Fast saliency detection method for any differentiable classifier.
problem Real-time interpretation of black box classifiers.
method Training a masking model to manipulate classifier scores.
result Produces interpretable, sharp saliency maps.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,341 papers · 148 categories
Trend · papers per month
48 results for “image saliency”
The study evaluates saliency metrics for image classifier outputs, finding inconsistencies and unreliability.
problem Inconsistencies and unreliability in saliency metrics for evaluating pixel relevance.
method Investigated existing saliency metrics, calculated and compared their consistency, and applied psychometric testing methods.
result Saliency metrics can be statistically unreliable and inconsistent, affecting comparative rankings.
Neural network classifies breast cancer lesions using global and local image features.
problem Classifying breast cancer lesions in medical images with high resolution and small regions of interest.
method Proposes a neural network that combines global saliency maps and local patches for pixel-level saliency maps.
result Achieves radiologist-level performance in screening mammography interpretation.
The paper evaluates saliency methods for image predictions, finding some inadequate.
problem The reliability of saliency methods in explaining model predictions.
method Proposed a methodology to evaluate saliency methods based on their independence from model and data.
result Some saliency methods are independent of both model and data, making them inadequate for certain tasks.
New method extracts high-quality saliency maps without classifier dependence.
problem Fixed classifier dependence limits saliency map extraction performance.
method Classifier-agnostic saliency map extraction.
result Sets new state of the art for localization tasks on ImageNet.
Bayesian optimisation generates saliency maps for black-box models.
problem Generating saliency maps for models without access to parameters.
method Bayesian optimisation sampling method to find global salient regions.
result Approach outperforms grid-based methods and performs similarly to gradient-based methods.
Enhanced deep learning model improves tumor segmentation in ultrasound images.
problem Challenges in integrating patient-specific medical priors into deep learning models.
method Integrates visual saliency into a U-Net architecture with attention blocks.
result Achieved a Dice similarity coefficient of 90.5 percent on a dataset of 510 images.
Paper proposes a method to detect adversarial examples using saliency.
problem Detecting adversarial perturbations in machine learning models.
method Trains a binary classifier with origin data and saliency data.
result Shows good performance in detecting adversarial perturbations.
RACDNN improves saliency detection by iteratively refining attention to multiple scales.
problem Saliency detection struggles with objects of varying scales.
method Recurrent attentional convolutional-deconvolution network (RACDNN) using spatial transformer and recurrent units.
result RACDNN outperforms state-of-the-art methods on saliency detection datasets.
Two JSMA variants improve speed and accuracy for image classification attacks.
problem Fooling deep neural networks with adversarial images.
method Maximizing pixel values to mislead classification models.
result Two JSMA variants perform well on digit and scene datasets.
Develops methods to show model confidence and feature importance in medical imaging.
problem Ensuring safety and understanding model confidence in medical applications.
method Creates a pipeline to visualize uncertainty and saliency maps for deep neural networks.
result Demonstrates how deep neural networks can be made more transparent and safe for medical applications.
XRAI improves saliency maps for deep neural networks.
problem Improving understanding of deep neural networks through better saliency methods.
method XRAI is a region-based attribution method built upon integrated gradients, with new evaluation methods and sanity checks.
result XRAI produces better results than other saliency methods for common models and the ImageNet dataset.
A saliency detection method for ECT images segments cellular components without supervision.
problem Automatic segmentation of cellular components from ECT images is difficult due to structural complexity and imaging limits.
method Supervoxel over-segmentation, feature extraction, feature matrix decomposition, and computation of saliency.
result The method successfully labels most salient regions detected by a human observer and filters out background regions.
Adversarial robust models have more interpretable saliency maps.
problem Understanding the relationship between adversarial robustness and saliency map interpretability.
method Quantifying the alignment between input images and saliency maps, hypothesizing and testing the relationship with linear and neural network models.
result The alignment between input images and saliency maps increases as the distance to the decision boundary grows, especially in linear models.
New method improves interpretability of fMRI decoding models.
problem Uninterpretable deep neural networks in fMRI decoding.
method Adversarial training to make DNNs robust to noise and improved saliency map methods.
result Saliency maps from adversarial-trained DNNs are more interpretable than those from other methods.
DANCE improves saliency maps by adding subtle input variations.
problem Poor performance of saliency methods in saturated gradients, adversarial perturbations, and inter-feature dependence.
method Two-step procedure: 1) Perturbation mechanism, 2) Aggregation of saliency maps.
result DANCE saliency method outperforms existing methods qualitatively and quantitatively.
