# AIBT Hackathon 2025 Image Retrieval — Data

来源：https://www.kaggle.com/competitions/aibt-hackathon-2025-image-retrieval-public/data

采集时间：2026-10-19T06:36:53Z

## Description  
Time-series patches are provided for training. The goal is to determine which series a future patch belongs to. Test queries are transformed (rotation, erasure, etc.), so your model must be invariant to these augmentations and rethink the problem beyond standard classification.

## Data  
- **Time-series database**  
  5 000 sequences of 8 Sentinel-2 patches (224 × 224 × 3 PNG)  
- **Test patches**  
  4 per sequence, each transformed (rotation, flip, contrast jitter, occlusion)

## Submission  
- **File**: `sample_submission.csv`  
- **Columns**:  
  | Column    | Description                                                                |
  |-----------|----------------------------------------------------------------------------|
  | file_name | Query patch filename                                                       |
  | label     | Space-separated list of **20** time-series IDs (ranked most → least likely)|

_Example_:

```csv
file_name,label
000123.png,45 12 67 … 89
```