- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
The proposed method (SV-RoPE) is an approach to finetune vision transformers in remote sensing by providing a context-aware positional encoding that adapts to the image's true resolution, and how heterogeneous or homogeneous different parts of the image are. The method claims to be more parameter-efficient and provide better adaptation compared to baselines.
Critical strengths
- The paper is well motivated. It clearly distinguishes physical scale from local structure: even at the same resolution, a uniform forest and a dense urban area present different spatial relationships. Adapting positional encoding to these differences is a reasonable direction.
- The evaluation is broad and the results are encouraging. Across three pretrained backbones and all downstream datasets, SV-RoPE achieves the highest overall average for each backbone. The component ablations also provide useful results that both physical-scale calibration and local-profile conditioning contribute meaningfully.
Critical weaknesses
I identify two main weaknesses in the work relating to the proposed methodology. Additionally, I cannot find any appendix in the paper either as additional pages in the main text or a separate supplementary material attachment. Appendix sections, however, are referenced multiple times in the main text.
My primary concern is a potential mismatch between the motivation and the implemented method. The authors propose a positional encoding that adapts to the local structure within an image, but their formulation also changes the interaction depending on where that structure exists within the image crop. For example, an image with a house next to a forest receives different positional treatment when moved from one part of the crop to another. The authors acknowledge that their formulation is not translation-invariant, but I do not think acknowledging this explains why the additional dependence is desirable. Satellite imagery is translation invariant, and I believe a positional encoding designed for satellite imagery should take this into account. Testing consistency across crop placements would directly address my concern.
Lastly, I find the writing to be very complicated and difficult to understand on a first read. For instance, the abstract's mention of the proposed method is incredibly dense.
Leveraging the coupled displacement–frequency structure of RoPE, SV-RoPE encodes spatial variation directly into a unified rotary phase, jointly parameterized by Relation Coordinate Calibration (RCC) for initial ground-extent-calibrated displacement and Relation Frequency Calibration (RFC) for SV-Profile-conditioned frequency modulation.
Some simplification of writing would help the readability of the paper.
I also find comparisons to baselines difficult to interpret in the paper. If the proposed adaptation techniques needs an attention-parallel branch to every block of the transformer, I believe the additional parameter and flop count, as well as the parameter and flop count of baselines could be reported. This will help clarify is the proposed SV-RoPE method is indeed parameter efficient compared to baselines.
My inclination is a weak reject given the current draft. However, if the authors can challenge and respond to my critiques surrounding the methodology, and provide a clean appendix with the experimental details, computational cost comparisons, and simplify the writing, I would be willing to increase my score.
Questions for authors
- I find the methods comparing with RoPE and RCC to be helpful and interesting. Could the authors comment on the relationship between the LoRA + RoPE ablation and the attention-parallel architecture? What is held constant here?
- Would performance improvements hold at similar parameter and computational budgets?
3 comments
Response to Reviewer xLxG
3. Ablation setup (Q3).
All ablation variants in manuscript Table 2 share the same training schedule, differ only in the components listed in Table 3. Every variant below the LoRA row adds the same attention-parallel branch, and every variant from the RCC row onward keeps RCC. The three conditioned variants (Global scaling, DAPE, and SV-RoPE) share the same frequency mapper and differ only in its input. Each row therefore isolates one change at constant capacity.
We will revise manuscript Table 2 to make these settings explicit.
Table 3. Configuration of the ablation variants in manuscript Tab. 2.
| Variant | Parallel branch | RCC | Conditioning input | Mapper output | Trainable params (M) |
|---|---|---|---|---|---|
| LoRA | – | – | – | – | 1.03 |
| + RoPE branch | ✓ | – | – | – | 1.33 |
| + RCC | ✓ | ✓ | – | – | 1.33 |
| Global scaling | ✓ | ✓ | SV-Profile averaged over tokens | one factor per band, shared across the image | 1.33 |
| DAPE [1] | ✓ | ✓ | token embedding | one factor per band per token | 1.34 |
| SV-RoPE | ✓ | ✓ | SV-Profile per token | one factor per band per token | 1.33 |
[1] DAPE: Data-Adaptive Positional Encoding for Length Extrapolation. In NeurIPS 2024.
