765 citations · 1.6k across the 39 of their papers we have counts for
9 papers · 1 filter
Hierarchical Semantic Tree Concept Whitening for Interpretable Image Classification
Haixing Dai, Lu Zhang, Lin Zhao +9
With the popularity of deep neural networks (DNNs), model interpretability is becoming a critical concern. Many approaches have been developed to tackle the problem through post-ho…
Review of Large Vision Models and Visual Prompt Engineering
Jiaqi Wang, Zhengliang Liu, Lin Zhao +18
Visual prompt engineering is a fundamental technology in the field of visual and image Artificial General Intelligence, serving as a key component for achieving zero-shot capabilit…
SAMAug: Point Prompt Augmentation for Segment Anything Model
Haixing Dai, Chong Ma, Zhiling Yan +14
This paper introduces SAMAug, a novel visual point augmentation method for the Segment Anything Model (SAM) that enhances interactive image segmentation performance. SAMAug generat…
SAM for Poultry Science
Xiao Yang, Haixing Dai, Zihao Wu +7
In recent years, the agricultural industry has witnessed significant advancements in artificial intelligence (AI), particularly with the development of large-scale foundational mod…
Instruction-ViT: Multi-Modal Prompts for Instruction Learning in ViT
Zhenxiang Xiao, Yuzhong Chen, Lu Zhang +14
Prompts have been proven to play a crucial role in large language models, and in recent years, vision models have also been using prompts to improve scalability for multiple downst…
Coupling Visual Semantics of Artificial Neural Networks and Human Brain Function via Synchronized Activations
Lin Zhao, Haixing Dai, Zihao Wu +8
Artificial neural networks (ANNs), originally inspired by biological neural networks (BNNs), have achieved remarkable successes in many tasks such as visual representation learning…
Eye-gaze-guided Vision Transformer for Rectifying Shortcut Learning
Chong Ma, Lin Zhao, Yuzhong Chen +15
Learning harmful shortcuts such as spurious correlations and biases prevents deep neural networks from learning the meaningful and useful representations, thus jeopardizing the gen…
Mask-guided Vision Transformer (MG-ViT) for Few-Shot Learning
Yuzhong Chen, Zhenxiang Xiao, Lin Zhao +10
Learning with little data is challenging but often inevitable in various application scenarios where the labeled data is limited and costly. Recently, few-shot learning (FSL) gaine…
Extracting 2D weak labels from volume labels using multiple instance learning in CT hemorrhage detection
Samuel W. Remedios, Zihao Wu, Camilo Bermudez +6
Multiple instance learning (MIL) is a supervised learning methodology that aims to allow models to learn instance class labels from bag class labels, where a bag is defined to cont…