Related papers: Weakly Supervised Concept Learning with Class-Leve…

Weakly supervised nuclei segmentation is a critical problem for pathological image analysis and greatly benefits the community due to the significant reduction of labeling cost. Adopting point annotations, previous methods mostly rely on…

Learning concepts that are consistent with human perception is important for Deep Neural Networks to win end-user trust. Post-hoc interpretation methods lack transparency in the feature representations learned by the models. This work…

Prompt learning has emerged as a promising paradigm for adapting pre-trained vision-language models (VLMs) to few-shot whole slide image (WSI) classification by aligning visual features with textual representations, thereby reducing…

Classification of pathological images is the basis for automatic cancer diagnosis. Despite that deep learning methods have achieved remarkable performance, they heavily rely on labeled data, demanding extensive human annotation efforts. In…

We propose Next Concept Prediction (NCP), a generative pretraining paradigm built on top of Next Token Prediction (NTP). NCP predicts discrete concepts that span multiple tokens, thereby forming a more challenging pretraining objective. Our…

Surface defect detection plays a critical role in industrial quality inspection. Recent advances in artificial intelligence have significantly enhanced the automation level of detection processes. However, conventional semantic segmentation…

Polyp segmentation is a crucial step towards computer-aided diagnosis of colorectal cancer. However, most of the polyp segmentation methods require pixel-wise annotated datasets. Annotated datasets are tedious and time-consuming to produce,…

Medical Vision Language Pretraining (VLP) has recently emerged as a promising solution to the scarcity of labeled data in the medical domain. By leveraging paired/unpaired vision and text datasets through self-supervised learning, models…

Weak supervision learning on classification labels has demonstrated high performance in various tasks, while a few pixel-level fine annotations are also affordable. Naturally a question comes to us that whether the combination of…

Despite the remarkable success of the end-to-end paradigm in deep learning, it often suffers from slow convergence and heavy reliance on large-scale datasets, which fundamentally limits its efficiency and applicability in data-scarce…

Weakly Supervised Semantic Segmentation (WSSS), which leverages image-level labels, has garnered significant attention due to its cost-effectiveness. The previous methods mainly strengthen the inter-class differences to avoid class semantic…

Biomedical word sense disambiguation (WSD) is an important intermediate task in many natural language processing applications such as named entity recognition, syntactic parsing, and relation extraction. In this paper, we employ…

The concept bottleneck model (CBM), as a technique improving interpretability via linking predictions to human-understandable concepts, makes high-risk and life-critical medical image classification credible. Typically, existing CBM methods…

Humans use abstract concepts for understanding instead of hard features. Recent interpretability research has focused on human-centered concept explanations of neural networks. Concept Activation Vectors (CAVs) estimate a model's…

Aligning large-scale commercial models with user intent is crucial to preventing harmful outputs. Current methods rely on human supervision but become impractical as model complexity increases. When models surpass human knowledge, providing…

The multimodal deep neural networks, represented by CLIP, have generated rich downstream applications owing to their excellent performance, thus making understanding the decision-making process of CLIP an essential research topic. Due to…

Healthcare fraud detection remains a critical challenge due to limited availability of labeled data, constantly evolving fraud tactics, and the high dimensionality of medical records. Traditional supervised methods are challenged by extreme…

Several studies have recently pointed that existing Visual Question Answering (VQA) models heavily suffer from the language prior problem, which refers to capturing superficial statistical correlations between the question type and the…

Weakly-supervised learning approaches have gained significant attention due to their ability to reduce the effort required for human annotations in training neural networks. This paper investigates a framework for weakly-supervised object…

Few-shot, fine-grained classification in computer vision poses significant challenges due to the need to differentiate subtle class distinctions with limited data. This paper presents a novel method that enhances the Contrastive…