Related papers: Shap-CAM: Visual Explanations for Convolutional Ne…

Explainability is a vital aspect of modern AI for real-world impact and usability. The main objective of this paper is to emphasise the need to understand the predictions of Computer Vision models, specifically Convolutional Neural Network…

In the past years, deep convolutional neural networks have been pushing the frontier of face recognition (FR) techniques in both verification and identification scenarios. Despite the high accuracy, they are often criticized for lacking…

In deep learning, visualization techniques extract the salient patterns exploited by deep networks for image classification, focusing on single images; no effort has been spent in investigating whether these patterns are systematically…

This paper proposes a deep learning model to efficiently detect salient regions in videos. It addresses two important issues: (1) deep video saliency model training with the absence of sufficiently large and pixel-wise annotated video data,…

Data series classification is an important and challenging problem in data science. Explaining the classification decisions by finding the discriminant parts of the input that led the algorithm to some decisions is a real need in many…

Despite the tremendous success of convolutional neural networks (CNNs) in computer vision, the mechanism of CNNs still lacks clear interpretation. Currently, class activation mapping (CAM), a famous visualization technique to interpret…

Saliency methods have become standard in the explanation toolkit of deep neural networks. Recent developments specific to image classifiers have investigated region-based explanations with either new methods or by adapting well-established…

As deep learning continues to advance, the transparency of neural network decision-making remains a critical challenge, limiting trust and applicability in high-stakes domains. Class Activation Mapping (CAM) techniques have emerged as a key…

Conventional saliency maps highlight input features to which neural network predictions are highly sensitive. We take a different approach to saliency, in which we identify and analyze the network parameters, rather than inputs, which are…

The gradient-weighted class activation mapping (Grad-CAM) method can faithfully highlight important regions in images for deep model prediction in image classification, image captioning and many other tasks. It uses the gradients in…

Advances in multi-modal embeddings, and in particular CLIP, have recently driven several breakthroughs in Computer Vision (CV). CLIP has shown impressive performance on a variety of tasks, yet, its inherently opaque architecture may hinder…

Convolutional Neural Networks (CNNs) are known for their ability to learn hierarchical structures, naturally developing detectors for objects, and semantic concepts within their deeper layers. Activation maps (AMs) reveal these saliency…

In this paper we propose two saliency models for salient object segmentation based on a hierarchical image segmentation, a tree-like structure that represents regions at different scales from the details to the whole image (e.g. gPb-UCM,…

Data-driven saliency detection has attracted strong interest as a result of applying convolutional neural networks to the detection of eye fixations. Although a number of imagebased salient object and fixation detection models have been…

This paper proposes a novel saliency detection method by developing a deeply-supervised recurrent convolutional neural network (DSRCNN), which performs a full image-to-image saliency prediction. For saliency detection, the local, global,…

Image retargeting is the task of making images capable of being displayed on screens with different sizes. This work should be done so that high-level visual information and low-level features such as texture remain as intact as possible to…

Saliency prediction is a well studied problem in computer vision. Early saliency models were based on low-level hand-crafted feature derived from insights gained in neuroscience and psychophysics. In the wake of deep learning breakthrough,…

Visual attention is one of the most significant characteristics for selecting and understanding the outside redundancy world. The human vision system cannot process all information simultaneously due to the visual information bottleneck. In…

Visual saliency models have recently begun to incorporate deep learning to achieve predictive capacity much greater than previous unsupervised methods. However, most existing models predict saliency using local mechanisms limited to the…

Saliency maps that identify the most informative regions of an image for a classifier are valuable for model interpretability. A common approach to creating saliency maps involves generating input masks that mask out portions of an image to…