Differentiable mask prunes deep networks for vision and text.
problem Efficiently compressing deep networks for edge devices.
method Introduces a differentiable mask for sparsity induction.
result Successfully prunes weights, filters, and nodes of convolutional and recurrent networks.
GmCN adapts GCN feature aggregation to improve graph learning.
problem Fixed neighborhood graph aggregation in GCNs is biased and can be affected by graph structure noises.
method GmCN allows nodes to adaptively select optimal neighbors for feature aggregation.
result GmCN improves graph learning effectiveness through adaptive neighbor selection.
Flow-based generative models, conceptually attractive due to tractability of both the exact log-likelihood computation and latent-variable inference, and efficiency of both training and sampling, has led to a number of impressive empirical successes and spawned many advanced variants and theoretical investigations. Des…
Transformers predict price movements from limit order books.
problem Predicting price movements from limit order books.
method Causal convolutional network with masked self-attention.
result Significantly outperforms existing architectures on FI-2010 dataset.
Invertible neural networks with masked convolutions improve classification and generative models.
problem Building robust invertible neural networks for better model interpretability and generative tasks.
method Combining masked convolutions and iterative inversion methods to create invertible architectures.
result Invertible neural networks achieve competitive performance in classification and generative tasks.
Deep Learning methods, specifically convolutional neural networks (CNNs), have seen a lot of success in the domain of image-based data, where the data offers a clearly structured topology in the regular lattice of pixels. This 4-neighbourhood topological simplicity makes the application of convolutional masks straightf…
LMConv improves autoregressive models for image generation and completion.
problem Limited generation order in autoregressive models restricts their applicability.
method Introduces LMConv, a modified 2D convolution that allows arbitrary masks to be applied to weights.
result LMConv achieves improved performance on image density estimation and coherent completions.
In this contribution, we present a novel approach for segmenting laser radar (lidar) imagery into geometric time-height cloud locations with a fully convolutional network (FCN). We describe a semi-supervised learning method to train the FCN by: pre-training the classification layers of the FCN with image-level annotati…
The ConditionaL Neural Networks (CLNN) and the Masked ConditionaL Neural Networks (MCLNN) exploit the nature of multi-dimensional temporal signals. The CLNN captures the conditional temporal influence between the frames in a window and the mask in the MCLNN enforces a systematic sparseness that follows a filterbank-lik…
Model detects electricity theft with high accuracy.
problem Detecting electricity theft on imbalanced datasets.
method Multi-head self-attention mechanism with dilated convolutions and binary mask.
result Achieved AUC of 0.926, improving previous work by 17%.
Improved YOLOv5 model detects mask-wearing with enhanced accuracy.
problem Detecting mask-wearing in high traffic public places.
method Improved YOLOv5l with Multi-Head Attentional Self-Convolution, Swin Transformer Block, I-CBAM module, and enhanced feature fusion.
result 1.1% improvement in mAP(0.5) and 1.3% improvement in mAP(0.5:0.95) compared to YOLOv5l.
Perturbative GAN, which replaces convolution layers of existing convolutional GANs (DCGAN, WGAN-GP, BIGGAN, etc.) with perturbation layers that adds a fixed noise mask, is proposed. Compared with the convolu-tional GANs, the number of parameters to be trained is smaller, the convergence of training is faster, the incep…
Automatic feature extraction using neural networks has accomplished remarkable success for images, but for sound recognition, these models are usually modified to fit the nature of the multi-dimensional temporal representation of the audio signal in spectrograms. This may not efficiently harness the time-frequency repr…
MASnet enhances speech on mobile devices with low latency.
problem Efficiently enhancing speech on mobile devices with low latency.
method MASnet processes linear-scale spectrograms, using ratio masks to enhance noisy frames, and operates in low-latency incremental inference mode.
result MASnet achieves efficient speech enhancement with low latency, reducing FMA/s operations.
Selfie pretrains image embeddings without pixel-level predictions.
problem Training image embeddings efficiently with limited labeled data.
method Contrastive Predictive Coding loss for masked patches, using convolutional and attention mechanisms.
result Significant improvement in ResNet-50 accuracy on ImageNet 224 x 224 with 60 examples per class (5%).
