Integrates competitive learning into CNNs to enhance representation and speed up fine-tuning.
problem Efficient use of unlabeled data for CNNs' fine-tuning.
method Integrates unsupervised competitive learning into the convolutional layer of CNNs.
result Effective representation learning using unlabeled data, accelerated fine-tuning process.
Reduces annotation costs in medical imaging by 50%.
problem Challenges in creating large annotated datasets for medical imaging.
method Integrates active learning and transfer learning into a single framework.
result Reduces annotation efforts by at least half.
Paper presents an unsupervised method for object recognition using pretrained CNN and associative memory.
problem Fine-tuning pretrained CNN models for new domains is time-consuming and requires labeled data.
method Uses a pretrained CNN for feature extraction and a Hopfield network associative memory bank for classification.
result Eliminates the need for backpropagation and achieves competitive performance on unseen datasets.
Self-supervised fine-tuning corrects SR CNNs for unseen models and artifacts.
problem SR CNNs' lack of robustness to unseen image formation models and generation of artifacts.
method Iterative fine-tuning using a data fidelity loss at test time.
result Successfully corrects SR solutions for unseen models and GAN artifacts.
In this paper we describe our attempt at producing a state-of-the-art Twitter sentiment classifier using Convolutional Neural Networks (CNNs) and Long Short Term Memory (LSTMs) networks. Our system leverages a large amount of unlabeled data to pre-train word embeddings. We then use a subset of the unlabeled data to fin…
SimCLR pre-training improves CNN performance with fewer labels.
problem Learning with fewer labeled data.
method SimCLR contrastive learning method combined with supervised fine-tuning.
result SimCLR pre-training with supervised fine-tuning achieves almost optimal test loss with fewer labeled data.
New CNN learns depth features from scratch, outperforming transfer learning.
problem Limited depth data for RGB-D scene recognition.
method Bottom-up approach combining local weakly supervised training and global fine-tuning, modified CNN architecture.
result State-of-the-art accuracy on NYU2 and SUN RGB-D datasets.
RIFLE improves deep transfer learning by reinitializing fully-connected layers.
problem Limited improvement in transfer learning accuracy with pre-trained models on small datasets.
method Re-Initializing fully-connected layers with random scratch during fine-tuning.
result Significant improvement in deep transfer learning accuracy across various datasets.
Study shows variability in CNN predictions for medical images, suggesting ensemble averaging to reduce it.
problem Variability in CNN predictions for medical images due to data ordering during training.
method Reproduced CheXNet results with random seeds to identify variability in predictions.
result Averaging predictions from multiple models reduces variability by nearly 70%.
Improved patent classification using fine-tuned BERT model.
problem Classifying large patent datasets efficiently and accurately.
method Fine-tuning a pre-trained BERT model on patent claims.
result Outperforms state-of-the-art methods by 20%.
PTU learns fine-grained parameter transfer for deep networks.
problem Discrete transfer states and lack of principled approach to learn transfer strategies.
method PTU learns a fine-grained nonlinear combination of activations from source and target networks using two gates.
result PTU outperforms heuristic methods in most settings.
Simplified trust region method reduces representation change during fine-tuning.
problem Stability and representational collapse in fine-tuning pre-trained models.
method Replaces adversarial objectives with parametric noise in trust region theory.
result Matches or exceeds previous trust region methods in performance and speed.
HOTCAKE compresses CNNs by decomposing kernels into smaller parts.
problem Compressing deep CNNs without significant accuracy loss.
method Input channel decomposition, guided Tucker rank selection, higher order Tucker decomposition, fine-tuning.
result HOTCAKE produces highly compressed CNN models with good accuracy.
A new method to compress CNNs without changing architectures.
problem Redundancy in CNN filter weights.
method Replacing filters with a fixed set and a learnable 1D layer.
result Significant reduction in parameters and operations with minimal performance loss.
A CNN-based approach tackles malware image classification imbalance.
problem Imbalance in malware families during image classification.
method Proposes a weighted softmax loss to address imbalance.
result Improves classification performance on malware images.
FixyNN splits CNN models into fixed and trainable parts for efficient on-device inference.
problem Energy inefficiency in on-device CNN inference for real-time computer vision.
method Co-designed hardware accelerator platform with transfer learning for training.
result Achieved nearly 2x better energy efficiency than a conventional accelerator.
