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.
The paper reviews techniques for detecting errors in semantic segmentation models.
problem Detecting false positives and false negatives in semantic segmentation models.
method Uncertainty quantification techniques applied to semantic segmentation.
result Techniques for detecting false positives and false negatives are proposed and discussed.
The paper examines uncertainty calibration for object detection models in autonomous driving.
problem Uncertainty in object detection predictions and its calibration.
method Definition and evaluation of semantic and spatial uncertainty, calibration methods for uncertainty distributions.
result Calibrated uncertainty improves the overall performance of object detection models in real-world scenarios.
Unified framework for OOD detection and generalization using graph theory.
problem Challenges in out-of-distribution (OOD) generalization and detection in real-world machine learning models.
method Graph-theoretic framework to jointly tackle OOD generalization and detection.
result Empirical validation of theoretical underpinnings with competitive performance.
Enhances neural language processing with a hierarchical context-aware model.
problem Limited context in neural language processing systems.
method Hierarchical recurrent neural network with multi-level context representation.
result Improves semantic error detection by 12.75% relative for unsupervised models and 20.37% relative for supervised models.
Paper introduces SDM for detecting LLM hallucinations, improving on entropy tests.
problem Challenges of Large Language Models (LLMs) with non-factual, nonsensical responses.
method Joint clustering on sentence embeddings to measure semantic divergence between prompts and responses.
result SDM framework detects deeper form of arbitrariness in LLM responses.
DCAE learns compact latent representations for one-class novelty detection.
problem Learning compact latent representations for one-class novelty detection.
method DCAE learns compact and collapse-free latent representations through internal discriminative layers of GANs, reconstructing in-class data finely and exclusively.
result DCAE achieves state-of-the-art performance on novelty and adversarial example detection.
Sherlock uses deep learning to accurately detect data types from column headers.
problem Detecting accurate semantic types of data columns for data science tasks.
method Sherlock is a multi-input deep neural network trained on a corpus of 686,765 data columns.
result Sherlock achieves a support-weighted F1 score of 0.89, outperforming existing methods.
DCoM uses deep neural networks to detect semantic data types from raw column values.
problem Detecting semantic data types from dirty and unseen data.
method DCoM employs multi-input NLP-based deep neural networks trained on 686,765 data columns.
result DCoM outperforms existing methods significantly on 78 different semantic data types.
Joint network for real-time object detection and semantic segmentation.
problem Real-time object detection and semantic segmentation for automated driving.
method Shared encoder for object detection and semantic segmentation, using YOLO v2 and FCN8 decoders.
result Joint network achieves the same accuracy as separate networks and 30 fps for 1280x384 resolution.
New framework detects near vs. far out-of-distribution samples for AI safety.
problem Binary OOD detection fails to distinguish between semantically close and distant unknown risks.
method Ternary classification based on Low-Entropy Semantic Manifolds and Semantic Surprise Vector.
result Framework achieves state-of-the-art performance on ternary OOD detection task.
Proposes a probabilistic method for generating semantically-aware adversarial examples.
problem Generating adversarial examples that are difficult for humans to detect while preserving semantics.
method Embeds subjective understanding of semantics as a distribution into adversarial example generation.
result Achieves higher success rates in circumventing adversarial defense mechanisms.
Early detection and precise characterization of emerging topics in text streams can be highly useful in applications such as timely and targeted public health interventions and discovering evolving regional business trends. Many methods have been proposed for detecting emerging events in text streams using topic modeli…
This work tackles out-of-distribution detection using multiple semantic label representations.
problem Detecting neural networks' performance on out-of-distribution examples.
method Using multiple semantic dense representations instead of sparse representation as target labels.
result The proposed method compares favorably with previous work on out-of-distribution detection.
Many methods have been proposed for detecting emerging events in text streams using topic modeling. However, these methods have shortcomings that make them unsuitable for rapid detection of locally emerging events on massive text streams. We describe Spatially Compact Semantic Scan (SCSS) that has been developed specif…
MADOD meta-learns invariant features for OOD detection across unseen domains.
problem Simultaneous covariate and semantic shifts in real-world machine learning applications.
method Meta-learning and G-invariance to learn robust, domain-invariant features.
result Superior performance in semantic OOD detection across unseen domains.
