Abstract: Few-shot Class Incremental Learning (FSCIL) presents a challenging yet realistic scenario, which requires the model to continually learn new classes with limited labeled data (i.e., ...
Pre-trained multi-modal Vision-Language Models like CLIP are widely used off-the-shelf for various applications. Our code currently supports 27 datasets for the tasks of image-to-image retrieval, text ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results