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.
Emerging properties in self-supervised vision transformers
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
dataset 1
method 1
citation-polarity summary
years
2026 10representative citing papers
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.
A 3D-warped synthetic triplet dataset plus GRPO post-training on real portraits yields state-of-the-art identity-preserving makeup transfer, evaluated on a new diverse BeautyBench benchmark.
A student model trained on JPEG-compressed chest CT via attention-style distillation and a factorized projection head reaches AUROC within 3–5 percentage points of the uncompressed-teacher baseline on three datasets, while halving the projection-head parameters.
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.
Proposes MODIAD framework with MIS scheduling solved via SMG algorithm and REC-LoRA adaptation for efficient multimodal online distributed industrial anomaly detection, reporting superior performance on MVTec 3D-AD and Eyecandies datasets.
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
-
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
A 3D-warped synthetic triplet dataset plus GRPO post-training on real portraits yields state-of-the-art identity-preserving makeup transfer, evaluated on a new diverse BeautyBench benchmark.
-
Learning from Compressed CT: Feature Attention Style Transfer and Structured Factorized Projections for Resource-Efficient Medical Image Analysis
A student model trained on JPEG-compressed chest CT via attention-style distillation and a factorized projection head reaches AUROC within 3–5 percentage points of the uncompressed-teacher baseline on three datasets, while halving the projection-head parameters.
-
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.
-
Parameter Efficient Multi-Class Intelligent Scheduling for Multimodal Online Distributed Industrial Anomaly Detection
Proposes MODIAD framework with MIS scheduling solved via SMG algorithm and REC-LoRA adaptation for efficient multimodal online distributed industrial anomaly detection, reporting superior performance on MVTec 3D-AD and Eyecandies datasets.
-
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.