Introduction to Deep Learning · HIT

Mid-term   20% of the grade · around weeks 9 to 10 · CNN-based

Mid-term mini-project examples

The mid-term is a convolutional-network project on an image task: build it, train it, run a controlled ablation, and report the findings. Pick one of the examples below or propose another in the same spirit. Datasets are suggestions; any comparable small image dataset works.

Deliverables.

📋Ten examples

01Residual CNN on CIFAR-10

Data: CIFAR-10.

Goal: A strong image classifier.

Build: A small ResNet-style CNN with batch normalization and residual blocks.

Required study: Ablate batch normalization and residual connections; report accuracy and training curves for each variant.

Stretch goal: Add mixup or cutout augmentation and measure the gain.

02Depth and width study on FashionMNIST

Data: FashionMNIST.

Goal: Understand model capacity.

Build: A configurable CNN with adjustable depth and width.

Required study: Sweep depth and width; plot accuracy against parameter count and identify under- and over-fitting.

Stretch goal: Add dropout and weight decay and compare the curves.

03Small-data classifier with augmentation

Data: Oxford-IIIT Pets or Flowers-102 subset.

Goal: Classify with limited data.

Build: A CNN trained from scratch.

Required study: Data-augmentation ablation: none versus flips, crops, and color jitter.

Stretch goal: Compare against a tiny pretrained backbone (a preview of transfer learning).

04Imbalanced medical-style images

Data: A small chest X-ray (pneumonia) set, binary.

Goal: Classify under class imbalance.

Build: A CNN with an imbalance strategy (class weighting or resampling).

Required study: Report precision, recall, and F1 (not just accuracy) and show the effect of the imbalance fix.

Stretch goal: Add a class-activation (Grad-CAM-style) visualization.

05Traffic-sign recognition

Data: GTSRB subset.

Goal: Multiclass sign classifier.

Build: A CNN classifier.

Required study: Compare input normalization schemes and input image sizes.

Stretch goal: Test robustness to brightness and small rotations.

06CNN versus MLP

Data: CIFAR-10 or FashionMNIST.

Goal: Quantify the value of convolution.

Build: A CNN and a parameter-matched MLP.

Required study: Compare accuracy and the generalization gap; explain the difference via inductive bias.

Stretch goal: Visualize the first-layer filters of the CNN.

07Feature maps and receptive fields

Data: Any image dataset.

Goal: Interpret a trained CNN.

Build: A CNN, plus code to extract and visualize feature maps across layers.

Required study: Relate receptive-field growth to what each layer appears to detect.

Stretch goal: Add occlusion-sensitivity maps.

08Optimizer and learning-rate study

Data: CIFAR-10.

Goal: A rigorous optimization study.

Build: A single fixed CNN architecture.

Required study: Grid over {SGD, SGD+momentum, Adam} and three learning rates; report curves and final accuracy.

Stretch goal: Add a learning-rate schedule and measure the effect.

09Corruption robustness

Data: FashionMNIST or CIFAR-10 with synthetic corruptions.

Goal: Measure robustness.

Build: A CNN classifier.

Required study: Accuracy under noise, blur, and brightness shifts; test augmentation as a defense.

Stretch goal: Build a small CIFAR-10-C-style corruption benchmark.

10Depth and residual connections

Data: CIFAR-10.

Goal: See why residuals matter.

Build: A plain deep CNN and a residual CNN.

Required study: Increase depth (for example 8, 14, 20 layers) and compare trainability with and without residuals.

Stretch goal: Measure gradient norms by layer to explain the difference.

Final project examples Syllabus Course home