## 1. General Competition Rules

### Entry Requirements
By entering this competition, you agree to adhere to all the competition rules. You must create and submit your own work in compliance with the phases and requirements detailed below. Participants will be judged based on reproducibility and the effectiveness of their approach.

### Team Size
- The maximum team size is two (2) members.

### Submission Limits
- Participants are allowed to submit up to twenty (20) submissions per day.

---

## 2. Phase-Specific Rules

### Phase 1 & Phase 2: Preprocessing Functions
- Participants must create a preprocessing function to be applied to input data (train, validation, and test sets).
- This function should address image enhancement and noise reduction, respectively, and **must** be applied before the data is fed into the model.
- You are **not** allowed to change the model architecture, number of epochs, or any other hyperparameters at this stage.

### Phase 3: Data Augmentation
- In this phase, the focus is on optimizing data augmentation techniques.
- You are allowed to modify augmentation-related hyperparameters to improve results.
- However, any changes outside augmentation (e.g., model architecture) are prohibited.

### Phase 4: Label Error Detection
- Participants must implement an algorithmic approach to detect and correct label errors in the training data.
- The approach must be **reproducible** and demonstrate improvements in model performance without manually altering the dataset.
  
### Important Considerations
- Manual corrections to the data are not allowed. All improvements must come from reproducible methods applied programmatically.
- The solutions must be robust, well-documented, and ensure that the steps taken are easy to replicate.

---

## 3. Reproducibility
- Participants must submit clear documentation and code so that the preprocessing, augmentation, and label correction techniques can be replicated.
  
Failure to adhere to these rules may result in disqualification.