concept activation vectors 1embedding perturbation 1explainability 1image similarity 1representation learning 1
From the 1 of 3 linked papers with an AI index.
3 papers
cs.CV2026
Explaining Image Similarity with Automatically Extracted Concept Activation Vectors
Isaac Roberts, Petra Bevandic, Alexander Schulz +1
The paper proposes a model‑agnostic method that uses automatically discovered concept activation vectors to explain why two images are considered similar, by perturbing embeddings…
cs.CV2025
TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models
Riza Velioglu, Petra Bevandic, Robin Chan +1
This paper introduces Virtual Try-Off (VTOFF), a novel task generating standardized garment images from single photos of clothed individuals. Unlike Virtual Try-On (VTON), which di…
cs.CV2025
MGT: Extending Virtual Try-Off to Multi-Garment Scenarios
Riza Velioglu, Petra Bevandic, Robin Chan +1
Computer vision is transforming fashion industry through Virtual Try-On (VTON) and Virtual Try-Off (VTOFF). VTON generates images of a person in a specified garment using a target…