1. Abstract
- Goal of the Competition
- Document Type Classification
- Task : Image Classification
- Evaluation Metric : Macro F1
- Timeline
- Start Date : April 11, 2024
- Final submission deadline : April 23, 2024 (19:00)
- Description of the work
-
- Class : 17 types of documents
- Train : 1570
- Test : 3140
- Analysis on label distribution of train data
- Analysis on size/hue distribution of train and test data
- Analysis on augmentation techniques used in test data
- Train data : data cleansing, upsampling, offline augmentation with augraphy
- Test data : rectification
- Online augmentation with Albumentation in models
-
2. Process : Competition Model
- Integrated version : using ResNet 152 and EfficientNet b4 to classify 17 types
- Individual version : using EfficientNet b4
- step1 : 3-class classification of car/dashboard/documents
- step2 : classification of 15 types of documents
3. Process : Issues
- Impossible to find suitable rotation angles for every single test data
- Build codes to detect angles by lines or object contour
4. Role
- EDA
- Augmentation Analysis
- Preprocessing
- conception & implemenation for Test data
- Rectificaiton
- Denoising
- Test time augmentation
- conception & implemenation for Test data
- Model Train
- Presentation
5. Results
- Public Score / Private Score
- 0.9578 / 0.9441ㅇ
- Final standings of the Leaderboard
6. Conclusion
- 저번 대회에서 부족했다고 느꼈던 바가 있어 최대한 열심히 참여하려고 노력한 것이 도움이 된 것 같음
- 데이터 전처리를 위해 아이디어를 내고 구현해 적용하였고 모델 성능 향상에 기여해볼 수 있어 좋았음
- 모델링 관련(fine, hyper-parameter tuning 등)에 좀 더 신경을 쓰면 좋았을 듯함
'일별 학습일지' 카테고리의 다른 글
5/30 :: Fast-up report (0) | 2024.05.30 |
---|---|
4/12~4/13 :: Ideation (0) | 2024.04.14 |
4/11 :: CV data (0) | 2024.04.11 |
4/5 :: CV (0) | 2024.04.05 |
ML Competition : Fast-UP Report (0) | 2024.04.03 |