Paper proposes using semantic spaces and traditional classifiers for sarcasm detection.
problem Sarcasm detection in text, especially on social media.
method Apply classical machine learning algorithms to texts represented in a Latent Semantic space.
result Established reference datasets and baselines for sarcasm detection.
ACERL embeds networks into a low-dimensional space preserving structural and semantic properties.
problem Challenges in brain connectivity data analysis with subject-specific, high-dimensional, and sparse networks.
method Contrastive learning of augmented network pairs with adaptive random masking.
result Achieves minimax optimal convergence rate for edge representation learning.
Motivation: The rapid growth of diverse biological data allows us to consider interactions between a variety of objects, such as genes, chemicals, molecular signatures, diseases, pathways and environmental exposures. Often, any pair of objects--such as a gene and a disease--can be related in different ways, for example…
MISIM improves code similarity systems with neural learning.
problem Improving accuracy of code semantics similarity systems.
method Context-aware semantics structure and neural code similarity scoring algorithm.
result MISIM achieves 8.08% better accuracy than state-of-the-art systems.
Graph signal processing detects hallucinations in large language models.
problem Detecting factual reasoning from hallucinations in large language models.
method Modeling transformer layers as dynamic graphs, using spectral analysis to define diagnostics.
result Spectral signatures can distinguish different types of hallucinations and achieve high accuracy.
Method explains anomaly detection by generating normal modifications.
problem Complexity of deep learning methods in anomaly detection.
method Generates multiple alternative modifications for anomalies.
result High-quality semantic explanations provided for anomaly detection.
CDDN tackles visual relationship detection with context-dependent diffusion networks.
problem Combustion of combinatorial explosion in relation triplets detection.
method CDDN framework using semantic and visual scene graphs for adaptive information aggregation.
result CDDN achieves state-of-the-art performance on visual relationship detection datasets.
We consider the task of semantic robotic grasping, in which a robot picks up an object of a user-specified class using only monocular images. Inspired by the two-stream hypothesis of visual reasoning, we present a semantic grasping framework that learns object detection, classification, and grasp planning in an end-to-…
TLMG4Eth combines language and graph models for Ethereum fraud detection.
problem Current fraud detection methods fail to consider semantic and similarity patterns in Ethereum transactions.
method TLMG4Eth uses a transaction language model and graph-based methods to capture semantic, similarity, and structural features.
result TLMG4Eth detects anomalies in Ethereum transactions more effectively than existing methods.
Paper uses LLMs to detect financial anomalies.
problem Detecting irregular financial entries.
method Non-semantic financial data encoding with LLMs embeddings, tested 3 models.
result LLMs improve anomaly detection in financial data.
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 …
ProtoX-AD: A self-explainable time series anomaly detection framework
problem Lack of explainability in self-supervised time series anomaly detection
method Learning transformation-aware latent representations and interpretable prototypes
result Achieves detection performance comparable to black-box methods while offering more consistent and semantically meaningful explanations
Method meta-classifies semantic segmentation predictions using dispersion measures.
problem Assessing the quality of semantic segmentation predictions.
method Aggregates dispersion measures (entropy) of predicted probabilities to derive metrics correlated with IoU.
result Metrics correlate well with IoU, providing reliable prediction quality ratings.
DoPa detects various physical adversarial attacks on CNNs.
problem Vulnerability of CNNs to physical adversarial attacks.
method Interprets CNN's vulnerability, adds self-verification stage.
result Achieves 90% success rate for image attacks and 92% for audio attacks.
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.
Normalizing flows fail to detect OOD data due to learning local pixel correlations.
problem Detecting out-of-distribution data in machine learning systems.
method Investigated why normalizing flows fail to distinguish between in- and out-of-distribution data, and modified flow architecture to improve OOD detection.
result Modifying flow architecture can improve OOD detection by biasing the flow towards learning semantic structure of the target data.
The paper teaches robots to navigate by learning costs from expert demonstrations.
problem Teaching robots to navigate autonomously using only expert observations.
method Developed a map encoder and cost encoder to infer semantic class probabilities and a cost function from expert observations.
result Robots can learn to follow traffic rules in a simulator using only semantic observations.
