FrequentNet uses frequency domain basis vectors for image classification, making models more interpretable and efficient.
problem Image classification models are often complex and hard to interpret.
method FrequentNet selects filter vectors from frequency domain basis vectors instead of training them with back propagation.
result The method improves interpretability and efficiency of image classification models.
Probability density estimation is a classical and well studied problem, but standard density estimation methods have historically lacked the power to model complex and high-dimensional image distributions. More recent generative models leverage the power of neural networks to implicitly learn and represent probability …
Automated detection of new, interesting, unusual, or anomalous images within large data sets has great value for applications from surveillance (e.g., airport security) to science (observations that don't fit a given theory can lead to new discoveries). Many image data analysis systems are turning to convolutional neur…
Study uses image analysis to predict MSI status in tumors.
problem Challenges in distinguishing MSI from its counterpart.
method Interpretable pathological image analysis strategies using Haematoxylin and eosin-stained images.
result Strategies achieve decent performance in MSI prediction.
Despite the advantages of all-weather and all-day high-resolution imaging, SAR remote sensing images are much less viewed and used by general people because human vision is not adapted to microwave scattering phenomenon. However, expert interpreters can be trained by compare side-by-side SAR and optical images to learn…
IntroVAC learns interpretable latent subspaces for better image quality.
problem Difficulties in interpreting latent spaces and limitations in image generation.
method Introspective Variational Classifier (IntroVAC) using additional labels and adversarial training.
result Improved image quality and meaningful latent directions for fine-grained manipulation.
Machine-generated interpretations do not improve users' guessing accuracy in image classifiers.
problem Determining the usefulness of machine-generated explanations for deep neural networks.
method Human evaluation of crowd workers guessing incorrectly predicted labels with and without visual interpretations.
result Showing machine-generated visual interpretations decreased average guessing accuracy by about 10%.
C2G-Net improves image classification of similar objects like cells.
problem Classifying images with many similar objects efficiently and interpretably.
method Combines image compression and a CNN with reduced parameters.
result C2G-Net achieves similar accuracy to conventional CNNs but with reduced training time and improved interpretability.
Deep neural networks for ordinal outcomes combining image and tabular data.
problem Lack of interpretable models for ordinal outcomes in mixed data types.
method Ordinal Neural Network Transformation Models (ONTRAMs) integrating DL and classical ordinal regression.
result ONTRAMs achieve performance equivalent to standard multi-class DL models but are faster and more interpretable.
3D CNNs interpret brain MRI differences between men and women.
problem Interpreting 3D CNNs for voxel-wise brain MRI analysis.
method Three interpretation methods: Meaningful Perturbations, Grad CAM, and Guided Backpropagation.
result Voxel-wise 3D CNN interpretation of brain MRI data.
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.
A decoder helps interpret neural network layers.
problem Understanding the output of neural network layers.
method Developed a Classifier-Decoder (ClaDec) architecture.
result Reconstructed images from ClaDec are more relevant for classification.
Tutorial on interpreting SPECT images for PD recognition using AI.
problem Difficulty in interpreting complex DL models for clinical use.
method Evaluation of six interpretation methods on four DCNN architectures.
result Guided backpropagation and SHAP methods are suitable for PD recognition.
NeuroMask provides interpretable explanations for deep neural networks.
problem Understanding how deep neural networks make decisions.
method Applies a mask to reveal or hide parts of an image, tuning mask values to preserve classification results and produce interpretable explanations.
result NeuroMask successfully localizes the most relevant parts of an image to a deep neural network's decision.
When we are faced with challenging image classification tasks, we often explain our reasoning by dissecting the image, and pointing out prototypical aspects of one class or another. The mounting evidence for each of the classes helps us make our final decision. In this work, we introduce a deep network architecture -- …
The paper tackles interpreting DCM with image data by addressing data isomorphism.
problem Interpreting DCM with image data due to isomorphic information.
method Proposes and benchmarks two methodologies: architectural adjustments and data source mitigation.
result Direct data source mitigation is more effective for maintaining DCM's interpretability.