We introduce backdrop, a flexible and simple-to-implement method, intuitively described as dropout acting only along the backpropagation pipeline. Backdrop is implemented via one or more masking layers which are inserted at specific points along the network. Each backdrop masking layer acts as the identity in the forwa…
Neural network based architectures used for sound recognition are usually adapted from other application domains such as image recognition, which may not harness the time-frequency representation of a signal. The ConditionaL Neural Networks (CLNN) and its extension the Masked ConditionaL Neural Networks (MCLNN) are des…
The ConditionaL Neural Network (CLNN) exploits the nature of the temporal sequencing of the sound signal represented in a spectrogram, and its variant the Masked ConditionaL Neural Network (MCLNN) induces the network to learn in frequency bands by embedding a filterbank-like sparseness over the network's links using a …
Mask-reconstruction pretraining helps in downstream tasks by capturing more semantic features.
problem How mask-reconstruction pretraining helps in downstream tasks and why it surpasses supervised learning.
method Theoretical analysis and experimental validation of mask-reconstruction pretraining (MRP) on auto-encoders.
result MRP provably captures more semantic features than supervised learning, leading to better performance in downstream tasks.
We applied pre-defined kernels also known as filters or masks developed for image processing to convolution neural network. Instead of letting neural networks find its own kernels, we used 41 different general-purpose kernels of blurring, edge detecting, sharpening, discrete cosine transformation, etc. for the first la…
Deep neural network architectures designed for application domains other than sound, especially image recognition, may not optimally harness the time-frequency representation when adapted to the sound recognition problem. In this work, we explore the ConditionaL Neural Network (CLNN) and the Masked ConditionaL Neural N…
WaveCRN improves E2E speech enhancement with efficient CNN and SRU.
problem Efficiently modeling speech locality and sequential properties for E2E speech enhancement.
method WaveCRN uses a CNN for speech locality and SRU for temporal sequential modeling, with RFM for noise suppression.
result WaveCRN outperforms state-of-the-art approaches with reduced complexity and inference time.
Novel framework for whole-slide blood cell segmentation.
problem Semantic segmentation of whole-slide blood cell images.
method Convolutional encoder-decoder framework with VGG-16 feature extraction.
result Outstanding accuracy (97.18% global accuracy) in classwise segmentation.
Automates defect detection using autoencoders on normal images only.
problem Manual defect detection is slow, tedious, and prone to human biases.
method Convolutional auto-encoder trained on normal images only, detects defects in residual masks.
result Achieved an impressive average F1 score of 0.885 on test images.
NeuroMask provides interpretable explanations for deep neural networks.
problem Understanding how deep neural networks make decisions.
method Applies a mask to reveal or hide parts of an image, tuning mask values to preserve classification results and produce interpretable explanations.
result NeuroMask successfully localizes the most relevant parts of an image to a deep neural network's decision.
A hybrid Convolutional VAE predicts crypto volatility surfaces, outperforming single-symbol approaches.
problem Predicting crypto volatility surfaces
method Convolutional VAE with hybrid predictor
result Model achieves 0.94-1.56 vol-point RMSE across BTC and ETH markets
Neural network based architectures used for sound recognition are usually adapted from other application domains, which may not harness sound related properties. The ConditionaL Neural Network (CLNN) is designed to consider the relational properties across frames in a temporal signal, and its extension the Masked Condi…
Convolutional sparse representations are a form of sparse representation with a structured, translation invariant dictionary. Most convolutional dictionary learning algorithms to date operate in batch mode, requiring simultaneous access to all training images during the learning process, which results in very high memo…
We propose a new blind source separation algorithm based on mixtures of alpha-stable distributions. Complex symmetric alpha-stable distributions have been recently showed to better model audio signals in the time-frequency domain than classical Gaussian distributions thanks to their larger dynamic range. However, infer…
RaMViD uses diffusion models for video prediction and infilling.
problem Predicting and infilling missing information in videos.
method Extends image diffusion models to videos using 3D convolutions and a new conditioning technique.
result Achieves state-of-the-art results on video prediction benchmarks.
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.
SPADE improves demand forecasting accuracy by 4.5% for post-promotion periods.
problem Overreacting to peak events in demand forecasting leads to biased forecasts.
method SPADE splits forecasting into two tasks: one for peak events and another for post-peak events, using masked convolution filters and a specialized Peak Attention module.
result Overall PPE improvement of 4.5%, 30% improvement for most affected forecasts after promotions and holidays, and 3.9% improvement in PE accuracy.
