- Rating
- 1
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
This paper proposes Spectral Saliency-Guided Erasure (SSGE), a concept erasure method that combines spectral saliency-based parameter gating with ordered gradient projection. The method estimates forget and retain gradient subspaces to identify concept-relevant parameters and projects the gated forget gradient away from the retain subspace. Experiments on Stable Diffusion 1.5 demonstrate effective suppression of artistic styles and object concepts, but also reveal noticeable degradation in non-target generation.
Critical strengths
-
The proposed framework is reasonably motivated, and the analysis of operator ordering provides a clear mathematical explanation of the local orthogonality constraint.
-
The experiments demonstrate consistent target suppression across multiple concepts, including held-out synonym and compositional prompts.
Critical weaknesses
-
Limited evidence for the effectiveness of the core designs is the major problem. The ablation results do not demonstrate clear or consistent benefits from the proposed spectral saliency gate and ordered gradient projection. In Table 2, removing the gate yields nearly identical erasure performance with better preservation, while reversing the projection order also improves preservation metrics. These results raise concerns about the practical contributions of the proposed components.
-
The baseline comparisons are insufficient. The experiments compare against only a small set of baselines, with limited coverage of recent concept erasure methods. In particular, comparisons with closely related gradient-based and preservation-aware approaches are missing, making it difficult to establish the competitiveness of SSGE.
-
The paper is not well-written. The manuscript would benefit from more careful organization and proofreading. For example, the comparison table on page 8 lacks a table number and caption, affecting the clarity and professionalism of the presentation.
Questions for authors
-
Could the authors further clarify the practical contributions of the spectral saliency gate and ordered gradient projection?
-
Could the authors provide additional comparisons with recent and closely related concept erasure methods to better establish the competitiveness of SSGE?