Paper classifies lung nodules in CT scans, improving diagnostic accuracy.
problem Early detection of lung nodules for better treatment planning.
method Proposes four 3D neural networks for direct mapping from 3D images to class labels.
result 3D multi-output DenseNet achieves state-of-the-art classification accuracy.
RADNET achieves radiologist-level accuracy in CT scan hemorrhage detection.
problem Automated detection of brain hemorrhages in CT scans.
method RADNET uses a 3D context-aware deep learning model with attention mechanisms.
result RADNET achieves 81.82% accuracy in hemorrhage prediction, comparable to radiologists.
MPSA-DenseNet improves accent classification accuracy.
problem Accurate English accent identification.
method Combines multi-task learning and PSA attention mechanism with DenseNet.
result MPSA-DenseNet outperforms other models in accent classification.
Invertible DenseNets improve model efficiency and performance.
problem Improving model efficiency and performance in neural networks.
method Enforcing invertibility in DenseNets by satisfying the Lipschitz constraint and proposing a learnable concatenation.
result i-DenseNets outperform Residual Flows in negative log-likelihood on various datasets.
Dilated DenseNets excel at relational reasoning without additional modules.
problem Deep neural networks struggle with relational reasoning.
method Dilated DenseNet architecture incorporating dilated convolutions.
result Dilated DenseNets surpass relational reasoning on Sort-of-CLEVR without additional modules.
i-DenseNets improve parameter efficiency and performance in density estimation.
problem Improving parameter efficiency and performance in density estimation models.
method Invertible Dense Networks (i-DenseNets) with learnable weighted concatenation and Concatenated LipSwish activation function.
result i-DenseNets outperform Residual Flows and other flow-based models in bits per dimension.
ResNets and DenseNets converge to NTK with depth and width, offering advantages for kernel regression.
problem Understanding convergence of ResNets and DenseNets to Neural Tangent Kernel (NTK).
method Analysis of finite width and depth corrections for NTK of ResNets and DenseNets.
result ResNets and DenseNets can converge to NTK with depth and width, unlike vanilla networks.
Enhances DenseNets with multi-scale convolutions and stochastic feature reuse.
problem Overfitting in DenseNets with dense feature reuse.
method Multi-scale Convolution Aggregation module and Stochastic Feature Reuse.
result Significant improvement in model accuracy with fewer parameters.
New metric reveals how topology affects deep network performance.
problem Understanding how topology influences deep network performance.
method Introduced NN-Mass metric to quantify gradient propagation and model performance.
result NN-Mass identifies models with similar accuracy but different sizes/compute requirements.
A DenseNet model classifies metastatic cancer in medical images.
problem Classifying metastatic cancer in medical images efficiently and accurately.
method Proposes a DenseNet-based model for metastatic cancer classification on medical images.
result The proposed model outperformed other classical methods like Resnet34, Vgg19.
DenseNets improve accuracy and efficiency in convolutional networks.
problem Improving accuracy and efficiency in deep convolutional networks.
method Introducing Dense Convolutional Networks (DenseNet) with direct connections between all layers.
result DenseNets achieve significant improvements over state-of-the-art networks on object recognition benchmarks.
Novel graph theory for neural networks improves understanding of their structure and performance.
problem Understanding the structural benefits and generalization power of neural networks.
method Developed a novel graph theoretical formulation and extended error analysis for neural networks.
result Similar a priori estimates can be obtained for neural networks under certain conditions, independent of input dimension.
End-to-end image super-resolution using Attention-based DenseNet with residual deconvolution.
problem Challenging task of improving low-resolution images.
method Proposes a novel ADRD model with weighted dense blocks and spatial attention modules.
result Demonstrates promising performance on publicly available datasets.
Deep learning models outperform dermatologists in skin cancer classification.
problem Skin cancer classification using dermoscopy images.
method Different pre-trained deep learning architectures (DenseNet 201, ResNet 152, Inception v3, InceptionResNet v2) applied on dermoscopy images.
result DenseNet 201 achieved highest AUC values for melanoma and basal cell carcinoma.
New defense DMP preserves ML model utility while enhancing membership privacy.
problem Membership inference attacks (MIAs) on machine learning models.
method Knowledge distillation to train ML models with membership privacy.
result DMP provides significantly better tradeoffs between membership privacy and classification accuracies.
Transform classical network structures to graph CNN for better graph recognition.
problem Transforming classical network structures to graph CNN for better graph recognition.
method Review and introduce ResNet, Inception, and DenseNet into graph CNN, constructing G_ResNet, G_Inception, G_DenseNet.
result Demonstrated how different network structures work on graph CNN in the graph recognition task.