Acoustic scenes are rich and redundant in their content. In this work, we present a spatio-temporal attention pooling layer coupled with a convolutional recurrent neural network to learn from patterns that are discriminative while suppressing those that are irrelevant for acoustic scene classification. The convolutiona…
PMI-Masking improves MLM pretraining by masking correlated spans efficiently.
problem Uniform token masking leads to inefficient and suboptimal performance in MLMs.
method PMI-Masking uses Pointwise Mutual Information to mask n-grams with high collocation.
result PMI-Masking reaches half the training time and improves performance.
We present a novel method to solve image analogy problems : it allows to learn the relation between paired images present in training data, and then generalize and generate images that correspond to the relation, but were never seen in the training set. Therefore, we call the method Conditional Analogy Generative Adver…
LatFormer improves geometric reasoning by incorporating lattice symmetry priors in attention mechanisms.
problem State-of-the-art models struggle with geometric reasoning tasks in the ARC and LARC datasets.
method Introduced LatFormer, a model that uses lattice symmetry priors in attention masks.
result LatFormer requires 2 orders of magnitude fewer data than standard attention mechanisms.
DNArch learns CNN architectures by backpropagation.
problem Discovering optimal CNN architectures.
method Differentiable Neural Architectures (DNArch) learns CNN architectures by backpropagation, controlling kernel sizes, channels, downsampling positions, and depth.
result DNArch finds performant CNN architectures across various tasks.
CNNs overinterpret inputs, leading to high accuracy without meaningful features.
problem High accuracy in image classifiers can mask subtle model failures.
method Batched Gradient SIS method for discovering sufficient input subsets.
result Overinterpretation allows models to make confident predictions with masked input features.
ST-MTM models complex time series by decomposing and masking seasonal and trend components.
problem Forecasting complex time series with intricate temporal variations.
method Seasonal-Trend Decomposition with Masking and Contrastive Learning.
result ST-MTM achieves superior forecasting performance compared to existing methods.
Study examines effects of pruning techniques on deep learning models.
problem Understanding the impact of pruning methods on deep learning model structure and dynamics.
method Investigated differences in connectivity and learning dynamics of pruned models using various iterative pruning techniques.
result Emergence of structure in pruned models through magnitude-based unstructured pruning and weight rewinding.
LcGAN generates synthetic CT images for hemorrhagic lesion segmentation.
problem Scarce training data for hemorrhagic lesion segmentation.
method Lesion conditional Generative Adversarial Network (LcGAN) for synthetic image generation.
result Segmentation improved by 12.8% with synthetic data augmentation.
Expands MLM by masking token positions, improving performance and convergence.
problem Improving language model performance and convergence.
method Masking token positions along with [MASK] tokens, using a fully connected classifier stage.
result Shows .3% improvement and 50% faster convergence for BERT Base with position masking.
SMART training improves mask-predict translations.
problem Closing the performance gap between semi-autoregressive and autoregressive models.
method SMART training method for conditional masked language models.
result SMART-trained models produce higher-quality translations.
New method reduces diffusion model function evaluations for discrete data.
problem High computational burden in generating samples from masked diffusion models.
method Modified causal attention mask and speculative sampling mechanism for non-factorized predictions.
result Achieved ~2x reduction in required network forward passes.
Proposes a proportional masking strategy for better tabular data imputation.
problem Heterogeneity of tabular data disrupts uniform random masking in MAEs.
method Computes missingness statistics, generates proportional masks, uses MLP token mixing.
result Proportional masking preserves missingness distribution, improves imputation performance.
New analysis reveals masked self-supervised learning's effectiveness in extracting data structure.
problem Analyzing masked self-supervised learning in high-dimensional data.
method Developed precise high-dimensional analysis of masked modeling objectives.
result Identified phase transitions and structured regimes for masked self-supervised learning.
We propose a new STAcked and Reconstructed Graph Convolutional Networks (STAR-GCN) architecture to learn node representations for boosting the performance in recommender systems, especially in the cold start scenario. STAR-GCN employs a stack of GCN encoder-decoders combined with intermediate supervision to improve the…
DCIts interprets complex time series data with interpretable coefficients.
problem Interpreting nonlinear multivariate time series data.
method Deep convolutional architecture with a Focuser and Modeler components.
result DCIts provides interpretable coefficients and interaction patterns.