Meta-learning improves few-shot acoustic event detection.
problem Detecting new audio events with limited labeled data.
method Formulated few-shot AED problem; explored supervised and meta-learning approaches.
result Meta-learning achieves superior performance in few-shot AED.
Wearable tech detects table tennis shots with high accuracy.
problem Lack of shot detection in table tennis using wearables.
method Fusion of IMU and audio sensor data for real-time shot detection.
result 95.6% accuracy in shot detection.
Zero-shot anomaly detection method using batch normalization.
problem Adapting anomaly detectors to new normal data distributions without training data.
method Adaptive Centered Representations (ACR) with batch normalization.
result First zero-shot AD results for tabular data and image data.
FROB model improves robustness and reliable confidence for few-shot OoD detection.
problem Challenges in few-shot classification and OoD detection due to limited samples and adversarial attacks.
method FROB model combines support boundary generation and few-shot Outlier Exposure (OE) for improved robustness and reliable confidence.
result FROB achieves generalization to unseen OoD and maintains robustness independent of few-shot number.
Detects out-of-domain cases with limited training data.
problem Detecting out-of-domain cases with insufficient in-domain training data.
method Proposes an OOD-resistant Prototypical Network.
result Outperforms state-of-the-art methods in zero-shot OOD detection.
BayPrAnoMeta tackles few-shot industrial image anomaly detection with Bayesian methods.
problem Challenges in industrial image anomaly detection, especially class imbalance and scarcity of labeled samples.
method Bayesian Proto-MAML approach with probabilistic normality models and Bayesian posterior predictive likelihood.
result Consistent and significant AUROC improvements over existing methods in few-shot anomaly detection.
Develops a cross-lingual hate speech detection model using pre-trained Transformers.
problem Detecting hate speech in low-resource languages.
method Utilizes frozen Transformer language models and AXEL attention-based classification block for zero-shot and few-shot learning.
result Demonstrates highly competitive results on English and Spanish subsets of the HatEval challenge.
Dissertation tackles zero-shot anomaly detection, focusing on consistent anomalies and proposing CoDeGraph framework.
problem Consistent anomalies bias distance-based zero-shot anomaly detection methods.
method Formalized consistent anomalies, identified similarity scaling and neighbor-burnout phenomena, introduced CoDeGraph framework.
result CoDeGraph effectively suppresses consistent anomalies in zero-shot anomaly detection.
Novel model identifies unseen classes with a single example.
problem Weakly supervised one-shot detection of unseen classes.
method Siamese similarity network with attention mechanism.
result Significantly outperforms baseline methods in experiments.
Few-shot models detect tweets in emerging disasters efficiently.
problem Detecting relevant tweets in emerging disaster events is challenging.
method Few-shot models (matching networks and prototypical networks) are used to detect tweets in emerging disaster events.
result Few-shot models can generalize to unseen classes with a small amount of examples.
Efficient binarized algorithm detects seizures from iEEG with one-shot learning.
problem Detecting seizures from iEEG data efficiently and accurately.
method Combines local binary patterns with hyperdimensional computing for end-to-end binary operations.
result Algorithm learns from one or two seizures and generalizes on 27 further seizures.
Algorithm detects hidden spike-patterns in neural networks with one-shot learning.
problem Detecting hidden spike-patterns in high activity neural networks.
method Constructive algorithm using spike-timing-dependent plasticity (STDP) and lateral inhibition.
result Successful one-shot detection of new spike-patterns after long intervals.
LogAnMeta detects anomalies from log events using meta learning.
problem Poor performance of current log anomaly detection on new or unseen anomalies.
method Meta-learning-based hybrid few-shot classifier trained in an episodic manner.
result Demonstrates efficacy of LogAnMeta on detecting anomalies with few samples.
Paper extends 2D ZSAD to 3D MRI without training, achieving robust anomaly detection.
problem Challenges in extending zero-shot anomaly detection to 3D medical images.
method Constructs localized volumetric tokens by aggregating 2D slices processed by 2D foundation models.
result Training-free, batch-based ZSAD effectively extends from 2D encoders to full 3D MRI volumes.
Deep nearest neighbors outperform self-supervised methods in anomaly detection.
problem Anomaly detection using self-supervised deep methods.
method Simple nearest-neighbor approach on Imagenet pretrained features.
result Nearest-neighbor method outperforms self-supervised methods in accuracy, few shot generalization, training time, and noise robustness.
Paper proposes SiSTA for single-shot domain adaptation using target-aware generative augmentation.
problem Adapting models from source to target domains with limited target data.
method Fine-tunes a generative model on a single-shot target and uses novel sampling strategies for synthetic data.
result Improves performance by up to 20% over existing baselines in face attribute detection.