A new neural network architecture reduces parameters and improves performance.
problem Reducing model complexity and improving performance in neural networks.
method Coupled ensembles of neural networks with parallel branches and tighter coupling.
result Significant performance improvements with reduced parameter count.
Study compares handcrafted and deep neural network features for OCT image classification.
problem Classifying OCT images for disease detection.
method Comparison of Histogram of Oriented Gradient (HOG), Local Binary Pattern (LBP), DenseNet-169, and ResNet50.
result Deep neural network methods outperform handcrafted features with higher accuracy and better underrepresented class performance.
This paper analyzes CNNs for malware detection in cloud IaaS.
problem Malware vulnerability in cloud IaaS environments.
method Analysis of Convolutional Neural Networks (CNNs) for online malware detection using process-level performance metrics.
result State-of-the-art DenseNets and ResNets effectively detect malware in online cloud systems.
Structured pruning yields inferior results compared to training from scratch.
problem Efficacy of structured pruning in neural network compression.
method Alternating pruning and fine-tuning of large networks, comparing to training from scratch.
result Reduced networks trained from scratch outperform pruned networks.
Improved ResNets and DenseNets models for better feature reuse.
problem Diminishing feature reuse in ResNets and DenseNets.
method ResNEsts and DenseNEsts are block-based DNN models with improved representation guarantees.
result Wide ResNEsts with bottleneck blocks can guarantee desirable training properties.
RDL-Net improves speech enhancement with fewer parameters and better performance.
problem Improving speech enhancement with fewer parameters and better performance.
method Proposes RDL-Net, a CNN combining residual and dense aggregations without over-allocating parameters.
result RDL-Net achieves higher speech enhancement performance with fewer parameters and lower computational requirements.
Skip connections make adversarial examples more transferable in ResNets.
problem Transferability of adversarial examples in ResNets with skip connections.
method Skip Gradient Method (SGM) to craft more transferable adversarial examples.
result SGM improves transferability of adversarial examples in various DNNs.
We study knots in 3d Chern-Simons theory with complex gauge group SL(N,C), in the context of its relation with 3d N=2 theory (the so-called 3d-3d correspondence). The defect has either co-dimension 2 or co-dimension 4 inside the 6d (2,0) theory, which is compactified on a 3-manifold M^. …
Study of 3d-3d correspondence involving q-Weyl algebra and 3d-index.
problem Understanding the action of a q-Weyl algebra on the 3d-index of knots. method Investigation of the q-Weyl algebra's module action on the 3d-index, conjecturing structural properties. result Bilinear factorization, pair of linear q-difference equations, and rational function matrix for the 3d-index determination. 3D Adversarial Autoencoder learns compact binary descriptors from 3D point clouds.
problem Learning meaningful representations of 3D shapes for various tasks.
method End-to-end Adversarial Autoencoder model trained on 3D input and output.
result 3D Adversarial Autoencoder (3dAAE) generates state-of-the-art results for 3D points clustering and retrieval.
New system defends deep neural networks like ResNet-34.
problem Training deep neural networks like ResNet-34 is challenging.
method Differentiable abstract interpretation and a DSL for training objectives.
result Can defend significantly larger networks than before.
Flexible pipeline for 3D vehicle detection from 2D images.
problem Current methods lack 3D perception of vehicles and other objects.
method Adopt any 2D detection network, fuse with 3D point cloud, develop model fitting algorithm, refine with CNN.
result 3D detection results rank second among algorithms, demonstrating competencies.
Improved deep CNNs for ASC by optimizing receptive field size.
problem Deep CNNs perform poorly in ASC compared to simpler models.
method Analyzed and adapted the receptive field of ResNet and DenseNet.
result State-of-the-art performance achieved with optimized receptive field.
3D dual field theories for Virasoro minimal models constructed using Seifert fiber spaces.
problem Constructing 3D dual field theories for Virasoro minimal models.
method 3D-3D correspondence and Seifert fiber spaces.
result 3D dual field theories constructed for Virasoro minimal models.
3D flying wings created for any angle asymptotic cones.
problem Creating 3D steady gradient Ricci solitons with any angle asymptotic cones.
method Constructing 3D flying wings for any angle asymptotic cones.
result 3D flying wings constructed for any angle asymptotic cones.
Proposes a new effective central charge for 3d N=2 theories.
problem Understanding the effective central charge in 3d N=2 theories.
method Analyzes the superconformal index to propose a new quantity and discusses its properties and computation.
result Proposes a new effective central charge for 3d N=2 theories.
