Cross-Modal Self-Training: Aligning Images and Pointclouds to Learn Classification without Labels.
Amaya DharmasiriMuzammal NaseerSalman KhanFahad Shahbaz KhanPublished in: CoRR (2024)
Keyphrases
- cross modal
- image classification
- image data
- training set
- class labels
- multi modal
- visual data
- object recognition
- image retrieval
- image features
- image database
- perceptual information
- visual similarity
- visual recognition
- image understanding
- feature extraction
- text classification
- feature vectors
- test images
- multi label
- feature space
- training data
- feature selection
- computer vision
- machine learning