Deep learning investigation for chess player attention prediction using eye-tracking and game datastat.ML
Deep learning predicts chess player attention using eye-tracking and game data.
problem Predicting chess player attention during game.
method Convolutional neural networks with skip-layer architecture and autoencoder.
result Deep features from natural images help in predicting saliency maps for chess.
Study identifies and mitigates causes of image misclassifications in CNN models.
problem Improving model interpretability and accuracy in image classification.
method Trained six CNN architectures on CIFAR-10, used conditional confusion matrices and misclassification networks to identify morphological similarity and non-essential information interference as causes of misclassification. Developed a method to reduce misclassifications by erasing pixels within top 5% saliency map bounding boxes.
result Identified two causes of misclassification: morphological similarity and non-essential information interference, and developed a method to reduce misclassifications caused by the latter.
Input-cell attention improves RNN saliency detection over time.
problem Vanishing saliency in RNNs makes them unreliable for detecting important features at arbitrary time intervals.
method Proposes input-cell attention, a novel RNN cell structure that uses a fixed-size matrix embedding to attend to different inputs from current or previous time steps.
result Input-cell attention produces a saliency map that can detect important features regardless of their occurrence in time.
Faster gaze prediction with less parameters.
problem Overparameterized networks for gaze prediction.
method Fisher pruning combined with knowledge distillation.
result 10x speedup for fixation prediction.
New approach makes adversarial examples less suspicious without changing perceptual salience.
problem Robustness of deep neural networks to unsuspicious adversarial examples.
method Splitting images into foreground and background, allowing larger perturbations in background while maintaining low cognitive salience.
result Dual-perturbation attacks are effective against classifiers robust to conventional attacks and adversarial training yields more robust classifiers.
New method interprets complex models by altering images.
problem Need to explain complex machine learning predictions.
method General framework for model-agnostic explanations.
result Find most responsible part of an image for a classifier.
Generative models improve image classifier explanations by realistically removing features.
problem Perturbation-based explanations often produce unrealistic counterfactual samples.
method Integrate generative inpainters into attribution methods to remove input features.
result Improved explanation methods in object localization, deletion, and saliency metrics.
Visualizes ConvNets without confounding effects.
problem Misinterpretation of saliency maps due to confounding variables.
method Univariate statistical tests and partial back-propagation to remove confounding effects.
result Visualization of confounder-free saliency maps.
1-Lipschitz neural networks produce clearer, more focused Saliency Maps for explainable AI.
problem Noisy and limited Saliency Maps from traditional neural networks.
method Dual loss of optimal transport problem for 1-Lipschitz neural networks.
result Saliency Maps from 1-Lipschitz networks are highly concentrated and less noisy, aligning with human explanations.
Improved saliency maps for deep neural networks with reduced noise.
problem Noisy explanations in Integrated Gradients for deep neural networks.
method SmoothTaylor, adaptive noising, and SmoothGrad techniques.
result SmoothTaylor and adaptive noising generate better quality saliency maps.
Study evaluates different saliency maps for CT image classification.
problem Understanding how deep learning models make decisions in medical imaging.
method Compared several saliency maps using three evaluation metrics.
result Two versions of SmoothGrad performed best across all metrics.
Proposes a stochastic optimization method for feature attribution.
problem Improving feature attribution methods for complex models.
method Reformulates the optimization problem as a differentiable function solvable by gradient-based algorithms, particularly stochastic optimization.
result The proposed method effectively identifies relevant parts of images.
Contextual PDA improves explanation of image classifications for saturated models.
problem Difficulty in explaining decisions of saturated classifiers.
method Proposes Contextual PDA, a faster method for explaining image classifications.
result Contextual PDA outperforms PDA in explaining image classifications of state-of-the-art deep networks.
A method to combine saliency metrics for better CNN pruning decisions.
problem Improving CNN pruning decisions by combining multiple saliency metrics.
method Proposes a method to compose different saliency metrics for better CNN pruning decisions.
result The composition of saliencies avoids many poor pruning choices identified by individual saliencies.
New hypothesis and method reduce noise in saliency maps.
problem Noisy saliency maps from deep neural networks.
method Proposed a new hypothesis and Rectified Gradient method.
result Rectified Gradient effectively reduces saliency map noise.
SaliencyMix augments images with salient patches to improve model generalization.
problem Improving deep learning model generalization through better data augmentation.
method Carefully selects salient patches from images and mixes them with the target image.
result Achieves state-of-the-art top-1 error rates and robustness against adversarial attacks.
