This paper proposes a generic method to learn interpretable convolutional filters in a deep convolutional neural network (CNN) for object classification, where each interpretable filter encodes features of a specific object part. Our method does not require additional annotations of object parts or textures for supervi…
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.
168,982 papers · 148 categories
Trend · papers per month
48 results for “CNN interpretability”
This paper presents an unsupervised method to learn a neural network, namely an explainer, to interpret a pre-trained convolutional neural network (CNN), i.e., the explainer uses interpretable visual concepts to explain features in middle conv-layers of a CNN. Given feature maps of a conv-layer of the CNN, the explaine…
AT-CNNs show improved shape recognition over texture recognition.
problem Understanding adversarial training's impact on CNNs' feature learning.
method Systematic qualitative and quantitative approaches to interpret AT-CNNs.
result Adversarial training reduces texture bias and improves shape recognition.
Model interpretability is a requirement in many applications in which crucial decisions are made by users relying on a model's outputs. The recent movement for "algorithmic fairness" also stipulates explainability, and therefore interpretability of learning models. And yet the most successful contemporary Machine Learn…
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.
Extracts decision trees from CNNs to explain concept importance.
problem Understanding how CNNs make decisions about human-understandable concepts.
method Inferring labeled concept data from CNN hidden layer activations and creating a shallow decision tree.
result Extracted decision trees accurately represent CNN classifications.
Convolutional neural networks (CNNs) are one of the driving forces for the advancement of computer vision. Despite their promising performances on many tasks, CNNs still face major obstacles on the road to achieving ideal machine intelligence. One is that CNNs are complex and hard to interpret. Another is that standard…
Convolutional neural networks (CNNs) achieve state-of-the-art performance in a wide variety of tasks in computer vision. However, interpreting CNNs still remains a challenge. This is mainly due to the large number of parameters in these networks. Here, we investigate the role of compression and particularly pruning fil…
Gradient Weighted Superpixels improve CNN interpretability without sacrificing speed.
problem Efficiency vs. interpretability trade-off in CNNs, especially for large input volumes.
method Gradient-based pixel scoring techniques applied to superpixels.
result Superpixels approximate LIME in a fraction of the time, improving interpretability.
New method makes CNN interpretations robust to adversarial attacks.
problem Adversarial attacks on CNN interpretation maps.
method Renyi Differential Privacy (RDP) for robust interpretation.
result Certifiable top- robustness and improved experimental robustness.
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…
New approximative kernels improve PDE-G-CNNs for geometric deep learning.
problem Inaccurate approximations of exact kernels in PDE-G-CNNs.
method Developed new approximative kernels that work regardless of spatial anisotropy.
result New kernels provide better error estimates and maintain reflectional symmetries.
Develops masks to explain neural network predictions.
problem Improving neural network interpretability for various applications.
method Creates explanation masks for pre-trained networks using a secondary network.
result Demonstrates the effectiveness of the method across different types of networks.
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.
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.
Convolutional Neural Networks for Text Categorization: Shallow Word-level vs. Deep Character-levelcs.CL
This paper reports the performances of shallow word-level convolutional neural networks (CNN), our earlier work (2015), on the eight datasets with relatively large training data that were used for testing the very deep character-level CNN in Conneau et al. (2016). Our findings are as follows. The shallow word-level CNN…
Proposes a new method for explaining deep CNNs used in MRI-based AD diagnosis.
problem Lack of transparency and interpretability in deep CNN models for AD diagnosis.
method Swap Test method designed specifically for brain scan task.
result Proposed method provides more suitable explanations for AD diagnosis using MRI.
DCENWCNet improves WBC classification with LIME-based explainability.
problem Classifying white blood cells from blood images with high accuracy and interpretability.
method Integrates three CNN architectures with different settings to balance feature learning and performance.
result Achieves highest mean accuracy on the Rabbin-WBC dataset, outperforming state-of-the-art networks.
GWNN uses graph wavelets for efficient graph CNNs.
problem Spectral graph CNNs' high computational cost and lack of interpretability.
method Graph wavelet transform for efficient graph convolution.
result GWNN significantly outperforms spectral graph CNNs.
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.
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.
One of the most crucial tasks in seismic reflection imaging is to identify the salt bodies with high precision. Traditionally, this is accomplished by visually picking the salt/sediment boundaries, which requires a great amount of manual work and may introduce systematic bias. With recent progress of deep learning algo…
Improves CNN stability by translating classical signal denoising methods.
problem Stability of CNNs is poorly understood.
method Interprets classical signal denoising methods as ResNet architectures.
result Translates diffusivities, shrinkage functions, and regularizers into CNN activation functions.
Convolutional neural networks have been successfully applied to various NLP tasks. However, it is not obvious whether they model different linguistic patterns such as negation, intensification, and clause compositionality to help the decision-making process. In this paper, we apply visualization techniques to observe h…
Proposes a new CNN for meshes that can handle orientation.
problem Isotropic kernels in graph convolutions are insensitive to mesh geometry.
method Introduces gauge equivariant kernels and geometric message passing.
result Significantly improved expressivity over conventional GCNs.
DoPa detects various physical adversarial attacks on CNNs.
problem Vulnerability of CNNs to physical adversarial attacks.
method Interprets CNN's vulnerability, adds self-verification stage.
result Achieves 90% success rate for image attacks and 92% for audio attacks.
