UMID infers membership in contrastive pre-training data using only text queries by performing latent inversion and comparing similarity and variability signals to synthetic gibberish references via unsupervised anomaly detection.
Pixclip: Achieving fine-grained visual language understand- ing via any-granularity pixel-text alignment learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
RADA achieves state-of-the-art barely-supervised 3D medical image segmentation by using a region-aware dual-encoder pre-trained on Alpha-CLIP within a triple-view training framework on LA2018, KiTS19 and LiTS datasets.
citing papers explorer
-
Membership Inference for Contrastive Pre-training Models with Text-only PII Queries
UMID infers membership in contrastive pre-training data using only text queries by performing latent inversion and comparing similarity and variability signals to synthetic gibberish references via unsupervised anomaly detection.
-
RADA: Region-Aware Dual-encoder Auxiliary learning for Barely-supervised Medical Image Segmentation
RADA achieves state-of-the-art barely-supervised 3D medical image segmentation by using a region-aware dual-encoder pre-trained on Alpha-CLIP within a triple-view training framework on LA2018, KiTS19 and LiTS datasets.