相关论文: On the Impact of Interpretability Methods in Activ…

Interpretability is an emerging area of research in trustworthy machine learning. Safe deployment of machine learning system mandates that the prediction and its explanation be reliable and robust. Recently, it has been shown that the…

Data augmentation is practically helpful for visual recognition, especially at the time of data scarcity. However, such success is only limited to quite a few light augmentations (e.g., random crop, flip). Heavy augmentations are either…

While data augmentation (DA) is generally applied to input data, several studies have reported that applying DA to hidden layers in neural networks, i.e., feature augmentation, can improve performance. However, in previous studies, the…

Adversarial distillation (AD) is a knowledge distillation technique that facilitates the transfer of robustness from teacher deep neural network (DNN) models to lightweight target (student) DNN models, enabling the target models to perform…

Deep neural networks have been shown to perform poorly on adversarial examples. To address this, several techniques have been proposed to increase robustness of a model for image classification tasks. However, in video understanding tasks,…

As the use of deep neural networks continues to grow, understanding their behaviour has become more crucial than ever. Post-hoc explainability methods are a potential solution, but their reliability is being called into question. Our…

Knowledge distillation (KD) methods are pivotal in compressing large pre-trained language models into smaller models, ensuring computational efficiency without significantly dropping performance. Traditional KD techniques assume homogeneity…

Deep Learning of neural networks has gained prominence in multiple life-critical applications like medical diagnoses and autonomous vehicle accident investigations. However, concerns about model transparency and biases persist. Explainable…

Vision Transformers (ViTs) have achieved state-of-the-art performance in image classification, yet their attention mechanisms often remain opaque and exhibit dense, non-structured behaviors. In this work, we adapt our previously proposed…

In Active Domain Adaptation (ADA), one uses Active Learning (AL) to select a subset of images from the target domain, which are then annotated and used for supervised domain adaptation (DA). Given the large performance gap between…

Machine learning is permeating every conceivable domain to promote data-driven decision support. The focus is often on advanced black-box models due to their assumed performance advantages, whereas interpretable models are often associated…

Deep neural networks have emerged as very successful tools for image restoration and reconstruction tasks. These networks are often trained end-to-end to directly reconstruct an image from a noisy or corrupted measurement of that image. To…

Data augmentation (DA) is an essential technique for training state-of-the-art deep learning systems. In this paper, we empirically show data augmentation might introduce noisy augmented examples and consequently hurt the performance on…

Vision-language models (VLMs) are vulnerable to adversarial image perturbations. Existing works based on adversarial training against task-specific adversarial examples are computationally expensive and often fail to generalize to unseen…

Deployment of machine learning models in real high-risk settings (e.g. healthcare) often depends not only on the model's accuracy but also on its fairness, robustness, and interpretability. Generalized Additive Models (GAMs) are a class of…

With the rise of deep neural networks, the challenge of explaining the predictions of these networks has become increasingly recognized. While many methods for explaining the decisions of deep neural networks exist, there is currently no…

Artificial Intelligence has emerged as a useful aid in numerous clinical applications for diagnosis and treatment decisions. Deep neural networks have shown same or better performance than clinicians in many tasks owing to the rapid…

Lithography modeling is a crucial problem in chip design to ensure a chip design mask is manufacturable. It requires rigorous simulations of optical and chemical models that are computationally expensive. Recent developments in machine…

State-of-the-art text-to-image diffusion models can produce impressive visuals but may memorize and reproduce training images, creating copyright and privacy risks. Existing prompt perturbations applied at inference time, such as random…

Recent advances in Deep Learning have greatly improved performance on various tasks such as object detection, image segmentation, sentiment analysis. The focus of most research directions up until very recently has been on beating…