SELF filters noisy labels to improve deep learning performance.
problem Overfitting to noisy labels in deep learning.
method Self-ensemble label filtering (SELF) using running averages of predictions.
result SELF improves task performance by filtering noisy labels dynamically.
Proposes IFCDA framework to improve cross-domain adaptation.
problem Negative transfer and difficulty in handling category-irrelevant losses in DA.
method Importance filtered mechanism to generate filtered soft labels, combined with graph-based label propagation.
result Significantly improves performance in both Closed-Set and Open-Set DA scenarios.
Graph-based methods have been demonstrated as one of the most effective approaches for semi-supervised learning, as they can exploit the connectivity patterns between labeled and unlabeled data samples to improve learning performance. However, existing graph-based methods either are limited in their ability to jointly …
ML-KFHE improves multi-label classification performance using Kalman filter fusion.
problem Lack of effective multi-label ensemble classification methods.
method Exploits Kalman filter sensor fusion properties for multi-label classification.
result Significantly improved predictive performance on multi-label datasets.
A filter detects and removes noisy labels in semi-supervised learning.
problem Label noise in semi-supervised learning reduces classifier accuracy.
method LGC_LVOF: leave-one-out filtering based on LGC algorithm.
result LGC_LVOF detects and removes noisy labels, improving SSL classifier performance.
Paper compares semi-supervised training for differentiable particle filters.
problem Lack of labelled data in real-world applications.
method Compares two semi-supervised training objectives.
result Improved performance in environments with scarce labelled data.
Simple k-NN filtering improves model accuracy on noisy labels.
problem Training models with noisy labels reduces performance and is hard to identify.
method A simple k-nearest neighbor-based filtering approach on the logit layer. result Improves model accuracy compared to recent methods.
Paper tackles label insufficiency and inaccuracy in semi-supervised learning.
problem Label insufficiency and inaccuracy in semi-supervised learning.
method Graph-based propagation for label insufficiency and label filtering for inaccuracy.
result SIIS improves performance in the presence of label noise and scarcity.
The paper proposes a method to detect and filter noisy or mislabeled data using pointwise mutual information.
problem Detecting and filtering noisy or mislabeled data in deep learning models.
method A mutual information-based framework quantifying statistical dependencies between inputs and labels.
result The method effectively filters low-quality samples, improving classification accuracy by up to 15%.
Develops novel techniques for collaborative filtering and multi-label classification.
problem Information overload and categorization of data objects.
method Hierarchical bi-level maximum margin matrix factorization and piecewise-linear embedding method.
result Effective multi-label classification and collaborative filtering techniques developed.
In this paper we formally analyse the use of sparse filtering algorithms to perform covariate shift adaptation. We provide a theoretical analysis of sparse filtering by evaluating the conditions required to perform covariate shift adaptation. We prove that sparse filtering can perform adaptation only if the conditional…
New Gibbs sampling reduces GLMB filtering complexity to linear time.
problem NP-hard GLMB density computation in multi-object systems.
method Tempered Gibbs sampler exploiting GLMB structure.
result Linear complexity O(T(P+M)) for GLMB filtering. Supervised object detection and semantic segmentation require object or even pixel level annotations. When there exist image level labels only, it is challenging for weakly supervised algorithms to achieve accurate predictions. The accuracy achieved by top weakly supervised algorithms is still significantly lower than …
Improved drug-protein interaction prediction using FTL method.
problem Predicting drug-protein interactions from noisy data with uncertain labels.
method Filtered Transfer Learning (FTL) method that fine-tunes a deep neural network across multiple tiers of data confidence.
result FTL method outperforms deep neural networks trained on single confidence ranges.
A new method simplifies noisy data filtering for CNNs.
problem Training CNNs with noisy labels is challenging.
method Joint Negative and Positive Learning (JNPL) combines NL+ and PL+ loss functions.
result Significantly simplifies the pipeline, achieving state-of-the-art accuracy.
RED-2400 is a public benchmark of trading events from a Solana exchange, labeled by algorithmic rejection.
problem Analyzing algorithmically-rejected trading events for insights into market dynamics.
method Public dataset of 6,660 algorithmically-rejected trading events, linked to post-rejection price and liquidity trajectories.
result First window of a planned series of datasets extending the time horizon and enabling regime-stratified analysis.