Early diagnosis, playing an important role in preventing progress and treating the Alzheimer\{'}s disease (AD), is based on classification of features extracted from brain images. The features have to accurately capture main AD-related variations of anatomical brain structures, such as, e.g., ventricles size, hippocamp…
Early diagnosis, playing an important role in preventing progress and treating the Alzheimer's disease (AD), is based on classification of features extracted from brain images. The features have to accurately capture main AD-related variations of anatomical brain structures, such as, e.g., ventricles size, hippocampus …
Improved speech translation model using cleaned data and ensemble decoding.
problem End-to-end speech translation from English to German.
method Fine-tuning on cleaned data, weight normalization, label smoothing, checkpoint averaging, ensemble decoding.
result Ensemble model achieved a BLEU score of 10.24 on test data.
Two KG-based methods explain transfer learning in CNN and ZSL.
problem Uninterpretable transfer learning for non-ML experts.
method Knowledge Graph-based explanation for transferability and model justification.
result Rich, human-understandable explanations for transfer learning.
New method constrains CNN filter frequencies to improve robustness.
problem CNN bias towards low frequency components, leading to poor performance in scenario transformations.
method Frequency domain regularization by constraining filter spectra, training valid frequency range end-to-end.
result Demonstrated effectiveness in defending adversarial perturbations, reducing generalization gap, and improving transfer learning.
Model projection transfers convolutional network properties to feedforward networks.
problem Transferring properties between feedforward and convolutional networks.
method Unified node-level framework with tensor-valued activations, model projection.
result Projected CNN nodes inherit GFFN-style trainable structure.
New method uses eigenspectrum to optimize object detector architectures.
problem Understanding the effects of ImageNet pre-training on object detectors.
method Analysis of eigenspectrum dynamics of feature maps in object detectors.
result Object detectors trained from scratch and ImageNet pre-trained models behave differently.
New CNN architecture detects face spoofing with deep local features.
problem Face recognition systems are vulnerable to face spoofing attacks.
method Two-step CNN architecture: first learns features from facial regions, then fine-tunes on whole images.
result Improves face spoofing detection performance and convergence speed.
When building a unified vision system or gradually adding new capabilities to a system, the usual assumption is that training data for all tasks is always available. However, as the number of tasks grows, storing and retraining on such data becomes infeasible. A new problem arises where we add new capabilities to a Con…
Tree-CNN adapts to new data by growing hierarchically.
problem Incremental learning for evolving datasets.
method Hierarchical deep convolutional neural network.
result Significant reduction in training effort with competitive accuracy.
Paper proposes CNN-based time series anomaly detection with transfer learning.
problem Time series anomaly detection in automated monitoring systems.
method CNN for segmentation, transfer learning framework, fine-tuning on unseen classes.
result Successfully tested on multiple synthetic and real data sets.
Alternative neural network training using monotone variational inequality.
problem Training neural networks efficiently and with guarantees.
method Using monotone variational inequality to solve non-convex problems efficiently.
result Our approach leads to fast convergence and competitive performance compared to traditional methods.
Transfer learning improves TSC models by 71 out of 85 datasets.
problem Improving deep CNNs for TSC using transfer learning.
method Pre-trained deep CNNs fine-tuned on various UCR datasets.
result Transfer learning can improve or degrade TSC model predictions.
FC-AIDE improves image denoising with a fully convolutional neural network.
problem Improving image denoising performance with neural networks.
method Fully convolutional neural network with adaptive fine-tuning.
result FC-AIDE outperforms state-of-the-art denoisers on benchmark datasets.
CNN accurately reconstructs lattice topology with strong thermal fluctuations.
problem Reconstructing lattice topology with strong thermal fluctuations and unbalanced data.
method Deep convolutional neural network (CNN) mapping local magnetic moments to coupling probabilities.
result CNN accurately reconstructs lattice topology where thermal fluctuations dominate.
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.
This paper proposes a method to compress and adapt CNNs for real-world applications.
problem Differences in data distributions and high computational costs limit CNN adoption.
method Joint optimization of CNNs for unsupervised domain adaptation and knowledge distillation.
result The proposed method achieves the highest accuracy with comparable or lower time complexity.
