New approach to modulation recognition using unsupervised learning.
problem Challenges in modulation recognition as a classification problem.
method Introducing new features, a new loss function, and investigating robustness.
result Improved robustness of modulation recognition pipeline.
Study shows stress affects emotion recognition models, improving generalizability.
problem Stress affects emotion recognition models, reducing their generalizability.
method Used adversarial networks to control for stress effects on emotion recognition.
result Emotion recognition models that control for stress during training have better generalizability.
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 paper shows how continuous attention can lead to better object representations.
problem Learning good representations from data without labeled examples.
method Integrating unsupervised learning and reinforcement learning with intrinsic motivation.
result The proposed algorithm improves object recognition in few-shot settings.
Scaling model capacity has been vital in the success of deep learning. For a typical network, necessary compute resources and training time grow dramatically with model size. Conditional computation is a promising way to increase the number of parameters with a relatively small increase in resources. We propose a train…
Framework tracks and predicts multiple objects in autonomous driving.
problem Challenges in multi-target tracking due to object number fluctuation and occlusion.
method Constrained mixture sequential Monte Carlo (CMSMC) method with a mixture representation.
result Framework can track and predict multiple objects simultaneously without explicit data association.
Improved recurrent neural networks learn long-term dependencies through multi-scale memory.
problem Capturing long-term dependencies in recurrent neural networks.
method Incremental training of a modular RNN architecture with multi-scale hidden states.
result Incremental training and multi-scale memory enhance RNNs' ability to learn long-term dependencies.
GTI network learns linguistic features for multi-task sequence tagging.
problem Improving neural model performance on multi-task sequence tagging without explicit features.
method GTI network with neural gate modules to learn relations between tasks.
result GTI network outperforms baselines on chunking and NER tasks.
Recently, there has been growing interest in multi-speaker speech recognition, where the utterances of multiple speakers are recognized from their mixture. Promising techniques have been proposed for this task, but earlier works have required additional training data such as isolated source signals or senone alignments…
Improved multi-user VoiceFilter-Lite model for speech recognition.
problem Limited performance of multi-user VoiceFilter-Lite models.
method Dual learning rate schedule and FiLM for feature conditioning.
result Closed the performance gap between multi-user and single-user VoiceFilter-Lite models.
Proposes a defense method against multiple adversarial video types.
problem Lack of multi-perturbation robustness in existing defense approaches.
method Adversarial training with multiple independent BN layers and a BN selection module.
result Demonstrates stronger multi-perturbation robustness against different adversarial video types.
GraphShield uses dynamic graph learning to detect and visualize financial risks.
problem Detecting and mitigating risks in financial networks.
method Enhanced Cross-Domain Information Learning, Advanced Risk Recognition, Risk Propagation Visualization.
result GraphShield effectively identifies and visualizes hidden financial risks.
System predicts vehicle interactions and trajectories with uncertainty.
problem Predicting future vehicle trajectories with uncertainty.
method Hierarchical Bayesian Generative Modeling with categorized and real-valued coordination variables.
result Categorized coordination better captures multi-modality and generates more diverse samples.
Detect knots from photos using machine learning and traditional algorithms.
problem Automatically recognize knots from images.
method Combining CNN and transformer architectures for image recognition with traditional knot invariants.
result Lightweight machine learning models can recover meaningful structural information from images.
Framework for handling long-tailed multi-modal data.
problem Class imbalance and long-tailed distributions in multi-modal data.
method Multi-expert architecture with modality-specific networks and dynamic fusion weights.
result Framework outperforms existing methods in long-tailed, class-imbalanced scenarios.
In this work, we investigate the value of employing deep learning for the task of wireless signal modulation recognition. Recently in [1], a framework has been introduced by generating a dataset using GNU radio that mimics the imperfections in a real wireless channel, and uses 10 different modulation types. Further, a …
Paper proposes a predictive maintenance system for solar plants using big data.
problem Fault prediction in photovoltaic plants to reduce downtime and maintenance costs.
method Data-driven approach with unsupervised clustering and Pattern Recognition Neural Network.
result Effective prediction of both generic and specific faults, up to 7 days in advance.
