Random erasing in Computer Vision - Model Pipeline Trace

Model Pipeline - Random erasing

This pipeline shows how random erasing helps a computer vision model learn better by randomly hiding parts of images during training. This makes the model stronger and less likely to get confused by small changes.

Data Flow - 4 Stages

1Input images

1000 images x 3 channels x 32 height x 32 width→Original images loaded for training→1000 images x 3 channels x 32 height x 32 width

Image of a cat with clear details

↓

2Random erasing augmentation

1000 images x 3 channels x 32 height x 32 width→Randomly erase a small rectangle area in each image by replacing pixels with random values→1000 images x 3 channels x 32 height x 32 width

Same cat image but with a small random patch erased (covered with noise)

↓

3Feature extraction

1000 images x 3 channels x 32 height x 32 width→Convolutional layers extract important features from images→1000 images x 64 feature maps x 8 height x 8 width

Feature maps highlighting edges and textures

↓

4Classification layer

1000 images x 64 feature maps x 8 height x 8 width→Fully connected layer predicts image class→1000 images x 10 classes

Predicted probabilities for 10 classes like cat, dog, car

Training Trace - Epoch by Epoch

Epochs
1 |***************...............| Loss=1.8
3 |********************..........| Loss=1.2
5 |************************......| Loss=0.9
7 |****************************..| Loss=0.7
10|*******************************| Loss=0.5

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.8	0.35	Model starts learning, loss high, accuracy low
3	1.2	0.55	Loss decreases, accuracy improves as model learns features
5	0.9	0.68	Random erasing helps model generalize, accuracy rises
7	0.7	0.75	Loss continues to drop, model becomes more confident
10	0.5	0.82	Training converges with good accuracy and low loss

Prediction Trace - 4 Layers

Layer 1: Input image

Layer 2: Random erasing (only during training, skipped here)

Layer 3: Feature extraction

Layer 4: Classification layer

Model Quiz - 3 Questions

What is the main purpose of random erasing in this pipeline?

A To increase image resolution

B To hide parts of images during training to improve model robustness

C To convert images to grayscale

D To speed up training by reducing image size

Key Insight

Random erasing helps the model learn to recognize objects even when parts are missing or hidden. This makes the model more flexible and better at handling real-world images that might have noise or occlusions.