Paper introduces a new loss function for deep learning with symbolic knowledge.
problem Learning structured objects like rankings and paths from semi-supervised data.
method Developed a semantic loss function that integrates neural outputs with logical constraints.
result Significantly improves deep learning's ability to predict structured objects.
Paper uses CNN to create realistic LiDAR data.
problem Creating high-resolution LiDAR data with missing points.
method Modified per-point loss and perceptual loss applied to generate realistic LiDAR data.
result Significant improvement in geometric and semantic accuracy over traditional methods.
Proposes a Dual Focal Loss method to improve semantic segmentation on unbalanced datasets.
problem Improving performance on unbalanced datasets in semantic segmentation.
method Adaptive Class Weight based Dual Focal Loss (DFL) function.
result DFL improves convergence and reduces class imbalance effect.
Unsupervised segmentation learns features without labels, improving accuracy.
problem Discover and localize semantically meaningful categories in images without annotations.
method Separates feature learning from cluster compactification; distills unsupervised features into discrete semantic labels using a contrastive loss function.
result Significant improvement over prior state of the art on semantic segmentation challenges.
Proposes a new loss function for deep learning image segmentation.
problem Efficiency and reliance on labeled data in deep learning image segmentation.
method Mumford-Shah functional adapted for deep learning.
result Improves efficiency and effectiveness of deep learning for image segmentation.
AuxNet uses auxiliary tasks to enhance semantic segmentation for automated driving.
problem Time-consuming and expensive semantic annotation for automated driving.
method Leveraging auxiliary tasks like depth estimation to improve semantic segmentation performance.
result 3% and 5% improvement in accuracy on SYNTHIA and KITTI datasets respectively.
New hashing method improves document retrieval precision.
problem Efficiently retrieving similar documents from large text databases.
method Pairwise supervised hashing with Bernoulli VAE and unbiased gradient estimator.
result Superior performance compared to existing methods.
Unsupervised learning identifies sound categories from unlabeled audio.
problem Learning sound categories from unlabeled audio recordings.
method Class-agnostic semantic constraints and triplet loss-based training.
result Low-dimensional embeddings recover 41% and 84% of supervised performance.
Improves cross-modal retrieval by integrating unlabeled data.
problem Lack of semantic similarity constraints and unlabeled data in cross-modal retrieval.
method Integrates quadruplet ranking loss and semi-supervised contrastive loss in a multi-task learning architecture.
result Boosts cross-modal retrieval accuracy by exploiting unlabeled data.
Max-pooling improves semantic segmentation by re-weighting under-represented classes.
problem Imbalanced training data distributions in semantic image segmentation datasets.
method Adaptive loss max-pooling that re-weights pixel contributions based on observed losses.
result Consistently improved semantic segmentation results on benchmark datasets.
This work aims to reduce inexplicable errors in deep neural networks by obtaining class-level semantics and penalizing misclassifications.
problem Deep neural networks misclassify images, leading to inexplicable errors that can harm trust and societal impact.
method Obtain class-level semantics, propose Weighted Loss Functions (WLFs), and train classifiers with these methods.
result Trained networks have more explicable failure modes and comparable accuracy to existing methods.
Framework translates unlabeled images between domains.
problem Translating unlabeled images between domains with no supervision.
method Skip-connected encoder-generator structure trained with GAN, cycle, and semantic consistency losses.
result Framework can learn semantic mappings for face images without supervised one-to-one mapping.
This work shows how transformers use multi-concept word semantics for efficient in-context learning.
problem Understanding the connection between transformer-based LLMs' multi-concept semantic representation and their innovative in-context learning abilities.
method A concept-based low-noise sparse coding prompt model, leveraging advanced techniques to analyze the exponential convergence of 0-1 loss over non-convex training dynamics.
result Transformers leverage multi-concept word semantics to enable powerful and excellent out-of-distribution in-context learning.
Optimizes contrastive learning with individualized temperatures for better performance on imbalanced datasets.
problem The common practice of using a global temperature parameter ignores the varying semantic similarity across different anchor data.
method Proposes a new robust contrastive loss inspired by distributionally robust optimization (DRO) and an efficient stochastic algorithm for automatic temperature individualization.
result Our method automatically learns a suitable temperature for each sample, improving performance on imbalanced datasets.
Hierarchical density embeddings capture word relationships with uncertainty.
problem Capturing semantic relationships and uncertainty in word embeddings.
method Learn hierarchical representations through probability density encapsulation, using simple loss functions and distance metrics.
result State-of-the-art performance on WordNet and Hyperlex datasets.
A new neural network model for sentiment analysis.
problem Accurate and transferable sentiment analysis models.
method A computationally-efficient feedforward neural network.
result Highly accurate models with low losses.