Paper proposes an iterative method to improve model robustness under noisy labels.
problem Training models with noisy labels.
method Iterative semi-supervised mechanism that filters noisy labels while retaining useful information.
result Robust models outperform state-of-the-art methods by up to 20% absolute improvement.
Improved deep learning models with less labelled data and better label quality.
problem High costs and effort in training deep neural networks with label errors.
method Iterative label improvement using confidence-based filtering and dataset partitioning.
result Significant improvement in label quality and model accuracy.
This paper introduces a new perspective on multi-class ensemble classification that considers training an ensemble as a state estimation problem. The new perspective considers the final ensemble classifier model as a static state, which can be estimated using a Kalman filter that combines noisy estimates made by indivi…
This paper tackles hidden state inference for HMMs using particle filtering.
problem Inference for hidden states under HMMs is challenging due to unavailable true labels.
method Adaptive conformal inference framework using particle filtering.
result The framework produces prediction sets with specific aggregated coverage levels.
Suitability filter detects model performance degradation in real-world deployment.
problem Ensuring model reliability in safety-critical domains without access to ground truth labels.
method Uses suitability signals to evaluate classifier performance on unlabeled user data.
result The suitability filter reliably detects performance deviations due to covariate shift.
Hybrid approach combines transformer and Bayesian filtering for robust multiple particle tracking.
problem Challenges in tracking multiple particles in noisy scenes due to combinatorial explosion of hypotheses.
method Attention-Bayesian hybrid framework using transformer for association and Bayesian filtering for pruning hypotheses.
result Improved tracking accuracy and robustness against spurious detections.
Improved action detection for multi-person videos using attention filtering.
problem Difficulty in distinguishing relevant parts of multi-person videos for action detection.
method Fovea attention filtering and generalized binary loss function.
result 20% relative improvement in mAP over baseline in AVA dataset.
Convolutional neural networks (CNNs) achieve state-of-the-art performance in a wide variety of tasks in computer vision. However, interpreting CNNs still remains a challenge. This is mainly due to the large number of parameters in these networks. Here, we investigate the role of compression and particularly pruning fil…
Bayesian methods improve tracking multiple objects through dynamic dependencies.
problem Tracking multiple objects with time-varying cardinality and unordered measurements.
method Employing Bayesian nonparametric models, specifically dependent Dirichlet and Pitman-Yor processes, for state estimation and Monte Carlo sampling for trajectory learning.
result The proposed methods outperform existing algorithms in estimating the time-varying number of objects and identifying object associations.
Semantic segmentation of land cover classes is fundamental for agricultural and economic development work, from sustainable forestry to urban planning, yet existing training datasets have significant limitations. To generate an open and comprehensive training library of high resolution Earth imagery and high quality la…
CNN predicts optimal filter parameters for BM3D denoising.
problem Optimizing denoising filter performance in real-time.
method Trained a CNN to predict the best filter parameter value for BM3D.
result CNN-guided BM3D outperforms unguided BM3D across different noise levels.
FPPI selectively uses predictions to improve inference efficiency.
problem Improving statistical inference with limited labeled data and heterogeneous prediction quality.
method Filtered Prediction-Powered Inference (FPPI) framework.
result FPPI achieves strictly improved asymptotic efficiency compared to existing methods.
DAL uses disentanglement for automatic labeling in GAN-based active learning.
problem Reducing human labeling in GAN-based active learning.
method DAL leverages disentanglement in InfoGAN to automatically label datapoints, deciding human labeling based on disagreement with InfoGAN labels and label correction.
result DAL achieves better performance than existing GAN-based active learning approaches on image classification tasks.
LoD improves model safety by integrating unlabeled wild data, reducing OOD misclassification.
problem Improving model safety and reliability using unlabeled wild data containing both in-distribution and out-of-distribution samples.
method Intentionally label-noisifying unlabeled wild data to enable joint learning of labeled ID and OOD data, distinguishing losses between ID and OOD samples.
result LoD framework achieves superior OOD detection without requiring thresholds, improving model safety.
New methods detect targets from imprecisely labeled hyperspectral data.
problem Challenges in acquiring labeled hyperspectral data.
method Multi-Target MI-ACE and MI-SMF methods that learn target signatures from imprecisely labeled samples.
result Effective at learning target signatures and performing target detection.
