Vision / Model

AA-CLIP, trained on MVTec AD (for VisA results)

Organisation: Zhejiang University et al.
Family: AA-CLIP
Released: 2025-03-09 (arXiv v1 submission date (https://arxiv.org/abs/2503.06661))
Weights: Closed · Apache-2.0
Links: Paper Code

Training data disclosure: Full list

Level determined for 12% of benchmark cells.

“Results of VisA are obtained using MVTec-AD as”

arxiv.org · paper · Section 4.1 · retrieved 2026-10-15

Everything these base models may have seen is inherited by AA-CLIP, trained on MVTec AD (for VisA results).

OpenAI CLIP · disclosure: Partial list
Evidence

“we use OpenCLIP with the ViT-L/14 architecture as the backbone”

arxiv.org · paper · Section 4.1, Implementation Details · retrieved 2026-10-15

“pretrained="openai", require_pretrained=True,”

raw.githubusercontent.com · code · train.py · retrieved 2026-10-15

Seen, split unclear MVTec AD · in fine-tuning data: the dataset was used; the source does not say which part

Evidence (1)

“Results of VisA are obtained using MVTec-AD as”

arxiv.org · paper · Section 4.1 · retrieved 2026-10-15

Unknown MVTec AD 2 · unknown for its base model OpenAI CLIP: training data not disclosed in enough detail

Unknown MVTec LOCO AD · unknown for its base model OpenAI CLIP: training data not disclosed in enough detail

Unknown VisA · unknown for its base model OpenAI CLIP: training data not disclosed in enough detail

Unknown Real-IAD · unknown for its base model OpenAI CLIP: training data not disclosed in enough detail

Unknown MPDD · unknown for its base model OpenAI CLIP: training data not disclosed in enough detail

Unknown BTAD · unknown for its base model OpenAI CLIP: training data not disclosed in enough detail

Unknown KolektorSDD2 · unknown for its base model OpenAI CLIP: training data not disclosed in enough detail

Configuration used only for VisA results; no released weights found.