Custom object detection dataset in Computer Vision - Model Pipeline Trace

Model Pipeline - Custom object detection dataset

This pipeline shows how a custom object detection dataset is prepared, used to train a model, and then how the model predicts objects in new images.

Data Flow - 5 Stages

1Raw dataset

1000 images x varying sizes→Collect images and bounding box annotations with labels→1000 images with bounding boxes and labels

Image1: cat at (50,30,150,130), dog at (200,100,300,250)

↓

2Preprocessing

1000 images with bounding boxes→Resize images to 224x224, normalize pixel values, adjust bounding boxes accordingly→1000 images 224x224 x 3 channels with normalized pixel values and updated bounding boxes

Image1 resized to 224x224, cat box now (20,12,60,52)

↓

3Data augmentation

1000 images 224x224 with bounding boxes→Apply random flips and color jitter, update bounding boxes for flips→1000 augmented images 224x224 with updated bounding boxes

Image1 flipped horizontally, cat box coordinates adjusted accordingly

↓

4Train/test split

1000 augmented images with bounding boxes→Split dataset into 800 training and 200 testing images→800 training images, 200 testing images with bounding boxes

Training set: 800 images, Testing set: 200 images

↓

5Model input preparation

800 training images 224x224 with bounding boxes→Convert bounding boxes and labels into model-specific tensor format→800 training samples with image tensors and target tensors

Sample: image tensor shape (3,224,224), target dict with boxes tensor shape (N,4), labels tensor shape (N)

Training Trace - Epoch by Epoch

Loss
2.5 |*****
2.0 |**** 
1.5 |***  
1.0 |**   
0.5 |*    
0.0 +-----
      1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	2.5	0.15	High loss and low accuracy as model starts learning
2	1.8	0.35	Loss decreases, accuracy improves as model learns object features
3	1.2	0.55	Model better detects objects, bounding box predictions improve
4	0.9	0.70	Loss continues to decrease, accuracy rises steadily
5	0.7	0.78	Model converging, good detection performance

Prediction Trace - 6 Layers

Layer 1: Input image preprocessing

Layer 2: Feature extraction (CNN layers)

Layer 3: Region proposal network

Layer 4: Bounding box regression and classification

Layer 5: Non-maximum suppression

Layer 6: Output prediction

Model Quiz - 3 Questions

What happens to the bounding boxes during image resizing in preprocessing?

A They are adjusted to match the new image size

B They remain the same as original image

C They are removed and recreated later

D They are converted to grayscale

Key Insight

This visualization shows how preparing a custom object detection dataset carefully and training a model step-by-step leads to improved detection accuracy and reliable bounding box predictions.