This paper shows how to use ℓ1 regularization effectively in training sparse CNNs.
problem Why ℓ1 regularization hasn't been used in sparse deep learning models like CNNs. method Demonstrated that SGD is not suitable for ℓ1 regularization and replaced it with a new training algorithm based on regularized dual averaging (RDA). result Achieved state-of-the-art sparsity for CNNs using RDA with ℓ1 regularization, achieving 95% sparsity for ResNet18 on CIFAR-10. Dual CNN for predicting links in graphs of graphs.
problem Link prediction in graphs of graphs.
method Dual Convolutional Neural Network (CNN) for combining external and internal graph structures.
result Effective link prediction on chemical network datasets.
In recent years, there has been a surge of interest in developing deep learning methods for non-Euclidean structured data such as graphs. In this paper, we propose Dual-Primal Graph CNN, a graph convolutional architecture that alternates convolution-like operations on the graph and its dual. Our approach allows to lear…
We propose a DTCWT ScatterNet Convolutional Neural Network (DTSCNN) formed by replacing the first few layers of a CNN network with a parametric log based DTCWT ScatterNet. The ScatterNet extracts edge based invariant representations that are used by the later layers of the CNN to learn high-level features. This improve…
This paper improves land cover classification using global spatial features in CNN.
problem Limited classification accuracy and universality of traditional remote sensing image classification methods.
method Integrates global spatial features into a dual-branch CNN for hyperspectral/SAR imagery classification.
result The proposed method outperforms traditional single-channel CNN methods.
Residual networks (ResNets) have recently achieved state-of-the-art on challenging computer vision tasks. We introduce Resnet in Resnet (RiR): a deep dual-stream architecture that generalizes ResNets and standard CNNs and is easily implemented with no computational overhead. RiR consistently improves performance over R…
CNN-Cert efficiently certifies robustness of CNNs, achieving significant speed-ups.
problem Verifying robustness of neural networks, especially convolutional neural networks, against adversarial perturbations.
method General and efficient framework that handles various architectures and activation functions, achieving up to 17 and 11 times speed-up compared to state-of-the-art algorithms.
result Achieves similar or better verification bounds compared to state-of-the-art algorithms while being significantly faster.
The paper addresses instability in CNNs' first layer by proving max pooling's shift invariance.
problem Instability in CNNs' first layer, leading to sensitivity to small input shifts.
method Establishing conditions for max pooling's shift invariance and deriving a measure of stability.
result Max pooling approximates a nearly shift-invariant complex modulus under certain conditions.
The MIMIC-CXR dataset is (to date) the largest released chest x-ray dataset consisting of 473,064 chest x-rays and 206,574 radiology reports collected from 63,478 patients. We present the results of training and evaluating a collection of deep convolutional neural networks on this dataset to recognize multiple common t…
Dual Student separates the teacher from the student in SSL, improving performance.
problem Performance bottleneck caused by coupled teacher in consistency-based SSL methods.
method Introduces Dual Student, replacing the teacher with another student and defining a stabilization constraint.
result Significant improvement in classification performance on SSL benchmarks.
New measures quantify dependence between variables without distribution estimation.
problem Measuring dependence between variables in arbitrary dimensions.
method Proposed matrix-based normalized total correlation and dual total correlation measures.
result Measures are differentiable and statistically more powerful than existing methods.
DeepIrisNet2 learns iris codes without iris segmentation or normalization.
problem Iris recognition under non-ideal conditions.
method Deep learning framework with spatial transformer layers and dual CNN segmentation.
result Significantly improves iris recognition performance.
V-CNN improves CNN performance in network intrusion detection.
problem Applying CNN directly to non-image data leads to poor performance.
method Integrates data visualization before CNN modeling.
result Significantly outperforms other studies in network intrusion detection.
Computer aided diagnostic (CAD) system is crucial for modern med-ical imaging. But almost all CAD systems operate on reconstructed images, which were optimized for radiologists. Computer vision can capture features that is subtle to human observers, so it is desirable to design a CAD system op-erating on the raw data. …
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.
