Related papers: Smooth Grad-CAM++: An Enhanced Inference Level Vis…

The explication of Convolutional Neural Networks (CNN) through xAI techniques often poses challenges in interpretation. The inherent complexity of input features, notably pixels extracted from images, engenders complex correlations.…

Visual scene understanding is an important capability that enables robots to purposefully act in their environment. In this paper, we propose a novel approach to object-class segmentation from multiple RGB-D views using deep learning. We…

Many efforts have been made for revealing the decision-making process of black-box learning machines such as deep neural networks, resulting in useful local and global explanation methods. For local explanation, stochasticity is known to…

Convolutional neural network (CNN) has led to significant progress in object detection. In order to detect the objects in various sizes, the object detectors often exploit the hierarchy of the multi-scale feature maps called feature…

Salient object detection has seen remarkable progress driven by deep learning techniques. However, most of deep learning based salient object detection methods are black-box in nature and lacking in interpretability. This paper proposes the…

Transparency and explainability in image classification are essential for establishing trust in machine learning models and detecting biases and errors. State-of-the-art explainability methods generate saliency maps to show where a specific…

Fine-grained image classification is a challenging task due to the large intra-class variance and small inter-class variance, aiming at recognizing hundreds of sub-categories belonging to the same basic-level category. Most existing…

Convolutional Neural Networks (CNNs) are nowadays the model of choice in Computer Vision, thanks to their ability to automatize the feature extraction process in visual tasks. However, the knowledge acquired during training is fully…

Class activation map (CAM) helps to formulate saliency maps that aid in interpreting the deep neural network's prediction. Gradient-based methods are generally faster than other branches of vision interpretability and independent of human…

SmoothGrad and VarGrad are techniques that enhance the empirical quality of standard saliency maps by adding noise to input. However, there were few works that provide a rigorous theoretical interpretation of those methods. We analytically…

Fine-grained categorization can benefit from part-based features which reveal subtle visual differences between object categories. Handcrafted features have been widely used for part detection and classification. Although a recent trend…

3D Convolutional Neural Networks (3D-CNN) have been used for object recognition based on the voxelized shape of an object. However, interpreting the decision making process of these 3D-CNNs is still an infeasible task. In this paper, we…

Explanation methods facilitate the development of models that learn meaningful concepts and avoid exploiting spurious correlations. We illustrate a previously unrecognized limitation of the popular neural network explanation method…

Post-hoc explanation methods, e.g., Grad-CAM, enable humans to inspect the spatial regions responsible for a particular network decision. However, it is shown that such explanations are not always consistent with human priors, such as…

Object classification is a significant task in computer vision. It has become an effective research area as an important aspect of image processing and the building block of image localization, detection, and scene parsing. Object…

The backbone of traditional CNN classifier is generally considered as a feature extractor, followed by a linear layer which performs the classification. We propose a novel loss function, termed as CAM-loss, to constrain the embedded feature…

In an effort to increase the capabilities of SLAM systems and produce object-level representations, the community increasingly investigates the imposition of higher-level priors into the estimation process. One such example is given by…

Quality Diversity (QD) algorithms have been proposed to search for a large collection of both diverse and high-performing solutions instead of a single set of local optima. While early QD algorithms view the objective and descriptor…

Deep convolutional neural networks (CNNs) have delivered superior performance in many computer vision tasks. In this paper, we propose a novel deep fully convolutional network model for accurate salient object detection. The key…

As AI-based medical devices are becoming more common in imaging fields like radiology and histology, interpretability of the underlying predictive models is crucial to expand their use in clinical practice. Existing heatmap-based…