End-to-end network predicts and aligns continuous emotion labels.
problem Inconsistent alignment of continuous emotion labels with speech signals.
method Convolutional neural network with a multi-delay sinc layer.
result State-of-the-art results in predicting and aligning continuous emotion labels.
New p-Laplacian GNN model tackles heterophilic graphs by improving node classification.
problem Heterophilic graphs where node labels differ, leading to poor GNN performance.
method Proposes p-Laplacian GNN model with a new message passing mechanism derived from discrete regularization. result Significantly outperforms state-of-the-art GNNs on heterophilic benchmarks.
In this study, we propose the integration of competitive learning into convolutional neural networks (CNNs) to improve the representation learning and efficiency of fine-tuning. Conventional CNNs use back propagation learning, and it enables powerful representation learning by a discrimination task. However, it require…
Proposes a new model for noisy labels considering multiple labelers and adversarial attacks.
problem Real-world noisy label models with multiple labelers and adversarial attacks.
method Labeler-dependent noise model with adversarial attack vectors.
result State-of-the-art approaches for learning from noisy labels are defeated by adversarial label attacks.
The omnipresence of deep learning architectures such as deep convolutional neural networks (CNN)s is fueled by the synergistic combination of ever-increasing labeled datasets and specialized hardware. Despite the indisputable success, the reliance on huge amounts of labeled data and specialized hardware can be a limiti…
I-AID categorizes disaster tweets into useful information types.
problem Filtering useful information from social media during disasters.
method Multimodel approach using BERT, GAT, and Relation Network.
result I-AID outperforms state-of-the-art approaches in F1 scores.
Model predicts political ideology using context vectors to mitigate bias and scarcity.
problem Scarcity and selection bias in political ideology prediction.
method Proposes a statistical model decomposing embeddings into context and position vectors, training an end-to-end model for deployment.
result Model can predict ideological labels even with minimal biased data, outperforming state-of-the-art methods.
Paper presents a neural network for recognizing human activities from unlabeled sensor data.
problem Time-consuming annotation of sensor data for activity recognition.
method Attention-based convolutional neural network for weakly labeled data.
result Attention model improves accuracy in recognizing human activities.
S2OSC improves OSC by filtering and re-training models with out-of-class instances.
problem Difficulty in classifying out-of-class instances during inference.
method S2OSC combines semi-supervised learning, out-of-class instance filtering, and model re-training.
result S2OSC achieves state-of-the-art performance in various OSC tasks.
Since the events of the Arab Spring, there has been increased interest in using social media to anticipate social unrest. While efforts have been made toward automated unrest prediction, we focus on filtering the vast volume of tweets to identify tweets relevant to unrest, which can be provided to downstream users for …
STAD adapts models to evolving time-based data shifts.
problem Gradual distribution shifts over time challenge existing test-time adaptation methods.
method Bayesian filtering method that learns time-varying dynamics in hidden features.
result STAD excels in handling small batch sizes and label shift on real-world data.
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.
MAS scores cluster size consistency from points, robust to label changes.
problem Desired uniformity in cluster sizes, stability under label perturbations.
method Mass Agreement Score (MAS) measures point-centric cluster size consistency, robust to label changes.
result MAS yields similar scores for partitions with similar bulk structure, sensitive to genuine redistribution of cluster mass.
New feature selection method for multi-labeled data.
problem Feature redundancy in multi-labeled data.
method Conditional information measure based on dependency maximization.
result Efficient and fast non-parametric feature selection.
CrossFilter tackles noisy labels in audio tagging.
problem Noisy labels in large audio datasets.
method CrossFilter framework using multiple representations and multi-task learning.
result Improves audio tagging performance on FSDKaggle2018 and FSDKaggle2019 datasets.
We consider the problem of recommending relevant labels (items) for a given data point (user). In particular, we are interested in the practically important setting where the evaluation is with respect to non-decomposable (over labels) performance metrics like the F1 measure, and the training data has missing labels…
Extreme multi-label classification refers to supervised multi-label learning involving hundreds of thousands or even millions of labels. Datasets in extreme classification exhibit fit to power-law distribution, i.e. a large fraction of labels have very few positive instances in the data distribution. Most state-of-the-…