Object detection concepts in TensorFlow - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Understanding bounding box coordinates

In object detection, bounding boxes are used to locate objects in an image. Which of the following correctly describes the format of bounding box coordinates in TensorFlow's Object Detection API?

A Coordinates are given as [xmin, ymin, width, height] in absolute pixel values.

B Coordinates are given as [center_x, center_y, width, height], normalized between 0 and 1.

C Coordinates are given as [ymin, xmin, ymax, xmax], normalized between 0 and 1 relative to image size.

D Coordinates are given as [x1, y1, x2, y2] in absolute pixel values.

💡 Hint

Think about how TensorFlow normalizes bounding box coordinates for easier processing.

TensorFlow's Object Detection API uses normalized coordinates in the order [ymin, xmin, ymax, xmax], where values range from 0 to 1 relative to the image dimensions.

❓ Model Choice

intermediate

Choosing an object detection model for real-time use

You want to deploy an object detection model on a mobile device that requires fast inference with limited computing power. Which TensorFlow model is the best choice?

A Mask R-CNN with ResNet-50 backbone

B Faster R-CNN with ResNet-101 backbone

C YOLOv3 with Darknet-53 backbone

D SSD MobileNet V2

💡 Hint

Look for a model optimized for speed and low resource use.

SSD MobileNet V2 is designed for fast inference on devices with limited resources, making it suitable for mobile deployment.

❓ Metrics

advanced

Interpreting mean Average Precision (mAP) in object detection

After training an object detection model, you evaluate it and get a mean Average Precision (mAP) of 0.75 at IoU threshold 0.5. What does this value mean?

A On average, the model correctly detects 75% of objects with at least 50% overlap between predicted and true boxes.

B The model's predictions overlap with ground truth boxes by exactly 75% at IoU 0.5.

C The model has 75% accuracy in classifying object categories regardless of location.

D The model detects 75% of objects but with no consideration of bounding box overlap.

💡 Hint

Recall that mAP combines precision and recall considering overlap thresholds.

mAP at IoU 0.5 means the average precision of detections that have at least 50% overlap with ground truth boxes is 75%, reflecting both detection and localization quality.

🔧 Debug

advanced

Identifying the cause of low detection accuracy

You trained an object detection model but it shows very low accuracy on the test set. Which of the following is the most likely cause?

A The training dataset has very few labeled examples and lacks diversity.

B The model uses a pretrained backbone network.

C The batch size during training was set to 32.

D The learning rate was set to a small value like 0.0001.

💡 Hint

Think about data quality and quantity impact on model performance.

A small and non-diverse training dataset limits the model's ability to learn object features well, causing low accuracy.

❓ Hyperparameter

expert

Effect of Non-Maximum Suppression (NMS) threshold on detection results

In object detection post-processing, Non-Maximum Suppression (NMS) removes overlapping boxes. What happens if you set the NMS IoU threshold too high (e.g., 0.9)?

A Most boxes are removed, possibly missing true objects.

B Many overlapping boxes remain, causing duplicate detections of the same object.

C The model training becomes unstable and loss increases.

D The model detects only large objects and ignores small ones.

💡 Hint

Consider how NMS threshold controls overlap allowed between boxes.

A high NMS threshold means boxes with high overlap are not suppressed, leading to multiple detections for 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