Bayesian CNN estimates uncertainty in bone age prediction.
problem Uncertainty quantification in age estimation models.
method Variational Inference for Bayesian CNNs.
result Model uncertainty distinguished from data uncertainty.
Convolutional Neural Networks (CNNs) are propelling advances in a range of different computer vision tasks such as object detection and object segmentation. Their success has motivated research in applications of such models for medical image analysis. If CNN-based models are to be helpful in a medical context, they ne…
CNN-F uses generative feedback to improve neural networks' robustness to perturbations.
problem Neural networks' vulnerability to input perturbations like noise and attacks.
method Enforces self-consistency in neural networks by incorporating generative recurrent feedback.
result CNN-F shows significantly improved adversarial robustness compared to conventional CNNs.
Deep semantic gaze embedding and scanpath comparison for expertise classification during OPT viewingcs.LG
Novel CNN-based gaze scanpath comparison distinguishes experts from novices in dental radiograph interpretation.
problem Distinguishing expertise in dental radiograph interpretation based on gaze behavior.
method Convolutional neural networks (CNN) process scene information at the fixation level, using image patches as input to compare gaze scanpaths.
result 93% accuracy in distinguishing experts from novices using image patch features.
New CNN approach reduces overconfidence in object classification predictions.
problem Overconfident predictions from deep models, especially SoftMax layer.
method Introduces CNN probabilistic approach using Logit layer for Bayesian inference.
result Proposed approach shows promising performance compared to SoftMax.
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 present a unique 3D-CNN based Gradient-weighted Class Activation Mapping method (3D…
New adversarial attack method based on deep feature distributions.
problem Adversarial attacks on CNN classifiers using output layer information.
method Modeling and exploiting class-wise and layer-wise deep feature distributions.
result Achieves state-of-the-art transfer-based attack results for undefended ImageNet models.
Interpretable deep learning classifies two-prong jets using jet spectra.
problem Lack of interpretability in deep learning for jet classification.
method Truncated Taylor series jet spectrum for interpretability.
result Interpretable network performs similarly to CNN but is simpler.
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.
We develop a multi-task convolutional neural network (CNN) to classify multiple diagnoses from 12-lead electrocardiograms (ECGs) using a dataset comprised of over 40,000 ECGs, with labels derived from cardiologist clinical interpretations. Since many clinically important classes can occur in low frequencies, approaches…
A novel pruning method finds relevant units in CNNs for efficient compression.
problem Reduction of computation and storage costs in deep neural networks.
method Pruning by explaining, using relevance scores from explainable AI.
result The method efficiently compresses CNN models without sacrificing performance.
The paper introduces a method to explain redundancy in deep CNNs using unit impulse response.
problem Redundancy in deep CNNs leads to unnecessary computations and increased cost.
method Empirical demonstration and unit impulse response analysis to identify and quantify redundancy across layers and depth.
result Identifies and quantifies redundancy in deep CNNs, providing better insights into their internal dynamics.
Convolutional Neural Networks (CNN) outperform traditional classification methods in many domains. Recently these methods have gained attention in neuroscience and particularly in brain-computer interface (BCI) community. Here, we introduce a CNN optimized for classification of brain states from magnetoencephalographic…
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…
Deep CNN model improves breast cancer screening exam classification.
problem Improving accuracy in breast cancer screening exam classification.
method Localization-based deep CNN trained on 200,000 exams.
result AUC of 0.919 in predicting malignancy, reducing error rate by 23%.
A CNN-based model improves stock price prediction accuracy.
problem Overfitting in image-based stock prediction models.
method SMSFR-CNN combining CNN and image features.
result SMSFR-CNN achieves high predictive accuracy on A-share stocks.
Study finds CNNs perform better with financial ratio data than fundamental data.
problem Improving CNN performance with financial data.
method Developed and analyzed three image encoding methods for financial data.
result Image encoding methods improve CNN performance for financial ratio data but not significantly for fundamental data.
Previous models for learning entity and relationship embeddings of knowledge graphs such as TransE, TransH, and TransR aim to explore new links based on learned representations. However, these models interpret relationships as simple translations on entity embeddings. In this paper, we try to learn more complex connect…
Deep Kronecker Networkstat.ML
DKN adapts to medical imaging data with limited samples and interpretable models.
problem Medical imaging data's unique nature makes general methods like CNN unsuitable.
method DKN uses a Kronecker product structure to adapt to low sample size and provide interpretable models.
result DKN achieves prediction power comparable to CNN and provides model interpretability.
ScDCFNet improves multiscale image classification with reduced model size.
problem Improving performance in multiscale image classification.
method Decomposed convolutional filters for ST-equivariant CNNs.
result ScDCFNet achieves significantly improved performance in multiscale image classification.
Improves CNN robustness by reducing texture bias.
problem CNNs' reliance on local texture over global shape.
method Inspired by human vision, InfoDrop decorrelates model output from local texture.
result Enhanced robustness across various scenarios.
Proposes ConRad model for lung cancer classification using radiomics and interpretable machine learning.
problem Lack of interpretability in deep neural networks for cancer diagnosis.
method Integration of radiomics and DNN-predicted biomarkers in interpretable classifiers (ConRad).
result ConRad models outperform CNNs in five-fold cross-validation.