Adversarial autoencoder networks detect accounting anomalies in latent space.
problem Detecting fraud in accounting data using handcrafted rules that fail to generalize.
method Adversarial autoencoder neural networks to learn semantic meaningful representations.
result The learned representation improves anomaly detection and interpretability.
Develops a power-calibrated framework for LLM watermarking, optimizing tradeoffs between detectability and distortion.
problem The trade-off between detectability and semantic distortion in logit-based watermarking.
method Power-calibrated statistical framework for watermark hyperparameters, establishing explicit relationships.
result Derives practical parameter selection procedures achieving optimal tradeoffs under constraints.
PointPainting fuses lidar and image data for better 3D object detection.
problem Lidar-only methods outperform fusion methods on 3D object detection benchmarks.
method Sequential fusion by projecting lidar points into image segmentation output and appending class scores.
result Significant improvements on state-of-the-art 3D object detection methods on KITTI and nuScenes datasets.
Semantic boundary and edge detection aims at simultaneously detecting object edge pixels in images and assigning class labels to them. Systematic training of predictors for this task requires the labeling of edges in images which is a particularly tedious task. We propose a novel strategy for solving this task, when pi…
A structured approach to generating adversarial attacks for ML systems.
problem Vulnerability of ML systems to adversarial perturbations.
method Developed an 'attack generator' to systematically create adversarial attacks.
result Summarized and extended existing adversarial perturbation taxonomies.
Paper evaluates Arabic question similarity, 9 teams participated.
problem Predicting semantic similarity between Arabic questions.
method 9 teams participated in a shared task to predict semantic similarity.
result 9 teams participated in the task, results made publicly available.
SAVeD detects dataset versions without metadata, improving accuracy and separation.
problem Difficulty in identifying similar versions of structured datasets.
method Contrastive learning with modified SimCLR pipeline, generating and contrasting augmented table views.
result SAVeD achieves higher accuracy and separation scores on unseen tables.
Extract class-specific subnetworks from neural models for better understanding and improved explanations.
problem Understanding and explaining the complex behavior of deep neural networks.
method For each semantic class, extract a class-specific subnetwork with a compressed structure that maintains comparable performance.
result Extracted subnetworks improve explanation saliency and adversarial example detection.
This paper detects function-level obfuscation in binary code using graph-based methods.
problem Detecting and characterizing function-level obfuscation in binary code.
method Graph-based approaches, including GNNs, are compared on various datasets.
result GNNs outperform baselines in function-level obfuscation detection, especially in a 11-class classification task.
We introduce a new approach to unsupervised estimation of feature-rich semantic role labeling models. Our model consists of two components: (1) an encoding component: a semantic role labeling model which predicts roles given a rich set of syntactic and lexical features; (2) a reconstruction component: a tensor factoriz…
In iterative supervised learning algorithms it is common to reach a point in the search where no further induction seems to be possible with the available data. If the search is continued beyond this point, the risk of overfitting increases significantly. Following the recent developments in inductive semantic stochast…
IdBench benchmarks semantic representations of identifiers, revealing strengths and weaknesses.
problem Evaluating semantic representations of identifiers in source code.
method Created a benchmark using developer ratings, evaluated natural language and source code embeddings, and compared lexical string distance functions.
result No single technique provides a satisfactory representation of semantic similarities, but ensemble models can improve performance.
SySeVR uses deep learning to detect software vulnerabilities.
problem Detecting software vulnerabilities is challenging and important.
method SySeVR combines syntax and semantic information to represent programs for deep learning.
result SySeVR detects 15 unknown vulnerabilities, including 7 unknown and 8 silently patched ones.
The paper uses differentiable rendering to generate semantic counterexamples for improving neural network robustness.
problem Neural networks' brittleness to semantic transformations.
method Differentiable rendering for generating realistic images that model semantic changes, combined with adversarial machine learning attacks.
result Semantic counterexamples improve generalization, robustness, and transferability of neural networks.
The use of robo-readers to analyze news texts is an emerging technology trend in computational finance. In recent research, a substantial effort has been invested to develop sophisticated financial polarity-lexicons that can be used to investigate how financial sentiments relate to future company performance. However, …