Paper proposes zero-shot transfer learning for semantic parsing.
problem Applying neural networks to tasks with little data remains challenging.
method Introduces a new method for learning shared space between domains based on domain label prediction.
result Method outperforms state-of-the-art techniques in zero-shot experimental setting.
SFAVEL distills features from language models for fact verification without annotations.
problem Fact verification with semantically meaningful and compact features.
method Self-supervised pretraining using contrastive loss with language models.
result Achieved state-of-the-art results on FB15k-237 and FEVER.
This paper shows how optimizing with hard negative examples improves image retrieval.
problem Training with hard negative examples leads to poor training behavior.
method Characterize the space of triplets, derive why hard negatives fail, and offer a fix to the loss function.
result Optimizing with hard negative examples leads to more generalizable features and better image retrieval.
Hybrid method uses LLM to filter lead-lag relationships in prediction markets.
problem Challenges in discovering robust lead-lag relationships in prediction markets due to spurious correlations.
method Two-stage approach: statistical Granger causality followed by LLM semantic re-ranking.
result LLM-based method outperforms statistical baseline, increasing win rate and reducing average loss magnitude.
A new method for image translation using disentangled style and content preservation.
problem Difficulty in maintaining original content during reverse diffusion in diffusion-based image translation.
method Disentangled style and content representation using intermediate keys from ViT model, CLIP loss, semantic divergence loss, and resampling strategy.
result Outperforms state-of-the-art models in text-guided and image-guided translation tasks.
LLMs show surprising confidence in their answers, beyond just tokens.
problem LLMs lack meaningful confidence estimates for their responses.
method Semantic calibration test based on local loss optimality and equivalence classes.
result Base LLMs are semantically calibrated across tasks, contrary to expectations.
New method neutralizes gender bias in word embeddings without losing semantic information.
problem Gender biases in word embeddings trained on human-generated corpora.
method Latent Disentanglement and Counterfactual Generation with siamese auto-encoder and gradient reversal layer.
result Our method outperforms existing debiasing methods in preserving semantic information and neutralizing gender biases.
ISDA augments deep networks by adding semantic transformations.
problem Improving deep network generalization through semantic data augmentation.
method ISDA augments deep feature space by estimating covariance and drawing random vectors.
result ISDA consistently improves deep model performance on various datasets.
The method learns disentangled representations for localized image manipulations.
problem Image generating neural networks are viewed as black boxes with global effects.
method Localized ResNet Autoencoder with multiple loss functions.
result The network can transfer specific facial attributes like shape and color of eyes, hair, mouth, etc. between persons.
Novel ramp loss method improves weakly supervised machine translation and parsing.
problem Training neural models without gold labels in weak supervision scenarios.
method Adapted ramp loss objectives to promote positive outputs and discourage negative ones.
result Bipolar ramp loss objectives outperform other methods on weakly supervised tasks.
ClusterNet uses few labeled data and unlabeled data to improve clustering performance.
problem Limited performance of current clustering approaches due to lack of labeled data and unsupervised learning limitations.
method ClusterNet employs pairwise semantic constraints from a small set of labeled data and utilizes abundant unlabeled data. It defines a new loss function combining semantic similarity and constrained k-means clustering.
result ClusterNet achieves superior clustering performance on various datasets compared to state-of-the-art deep clustering methods.
Paper proposes a new speech representation benchmark and model.
problem Lack of benchmarks for comparing speech representations.
method Unsupervised triplet-loss objective for training a universal non-semantic speech representation.
result Proposed representation outperforms other models on benchmark and transfer learning tasks.
Improved zero-shot learning with graph-based regularization.
problem Transfer knowledge to unknown classes in zero-shot learning.
method Isoperimetric loss for learning map between visual and semantic embeddings, exploiting graph structure.
result Regularization alone outperforms state-of-the-art methods in zero-shot learning benchmarks.
Paper proposes AoA, a new adversarial attack method that significantly increases transferability.
problem Developing universal adversarial attacks on deep neural networks.
method AoA attacks the semantic property of attention in DNNs, enhancing transferability by altering the loss function.
result AoA generates adversarial samples that defeat 13 well-trained DNNs, achieving over 85% error rate.
Zero-shot contrastive loss improves text-guided image style transfer without extra training.
problem Stochastic nature of diffusion models leads to trade-offs between style transformation and content preservation.
method Proposes a zero-shot contrastive loss for diffusion models that doesn't require additional fine-tuning or auxiliary networks.
result Method outperforms existing methods while preserving content and requiring no additional training.
