Object detection concepts in TensorFlow - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is object detection in machine learning?

Object detection is a task where a model finds and labels objects in an image or video. It tells what objects are there and where they are located by drawing boxes around them.

beginner

What are bounding boxes in object detection?

Bounding boxes are rectangles drawn around objects in an image. They show the position and size of each detected object.

beginner

What is the role of confidence score in object detection?

The confidence score tells how sure the model is that an object is correctly detected. A higher score means more confidence.

beginner

Explain the difference between classification and object detection.

Classification tells what object is in an image (like cat or dog). Object detection also tells where the object is by drawing boxes around it.

intermediate

What is Non-Maximum Suppression (NMS) in object detection?

NMS is a method to remove extra overlapping boxes for the same object. It keeps the box with the highest confidence and removes others to avoid duplicates.

What does an object detection model output for each detected object?

A Only a label

B A confidence score only

C Only a bounding box

D A label and a bounding box

Object detection models output both the label (what the object is) and the bounding box (where it is).

Which of these is NOT a common use of object detection?

A Finding objects in videos

B Translating text from images

C Counting objects in images

D Detecting faces in photos

Translating text is a task for OCR and language models, not object detection.

What does Non-Maximum Suppression help with?

A Improving image quality

B Increasing the number of detected objects

C Removing duplicate overlapping boxes

D Labeling objects with names

NMS removes duplicate boxes that overlap too much, keeping only the best one.

What does a high confidence score mean in object detection?

A The model is confident the object is correctly detected

B The object is very small

C The model is unsure about the object

D The object is not detected

A high confidence score means the model is sure about the detection.

Which TensorFlow API is commonly used for object detection?

A TensorFlow Object Detection API

B TensorFlow Datasets

C TensorFlow Lite

D TensorFlow Hub

TensorFlow Object Detection API provides tools and models specifically for object detection tasks.

Describe the main steps an object detection model performs when analyzing an image.

Think about what the model finds and how it shows it.

Explain why Non-Maximum Suppression is important in object detection results.

Consider what happens when multiple boxes cover the same object.

Practice

1. What is the main goal of object detection in TensorFlow?

easy

A. To find and label objects in images with bounding boxes

B. To generate captions for images

C. To classify images into categories without localization

D. To enhance image resolution

Solution

1. Step 1: Understand object detection task

   Object detection locates objects in images and labels them with boxes.

2. Step 2: Compare options with definition

   Only To find and label objects in images with bounding boxes describes finding and labeling objects with boxes, matching object detection.

3. Final Answer:

   To find and label objects in images with bounding boxes -> Option A

4. Quick Check:

   Object detection = find and label objects [OK]

Hint: Object detection = find + label objects with boxes [OK]

Common Mistakes:

• Confusing object detection with image classification
• Thinking object detection generates captions
• Mixing up image enhancement with detection

2. Which part of an object detection model is responsible for extracting features from images?

easy

A. Head

B. Backbone

C. Loss function

D. Anchor generator

Solution

1. Step 1: Identify model components

   Backbone extracts features; head predicts boxes and classes.

2. Step 2: Match roles to options

   Backbone matches feature extraction role, so Backbone is correct.

3. Final Answer:

   Backbone -> Option B

4. Quick Check:

   Feature extractor = Backbone [OK]

Hint: Backbone extracts features, head predicts boxes [OK]

Common Mistakes:

• Confusing head with feature extractor
• Thinking loss function extracts features
• Mixing anchor generator with backbone

3. Given this TensorFlow code snippet for object detection model summary, what is the output shape of the backbone's last layer?

import tensorflow as tf
base_model = tf.keras.applications.MobileNetV2(input_shape=(224,224,3), include_top=False)
print(base_model.output_shape)

medium

A. (None, 7, 7, 1280)

B. (None, 14, 14, 512)

C. (None, 224, 224, 3)

D. (None, 1, 1, 1000)

Solution

1. Step 1: Understand MobileNetV2 output shape

   MobileNetV2 with include_top=False outputs feature maps of shape (None, 7, 7, 1280) for 224x224 input.

2. Step 2: Match output shape to options

   (None, 7, 7, 1280) matches expected output shape; others do not.

3. Final Answer:

   (None, 7, 7, 1280) -> Option A

4. Quick Check:

   MobileNetV2 backbone output = (None,7,7,1280) [OK]

Hint: MobileNetV2 backbone outputs 7x7x1280 feature maps [OK]

Common Mistakes:

• Confusing input shape with output shape
• Choosing output with wrong spatial dimensions
• Assuming include_top=True output shape

4. Identify the error in this TensorFlow object detection training code snippet:

model.compile(optimizer='adam', loss='categorical_crossentropy')
model.fit(train_images, train_boxes, epochs=5)

medium

A. fit method missing batch_size argument

B. Missing optimizer parameter in compile

C. Using 'categorical_crossentropy' loss instead of a detection loss

D. train_boxes should be train_labels

Solution

1. Step 1: Check loss function suitability

   Object detection needs specialized loss (e.g., localization + classification), not plain categorical_crossentropy.

2. Step 2: Validate other code parts

   Optimizer is given, train_boxes is correct for boxes, batch_size is optional.

3. Final Answer:

   Using 'categorical_crossentropy' loss instead of a detection loss -> Option C

4. Quick Check:

   Detection needs special loss, not categorical_crossentropy [OK]

Hint: Detection needs combined loss, not plain classification loss [OK]

Common Mistakes:

• Using classification loss for detection
• Confusing train_boxes with labels
• Assuming batch_size is mandatory

5. You want to improve an object detection model's accuracy on small objects. Which approach is best to try first?

hard

A. Remove the backbone and use only the head

B. Reduce number of training epochs

C. Use grayscale images instead of color

D. Increase input image resolution and adjust anchor box sizes

Solution

1. Step 1: Understand small object detection challenges

   Small objects need higher resolution and anchors matching their size for better detection.

2. Step 2: Evaluate options for improving small object accuracy

   Increasing resolution and adjusting anchors directly helps; reducing epochs or removing backbone harms performance; grayscale reduces info.

3. Final Answer:

   Increase input image resolution and adjust anchor box sizes -> Option D

4. Quick Check:

   Small objects = higher res + proper anchors [OK]

Hint: Small objects need bigger input and matching anchors [OK]

Common Mistakes:

• Reducing epochs thinking it helps accuracy
• Removing backbone reduces feature quality
• Using grayscale loses color info needed for detection