Related papers: Score-CAM: Score-Weighted Visual Explanations for …

Despite the success of deep learning in video understanding tasks, processing every frame in a video is computationally expensive and often unnecessary in real-time applications. Frame selection aims to extract the most informative and…

Successful visual navigation depends upon capturing images that contain sufficient useful information. In this letter, we explore a data-driven approach to account for environmental lighting changes, improving the quality of images for use…

Spiking Neural Networks (SNNs) compute and communicate with asynchronous binary temporal events that can lead to significant energy savings with neuromorphic hardware. Recent algorithmic efforts on training SNNs have shown competitive…

Explaining the output of a deep network remains a challenge. In the case of an image classifier, one type of explanation is to identify pixels that strongly influence the final decision. A starting point for this strategy is the gradient of…

In this paper, an enhancement technique for the class activation mapping methods such as gradient-weighted class activation maps or excitation backpropagation is proposed to present the visual explanations of decisions from convolutional…

The predictive power of neural networks often costs model interpretability. Several techniques have been developed for explaining model outputs in terms of input features; however, it is difficult to translate such interpretations into…

Causal discovery is a crucial initial step in establishing causality from empirical data and background knowledge. Numerous algorithms have been developed for this purpose. Among them, the score-matching method has demonstrated superior…

With the growing demand for interpretable deep learning models, this paper introduces Integrative CAM, an advanced Class Activation Mapping (CAM) technique aimed at providing a holistic view of feature importance across Convolutional Neural…

Reliable and interpretable decision-making is essential in medical imaging, where diagnostic outcomes directly influence patient care. Despite advances in deep learning, most medical AI systems operate as opaque black boxes, providing…

Convolutional Neural Networks (CNNs) have achieved remarkable success across a wide range of machine learning tasks by leveraging hierarchical feature learning through deep architectures. However, the large number of layers and millions of…

Current techniques in Visual Simultaneous Localization and Mapping (VSLAM) estimate camera displacement by comparing image features of consecutive scenes. These algorithms depend on scene continuity, hence requires frequent camera inputs.…

Understanding and explaining deep learning models is an imperative task. Towards this, we propose a method that obtains gradient-based certainty estimates that also provide visual attention maps. Particularly, we solve for visual question…

Evolutionary computation methods have been successfully applied to neural networks since two decades ago, while those methods cannot scale well to the modern deep neural networks due to the complicated architectures and large quantities of…

Gradient based attribution methods for neural networks working as classifiers use gradients of network scores. Here we discuss the practical differences between using gradients of pre-softmax scores versus post-softmax scores, and their…

Whether it is computer vision, natural language processing or speech recognition, the essence of these applications is to obtain powerful feature representations that make downstream applications completion more efficient. Taking image…

Class activation mapping (CAM) is a widely adopted class of saliency methods used to explain the behavior of convolutional neural networks (CNNs). These methods generate heatmaps that highlight the parts of the input most relevant to the…

In this work, we develop convolutional neural generative coding (Conv-NGC), a generalization of predictive coding to the case of convolution/deconvolution-based computation. Specifically, we concretely implement a flexible…

Unlike standard object classification, where the image to be classified contains one or multiple instances of the same object, indoor scene classification is quite different since the image consists of multiple distinct objects. Further,…

Saliency maps have become one of the most widely used interpretability techniques for convolutional neural networks (CNN) due to their simplicity and the quality of the insights they provide. However, there are still some doubts about…

The different families of saliency methods, either based on contrastive signals, closed-form formulas mixing gradients with activations or on perturbation masks, all focus on which parts of an image are responsible for the model's…