasing, while precision can both decrease and increase.
+                Recall is monotonically increasing, while precision can both decrease and increase.
             \end{remark}
         \end{example}
 
diff --git a/src/year2/machine-learning-for-computer-vision/sections/_segmentation.tex b/src/year2/machine-learning-for-computer-vision/sections/_segmentation.tex
index 889d853..5cfc915 100644
--- a/src/year2/machine-learning-for-computer-vision/sections/_segmentation.tex
+++ b/src/year2/machine-learning-for-computer-vision/sections/_segmentation.tex
@@ -53,7 +53,7 @@
         \end{figure}
 
     \item[Depth comparison features] \marginnote{Depth comparison features}
-        Given a depth image $D$ and the offsets $\theta = (\Delta p, \Delta n)$, each pixel $x$ of $D$ produces a feature as follows:
+        Given a depth image $D$ and the offsets $\theta = (\Delta p, \Delta n)$, each pixel $x$ of $D$ produces a set features of form:
         \[ f(x; D, (\Delta p, \Delta n)) = D\left[ x + \frac{\Delta p}{D[x]} \right] - D\left[ x + \frac{\Delta n}{D[x]} \right] \]
         In other words, each $x$ is described by the difference in depth between two points offset from $x$. The depth at background pixels is a large positive number.