Telescope detects LLM generated text by measuring token repetition probability.
problem Distinguishing LLM generated text from human writing.
method Telescope Perplexity, evaluating token repetition probability.
result Telescope Perplexity enables effective zero-shot LLM detection.
This paper detects multi-stage Feint Attacks using Bi-RNN and few-shot learning.
problem Detecting multi-stage Feint Attacks due to lack of professional datasets and semantic relationships.
method Fuzzy clustering for attack chain mining, few-shot deep learning, Bi-RNN for feature extraction.
result Accurately detected Feint Attacks using Bi-RNN and few-shot learning.
Meta-learning improves anomaly detection with few labeled instances.
problem High requirement of training data for neural network-based anomaly detection.
method Meta-learning framework with one-class classification and generalized eigenvalue problem.
result Meta-learning method achieves better performance than existing methods on various datasets.
TAMA uses LMMs to detect and interpret anomalies in time series data with few labels.
problem Challenges in manual feature engineering and extensive labeled training data for TSAD.
method Leverages LMMs to convert time series into visual formats for few-shot in-context learning.
result Consistently outperforms state-of-the-art methods in TSAD tasks.
Zero-shot KD for object detection without training data.
problem Challenges in using training data for knowledge distillation.
method Synthesizes pseudo-targets and samples using pretrained network.
result Achieves respectable mAP on object detection benchmarks.
Paper tackles zero-shot learning for semantic image interpretation.
problem Extracting structured semantic descriptions from images requires complete training sets, which are often unavailable.
method Uses Logic Tensor Networks to leverage logical constraints and similarities among relationships in the training set.
result Background knowledge can alleviate the incompleteness of training sets, improving zero-shot learning performance.
Paper uses SSD to detect miners' activities in a mining environment.
problem Tracking miners' activities in a mining environment with little obstruction.
method Used SSD trained on COCO dataset to detect miners' activities. Implemented machine learning algorithms using Tensorflow and C++.
result Improved accuracy of detecting miners' activities through data fusion.
DeROL tackles one-shot learning for AI systems with limited data.
problem Handling few training instances for classification tasks.
method Develops a Deep Reinforcement Learning framework to optimize resource usage.
result Demonstrates efficient resource allocation in one-shot learning.
New method detects and prevents unfairness in few-shot regression models.
problem Fairness issues in supervised few-shot meta-learning models.
method Causal Bayesian knowledge graph for dependency visualization, risk difference quantification, and fast-adapted bias-control approach.
result Efficiently detects and mitigates unfairness in model predictions.
Zero-Shot Learning helps learn new concepts without examples, useful for COVID-19 diagnosis.
problem Learning new concepts without examples, especially in medical imaging.
method Uses existing knowledge and auxiliary information to predict unknown concepts.
result Effective in diagnosing COVID-19 from chest X-rays.
Fast object detection in JPEG images without decompression.
problem Efficient object detection in compressed JPEG images.
method Modified SSD with DCT coefficients input processing.
result 2x faster detection with promising performance.
Paper proposes a method to generate synthetic anomalies for robust anomaly detection.
problem Anomaly detection struggles with unbalanced data and rare anomalies.
method Two-level hierarchical latent space representation for feature distillation and synthesis.
result The method creates robust synthetic anomalies for training robust binary classifiers.
Graph neural networks detect collusion patterns across markets.
problem Detecting and predicting collusion in different national markets.
method Two-phase approach using GNNs for zero-shot learning and OOD generalization.
result GNNs outperform NNs in detecting complex collusive patterns.
Method improves few-shot one-class classification.
problem Learning binary classifier with data from only one class.
method Modified MAML algorithm to learn initialization for few-shot OCC.
result Method leads to better results than classical approaches.
Graph Prototypical Networks improve few-shot node classification on attributed networks.
problem Few-shot node classification in attributed networks with limited labeled instances.
method Graph Prototypical Networks (GPN) using meta-learning to extract meta-knowledge and identify informative labeled instances.
result GPN achieves superior performance in few-shot node classification.
Zero-shot understanding of accidents from surveillance videos using vision-language models
problem Accident understanding from surveillance videos
method Three-stage pipeline with vision-language similarity, metadata-driven multi-prompt reasoning, and entropy-gated pairwise adjudicator
result Substantial improvement in harmonic-mean score over baseline
Semantic embeddings improve safety-critical classifier performance.
problem Improving interpretability and error detection in safety-critical neural networks.
method Created embeddings from symbolic domain knowledge, used for misprediction interpretation and error detection, introduced semantic distance for confidence measurement.
result Semantic distance achieves near state-of-the-art performance in a traffic sign classifier, faster than other methods.
