Related papers: Attribution Methods Reveal Flaws in Fingerprint-Ba…

Bias in classifiers is a severe issue of modern deep learning methods, especially for their application in safety- and security-critical areas. Often, the bias of a classifier is a direct consequence of a bias in the training dataset,…

Motivation: The scalable identification of bioactive compounds is essential for contemporary drug discovery. This process faces a key trade-off: structural screening offers scalability but lacks biological context, whereas high-content…

Text-conditioned image generation models often generate incorrect associations between entities and their visual attributes. This reflects an impaired mapping between linguistic binding of entities and modifiers in the prompt and visual…

Melanoma is the deadliest form of skin cancer. Automated skin lesion analysis plays an important role for early detection. Nowadays, the ISIC Archive and the Atlas of Dermoscopy dataset are the most employed skin lesion sources to benchmark…

As protein therapeutics play an important role in almost all medical fields, numerous studies have been conducted on proteins using artificial intelligence. Artificial intelligence has enabled data driven predictions without the need for…

Dense registration of fingerprints is a challenging task due to elastic skin distortion, low image quality, and self-similarity of ridge pattern. To overcome the limitation of handcraft features, we propose to train an end-to-end network to…

Deep neural networks are very successful on many vision tasks, but hard to interpret due to their black box nature. To overcome this, various post-hoc attribution methods have been proposed to identify image regions most influential to the…

Learning under one-sided feedback (i.e., where we only observe the labels for examples we predicted positively on) is a fundamental problem in machine learning -- applications include lending and recommendation systems. Despite this, there…

Deep neural networks have demonstrated promising performance on image recognition tasks. However, they may heavily rely on confounding factors, using irrelevant artifacts or bias within the dataset as the cue to improve performance. When a…

Societal biases are reflected in large pre-trained language models and their fine-tuned versions on downstream tasks. Common in-processing bias mitigation approaches, such as adversarial training and mutual information removal, introduce…

Prior work has shown that Visual Recognition datasets frequently underrepresent bias groups $B$ (\eg Female) within class labels $Y$ (\eg Programmers). This dataset bias can lead to models that learn spurious correlations between class…

Inverse protein folding generates valid amino acid sequences that can fold into a desired protein structure, with recent deep-learning advances showing strong potential and competitive performance. However, challenges remain, such as…

Backpropagation is widely used to train artificial neural networks, but its relationship to synaptic plasticity in the brain is unknown. Some biological models of backpropagation rely on feedback projections that are symmetric with…

Deep learning models, particularly Convolutional Neural Networks (CNNs), have demonstrated exceptional performance in diagnosing skin diseases, often outperforming dermatologists. However, they have also unveiled biases linked to specific…

Interpretability is an important area of research for safe deployment of machine learning systems. One particular type of interpretability method attributes model decisions to input features. Despite active development, quantitative…

The promise of active learning (AL) is to reduce labelling costs by selecting the most valuable examples to annotate from a pool of unlabelled data. Identifying these examples is especially challenging with high-dimensional data (e.g.…

Weak supervision enables efficient development of training sets by reducing the need for ground truth labels. However, the techniques that make weak supervision attractive -- such as integrating any source of signal to estimate unknown…

The deep learning (DL) technology has been widely used for image classification in many scenarios, e.g., face recognition and suspect tracking. Such a highly commercialized application has given rise to intellectual property protection of…

Contextual information plays a critical role in object recognition models within computer vision, where changes in context can significantly affect accuracy, underscoring models' dependence on contextual cues. This study investigates how…

Model fingerprinting has emerged as a powerful tool for model owners to identify their shared model given API access. However, to lower false discovery rate, fight fingerprint leakage, and defend against coalitions of model users attempting…