Visual prompt engineering is a fundamental methodology in the field of visual and image
artificial general intelligence. As the development of large vision models progresses, the …

Fine-tuning visual models has been widely shown promising performance on many
downstream visual tasks. With the surprising development of pre-trained visual foundation …

Abstract Convolutional Neural Networks (CNNs) have achieved remarkable performance in
various computer vision tasks but this comes at the cost of tremendous computational …

Whole-body pose estimation localizes the human body, hand, face, and foot keypoints in an
image. This task is challenging due to multi-scale body parts, fine-grained localization for …

Abstract Segment Anything Model (SAM) has emerged as a powerful tool for numerous
vision applications. A key component that drives the impressive performance for zero-shot …

Human multimodal emotion recognition (MER) aims to perceive human emotions via
language, visual and acoustic modalities. Despite the impressive performance of previous …

Large Language Models (LLMs) have revolutionized natural language processing tasks with
remarkable success. However, their formidable size and computational demands present …

Abstract Knowledge Distillation (KD) aims at distilling the knowledge from the large teacher
model to a lightweight student model. Mainstream KD methods can be divided into two …

Most existing distillation methods ignore the flexible role of the temperature in the loss
function and fix it as a hyper-parameter that can be decided by an inefficient grid search. In …

Abstract Knowledge Distillation (KD) uses the teacher's prediction logits as soft labels to
guide the student, while self-KD does not need a real teacher to require the soft labels. This …