CNNs improve medical image classification with few samples.
problem Classifying medical images with limited training data.
method Transfer learning using CNNs, representation extraction, and a novel metric for performance prediction.
result CNN-based transfer learning outperforms feature-based methods with high correlation to test set performance.
The surfaces of many cultural heritage objects were embellished with various patterns, especially curve patterns. In practice, most of the unearthed cultural heritage objects are highly fragmented, e.g., sherds of potteries or vessels, and each of them only shows a very small portion of the underlying full design, with…
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.
Paper learns an explainer to interpret CNN features without annotations.
problem Interpreting complex features in CNNs without labeled data.
method Unsupervised learning of an explainer to decompose and reconstruct feature maps.
result Explainer learns to reconstruct CNN features without losing information.
Paper uses CNNs to classify heart sounds from short segments.
problem Classifying heart sounds from short segments of individual beats.
method Developed a 1D-CNN and 2D-CNN ensemble for feature learning and score-level fusion.
result ECNN ensemble achieved 89.22% accuracy and 89.94% sensitivity on the PhysioNet CinC 2016 database.
Simplified Butterfly-Net2 improves CNN efficiency in solving PDEs and signal processing tasks.
problem Improving CNN efficiency in solving PDEs and signal processing tasks.
method Introducing BNet2, a simplified Butterfly-Net, and Fourier transform initialization.
result BNet2 achieves similar accuracy as CNN but with fewer parameters and improves accuracy over randomly initialized CNN.
Automates resource-efficient CNN design for IoT.
problem Designing custom CNNs for IoT applications is impractical and resource-intensive.
method Automated synthesis of resource scalable CNNs from an existing optimized baseline CNN.
result Synthesized CNNs are resource-efficient and competitive in accuracy.
Develops GIN for fMRI sex classification, explaining results.
problem Difficulty in explaining GNN classification results in neuroscientific terms.
method Develops Graph Isomorphism Network (GIN) for fMRI data, leveraging CNN saliency maps.
result GIN enables visualization of brain regions important for sex classification.
2D CNNs approximate Korobov functions with near-optimal rates.
problem Approximating Korobov functions using 2D CNNs.
method Constructive approach for 2D CNNs with ReLU activations and fully connected layers.
result 2D CNNs achieve near-optimal approximation rates for Korobov functions.
Proposes interpretable filters in CNNs for object classification.
problem Learning interpretable filters in deep CNNs without additional annotations.
method Assigns each filter in a CNN to an object part during training.
result Interpretable filters are more semantically meaningful than traditional filters.
New metrics differentiate effective OOD sets for training calibrated CNNs.
problem Vanilla CNNs struggle with out-of-distribution (OOD) samples.
method Developed metrics based on generalization errors of Augmented-CNN.
result Most protective OOD sets lead to better A-CNN performance.
In image classification, visual separability between different object categories is highly uneven, and some categories are more difficult to distinguish than others. Such difficult categories demand more dedicated classifiers. However, existing deep convolutional neural networks (CNN) are trained as flat N-way classifi…
Proposes a fixed smooth convolutional layer to reduce checkerboard artifacts in CNNs.
problem Checkerboard artifacts in CNNs during upsampling and strided convolution.
method Fixed convolutional layer with adjustable smoothness, applied to four CNNs and GANs.
result Significantly improves classification performance and image generation quality.
In this paper, we address the issue of how to enhance the generalization performance of convolutional neural networks (CNN) in the early learning stage for image classification. This is motivated by real-time applications that require the generalization performance of CNN to be satisfactory within limited training time…
TinyCNN accelerates CNN models on embedded FPGA with 15x speedup.
problem Limited memory on embedded FPGAs restricts CNN performance.
method Software and hardware design tool for FPGA resource-aware CNN accelerator.
result 3% accuracy loss with 15.75x speedup on image classification.
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.
Study improves CNNs for audio scene classification by restricting receptive fields and adding frequency awareness.
problem Improving CNNs for robust acoustic scene classification.
method Investigated different receptive field configurations for various CNN architectures and introduced Frequency Aware CNNs.
result Several well-performing submissions to DCASE 2019 Challenge were achieved.
