Related papers: LaFAM: Unsupervised Feature Attribution with Label…

Complex-valued neural networks (CVNNs) are a powerful modeling tool for domains where data can be naturally interpreted in terms of complex numbers. However, several analytical properties of the complex domain (e.g., holomorphicity) make…

Facial action units (AUs) are essential to decode human facial expressions. Researchers have focused on training AU detectors with a variety of features and classifiers. However, several issues remain. These are spatial representation,…

Class activation mapping~(CAM), a visualization technique for interpreting deep learning models, is now commonly used for weakly supervised semantic segmentation~(WSSS) and object localization~(WSOL). It is the weighted aggregation of the…

Deep learning models have achieved remarkable success across diverse domains. However, the intricate nature of these models often impedes a clear understanding of their decision-making processes. This is where Explainable AI (XAI) becomes…

While deep learning, including Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), has significantly advanced classification performance, its typical reliance on extensive annotated datasets presents a major obstacle in…

We present a novel approach to leverage large unlabeled datasets by pre-training state-of-the-art deep neural networks on randomly-labeled datasets. Specifically, we train the neural networks to memorize arbitrary labels for all the samples…

Self-supervised learning, which benefits from automatically constructing labels through pre-designed pretext task, has recently been applied for strengthen supervised learning. Since previous self-supervised pretext tasks are based on…

Deep Convolutional Neural Networks (CNN) have shown great success in supervised classification tasks such as character classification or dating. Deep learning methods typically need a lot of annotated training data, which is not available…

Class Activation Mapping (CAM) and its extensions have become indispensable tools for visualizing the evidence behind deep network predictions. However, by relying on a final softmax classifier, these methods suffer from two fundamental…

Semantic segmentation is a challenging task in the absence of densely labelled data. Only relying on class activation maps (CAM) with image-level labels provides deficient segmentation supervision. Prior works thus consider pre-trained…

In the contemporary of deep learning, where models often grapple with the challenge of simultaneously achieving robustness against adversarial attacks and strong generalization capabilities, this study introduces an innovative Local Feature…

Weakly supervised semantic segmentation (WSSS) with only image-level supervision is a challenging task. Most existing methods exploit Class Activation Maps (CAM) to generate pixel-level pseudo labels for supervised training. However, due to…

In weakly-supervised semantic segmentation (WSSS) using only image-level class labels, a problem with CNN-based Class Activation Maps (CAM) is that they tend to activate the most discriminative local regions of objects. On the other hand,…

Active contour models have achieved prominent success in the area of image segmentation, allowing complex objects to be segmented from the background for further analysis. Existing models can be divided into region-based active contour…

Convolutional neural networks (CNNs) are widely used for high-stakes applications like medicine, often surpassing human performance. However, most explanation methods rely on post-hoc attribution, approximating the decision-making process…

Class activation map (CAM) has been widely used to highlight image regions that contribute to class predictions. Despite its simplicity and computational efficiency, CAM often struggles to identify discriminative regions that distinguish…

Graph convolutional networks (GCNs) allow to apply traditional convolution operations in non-Euclidean domains, where data are commonly modelled as irregular graphs. Medical imaging and, in particular, neuroscience studies often rely on…

Since Convolutional Neural Networks (ConvNets) are able to simultaneously learn features and classifiers to discriminate different categories of activities, recent works have employed ConvNets approaches to perform human activity…

Image segmentation is considered to be one of the critical tasks in hyperspectral remote sensing image processing. Recently, convolutional neural network (CNN) has established itself as a powerful model in segmentation and classification by…

Neural networks are generally built by interleaving (adaptable) linear layers with (fixed) nonlinear activation functions. To increase their flexibility, several authors have proposed methods for adapting the activation functions…