Category-wise Fine-Tuning: Resisting Incorrect Pseudo-Labels in Multi-Label Image Classification with Partial Labels.
Chak Fong ChongXinyi FangJielong GuoYapeng WangWei KeChan-Tong LamSio Kei ImPublished in: CoRR (2024)
Keyphrases
- multi label
- image classification
- fine tuning
- multi label classification
- multiple labels
- label space
- multi label learning
- text categorization
- image annotation
- graph cuts
- binary classification
- multi instance
- class labels
- visual features
- bag of words
- image features
- single label classification
- image representation
- protein function prediction
- automatic image annotation
- max margin
- visual words
- svm classifier
- feature extraction
- object categories
- hierarchical text categorization
- data sets
- object recognition
- training data
- classifier training
- image processing
- label assignment
- neural network