Invisible Shortcuts: Why Vision Encoders Know Your Camera

arXiv:2608.05424 · cs.CV, cs.LG · Submitted 2026-08-05 · Read on arXiv

Vladan Stojnić, Ryan Ramos, Giorgos Kordopatis-Zilos, Noa Garcia, Giorgos Tolias

cs.CV, cs.LG

Submitted: 2026-08-05

Comments: ECCV 2026

Code: https://github.com/ryan-caesar-ramos/visual-encoder-traces

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 44× in this paper · explained in 1 episode
• Semantic Prediction — 22× in this paper
• Trace — 22× in this paper · explained in 2 episodes
• Augmentation — 19× in this paper · explained in 2 episodes
• Robustness — 14× in this paper · explained in 6 episodes
• Metadata Prediction — 11× in this paper
• Shortcut Learning — 11× in this paper · explained in 3 episodes
• Generalization — 10× in this paper · explained in 14 episodes
• Transformer — 5× in this paper · explained in 2 episodes
• Benchmark — 4× in this paper · explained in 2 episodes
• Distribution Shift — 4× in this paper · explained in 12 episodes
• Embeddings — 4× in this paper · explained in 2 episodes
• Semantic Prediction Distraction — 4× in this paper
• Data Augmentation — 3× in this paper · explained in 10 episodes
• Distribution Shifts — 3× in this paper · explained in 2 episodes
• Downstream Tasks — 3× in this paper · explained in 2 episodes
• Transformers — 3× in this paper · explained in 2 episodes
• Weight Decay — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Foundation Model — 2× in this paper · explained in 3 episodes
• Foundation Models — 2× in this paper · explained in 8 episodes
• Frozen model — 2× in this paper · explained in 3 episodes
• Generative Model — 2× in this paper · explained in 2 episodes
• Generative Models — 2× in this paper · explained in 3 episodes
• Random Augment — 2× in this paper
• Regularization — 2× in this paper · explained in 3 episodes
• Representation Learning — 2× in this paper · explained in 3 episodes
• Topic Modeling — 2× in this paper · explained in 2 episodes
• Training Objective — 2× in this paper · explained in 3 episodes
• Vision-language models — 2× in this paper · explained in 2 episodes
• Ablation Study — 1× in this paper · explained in 3 episodes
• Benchmarking — 1× in this paper · explained in 4 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Contrastive Learning — 1× in this paper · explained in 9 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Diffusion Model — 1× in this paper · explained in 10 episodes
• Diffusion Models — 1× in this paper · explained in 9 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Feature Extraction — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generator — 1× in this paper · explained in 2 episodes
• Latent Diffusion Model — 1× in this paper · explained in 3 episodes
• Latent Diffusion Models — 1× in this paper · explained in 2 episodes
• Localization — 1× in this paper · explained in 2 episodes
• Scaling Laws — 1× in this paper · explained in 4 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes

Sources

• BERTopic: Neural topic modeling with a class-based TF-IDF procedure
• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction

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