# Data-Centric AI: Noisy PASCAL VOC Challenge — Data

来源：https://www.kaggle.com/competitions/data-centric-noisy-pascal-challenge/data

采集时间：2026-10-19T08:20:41Z

### Data

This competition uses a noisy version of the **PASCAL VOC 2007 dataset**, where the training data has been corrupted in phases to simulate real-world challenges. Your task is to improve data quality and object detection performance without any changes to the model.

#### Files

- **`voc2007/images/train/`**: Contains training images in `.jpg` format.
- **`voc2007/labels/train/`**: Corresponding YOLOv5 format `.txt` files with annotations for each image.
- **`voc2007/images/test/`**: Test images without labels.

#### YOLOv5 Label Format

Each `.txt` file contains:

```
class_id x_center y_center width height
```
- **class_id**: Object class ID.
- **x_center, y_center**: Bounding box center coordinates (normalized).
- **width, height**: Bounding box size (normalized).

Example:

```
6 0.485 0.533 0.122 0.250
14 0.719 0.442 0.098 0.143
```

#### Prediction Task

You will predict bounding boxes and object classes for test images.