- Rating
- 2
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper proposes CASAdapter for controlling the visual saliency of a selected object. It modifies the object’s CLIP image embedding based on scene context while keeping CLIP, IP-Adapter, and the diffusion inpainting model frozen. The adapter predicts a gated update orthogonal to the original embedding, then normalizes and rescales the result to preserve its norm and bound the angular change. Training combines saliency, semantic consistency, and color-gradient losses. The method is evaluated on 300 images from the COCO validation set. The authors report predicted saliency changes and CLIP similarity at different modulation strengths. Positive modulation increases the object’s average share of predicted saliency across several saliency models, while stronger modulation reduces similarity to the reference object.
Critical strengths
-
CASAdapter works with a frozen reference-guided diffusion pipeline and requires training only a small modulation module. Its signed control parameter allows users to increase or decrease the target object’s predicted saliency.
-
The evaluation includes several saliency models beyond UniSal, which provides the training signal. The paper also acknowledges that these predictions do not establish control over human attention or guarantee preservation of object identity.
Critical weaknesses
-
Object-level saliency editing has been studied before, but the paper does not adequately discuss closely related work or establish a clear advance over existing methods. The proposed module combines scene cross-attention, gating, and an orthogonal update followed by normalization, without ablations showing the separate contributions of scene context and orthogonal projection. Preserving the embedding norm and bounding its angular change do not, by themselves, ensure better preservation of the generated object’s semantics or appearance.
-
General-purpose image editing models already support local changes to color, lighting, and appearance. The paper neither compares against these models nor includes simple brightness, saturation, or contrast adjustments as baselines. The results therefore do not establish why saliency enhancement requires a dedicated adapter, or whether the proposed method offers advantages in control consistency, object fidelity, or computational cost.
Questions for authors
-
How were the 300 test images selected? When an image contains multiple instances, how was the target object chosen? Were any filters applied based on object category, size, or initial saliency?
-
Could you provide ablations without scene context and with a non-orthogonal residual update that retains norm normalization? These would help distinguish the contributions of context, normalization, and orthogonal projection.
-
What is the exact formulation of the affine baseline, and why is only a modulation strength of 0.15 reported? Could you evaluate several strengths and compare the two methods at matched saliency gains or reference similarity?
-
How does CASAdapter compare with simple brightness, saturation, and contrast adjustments, as well as representative general-purpose instruction-based editing models? Do these comparisons show an advantage in the consistency of saliency control or object fidelity?