Attention-based encoder decoder network uses a left-to-right beam search algorithm in the inference step. The current beam search expands hypotheses and traverses the expanded hypotheses at the next time step. This traversal is implemented using a for-loop program in general, and it leads to speed down of the recogniti…
CSML learns causal structures for few-shot learning.
problem Spurious correlations limit deep learning generalization.
method CSML combines perception, causal induction, and reasoning modules.
result CSML achieves superior few-shot learning across tasks.
Paper closes neural-symbolic learning loop with grammar model and back-search algorithm.
problem Slow convergence in neural-symbolic learning due to error propagation issues.
method Introduces grammar model as symbolic prior and back-search algorithm for efficient error propagation.
result Significantly outperforms RL methods in performance, converging speed, and data efficiency.
Smart devices of everyday use (such as smartphones and wearables) are increasingly integrated with sensors that provide immense amounts of information about a person's daily life such as behavior and context. The automatic and unobtrusive sensing of behavioral context can help develop solutions for assisted living, fit…
Deep learning improves automatic modulation classification from subsampled data.
problem Automatic recognition of wireless communication signal modulations from imperfect data.
method Developed and tested Convolutional Long Short-term Deep Neural Network (CLDNN), LSTM, and ResNet architectures.
result Achieved high classification accuracy (around 90%) at high SNR with minimal training data.
SA-GAN improves HAR model performance across new users.
problem Poor performance of HAR models on new user data.
method Generative Adversarial Network (GAN) for cross-subject transfer learning.
result SA-GAN outperformed other methods in HAR tasks.
New networks interpret kernel decompositions for signal analysis.
problem Mode decomposition in signal analysis.
method Programmable and interpretable regression networks using kernels and data.
result Near machine precision recovery of signal modes under regularity and separation assumptions.
New method improves object detection models for long-tailed datasets.
problem Classifier imbalance in long-tail object detection datasets.
method Balanced Group Softmax (BAGS) module for balanced training of classifiers.
result Significantly improves performance of object detection models.
Patch ranking improves CNN performance by focusing on object content, not location.
problem CNNs lack rotation and translation invariance, limiting model capacity.
method Patch ranking before convolution and pooling to encode invariance.
result Patch ranking module improves CNN performance on various tasks.
Recent successes and advances in Deep Neural Networks (DNN) in machine vision and Natural Language Processing (NLP) have motivated their use in traditional signal processing and communications systems. In this paper, we present results of such applications to the problem of automatic modulation recognition. Variations …
We propose a novel method, Modality-based Redundancy Reduction Fusion (MRRF), for understanding and modulating the relative contribution of each modality in multimodal inference tasks. This is achieved by obtaining an (M+1)-way tensor to consider the high-order relationships between M modalities and the output laye…
XceptionTime improves hand gesture recognition accuracy using novel deep learning.
problem Improving hand gesture recognition from sparse sEMG signals.
method Depthwise separable convolutions, adaptive pooling, non-linear normalization.
result Significantly improved accuracy (5.71% improvement) in hand gesture recognition.
Proposes a new method to improve target annotation in ATR.
problem Challenges in annotating automatic target recognition due to lack of labeled data.
method Hybrid contrastive learning and cycle-consistency-based transductive transfer learning (C3TTL) framework.
result Significantly lower Fréchet Inception Distance (FID) score and improved performance in annotating civilian and military vehicles, as well as ship targets.
Improved robustness in ASR systems with speaker adaptation.
problem Improving robustness in automatic speech recognition systems.
method Weighted-Simple-Add method for adding weighted speaker information vectors to the conformer-based acoustic model.
result Achieved 11% relative improvement in WER on Switchboard 300h Hub5'00 dataset.
This paper proposes a new approach to Transformers by integrating hierarchical associative memory with MetaFormers.
problem Theoretical framework for Transformers and MLP-Mixers remains underdeveloped.
method Integrating hierarchical associative memory with MetaFormers to create a parallelized MLP-Mixer.
result Symmetry-breaking effects improve the performance of the MLP-Mixer in image recognition tasks.
