SAFe: Segment-guided Aggregation of Feature Densities for Anomaly-aware Segmentation

arXiv:2609.24204 · cs.CV · Submitted 2026-09-21 · Read on arXiv

cs.CV

Submitted: 2026-09-21

Updated: 2026-09-21

Terminology

• Normalizing Flow — 22× in this paper · explained in 3 episodes
• Aggregation — 19× in this paper · explained in 1 episode
• Clustering — 16× in this paper · explained in 2 episodes
• Transformer — 16× in this paper · explained in 2 episodes
• Benchmark — 12× in this paper · explained in 2 episodes
• Normalizing Flows — 12× in this paper · explained in 4 episodes
• Consistency — 7× in this paper · explained in 3 episodes
• Foundation Model — 6× in this paper · explained in 3 episodes
• Instance Segmentation — 5× in this paper · explained in 3 episodes
• Feature Extraction — 4× in this paper · explained in 2 episodes
• Foundation Models — 4× in this paper · explained in 7 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Homogeneity — 2× in this paper · explained in 2 episodes
• Spectral clustering — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Abstention — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Bayesian Information Criterion — 1× in this paper
• Contrastive Learning — 1× in this paper · explained in 5 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• F1 Score — 1× in this paper · explained in 3 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Temporal consistency — 1× in this paper · explained in 2 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Transformer Architecture — 1× in this paper · explained in 2 episodes
• Vision Transformer (ViT) — 1× in this paper · explained in 2 episodes

Sources

• DINOv3
• SAM 3: Segment Anything with Concepts
• SAM 2: Segment Anything in Images and Videos
• Open-World Panoptic Segmentation
• DINOv2: Learning Robust Visual Features without Supervision
• VL4AD: Vision-Language Models Improve Pixel-wise Anomaly Detection
• Learning Likelihoods with Conditional Normalizing Flows
• GLU Variants Improve Transformer
• Searching for Activation Functions

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models