Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 56 for “"saliency map"”.
-
Explainable AI for malware opcode sequence analysis and explainability-motivated saliency-map based spurious correlation robustness in images
… process of image classifiers by leveraging saliency maps to guide model behaviour. ULE trains two models concurrently: a student model and a teacher model. The student is trained using standard Empirical Risk Minimisation and learns to rely on spurious correlations present in the data. …
-
Visual understanding by salient proto-objects
… a coherent and stable object on the basis of saliency. It is been demonstrated in this work that the salient proto-object is useful in machine based visual understanding. First, we propose a novel computational framework for salient proto-object detection, which integrates the saliency map …
-
Image analysis using visual saliency with applications in hazmat sign detection and recognition
Visual saliency is the perceptual process that makes attractive objects "stand out" from their surroundings in the low-level human visual system. Visual saliency has been modeled as a preprocessing step of the human visual system for selecting the important visual information from a scene. We …
-
Supervised attention from natural language feedback for reinforcement learning
… we translate human linguistic narration to a saliency map over the perceptual field. This saliency map is used to inform a deep-reinforcement learning system which features in the visual observation are most important relative to its position in the environment and optimize task learning. We …
-
FAST–AT: FAST AUTOMATIC THUMBNAIL GENERATION USING DEEP NEURAL NETWORKS
… most previous work, Fast-AT does not utilize saliency but addresses the problem directly. In addition, it eliminates the need to conduct region search on the saliency map. The model generalizes to thumbnails of different sizes including those with extreme aspect ratios and can generate …
-
INVESTIGATING THE IMPORTANCE OF OBJECT AND SEMANTICS IN GAZE DEPLOYMENT : A DATASET AND ANALYSES.
… WHERE TO LOOK IN A NATURAL IMAGE BY COMPUTING A "SALIENCY MAP" THAT HIGHLIGHTS THE REGIONS STANDING OUT OF THE SCENE. HOWEVER, RECENT EVIDENCE SUGGESTS THAT HUMAN VISUAL ATTENTION IS ATTRACTED BY INTERESTING OBJECTS IN THE SCENE, BUT NOT ONLY THE PIXEL-LEVEL FEATURES. OBJECTS AND SEMANTICS MAY …
-
Presenting Visual Information to the User: Combining Computer Vision and Interface Design
… thumbnails, we first find salient regions (saliency map) using local statistical features of the image. We crop and downsample the images based on these saliency maps, and obtain better thumbnails. The suggested methods of finding salient regions are faster than existing methods while giving …
-
VISUAL ATTENTION IN DYNAMIC NATURAL SCENES
… section describes a novel computational model of saliency that makes use of gist information to compute the final saliency map. The model was tested with eye movement data from 32 subjects, and demonstrated comparable performance to several well-known models of visual saliency.
-
Dense image labeling using deep learning
… that employs recurrent refinement to generate a saliency map in a coarse-to-fine fashion. Experimental results demonstrate the superiority and effectiveness of our proposed approaches.
-
Learning Image Saliency from Human Touch Behaviors
The concept of touch saliency has recently been introduced as a possible alternative for eye tracking in usability studies. This touch saliency study shows that image saliency maps can be generated based on human simple zoom behavior on touch devices. However, when browsing images on touch screen, …
-
Interpreting Deep Neural Networks and Beyond: Visualization, Learning Dynamics, and Disentanglement
… has attracted much attention recently, including Saliency Map, DeconvNet, and Guided Backprop (GBP). However, we find that there exist some perplexing behaviors: DeconvNet and GBP are more human-interpretable but less class-sensitive than Saliency Map. Motivated by this, we develop a theory that …
-
Active Stereo Vision For Manipulator Robot
… model of attention with three main features map is used to control the gaze of the camera system. The three feature maps are (A) an online epipolar geometry update to produce a disparity map and affordance of grasping, (B) a vergence controller to provide a map of the depth of tomatoes at …
-
Visual Saliency Estimation Via HEVC Bitstream Analysis
… study of the existing compressed domain video saliency detection model, a new saliency estimation model for video based on High Efficiency Video Coding (HEVC) is presented. First, the relative features are extracted from HEVC encoded bitstream. The naive Bayesian model is used to train and test …
-
SRED: Secure and Robust Emotion Detection for Advanced Driver Assistance Systems
… enhance interpretability, SRED also integrates saliency map analysis, offering insights into the critical facial regions influencing the model's decisions.
-
Adversarial Attack and Defense
… to adversarial point dropping. We construct a saliency map for a whole point cloud, which assigns each point a score reflecting its contribution to the model-recognition loss. Based on the learned saliency map, maliciously point-dropping attack can be achieved by dropping points with the …
-
Assessing Structure–Property Relationships of Crystal Materials using Deep Learning
… CNN, GNN) and advanced analysis methods (i.e., saliency map). In Chapter 2, the convolutional neural network (CNN) model is established to find the correlation between the physically intuitive partial electronic density of state (PDOS) and the formation energies of crystals. Importantly, …
-
First trimester gaze and visual-assisted probe motion guidance for obstetric ultrasound scanning
… (RA) and RA with Mixup (Mix.RA) for single frame saliency prediction was developed. The proposed policy improves the saliency map segmentation performance in the first trimester by predicting the eye gaze of a sonographer. In addition, the automated data augmentation reduces class imbalance and …
-
Autonomous Vehicle Perception Quality Assessment
… perception quality assessment by using image saliency and 2D object detection algorithms to create an image-based quality index. We then develop a neural network model to regress the proposed quality index score. Furthermore, we extend our research to LiDAR-based point cloud quality assessment …
-
How deep learning can help emotion recognition
… the output prediction by using the gradient as a saliency map. Lastly, we explore the merit of doing multimodal emotion recognition by combining our model with other models trained on audio and physiological data.
-
Visual Interpretability of Multimodal Tissue Perfusion Classification Using Grad-Cam and Saliency Maps
… models, achieved through the analysis of saliency maps and the Gradient-weighted Class Activation Mapping (Grad-CAM) methods. The purpose of this method is to find out how the convolutional neural networks (CNNs) are able to find discriminative regions in di!erent types of data during the …
Page 1 of 3