相关论文: This Looks Better than That: Better Interpretable …

Recently vision transformer models have become prominent models for a range of tasks. These models, however, usually suffer from intensive computational costs and heavy memory requirements, making them impractical for deployment on edge…

The current modus operandi in adapting pre-trained models involves updating all the backbone parameters, ie, full fine-tuning. This paper introduces Visual Prompt Tuning (VPT) as an efficient and effective alternative to full fine-tuning…

Large Language Models (LLMs) have significantly advanced the field of Natural Language Processing (NLP), but their lack of interpretability has been a major concern. Current methods for interpreting LLMs are post hoc, applied after…

Models based on human-understandable concepts have received extensive attention to improve model interpretability for trustworthy artificial intelligence in the field of medical image analysis. These methods can provide convincing…

Despite recent advances in machine learning and explainable AI, a gap remains in personalized preventive healthcare: predictions, interventions, and recommendations should be both understandable and verifiable for all stakeholders in the…

Complex black-box predictive models may have high performance, but lack of interpretability causes problems like lack of trust, lack of stability, sensitivity to concept drift. On the other hand, achieving satisfactory accuracy of…

Over the last century, deep learning models have become the state-of-the-art for solving complex computer vision problems. These modern computer vision models have millions of parameters, which presents two major challenges: (1) the…

Artificial neural networks have proven to be extremely useful models that have allowed for multiple recent breakthroughs in the field of Artificial Intelligence and many others. However, they are typically regarded as black boxes, given how…

Concept bottleneck models (CBM) aim to produce inherently interpretable models that rely on human-understandable concepts for their predictions. However, existing approaches to design interpretable generative models based on CBMs are not…

Human perception is routinely assessing the similarity between images, both for decision making and creative thinking. But the underlying cognitive process is not really well understood yet, hence difficult to be mimicked by computer vision…

Large-scale pre-trained transformers have demonstrated remarkable success in various computer vision tasks. However, it is still highly challenging to fully fine-tune these models for downstream tasks due to their high computational and…

Large language models (LLMs) have demonstrated impressive performance on natural language tasks, but their decision-making processes remain largely opaque. Existing explanation methods either suffer from limited faithfulness to the model's…

Deep neural networks (DNNs) have become a widely deployed model for numerous machine learning applications. However, their fixed architecture, substantial training cost, and significant model redundancy make it difficult to efficiently…

Black-box deep neural networks excel in text classification, yet their application in high-stakes domains is hindered by their lack of interpretability. To address this, we propose Text Bottleneck Models (TBM), an intrinsically…

Clinicians are often very sceptical about applying automatic image processing approaches, especially deep learning based methods, in practice. One main reason for this is the black-box nature of these approaches and the inherent problem of…

This paper presents a parameter-efficient prompt tuning method, named PPT, to adapt a large multi-modal model for 3D point cloud understanding. Existing strategies are quite expensive in computation and storage, and depend on time-consuming…

Pretrained transformer-based Language Models (LMs) are well-known for their ability to achieve significant improvement on NLP tasks, but their black-box nature, which leads to a lack of interpretability, has been a major concern. My…

We show that combining human prior knowledge with end-to-end learning can improve the robustness of deep neural networks by introducing a part-based model for object classification. We believe that the richer form of annotation helps guide…

Pre-trained models have been shown effective in many code intelligence tasks. These models are pre-trained on large-scale unlabeled corpus and then fine-tuned in downstream tasks. However, as the inputs to pre-training and downstream tasks…

The success of convolutional neural networks (CNNs) in various applications is accompanied by a significant increase in computation and parameter storage costs. Recent efforts to reduce these overheads involve pruning and compressing the…