相关论文: Explainable Systematic Analysis for Synthetic Aper…

Deep learning (DL) has emerged as a powerful tool for Synthetic Aperture Radar (SAR) ship classification. This survey comprehensively analyzes the diverse DL techniques employed in this domain. We identify critical trends and challenges,…

Respiratory sound classification is hindered by the limited size, high noise levels, and severe class imbalance of benchmark datasets like ICBHI 2017. While Transformer-based models offer powerful feature extraction capabilities, they are…

Even though the large-scale language models have achieved excellent performances, they suffer from various adversarial attacks. A large body of defense methods has been proposed. However, they are still limited due to redundant attack…

Class-imbalance is an inherent characteristic of multi-label data which affects the prediction accuracy of most multi-label learning methods. One efficient strategy to deal with this problem is to employ resampling techniques before…

Accurate detection and segmentation of marine debris is important for keeping the water bodies clean. This paper presents a novel dataset for marine debris segmentation collected using a Forward Looking Sonar (FLS). The dataset consists of…

Recent advances in mechanistic interpretability have highlighted the potential of automating interpretability pipelines in analyzing the latent representations within LLMs. While this may enhance our understanding of internal mechanisms,…

Understanding the decisions made by deep neural networks is essential in high-stakes domains such as medical imaging and autonomous driving. Yet, these models often lack transparency, particularly in computer vision.…

Recent advances in generative deep learning have enabled the creation of high-quality synthetic images in text-to-image generation. Prior work shows that fine-tuning a pretrained diffusion model on ImageNet and generating synthetic training…

Deep neural networks (DNNs) are successfully applied in a wide variety of music information retrieval (MIR) tasks. Such models are usually considered "black boxes", meaning that their predictions are not interpretable. Prior work on…

Deep learning dominates image classification tasks, yet understanding how models arrive at predictions remains a challenge. Much research focuses on local explanations of individual predictions, such as saliency maps, which visualise the…

In computer-assisted surgery, automatically recognizing anatomical organs is crucial for understanding the surgical scene and providing intraoperative assistance. While machine learning models can identify such structures, their deployment…

Supervised fine-tuning (SFT) is a critical step in aligning large language models (LLMs) with human instructions and values, yet many aspects of SFT remain poorly understood. We trained a wide range of base models on a variety of datasets…

A novel evolutionary approach for Explainable Artificial Intelligence is presented: the "Evolved Explanations" model (EvEx). This methodology consists in combining Local Interpretable Model Agnostic Explanations (LIME) with Multi-Objective…

Data augmentation is a key element for training accurate models by reducing overfitting and improving generalization. For image classification, the most popular data augmentation techniques range from simple photometric and geometrical…

The Synthetic Minority Oversampling TEchnique (SMOTE) is widely-used for the analysis of imbalanced datasets. It is known that SMOTE frequently over-generalizes the minority class, leading to misclassifications for the majority class, and…

We present a set of metrics that utilize vision priors to effectively assess the performance of saliency methods on image classification tasks. To understand behavior in deep learning models, many methods provide visual saliency maps…

Interpretability in object detection provides crucial confidence support for clinical auxiliary diagnosis. However, in tiny bacteria detection, traditional explanation methods often suffer from blurred foreground boundaries and diffuse…

We present in this article a new evaluation method for classification and segmentation of textured images in uncertain environments. In uncertain environments, real classes and boundaries are known with only a partial certainty given by the…

We develop an efficient algorithm for Synthetic Aperture Sonar imaging based on the one-way wave equations. The algorithm utilizes the operator-splitting method to integrate the one-way wave equations. The well-posedness of the one-way wave…

Text-based editing diffusion models exhibit limited performance when the user's input instruction is ambiguous. To solve this problem, we propose $\textit{Specify ANd Edit}$ (SANE), a zero-shot inference pipeline for diffusion-based editing…