CNNs estimate poverty from satellite images, explaining 47% of variation in Mexico.
problem Mapping poverty in developing countries.
method Convolutional Neural Networks trained on high and medium resolution satellite images.
result CNNs explain 47% of poverty variation in Mexico's municipalities.
Transfer learning improves image classifier performance in data-starved regimes.
problem Deploying image classifiers in domains with limited labeled data.
method Transfer learning with deep neural networks, focusing on feature reuse and overparameterization.
result Transfer learning enhances CNN performance in data-starved regimes.
CNN improves stock price prediction accuracy.
problem Predicting future stock price movements.
method Hybrid approach combining machine learning and CNN.
result CNN-based model outperforms other models.
CNN predicts stock fluctuations using company news headlines.
problem Predicting next-day stock fluctuations based on company-specific news.
method Convolutional Neural Network (CNN) with reduced filter dimensions and multiple hidden layers. Fine-tuned word embeddings and various filter widths.
result 61.7% classification accuracy achieved using pre-learned embeddings.
Cost-effective training of deep CNNs with active model adaptation.
problem Challenges in training deep CNNs for specific tasks.
method Active model adaptation of a pre-trained model with selective fine-tuning of examples.
result Significant reduction in labeling cost with improved model performance.
Early diagnosis of interstitial lung diseases is crucial for their treatment, but even experienced physicians find it difficult, as their clinical manifestations are similar. In order to assist with the diagnosis, computer-aided diagnosis (CAD) systems have been developed. These commonly rely on a fixed scale classifie…
Emotion being a subjective thing, leveraging knowledge and science behind labeled data and extracting the components that constitute it, has been a challenging problem in the industry for many years. With the evolution of deep learning in computer vision, emotion recognition has become a widely-tackled research problem…
Proposes a FoE prior for improving CNN performance in distribution shifts.
problem Improving CNN performance in image analysis tasks with distribution shifts.
method Uses a field-of-experts (FoE) prior to match feature distributions of test and training images.
result Outperforms previous TTA methods in lesion segmentation and most healthy tissue segmentation tasks.
Deep learning identifies unique walking patterns from pressure data.
problem Tackling the challenge of accurately identifying individuals based on their walking style.
method Used deep learning, specifically convolutional neural networks (CNNs), to analyze the center-of-pressure trajectory of 36 adults walking on a treadmill.
result CNNs achieved 99.9% accuracy in classifying 2,250 segments and 100% accuracy in fine-tuning a subset of 4,500 segments, suggesting unique pressure patterns for each person.
A genetic algorithm-based method prunes deep neural networks for resource-constrained devices.
problem Resource constraints in deploying deep neural networks on embedded devices.
method Genetic algorithm for channel pruning of deep CNNs.
result Significant reduction in model size with minimal accuracy loss.
U-CNNpred improves stock market prediction by extracting general market patterns.
problem Improving financial market prediction through better feature extraction.
method A CNN-based framework trained on diverse historical data to identify common market patterns.
result U-CNNpred outperforms baseline algorithms in predicting market directional movements.
Proposes a deep learning churn prediction system for telecom using TL and meta-classification.
problem Churn prediction challenges in telecom due to large data, high dimensions, and imbalanced data.
method Transfer Learning (TL) and Ensemble-based Meta-Classification. Two stages: TL on Deep CNNs, then GP-AdaBoost meta-classifier.
result TL-DeepE system achieved 75.4% and 68.2% prediction accuracy on Orange and Cell2cell datasets, respectively.
The paper fine-tunes language models using human preferences for natural language tasks.
problem Applying reinforcement learning to natural language tasks with human-defined rewards.
method Fine-tuning language models using reward learning techniques, leveraging generative pretraining.
result The approach achieves good results in natural language tasks like text continuation and summarization.
Hybrid model predicts stock prices with high accuracy.
problem Complex volatility of stock market makes traditional models unsatisfactory.
method Attention-based CNN-LSTM and XGBoost integrated model.
result Hybrid model improves prediction accuracy.
Improved 3D MRI classification using contrastive learning with continuous proxy metadata.
problem Insufficient labelled data for 3D medical image classification.
method Proposed a new loss function (y-Aware InfoNCE) to leverage continuous proxy metadata in contrastive learning.
result 3D CNN model pre-trained on 10^4 multi-site healthy brain MRI scans outperforms fully-supervised methods.