Dual-edge spatial Jacobian image graph for interpretable diabetic retinopathy grading
problem Automated diabetic retinopathy grading from color fundus photographs
method Dual-edge spatial-Jacobian image graph
result 0.8076 accuracy, 0.8312 quadratic weighted kappa, 0.5915 macro-F1, 0.9330 adjacent-grade accuracy
ICAM creates interpretable feature attribution maps for brain images.
problem Challenges in predicting class relevance from brain images due to heterogeneity and background variation.
method A VAE-GAN framework for disentangling class relevance from background features.
result FA maps generated by ICAM outperform baseline methods and support phenotype variation exploration.
Improves deep generative models to generate images of any size.
problem Fixed-sized output images from deep generative models.
method Integrates spatial noise vectors into fully convolutional neural networks.
result Theoretical interpretation of infinite spatial generation using spatial stochastic processes.
Model learns Lagrangian dynamics from images for better prediction and control.
problem Lack of interpretability and applicability to high-dimensional data like images.
method Unsupervised neural network model that learns Lagrangian dynamics from images using a coordinate-aware VAE.
result Model infers interpretable Lagrangian dynamics, enabling long-term prediction and synthesis of controllers.
Model interprets image classification using hierarchical prototypes.
problem Lack of hierarchical interpretation in vision models.
method Uses hierarchically organized prototypes to classify objects at each level of a taxonomy.
result Model interprets image classification at each level of the taxonomy.
DCMIX learns channel importance for high content imaging.
problem Lack of channel importance information in deep learning-based image analysis.
method Image blending concepts with alpha compositing for arbitrary channels.
result DCMIX learns biologically relevant channel importance without sacrificing prediction performance.
Framework learns image dynamics between time steps using latent variables.
problem Challenges in capturing evolving image patterns and temporal information.
method Estimates intermediary image stages using a physical latent variable model.
result Demonstrates robustness and effectiveness in geoscientific imagery.
GT-PCA improves PCA for image and time series data.
problem Lack of robustness to transformations in PCA.
method GT-PCA is a neural network that estimates components invariant to specific transformations.
result GT-PCA outperforms alternative methods in synthetic and real data experiments.
RealStats detects fake images rigorously, combining multiple detectors for robustness.
problem Detecting AI-generated images remains challenging due to evolving generative models.
method Combines training-free statistics to compute p-values and aggregate them for a unified real-image distribution.
result Framework produces interpretable probability scores for robust fake image detection.
Deep neural network models have been proven to be very successful in image classification tasks, also for medical diagnosis, but their main concern is its lack of interpretability. They use to work as intuition machines with high statistical confidence but unable to give interpretable explanations about the reported re…
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).
Saccader improves hard attention models for vision tasks.
problem Challenges in training hard attention models with class label supervision.
method Proposes Saccader, a novel hard attention model trained with only class labels and policy gradient optimization.
result Achieves 75% top-1 and 91% top-5 accuracy while attending to less than one-third of the image.
Unified framework explains few-shot multimodal medical imaging performance.
problem Limited labeled data in rare diseases and low-resource settings.
method PAC learning, VC theory, PAC Bayesian analysis, information gain, Chain of Thought reasoning.
result Unified theoretical framework for few-shot multimodal medical imaging.
Image compression techniques reveal network structure for shipping box optimization.
problem Designing and planning shipping box networks between nodes.
method Image transformations and Bayesian reinforcement learning.
result Learned network structure can recommend future connectivity.
Paper tackles zero-shot learning for semantic image interpretation.
problem Extracting structured semantic descriptions from images requires complete training sets, which are often unavailable.
method Uses Logic Tensor Networks to leverage logical constraints and similarities among relationships in the training set.
result Background knowledge can alleviate the incompleteness of training sets, improving zero-shot learning performance.
V-HMN integrates memory mechanisms for improved image recognition.
problem Limited interpretability and high data requirements of existing vision backbones.
method Brain-inspired hierarchical memory modules with iterative refinement.
result V-HMN achieves strong performance on image classification benchmarks.
The chapter improves deep learning models by interpreting and improving their performance.
problem Deep learning models often lack interpretability, leading to poor understanding of their predictions.
method The approach involves attributing importance to features and feature groups, including interactions, to improve model performance.
result The proposed attributions provide insights across various domains and can be used to improve model generalization.