3D-CNN method visualizes localized geometric features for manufacturability analysis.
problem Interpreting 3D-CNN decisions for complex geometries.
method 3D-CNN with surface normals, 3D-GradCAM for feature visualization.
result Identifies critical local features for manufacturability.
Smooth 3D flows from non-smooth starting points.
problem Creating smooth Ricci flows from non-smooth initial conditions.
method Generalized singular Ricci flow applied to 3D complete manifolds.
result Existence of smooth Ricci flows starting from non-smooth initial conditions.
3D Axial-Attention improves lung nodule classification accuracy.
problem Limited 3D attention in existing methods.
method Proposes 3D Axial-Attention network with 3D positional encoding.
result 3D Axial-Attention achieves state-of-the-art performance.
The paper tackles mapping tori by proposing a new approach to 3d-3d correspondence.
problem No existing approach fully describes 3d N=2 SCFTs for all types of 3-manifolds. method Systematic study of 3d N=2 gauge theories with non-linear matter fields. result Recovery of 3-manifold invariants from T[M3] indices and proposal of new q-series invariants. Novel method REACH-3D reconstructs 3D chromatin structure from HiC data.
problem Understanding the 3D structure of the genome and its temporal behavior.
method Autoencoders with recurrent neural units for manifold learning.
result REACH-3D outperforms existing methods in reconstructing chromatin structure and dynamics.
DreamFusion uses text-to-image diffusion models to create 3D images efficiently.
problem Lack of large-scale 3D datasets and efficient architectures for 3D synthesis.
method Adapting a 2D diffusion model to 3D synthesis using a loss based on probability density distillation.
result A 3D model can be optimized from a 2D diffusion model, allowing for text-to-3D synthesis.
3D steady gradient Ricci solitons are all O(2)-symmetric.
problem Characterizing 3D steady gradient Ricci solitons.
method Analyzing asymptotic behavior and using O(2) symmetry.
result All 3D steady gradient Ricci solitons are O(2)-symmetric.
Proposes a new layer for efficient 3D shape discrimination.
problem Irregular structure and redundancy in 3D point clouds hinder efficient inter-class discrimination.
method Integrates Blended Convolution and Synthesis layer that projects and synthesizes 3D point clouds, followed by 3D convolution in the unit ball.
result End-to-end architecture achieves compelling results on 3D shape recognition and retrieval.
LOCO-Reg improves CNN accuracy by promoting feature cohesion near filter centers.
problem Current regularization schemes in CNNs violate the principle that weights near the center of a filter are larger than weights on the outside.
method Introduces Locality-Promoting Regularization (LOCO-Reg) to correct this issue.
result LOCO-Reg yields accuracy gains across multiple architectures and datasets.
Improved 3D scene understanding from partial point sets using multiview fusion.
problem Challenging task of 3D scene semantic understanding from partial point clouds.
method Multiview representation of 360° point clouds and fusion with original data.
result Overall increase of 31.9% and 4.3% in segmentation accuracy for partial and complete scenes.
The early layers of a deep neural net have the fewest parameters, but take up the most computation. In this extended abstract, we propose to only train the hidden layers for a set portion of the training run, freezing them out one-by-one and excluding them from the backward pass. Through experiments on CIFAR, we empiri…
DepthNets learns 3D face geometry and transformations without supervision.
problem Learning 3D face geometry and transformations from a single image.
method Unsupervised learning of facial keypoints depth, using backpropable loss for 3D transformations.
result DepthNets can predict 3D transformations and re-target faces to new poses or geometries.
Generative model disentangles 3D shapes into independent factors.
problem Learning rich representations of deformable 3D shapes.
method Supervised 3D mesh-convolutional Variational AutoEncoder with latent feature disentanglement.
result Explicit disentanglement of latent factors improves shape generation and downstream tasks.
3D point cloud attacks examine how neural networks can be fooled.
problem Understanding how 3D neural networks can be exploited by attackers.
method Examined two categories of attacks: distributional and shape attacks.
result Some shape attacks can fool 3D point cloud classification models even after preprocessing.
Graph Neural Networks improve 3D object detection in LiDAR point clouds.
problem Challenges in processing LiDAR data due to its 3D geometry and massive volume.
method Proposes a Graph Neural Network (GNN) based framework for 3D object detection.
result GNNs successfully identify objects in 3D LiDAR point clouds.
End-to-end CAD system for thyroid nodule classification using multimodal data and expert guidance.
problem Improving accuracy in thyroid nodule classification for clinicians.
method Knowledge-driven DenseNet framework using multimodal ultrasound data and expert cues.
result The proposed system achieves relevant performances in thyroid nodule classification.