Enhances deep reinforcement learning with object recognition.
problem Few works consider object characteristics in deep reinforcement learning.
method Proposes a novel method to incorporate object recognition into deep reinforcement learning models.
result Shows state-of-the-art results on Atari games.
Proposes novel method for detecting novel scenarios in autonomous systems.
problem Detecting when a machine learning model makes a trustworthy prediction in dynamic, real-world situations.
method Leverages trained model's learned information and a new image similarity metric.
result Demonstrates the method's efficacy on real-world driving and indoor racing datasets.
A taxonomy of saliency metrics helps in pruning deep neural networks.
problem Difficulty in separating saliency metric effectiveness from pruning algorithms.
method Proposed a taxonomy based on four orthogonal components.
result Constructed metrics can outperform existing state-of-the-art metrics.
Study evaluates saliency maps on artificial data with different backgrounds.
problem Objective evaluation of saliency methods on artificial data with varying backgrounds.
method Developed a framework to generate artificial data with synthetic lesions and a known ground truth map, evaluated two data sets with different backgrounds (Perlin noise and 2D brain MRI slices).
result Heatmaps vary strongly between saliency methods and backgrounds.
New method creates universal perturbations to fool neural network interpretations.
problem Vulnerability of gradient-based saliency maps to adversarial perturbations.
method Gradient-based optimization and PCA-based approach to create UPI.
result Existence and successful application of Universal Perturbation for Interpretation (UPI).
Saliency methods often misattribute predictions due to input transformations.
problem Saliency methods lack reliability when explanations are sensitive to non-contributing factors.
method Used a simple pre-processing step to demonstrate that transformations with no effect on the model can cause misleading attributions.
result Saliency methods that do not satisfy input invariance (mirror model sensitivity to input transformations) result in misleading attributions.
When saliency goes off on a tangent: Interpreting Deep Neural Networks with nonlinear saliency mapscs.LG
New nonlinear saliency maps improve deep neural network interpretability.
problem Lack of understanding why and how deep neural networks make decisions.
method Developed novel nonlinear saliency maps to better interpret deep neural networks.
result Nonlinear saliency maps provide more specific drivers of classification on complex examples.
New method for visualizing high-level concepts in generative models.
problem Challenges in evaluating and visualizing concepts in generative models.
method Introduces a method to compute concept saliency maps for latent representations of known or novel high-level concepts.
result Concept saliency maps highlight input features important for high-level concepts.
A new method extracts linguistic objects from text using CNNs.
problem Lack of interpretability in deep learning models for text.
method Weighted extension of Text Deconvolution Saliency (wTDS) measure.
result Extracts interpretable linguistic objects from text.
The paper introduces a statistical distance matrix for better feature representation and clustering.
problem Lack of detailed distance representation between feature elements.
method Extended traditional statistical distance to a matrix form (statistical distance matrix) and applied hierarchical clustering.
result The statistical distance matrix with clustering (Information Mandala) provides clearer and geometrically arranged feature representations.
RCAV quantifies model sensitivity to semantic concepts, improving interpretability methods.
problem Lack of semantic interpretability in image classification models.
method RCAV calculates concept gradients and ascent steps to assess model sensitivity to semantic concepts.
result RCAV yields more accurate and robust interpretations of model behavior.
Deep learning improves mammography assessment with high accuracy.
problem Challenges in mammography assessment due to noise, resolution, and lack of ground truths.
method Proposes a classification approach using multi-scale deep tissue classifiers.
result Highest AUC of 0.9 achieved in classifying suspicious tissue patches.
The paper benchmarks saliency methods for time series predictions.
problem Benchmarking saliency methods for time series predictions.
method Compared saliency-based interpretability methods across diverse neural architectures.
result Saliency methods fail to reliably identify feature importance over time in time series data.
Study validates saliency maps of GNNs using selective inference.
problem Reliability of GNN saliency maps in graph-structured data.
method Statistical testing framework with selective inference to control Type I error rate.
result Valid -values for salient subgraphs, ensuring meaningful information.
A new LDA variant improves multi-label classification performance.
problem Improving multi-label classification performance.
method Saliency-based weights redefine between-class and within-class scatter matrices for multi-label classification.
result The proposed method leads to performance improvements in various multi-label classification problems.
Method uses ANN to estimate incentive salience from large behavioral data.
problem Estimating incentive salience in naturalistic settings.
method Artificial Neural Networks (ANNs) for latent state approximation.
result ANNs produce better representations for predicting future behaviour.