The paper proposes a new method for online image decomposition using auto-encoders.
problem Building a part-based representation of image datasets for interpretation and online computation.
method Sparse, non-negative auto-encoder with deep encoder and shallow decoder for online computation.
result The method outperforms state-of-the-art online methods on MNIST and Fashion MNIST datasets.
Interpretable representations improve explainable AI by translating complex data into understandable concepts.
problem Many explainers use interpretable representations but overlook their full potential and assumptions.
method An in-depth analysis of interpretable representations for tabular, image, and text data, identifying strengths, weaknesses, and desiderata.
result Linear model quantifies interpretable concepts' influence on black-box predictions, revealing their explanatory properties and manipulability.
Partial differential equations (PDEs) are indispensable for modeling many physical phenomena and also commonly used for solving image processing tasks. In the latter area, PDE-based approaches interpret image data as discretizations of multivariate functions and the output of image processing algorithms as solutions to…
LCBM model improves image classification without human supervision.
problem Improving interpretability and generalization of unsupervised concept-based models.
method LCBM models concepts as random variables in a Bernoulli latent space, reducing the number of concepts without sacrificing performance.
result LCBM outperforms existing models in generalization and interpretability.
Recently, a unified model for image-to-image translation tasks within adversarial learning framework has aroused widespread research interests in computer vision practitioners. Their reported empirical success however lacks solid theoretical interpretations for its inherent mechanism. In this paper, we reformulate thei…
Deep Relevance Regularization improves neural network performance in tumor typing.
problem Confounding factors hinder neural network performance in multi-laboratory imaging mass spectrometry data.
method Introduces Deep Relevance Regularization to restrict neural network focus.
result Deep Relevance Regularization robustifies neural networks and improves interpretability.
Adversarial training improves gradient interpretability, reducing misinterpretations.
problem Improving gradient interpretability in adversarially trained deep networks.
method Identified and demonstrated that adversarial training restricts gradients closer to the image manifold, making them more interpretable.
result Adversarial training leads to more meaningful loss gradients, aligning better with human perception.
This paper learns hierarchical compositional models for image synthesis.
problem Creating interpretable and hierarchical image representations.
method Sparsifying a generator network to induce an AND-OR hierarchy.
result The method learns meaningful and interpretable hierarchical representations.
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.
New framework for explainable AI on high-dimensional data.
problem Challenges in explainability with high-dimensional data.
method Two modules: latent representation and Shapley paradigm adaptation.
result Interpretable model explanations for high-dimensional data.
Enhances image captioning with novel context combination methods.
problem Improving machine learning for image captioning with structured learning and meaningful interpretation.
method Combines Feature Distribution Composition (FDC), Multiple Role Representation Crossover (MRRC) attention layers, and language decoder.
result Significantly improved image captioning performance (35.3%) and established new standards.
Proposes a technique to interpret deep learning models by generating counterfactual inputs.
problem Understanding and explaining the decisions made by deep neural networks.
method Uses a generative model to edit input images and generate counterfactual scenarios for model interpretation.
result Demonstrates the effectiveness of the introspection approach on MNIST and CelebA datasets.
CTM uses conjunctive clauses for image recognition, achieving high accuracy.
problem High computational complexity and lack of interpretability in CNNs.
method Introduces Convolutional Tsetlin Machine (CTM) using conjunctive clauses in propositional logic.
result CTM achieves competitive accuracy on various benchmarks, including MNIST and Fashion-MNIST.
The geometric approach to diffeomorphic image registration known as "large deformation by diffeomorphic metric mapping" (LDDMM) is based on a left action of diffeomorphisms on images, and a right-invariant metric on a diffeomorphism group, usually defined using a reproducing kernel. We explore the use of left-invariant…
Machine learning speeds up FLIM analysis in biomedical research.
problem Complex, slow, and computationally expensive FLIM analysis.
method Machine learning techniques for faster and smarter FLIM data extraction and interpretation.
result Higher accuracy in classifying and segmenting FLIM images compared to conventional methods.