CT-Lite combines Feature Attention Style Transfer (FAST) and Structured Factorized Projections (SFP) with contrastive learning to reach AUROC within 5-7% of uncompressed baselines on compressed CT volumes across three datasets while using far fewer parameters.
Emerging properties in self-supervised vision transformers
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
dataset 1
method 1
citation-polarity summary
fields
cs.CV 9years
2026 9verdicts
UNVERDICTED 9representative citing papers
VFM4SDG is a dual-prior framework that distills cross-domain stable relations from VFMs into DETR encoders and injects semantic-contextual priors into decoder queries to reduce missed detections in single-domain generalized object detection.
ToLL pretrains 3D scene graph generators via anchor-conditioned topological layout recovery and asymmetric structural distillation to learn predicate constraints rather than geometric interpolation shortcuts.
Contrastive-SDXL augments daytime images into realistic night-time versions using SDXL-Turbo with LoRA and multi-level DINOv2 contrastive losses, yielding 6-7% lower miss rate on pedestrian detection versus daytime-only training.
The work creates identity-consistent synthetic makeup data via ConsistentBeauty and adapts models to real images using reinforcement learning in RealBeauty, achieving better identity preservation and real-world performance than prior methods.
Transformer-based ReID embeddings encode BMI most strongly in deeper layers, followed by pitch, gender, and yaw, with pose peaking in middle layers and BMI increasing with depth; cross-spectral settings shift reliance toward structural cues.
LAA-X uses multi-task learning with explicit localized artifact attention and blending synthesis to build a deepfake detector that generalizes to high-quality and unseen manipulations after training only on real and pseudo-fake samples.
SurgMotion outperforms prior methods on 17 surgical video benchmarks by shifting pretraining to latent motion prediction with motion-guided masking, affinity distillation, and diversity regularization on a 15M-sample dataset.
ST-STORM introduces a dual-branch SSL framework that disentangles semantic content from stylistic appearance using gated latent streams, JEPA for content invariance, and adversarial constraints for style capture.
citing papers explorer
-
Learning from Compressed CT: Feature Attention Style Transfer and Structured Factorized Projections for Resource-Efficient Medical Image Analysis
CT-Lite combines Feature Attention Style Transfer (FAST) and Structured Factorized Projections (SFP) with contrastive learning to reach AUROC within 5-7% of uncompressed baselines on compressed CT volumes across three datasets while using far fewer parameters.
-
VFM$^{4}$SDG: Unveiling the Power of VFMs for Single-Domain Generalized Object Detection
VFM4SDG is a dual-prior framework that distills cross-domain stable relations from VFMs into DETR encoders and injects semantic-contextual priors into decoder queries to reduce missed detections in single-domain generalized object detection.
-
ToLL: Topological Layout Learning with Asymmetric Cross-View Structural Distillation for 3D Scene Graph Generation Pretraining
ToLL pretrains 3D scene graph generators via anchor-conditioned topological layout recovery and asymmetric structural distillation to learn predicate constraints rather than geometric interpolation shortcuts.
-
Contrastive-SDXL: Annotation-Preserving Night-Time Augmentation for Pedestrian Detection
Contrastive-SDXL augments daytime images into realistic night-time versions using SDXL-Turbo with LoRA and multi-level DINOv2 contrastive losses, yielding 6-7% lower miss rate on pedestrian detection versus daytime-only training.
-
From Synthetic to Real: Toward Identity-Consistent Makeup Transfer with Synthetic and Real Data
The work creates identity-consistent synthetic makeup data via ConsistentBeauty and adapts models to real images using reinforcement learning in RealBeauty, achieving better identity preservation and real-world performance than prior methods.
-
AttriBE: Quantifying Attribute Expressivity in Body Embeddings for Recognition and Identification
Transformer-based ReID embeddings encode BMI most strongly in deeper layers, followed by pitch, gender, and yaw, with pose peaking in middle layers and BMI increasing with depth; cross-spectral settings shift reliance toward structural cues.
-
LAA-X: Unified Localized Artifact Attention for Quality-Agnostic and Generalizable Face Forgery Detection
LAA-X uses multi-task learning with explicit localized artifact attention and blending synthesis to build a deepfake detector that generalizes to high-quality and unseen manipulations after training only on real and pseudo-fake samples.
-
SurgMotion: A Video-Native Foundation Model for Universal Understanding of Surgical Videos
SurgMotion outperforms prior methods on 17 surgical video benchmarks by shifting pretraining to latent motion prediction with motion-guided masking, affinity distillation, and diversity regularization on a 15M-sample dataset.
-
Stylistic-STORM (ST-STORM) : Perceiving the Semantic Nature of Appearance
ST-STORM introduces a dual-branch SSL framework that disentangles semantic content from stylistic appearance using gated latent streams, JEPA for content invariance, and adversarial constraints for style capture.