Paper proposes adaptive margin loss to improve few-shot learning.
problem Few-shot learning's difficulty in generalizing from a few examples.
method Develops class-relevant and task-relevant additive margin losses.
result Boosts performance of metric-based meta-learning approaches.
The paper presents a method for generating well-calibrated prediction intervals using quality-driven deep ensembles.
problem Generating reliable prediction intervals for regression analysis.
method A multi-objective loss function combining quality measures for prediction intervals and point estimates, with a penalty function to ensure semantic integrity and stability.
result The method produces well-calibrated prediction intervals and point estimates, capturing both aleatoric and epistemic uncertainty.
New Bayes' theorem optimizes semantic channels for machine learning.
problem Class imbalance and semantic meaning evolution in natural language.
method Convert Shannon's channel to semantic channel using third kind of Bayes' theorem.
result CM algorithm explains natural language evolution and improves predictive models.
Study improves semantic segmentation of LiDAR point clouds for autonomous vehicles.
problem Semantic understanding of 3D LiDAR data for autonomous vehicles.
method Image-based semantic segmentation architectures, network size optimization, improved point cloud projection, soft Dice loss, reduced weight-sharing convolution.
result 3.2% increase in mIoU segmentation performance with 42% reduction in inference time.
Adversarial tweets can fool stock prediction models, causing financial loss.
problem Vulnerability of stock prediction models to adversarial attacks on social media.
method Solving combinatorial optimization problems with semantic and budget constraints to generate adversarial tweets.
result Adversarial tweets can fool stock prediction models and cause significant financial loss.
MDEQ models learn multi-resolution features efficiently.
problem Large-scale, hierarchical pattern recognition.
method Implicit differentiation, multiscale deep equilibrium model.
result MDEQs achieve performance on par with recent models.
New insights show embedding lengths correlate with semantic properties.
problem Contrastive embedding norms ignore embedding magnitudes but correlate with semantic properties.
method Formal theoretical framework and analysis of optimization dynamics.
result Embedding lengths encode semantic information as a byproduct of training.
CM algorithm matches Shannon's and semantic channels for multi-label classification.
problem Tackles label learning and selection for multi-label classification.
method Adheres to maximum semantic information criterion, uses Bayes' theorem, and trains truth functions.
result Shows improved performance and adaptability to changing source distributions.
Proposes a novel framework for multi-label text classification.
problem Lack of coherent consideration of non-consecutive and long-distance semantics and hierarchical relations among labels.
method Hierarchical taxonomy-aware and attentional graph capsule recurrent CNNs framework.
result Significantly improves multi-label text classification performance.
Paper improves robustness of semantic segmentation models.
problem Improving robustness of semantic segmentation models for safer interactions.
method Analyzes and corrects softmax function mappings to improve model robustness.
result Improves robustness with minimal performance impact and code changes.
W-RNN improves text classification by extracting serialized text semantics.
problem Semantic constraint in sparse representation classification methods.
method Weighted RNN using word vectors and recurrent neural networks.
result W-RNN outperforms other methods in precision, recall, F1, and loss values.
New method calibrates Bayesian neural network approximations for better task-specific predictions.
problem Inaccurate approximations of Bayesian neural networks without task-specific knowledge.
method Introduces a loss-calibrated evidence lower bound informed by Bayesian decision theory.
result Achieves higher utility for applications with asymmetric utility functions.
Deep learning captures semantic structure of large documents.
problem Understanding complex, structured documents like scholarly articles and business reports.
method Deep learning-based document ontology to capture semantic structure and domain-specific concepts.
result The ontology enhances semantic indexing for better understanding by humans and machines.
Enhances hand gesture recognition with separate networks and shared features.
problem Improving recognition accuracy of unimodal 3D-CNNs for dynamic hand gestures.
method Separate networks for each modality, collaborative learning, spatiotemporal semantic alignment loss, focal regularization.
result Improves test time recognition accuracy and state-of-the-art performance.
CSTEM models document topics using VAE with semantic distance.
problem Inability of previous topic models to explain semantic relations correctly.
method Continuous semantic topic embedding model using variational autoencoder and Mahalanobis distance.
result Improves topic coherence and semantic relation explanation.
Paper explores vector embeddings, distributional hypothesis, and PIP loss for natural language processing.
problem Understanding the effect of dimensionality on vector embeddings and their functionality.
method Formulates a theoretical framework, proposes PIP loss, and reveals bias-variance trade-off.
result Discovers robustness and forward stability of vector embeddings, answers dimensionality selection problem.
A novel method for efficient CDRL over wireless networks.
problem Challenges in collaborative deep reinforcement learning over wireless networks.
method Semantic-aware heterogeneous federated deep reinforcement learning (HFDRL) algorithm.
result Superior performance compared to state-of-the-art baselines.