Bruno model learns from sets of complex observations using deep learning.
problem Learning from sets of high-dimensional, complex observations with generalization.
method Deep Recurrent Model leveraging deep learning for exact Bayesian inference, provably exchangeable.
result The model can generate new samples conditionally on previous ones with linear cost in the size of the conditioning set.
MetaNAS improves few-shot learning by optimizing neural architectures with meta-learning.
problem Few-shot learning challenges due to limited data and compute time.
method MetaNAS integrates NAS with gradient-based meta-learning to adapt neural architectures to new tasks efficiently.
result MetaNAS achieves state-of-the-art results on few-shot classification benchmarks.
Study compares DSPy teleprompter algorithms for aligning LLM evaluations with human annotations.
problem Aligning LLM evaluation metrics with human annotations.
method Comparative analysis of five teleprompter algorithms within the DSPy framework.
result Certain teleprompters outperform others in detecting hallucinations.
Study evaluates financial anomaly detection methods on Canadian stock market.
problem Detecting financial anomalies in the Canadian stock market.
method Topological data analysis (TDA), principal component analysis (PCA), and neural network-based approaches.
result Neural network-based methods achieve the strongest performance in detecting financial anomalies.
FSN model improves few-shot learning by generalizing to new tasks.
problem Few-shot learning struggles with tasks outside its training domain.
method FSN uses topology-inspired approach to model classes flexibly.
result FSN outperforms state-of-the-art models on new tasks.
Paper tackles novel object recognition by improving hierarchical classification.
problem Challenges in recognizing novel object classes unseen during training.
method Proposes top-down and flatten methods for hierarchical novelty detection.
result Generates a hierarchical embedding leading to improved zero-shot learning performance.
Few-shot learning with per-sample rich supervision reduces sample complexity.
problem Learning with few samples is challenging for deep models.
method Use per-sample semantic information to reduce sample complexity.
result Improved generalization error bound and online algorithm for few-shot learning.
Deep learning improves real-time illegal parking detection.
problem Weak robustness of traditional illegal parking detection methods.
method Used SSD algorithm for vehicle location and classification, optimized default box aspect ratio, and adopted tracking and analysis for movement judgment.
result Achieved 99% accuracy and 25FPS real-time detection with strong robustness in complex environments.
RCS-YOLO improves brain tumor detection speed and accuracy.
problem Efficiently detecting brain tumors with high accuracy and speed.
method Proposes RCS-YOLO, a fast and accurate brain tumor detector using YOLO with Reparameterized Convolution and channel Shuffle.
result RCS-YOLO outperforms other YOLO versions in speed and accuracy on brain tumor detection.
LLMs struggle with zero-shot annotation tasks due to model-internalized priors.
problem Impact of model-internalized priors on LLM performance in zero-shot annotation tasks.
method Investigated three dimensions: familiarity, decision stickiness, and susceptibility to misaligned task definitions.
result Nearly two-thirds of zero-shot errors are resistant to correction, with a rescue rate of 34.8%. Definition-Specific Familiarity (DSF) shows a positive association with model performance.
Study uses few-shot learning to analyze claims and arguments in German debate on arms deliveries.
problem Limited data and computational resources for automated content analysis.
method Multilingual transformer model with adapter extension and few-shot learning.
result Parameter-efficient approach performs well on varying training set sizes.
S4ND detects lung nodules faster and more accurately.
problem Efficient lung nodule detection from CT scans.
method Single-Shot Single-Scale 3D Convolutional Neural Network (CNN) trained end-to-end.
result S4ND outperforms state-of-the-art methods in terms of efficiency and accuracy.
New dataset and models detect cryptocurrency bubbles using social media data.
problem Detecting anomalous market behavior in cryptocoins and meme stocks.
method Developed a novel multi-span identification task and sequence-to-sequence hyperbolic models.
result Models effectively detect cryptocoins and meme stocks bubbles in zero-shot settings.
Theoretical analysis improves few-shot learning performance.
problem Optimizing the number of labeled examples per category in few-shot learning.
method Theoretical analysis of Prototypical Networks, proposing a robust method to the shot number.
result Model trained for arbitrary meta-training shot number performs well across different meta-testing shot numbers.
A new method for few-shot learning using embedded class models and shot-free meta training.
problem Few-shot learning with limited data and varying number of samples per class.
method Learning embeddings for few-shot learning with embedded class models and shot-free meta training.
result Achieves state-of-the-art performance on standard few-shot benchmark datasets.