3 accepted papers
Knowledge distillation based on large vision-language models (VLMs) has recently emerged as a significant solution to transfer knowledge from the source domain to the target domain in unsupervised domain adaptation (UDA) tasks. However, existing methods employ a two-stage training pipeline, which no
Transformers trained with self-supervision using self-distillation loss (DINO) have been shown to produce attention maps that highlight salient foreground objects. In this paper, we show a graph-based method that uses the self-supervised transformer features to discover an object from an image. Visu…
For the multi-label image retrieval, the existing hashing algorithms neglect the dependency between objects and thus fail to capture the attention information in the feature extraction, which affects the precision of hash codes. To address this problem, we explore the inter-dependency between object…