Related papers: Exploring and Distilling Posterior and Prior Knowl…

Despite the outstanding success of self-supervised pretraining methods for video representation learning, they generalise poorly when the unlabeled dataset for pretraining is small or the domain difference between unlabelled data in source…

Structured radiology reporting promises faster, more consistent communication than free text, but automation remains difficult as models must make many fine-grained, discrete decisions about rare findings and attributes from limited…

Over the last few decades, artificial intelligence research has made tremendous strides, but it still heavily relies on fixed datasets in stationary environments. Continual learning is a growing field of research that examines how AI…

Online Action Detection (OAD) in videos is proposed as a per-frame labeling task to address the real-time prediction tasks that can only obtain the previous and current video frames. This paper presents a novel learning-with-privileged…

Deep neural networks often have a huge number of parameters, which posts challenges in deployment in application scenarios with limited memory and computation capacity. Knowledge distillation is one approach to derive compact models from…

Recently, large-scale pre-trained models have shown their advantages in many tasks. However, due to the huge computational complexity and storage requirements, it is challenging to apply the large-scale model to real scenes. A common…

Medical images are widely used in clinical practice for diagnosis. Automatically generating interpretable medical reports can reduce radiologists' burden and facilitate timely care. However, most existing approaches to automatic report…

Recently, knowledge editing (KE) has emerged as a promising approach to update specific facts in Large Language Models (LLMs) without the need for full retraining. Despite the effectiveness in general-domain benchmarks, their applicability…

In this work, we propose Mutual Information Maximization Knowledge Distillation (MIMKD). Our method uses a contrastive objective to simultaneously estimate and maximize a lower bound on the mutual information of local and global feature…

Data-free knowledge distillation (DFKD) has emerged as a pivotal technique in the domain of model compression, substantially reducing the dependency on the original training data. Nonetheless, conventional DFKD methods that employ…

Data-Free Knowledge Distillation (DFKD) is an advanced technique that enables knowledge transfer from a teacher model to a student model without relying on original training data. While DFKD methods have achieved success on smaller datasets…

This work explores knowledge distillation (KD) for visually-rich document (VRD) applications such as document layout analysis (DLA) and document image classification (DIC). While VRD research is dependent on increasingly sophisticated and…

Large-scale pre-training has been proven to be crucial for various computer vision tasks. However, with the increase of pre-training data amount, model architecture amount, and the private/inaccessible data, it is not very efficient or…

In this paper, we consider enhancing medical visual-language pre-training (VLP) with domain-specific knowledge, by exploiting the paired image-text reports from the radiological daily practice. In particular, we make the following…

Dynamically integrating new or rapidly evolving information after (Large) Language Model pre-training remains challenging, particularly in low-data scenarios or when dealing with private and specialized documents. In-context learning and…

Human pose estimation using deep neural networks aims to map input images with large variations into multiple body keypoints which must satisfy a set of geometric constraints and inter-dependency imposed by the human body model. This is a…

Large language models (LLMs) have demonstrated remarkable capabilities, but they also pose risks related to the generation of toxic or harmful content. This work introduces Precision Knowledge Editing (PKE), an advanced technique that…

Chest X-ray (CXR) anatomical abnormality detection aims at localizing and characterising cardiopulmonary radiological findings in the radiographs, which can expedite clinical workflow and reduce observational oversights. Most existing…

Distilling demonstration effects into hidden-space interventions offers a lightweight alternative to full finetuning. However, existing multimodal variants are mostly evaluated on short-form tasks, where outputs end after a few tokens.…

Since visual perception can give rich information beyond text descriptions for world understanding, there has been increasing interest in leveraging visual grounding for language learning. Recently, vokenization (Tan and Bansal, 2020) has…