SeBA is a joint-embedding framework that separates tabular data into two complementary views and aligns one view's representations to the nearest-neighbor structure of the other, improving feature-label relationships and achieving SOTA results in most benchmarks without relying on augmentations.
In: Advances in Neural Information Processing Systems
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
SimCLR learns visual representations by contrasting augmented views of the same image and reaches 76.5% ImageNet top-1 accuracy with a linear classifier, matching a supervised ResNet-50.
An unsupervised adaptation framework for VLMs enables label-free multi-label image recognition by using multi-sampling to counter iconic bias and blend adaptation to match multi-label distributions, outperforming prior unsupervised methods on four datasets.
VISTA is a test-time adaptation framework for multi-sequence MRI that uses inter-sequence intervention probes and cross-view disagreement variance to gate self-training, yielding Dice gains of +1.89% on low-field African data and +2.82% on pediatric data over the source model.
A hybrid semi-supervised framework fusing Whisper embeddings with acoustic and prosodic features achieves 0.751 Macro-F1 for speaker confidence detection and outperforms baselines including WavLM, HuBERT, and Wav2Vec 2.0.
V-JEPA models trained only on feature prediction from 2 million public videos achieve 81.9% on Kinetics-400, 72.2% on Something-Something-v2, and 77.9% on ImageNet-1K using frozen ViT-H/16 backbones.
A two-stage framework adapts source models for cross-device meibomian gland segmentation using weak clinical priors and self-distillation, reaching Dice 0.716 on a 1000-to-100 image benchmark while enabling mask-free operation.
citing papers explorer
-
A Semi-Supervised Framework for Speech Confidence Detection using Whisper
A hybrid semi-supervised framework fusing Whisper embeddings with acoustic and prosodic features achieves 0.751 Macro-F1 for speaker confidence detection and outperforms baselines including WavLM, HuBERT, and Wav2Vec 2.0.