Quantitative evaluation of tissue images is crucial for computational pathology (CPath) tasks,
requiring the objective characterization of histopathological entities from whole-slide images …

In this paper, we question if self-supervised learning provides new properties to Vision
Transformer (ViT) that stand out compared to convolutional networks (convnets). Beyond the …

Dropout is a powerful and widely used technique to regularize the training of deep neural
networks. Though effective and performing well, the randomness introduced by dropout …

Abstract Current Knowledge Distillation (KD) methods for semantic segmentation often
guide the student to mimic the teacher's structured information generated from individual …

Recent breakthroughs in self-supervised learning show that such algorithms learn visual
representations that can be transferred better to unseen tasks than cross-entropy based …

Large vision-language models have achieved outstanding performance, but their size and
computational requirements make their deployment on resource-constrained devices and …

Benefiting from masked visual modeling, self-supervised video representation learning has
achieved remarkable progress. However, existing methods focus on learning …

Online continual learning (CL) studies the problem of learning continuously from a single-
pass data stream while adapting to new data and mitigating catastrophic forgetting …

Large-scale vision-language pre-training has achieved promising results on downstream
tasks. Existing methods highly rely on the assumption that the image-text pairs crawled from …

Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved
great success in learning visual representations without data annotations. However, most of …