New approach tackles open compound domain adaptation without clear domain labels.
problem Adapting models to new, mixed domains without domain labels.
method Curriculum domain adaptation strategy and memory module.
result Demonstrated effectiveness on various tasks.
Deep neural network learns robust acoustic models from speech waveforms.
problem Robustness in speech recognition systems using standard feature extraction techniques.
method Deep convolutional neural network with stochastic variational inference and cosine modulated filters.
result Superior performance compared to baseline waveform-based models and deep CNNs with FBANK features.
Deep learning model classifies concurrent human interactions from WiFi data with high accuracy.
problem Classifying concurrent human interactions from WiFi data with high accuracy.
method Attention-BiGRU deep learning model using Multiple Input Multiple Output radio link.
result Maximum benchmark accuracy of 94% for a single subject-pair, 88% for ten subject pairs.
AaSP improves audio self-supervised learning by addressing aliasing issues.
problem Alias issues in audio spectrogram transformers.
method AaSP combines aliasing-aware patch representation, teacher-student masked modeling, cross-attention predictor, and contrastive regularization.
result AaSP learns more stable representations that integrate high-frequency cues.
In this paper, we address the task of Optical Character Recognition(OCR) for the Telugu script. We present an end-to-end framework that segments the text image, classifies the characters and extracts lines using a language model. The segmentation is based on mathematical morphology. The classification module, which is …
It is very useful to integrate human knowledge and experience into traditional neural networks for faster learning speed, fewer training samples and better interpretability. However, due to the obscured and indescribable black box model of neural networks, it is very difficult to design its architecture, interpret its …
Deep generative models can emulate the perceptual properties of complex image datasets, providing a latent representation of the data. However, manipulating such representation to perform meaningful and controllable transformations in the data space remains challenging without some form of supervision. While previous w…
RFML systems are vulnerable to adversarial attacks, especially in OTA transmissions.
problem Vulnerability of RFML systems to adversarial machine learning attacks.
method Differentiated adversarial threats, developed methodology for evaluating vulnerabilities, used Fast Gradient Sign Method.
result RFML systems are vulnerable to adversarial examples, even in OTA attacks.
Optimal transport embedding learns feature sets efficiently.
problem Learning on sets of features with long-range dependencies and few labeled data.
method Parametrized fixed-size embedding that aggregates features according to optimal transport plan.
result Achieves state-of-the-art results on protein fold recognition and chromatin profiles.
Enhances SNNs for spatio-temporal feature extraction.
problem Insufficient temporal dependencies in existing SNN synaptic structures.
method Integrates temporal convolution and attention mechanisms into synaptic connections.
result Improves SNN performance on classification tasks.
Improved speech recognition using EEG and video.
problem Enhancing continuous speech recognition systems.
method Implemented a CTC-based ASR model using EEG features.
result EEG features improve continuous visual speech recognition.
Study shows emotion affects speaker recognition and vice versa.
problem Dependencies between emotion and speaker recognition.
method Transfer learning and fine-tuning for emotion classification.
result Fine-tuning improves emotion recognition performance by 30.40% on IEMOCAP, 7.99% on MSP-Podcast, and 8.61% on Crema-D.
With the recent renaissance of deep convolution neural networks, encouraging breakthroughs have been achieved on the supervised recognition tasks, where each class has sufficient training data and fully annotated training data. However, to scale the recognition to a large number of classes with few or now training samp…
End-to-end speech recognition using EEG without speech input.
problem Speech recognition without direct speech input.
method Implemented attention model and CTC-based ASR systems for EEG signals; fused EEG with noisy speech features.
result Demonstrated end-to-end speech recognition using EEG signals.
Classifies modules of surface-knots in terms of their properties.
problem Characterizing modules of surface-knots in terms of their properties.
method Using homology and covering spaces, the reduced first module is characterized.
result The reduced first module for every genus g is characterized in terms of properties of a finitely generated module.
A new network controls task execution in a single vision system.
problem Executing multiple tasks accurately and efficiently in a single network.
method A top-down control network modifies main recognition network activations based on selected task, image content, and spatial location.
result Significantly better results on four datasets compared to state-of-the-art approaches.