Simple 1D-CNN network predicts electricity loads 36 hours ahead.
problem Forecasting electricity loads for future time periods.
method Used a one-dimensional CNN with parameter scanning to optimize kernel size, filters, and dense size.
result Good forecast quality achieved with basic CNN architectures.
Morph accelerates 3D CNNs for video recognition, reducing energy consumption and improving performance.
problem Efficiently accelerating 3D CNNs for video recognition is challenging due to their large memory footprint and higher dimensionality.
method Designing a flexible accelerator called Morph that adapts to different spatial and temporal tiling strategies, and codesigning a software infrastructure to control the hardware.
result Morph achieves up to 3.4x reduction in energy consumption and up to 5.1x improvement in performance/watt compared to a baseline 3D CNN accelerator.
Convolutional neural networks (CNN) have achieved state of the art performance on both classification and segmentation tasks. Applying CNNs to microscopy images is challenging due to the lack of datasets labeled at the single cell level. We extend the application of CNNs to microscopy image classification and segmentat…
MBS reduces CNN model size with minimal accuracy loss.
problem Reducing CNN model size while maintaining accuracy.
method Adaptive macroblock scaling based on effective flops.
result Significant model size reduction across various CNN architectures.
Improved robustness of 1D CNNs for heart arrhythmia classification.
problem Improving the robustness of 1D CNNs for classification tasks.
method Parameterization using Cayley transform and controllability Gramian for Lipschitz-bounded CNNs.
result Improved robustness of trained Lipschitz-bounded 1D CNNs for heart arrhythmia classification.
Efficient CNN for VQA achieves similar performance to standard models.
problem Computational intensity of standard VQA models.
method Proposes a sparsely activated CNN architecture.
result Sparsely activated CNN achieves comparable performance.
CNN-PCA method uses deep learning to parameterize complex geological models.
problem Representing complex geological models in a low-dimensional space.
method CNN-PCA method combines PCA and CNN to honor geological features.
result CNN-PCA provides high-quality realizations and history matching results.
Computer vision performances have been significantly improved in recent years by Convolutional Neural Networks(CNN). Currently, applications using CNN algorithms are deployed mainly on general purpose hardwares, such as CPUs, GPUs or FPGAs. However, power consumption, speed, accuracy, memory footprint, and die size sho…
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…
Study on CNNs' learning rates and approximation capacities.
problem Learning rates and approximation capacities of CNNs.
method New approximation bound and covering number analysis for CNNs.
result Derives minimax optimal convergence rates for CNNs in various learning problems.
Graph-CNN for 3D point cloud classification tackles non-regular graph topology.
problem Classifying 3D point cloud data with non-regular graph topology.
method Developed PointGCN combining localized graph convolutions and graph downsampling.
result Achieves competitive performance on 3D object classification benchmark ModelNet.
Paper introduces zero-space memory protection for CNNs without ECC overhead.
problem Ensuring reliability of CNNs in safety-critical applications.
method In-place zero-space ECC with weight distribution-oriented training.
result First known zero-space cost memory protection for CNNs.
New CNN layer selects important channels to improve model capacity.
problem Improving model capacity under resource constraints.
method Selective allocation of channels in convolutional layers.
result New layer allows new optima that generalize better.
Authors propose GRI-CNN systems for rotationally invariant processing.
problem Creating rotationally invariant CNN systems.
method Designed geared rotationally identical CNN systems (GRI-CNN) with a small step angle.
result GRI-CNN produces quantitatively identical output results under rotation.
CNNs solve inverse problems during training, proving mutual coherence crucial for convergence.
problem Validation of CNN learning during training.
method Proved CNN elements solve inverse problems, discussed mutual coherence, and set training rules.
result Mutual coherence is necessary for CNNs to converge to optimum solutions.
iSTFTNet2 improves iSTFTNet's speed and lightness with 1D-2D CNN.
problem Efficiently synthesizing high-fidelity speech.
method Improved iSTFTNet using 1D-2D CNNs for temporal and spectrogram structures.
result iSTFTNet2 is faster and more lightweight with comparable speech quality.