TrajGANR learns continuous neural representations of trajectories to enable fine-grained alignment with street-view images and locations in a joint multimodal self-supervised objective, outperforming prior geospatial MSSL methods on urban mobility and road tasks.
A simple framework for contrastive learning of visual representations
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 2
other 1
citation-polarity summary
verdicts
UNVERDICTED 10representative citing papers
VACE learns compact directionally coherent representations for multivariate time series anomaly detection via velocity-consistency training and reports state-of-the-art results on TSB-AD-M.
Discrete decentralized learning dynamics on manifolds converge uniformly to an overdamped Langevin SDE whose stationary states produce orthogonally disentangled, linearly separable features.
Rotation-equivariant convolutions and adaptive TL-Conv layers are added to I2I networks to preserve rotation symmetry and improve translation quality across domains.
The work introduces uncertainty-aware foundation models for clinical data by learning set-valued patient representations that enforce consistency across partial observations and integrate multimodal self-supervised objectives.
CoUn emulates retrained-model behavior on forget data by using contrastive learning on retain data to adjust semantic representations while preserving retain clusters via supervised learning, outperforming prior MU methods in experiments.
ECG-NAT combines masked autoencoder pretraining with hierarchical neighborhood attention and dual-loss fine-tuning to reach 88.1% accuracy on ECG classification using just 1% labeled data.
A per-class loss reweighting scheme based on distributional robustness allows CLIP models to perform class-incremental and domain-incremental learning with minimal memory while limiting forgetting on CIFAR-100, ImageNet1K, and DomainNet.
One-class methods DSVDD and DROC outperform MIL baselines for instance-level detection of rare malignant cells at witness rates ≤1% on bone marrow and oral cytology datasets.
Random label bridge training aligns LLM parameters with vision tasks, and partial training of certain layers often suffices due to their foundational properties.
citing papers explorer
-
TRAJGANR: Trajectory-Centric Urban Multimodal Learning via Geospatially Aligned Neural Representations
TrajGANR learns continuous neural representations of trajectories to enable fine-grained alignment with street-view images and locations in a joint multimodal self-supervised objective, outperforming prior geospatial MSSL methods on urban mobility and road tasks.
-
VACE: Learning Geometrically Structured Representations for Time Series Anomaly Detection
VACE learns compact directionally coherent representations for multivariate time series anomaly detection via velocity-consistency training and reports state-of-the-art results on TSB-AD-M.
-
Continuous Limits of Coupled Flows in Representation Learning
Discrete decentralized learning dynamics on manifolds converge uniformly to an overdamped Langevin SDE whose stationary states produce orthogonally disentangled, linearly separable features.
-
Image-to-Image Translation Framework Embedded with Rotation Symmetry Priors
Rotation-equivariant convolutions and adaptive TL-Conv layers are added to I2I networks to preserve rotation symmetry and improve translation quality across domains.
-
Uncertainty-Aware Foundation Models for Clinical Data
The work introduces uncertainty-aware foundation models for clinical data by learning set-valued patient representations that enforce consistency across partial observations and integrate multimodal self-supervised objectives.
-
CoUn: Empowering Machine Unlearning via Contrastive Learning
CoUn emulates retrained-model behavior on forget data by using contrastive learning on retain data to adjust semantic representations while preserving retain clusters via supervised learning, outperforming prior MU methods in experiments.
-
ECG-NAT: A Self-supervised Neighborhood Attention Transformer for Multi-lead Electrocardiogram Classification
ECG-NAT combines masked autoencoder pretraining with hierarchical neighborhood attention and dual-loss fine-tuning to reach 88.1% accuracy on ECG classification using just 1% labeled data.
-
Memory-Efficient Continual Learning with CLIP Models
A per-class loss reweighting scheme based on distributional robustness allows CLIP models to perform class-incremental and domain-incremental learning with minimal memory while limiting forgetting on CIFAR-100, ImageNet1K, and DomainNet.
-
Needle in a Haystack: One-Class Representation Learning for Detecting Rare Malignant Cells in Computational Cytology
One-class methods DSVDD and DROC outperform MIL baselines for instance-level detection of rare malignant cells at witness rates ≤1% on bone marrow and oral cytology datasets.
-
Language-Pretraining-Induced Bias: A Strong Foundation for General Vision Tasks
Random label bridge training aligns LLM parameters with vision tasks, and partial training of certain layers often suffices due to their foundational properties.