- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 3
- Soundness
- 1
Read review
Paper summary
To achieve finer control while preserving good generalization in anomaly generation, this work proposes Controllable and Generalization Anomaly Generation (CGAG). This method formulates controllable generation as a visual understanding problem and employs a fixed pretrained generator to retain the generalization prior. Specifically, it introduces grounded attribute understanding, on-policy generation alignment, and test-time attribute steering to achieve these goals. Empirical evaluation under the ViaA to MVTec AD setting demonstrates improved anomaly controllability and effectiveness in the downstream detection task.
Critical strengths
-
Anomaly generation is a crucial and urgent problem for industrial detection scenarios, especially in the era of LLMs.
-
The paper is well structured and easy to follow.
-
The empirical results in Table 2 demonstrate the effectiveness of the generated anomalies.
Critical weaknesses
-
The research motivation is not clearly articulated. The authors should explain why finer controllability is important for industrial anomaly generation.
-
Based on the training recipe, a well-trained model constructs a good mapping between an input and a generated anomaly . To encourage generation diversity, varying and is inevitable, which introduces new problems for the generation process: (1) How should these be designed, and why would such designs be reasonable? How many are sufficient? These problems impede the deployment in the real-world detection tasks.
-
The scope of empirical evaluation is limited, mainly to benchmarks and experimental settings (leave-one-out would be better). Moreover, for anomaly generation, the most important evaluation is to verify the effectiveness of generated anomalies on different detection algorithms under scarce real anomalous samples. The proposed method conducts this experiment on only one detection algorithm.
-
The ablation study in Table 3 indicates that the positive gains from Grounding and Alignment are quite limited, suggesting an inconsistency between the method design and the empirical evaluation.
Questions for authors
-
In Table 2, what is the detailed difference between generic and targeted augmentation?
-
Based on the proposed method, if instruction e can be regarded as an anomaly generation prompt? If yes, can the authors compare the contributions of different prompt construction strategies?