Related papers: Causal Attribution via Activation Patching

Although Vision Transformers (ViTs) have recently demonstrated superior performance in medical imaging problems, they face explainability issues similar to previous architectures such as convolutional neural networks. Recent research…

Data Augmentation is a common technique used to enhance the performance of deep learning models by expanding the training dataset. Automatic Data Augmentation (ADA) methods are getting popular because of their capacity to generate policies…

Decisions made by convolutional neural networks(CNN) can be understood and explained by visualizing discriminative regions on images. To this end, Class Activation Map (CAM) based methods were proposed as powerful interpretation tools,…

To assist humans in efficiently validating RAG-generated content, developing a fine-grained attribution mechanism that provides supporting evidence from retrieved documents for every answer span is essential. Existing fine-grained…

Recent work has shown the potential of transformers for computer vision applications. An image is first partitioned into patches, which are then used as input tokens for the attention mechanism. Due to the expensive quadratic cost of the…

Interpretability methods for image classification assess model trustworthiness by attempting to expose whether the model is systematically biased or attending to the same cues as a human would. Saliency methods for feature attribution…

Vision Transformers (ViTs) have shown impressive performance but still require a high computation cost as compared to convolutional neural networks (CNNs), one reason is that ViTs' attention measures global similarities and thus has a…

Feature attribution (FA), or the assignment of class-relevance to different locations in an image, is important for many classification problems but is particularly crucial within the neuroscience domain, where accurate mechanistic models…

Vision transformers (ViTs) have demonstrated impressive performance in various computer vision tasks. However, the adversarial examples generated by ViTs are challenging to transfer to other networks with different structures. Recent attack…

Within the field of causal inference, we consider the problem of estimating heterogeneous treatment effects from data. We propose and validate a novel approach for learning feature representations to aid the estimation of the conditional…

Attention-based models are proliferating in the space of image analytics, including segmentation. The standard method of feeding images to transformer encoders is to divide the images into patches and then feed the patches to the model as a…

Spatio-temporal (ST) prediction has garnered a De facto attention in earth sciences, such as meteorological prediction, human mobility perception. However, the scarcity of data coupled with the high expenses involved in sensor deployment…

As agentic AI becomes increasingly involved in creative production, documenting authorship has become critical for artists, collectors, and legal contexts. We present a patch-based framework for spatial authorship attribution within…

This paper presents a novel approach to address the challenges of understanding the prediction process and debugging prediction errors in Vision Transformers (ViT), which have demonstrated superior performance in various computer vision…

Vision Transformers (ViTs) have achieved comparable or superior performance than Convolutional Neural Networks (CNNs) in computer vision. This empirical breakthrough is even more remarkable since, in contrast to CNNs, ViTs do not embed any…

Deep learning models for medical image segmentation suffer significant performance drops due to distribution shifts, but the causal mechanisms behind these drops remain poorly understood. We extend causal attribution frameworks to…

Visual language pre-training (VLP) models have demonstrated significant success across various domains, yet they remain vulnerable to adversarial attacks. Addressing these adversarial vulnerabilities is crucial for enhancing security in…

Recent methods demonstrate that large-scale pretrained models, such as CLIP vision transformers, effectively detect AI-generated images (AIGIs) from unseen generative models when used as feature extractors. Many state-of-the-art methods for…

Large-scale diffusion models have made significant advances in image generation, particularly through cross-attention mechanisms. While cross-attention has been well-studied in text-to-image tasks, their interpretability in image-to-image…

Among the image forensic issues investigated in the last few years, great attention has been devoted to blind camera model attribution. This refers to the problem of detecting which camera model has been used to acquire an image by only…