- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper investigates the sensitivity of text-to-image diffusion models to semantically equivalent prompt variations. It introduces a conditioning-sensitivity statistic and the CoRBen benchmark, then proposes averaging network predictions across paraphrases to stabilize generation. Early-step averaging and SVRG/SAGA-based estimators reduce the additional network evaluations. Experiments on SD1.5 and FLUX assess image consistency, while full latent averaging is also evaluated through object recall and distributional image-quality metrics.
Critical strengths
-
The paper addresses a meaningful problem with a well-motivated approach. The early-step sensitivity analysis suggests where additional computation is most useful. The conditional-unbiasedness arguments support the proposed estimators, and the residual-cache formulation provides a sensible adaptation to time-dependent diffusion predictions.
-
The benchmark construction includes useful methodological improvements. Prompt-derived concept targets are more appropriate than treating every source-image object as required content. The FSP subset directly targets meaning-preserving perturbations, and full LA3 produces a positive object-recall improvement on this subset.
Critical weaknesses
-
The semantic benefits of the lowest-cost variants remain unverified. Their primary evaluation uses LPIPS and DINO consistency on 100 prompt groups, whereas the object-recall and distributional results concern full LA3. More similar outputs do not necessarily preserve attributes, relations, or appropriate prompt sensitivity. Network-evaluation counts also omit paraphrase-generation and text-encoding costs.
-
Some benchmark results are difficult to interpret as semantic robustness. Alternative captions and several legacy corruptions can change the requested content while retaining the clean anchor’s targets. Consequently, improved recall may reflect recovery of anchor content. The more relevant FSP subset needs a clearer semantic audit and an explicit description of evaluation-time auxiliary-prompt construction.
Questions for authors
-
Do the lowest-cost SVRG and SAGA variants improve semantic correctness and image quality on the existing FSP subset?
-
How are auxiliary prompts constructed, can they access the clean anchor, and what is the measured end-to-end latency?
2 comments
Dear Reviewer T6vr,
We thank the reviewer for their thoughtful feedback. We kindly invite them to revisit our rebuttal and revised manuscript. We would welcome their updated assessment and any remaining questions.
We thank the reviewer for the time invested in assessing our work and their careful evaluation. We address their questions point by point, and then the remaining benchmark concern.
Q1. Both lowest-cost variants improve semantic correctness. We added SVRG35 and SAGA3∗5 to the full CoRBen FSP evaluation (Appendix B.2, pp. 17-18, Table 5). For convenience, all new results in the revised manuscript are highlighted in blue. At GLIP threshold 0.5, instance recall increases from 87.41% to 87.82% and 87.88%, respectively. On independently selected unstable concepts, OR0.5∗∗ increases from 73.27% to 74.30% and 73.88%.
We also evaluated every efficient variant on all 2,400 T2I-CompBench++ prompts (Appendix B.1, pp. 16-17, Tables 3-4). Every scheme improves all eight category scores and all five atomic recall metrics, covering attributes, spatial and non-spatial relations, counting, and complex compositions. Thus, improved consistency accompanies better realization of requested content.
Q2. The user supplies one prompt. Auxiliary formulations are generated automatically by a few-shot LLM instructed to preserve visual semantics exactly. Exact instructions and settings appear in Appendices G (p. 30), H.4 (pp. 32-33), and J (pp. 37-43). The timed FSP pipeline uses Qwen3-30B-A3B to generate nine candidates and select two.
Appendix B.5 (pp. 19-20) now measures encoding, denoising, and VAE decoding, plus rewriting separately. On A100, baseline generation takes 0.98 s, SVRG 1.00 s, and SAGA 1.01 s. Rewriting adds 0.079 s per prompt at batch size 256, corresponding to approximately 1.08-1.09 s of combined amortized work for one image per prompt. For a detailed discussion, see Appendix B.5 (pp. 19-20). Peak generation memory remains 2.61 GB since VAE decoding determines it.
The answers above address W1. Regarding W2, legacy captions and corruptions can indeed alter semantics. We used them to test the proposed averaging mechanism. The newly introduced FSP represent the practically relevant setting of semantics-preserving reformulations.
We added a quantified FSP audit with Claude Opus 5.5, a higher-capacity judge from a different family than the Qwen generator (Appendix H.4, pp. 32-33, Table 19). It evaluates 849 FSP pairs, 400 alternative-caption pairs, and 50 negative controls from 100 anchors using Listing 5's instruction. Exact preservation is 84.8% [82.1, 87.4] for FSP versus 1.0% [0.2, 2.0] for alternative captions. Approximate preservation is 99.1% [98.3, 99.8] versus 71.5% [64.8, 77.3]. This quantifies both FSP's substantially greater semantic fidelity and its remaining errors. Our expanded comparisons focus on FSP and explicit attribute/relation tests.
Additional evaluations motivated by other reviewers
We appreciate the reviewer's attention and valuable suggestions. The revisions have substantially strengthened the evaluation of the proposed schemes and addressed all concerns raised. We hope these improvements provide a basis for reconsidering the score.