4. Adapter parameter budget (Q4).
Doubling the LoRA rank from 8 to 16 doubles its parameters but barely moves its scores, and rank 16 still trails SV-RoPE with fewer parameters (Table 4). The gap is therefore not a matter of adapter capacity.
Table 4. Performance at different adapter parameter budgets.
| Method | Trainable adapter parameters | CLS | SEG |
|---|---|---|---|
| LoRA (rank 8) | 1.03 | 82.93 | 63.76 |
| LoRA (rank 9) | 1.16M | 83.28 | 65.38 |
| LoRA (rank 16) | 2.06M | 83.35 | 65.58 |
| SV-RoPE | 1.33M | 84.33 | 66.43 |
5. Writing clarity and the missing appendix (Q5).
(i) Appendix. Thank you for flagging that it was missing. The revised appendix will contain:
- Dataset descriptions: source, resolution, split sizes, and GSD for each of the 12 datasets.
- Implementation details: parallel-branch design, SV-Profile scales, optimizer, and schedule.
- Computation cost comparison (as already presented in Q2 Table 2)
(ii) Writing. We will make three specific changes. First, we will refine the presentation to make it more readable; Second, section 3 will open with a one-paragraph overview that states the two problems (scale mismatch across GSDs and uniform positional frequencies across heterogeneous content) and maps RCC and RFC to them before any equations; Third, we will correct Eq. (8), unify the notation for the modulation factors.
We thank you again for your feedback. We would be happy to provide any further clarification during the discussion period.
Best regards,
The Authors
Response by Reviewer xLxG to Authors
Thank you for the additional experiments and clarifications. I remain at weak reject given the memory and latency costs relative to the performance gains. More importantly, the authors' rebuttal revisions still do not contain an appendix a month after the submission deadline despite references made to it in the main text. Creation of an appendix is a substantial revision. The paper is thus incomplete, and I encourage the authors to finish the manuscript and resubmit.
Response to Reviewer xLxG
Dear Reviewer xLxG,
We are grateful for your careful reading and constructive feedback. We address the methodology in Q1–Q4 below with new experiments, and Q5 lists the concrete contents of the appendix and the specific writing changes we will make.
1. Translation invariance and crop-placement consistency (Q1).
We agree that dependence on crop placement is undesirable and unintended. Our goal is to assign distinct positional sensitivities to tokens with heterogeneous local spatial variation; origin dependence is merely a side effect of token-wise phase scaling, which our design minimizes rather than exploits.
In the reviewer's example, the scales κ for both the house and forest tokens are computed over symmetric, content-tracking neighborhoods and thus remain invariant as the pair shifts within the crop. Only their coupling with absolute coordinates changes: a spatial shift c alters the relative phase by θmc(κv,m−κu,m), proportional to the scale difference between the two tokens. Because neighborhood averaging (Eq. 14) keeps adjacent scales close, this residual term stays small for the local token pairs.
Moreover, since the frozen DOFA backbone relies on absolute position embeddings, the LoRA baseline is not translation-invariant either; the key question is whether SV-RoPE introduces additional sensitivity. We further evaluated the spatial sensitivity in three settings:
As shown in Table 1, coordinate shifts leave both scores essentially unchanged. Under crop placement, SV-RoPE exhibits sensitivity comparable to LoRA without degrading accuracy or mIoU. Tiling drops several mIoU points on both methods, so that degradation is a tiling effect rather than a phase effect. We will state the limitation and this analysis in Section 3.3.3.
Table 1. Spatial consistency. Parentheses show the score change from the original setting.
2. Baseline comparability and efficiency (Q2).
SV-RoPE follows the same downstream PEFT setting as the baselines. We freeze the pretrained backbone and train a small set of additional parameters. SV-RoPE merely adapts positional interactions to ground scale and local spatial variation.
(i) Parameters. The branch adds 0.30M low-rank parameters over rank-8 LoRA; the frequency mapper adds <0.01M.
(ii) Compute. On RTX A6000, training FLOPs rise by about 10% for classification and 30% for segmentation and stay below SLR. Peak memory and inference latency are higher than both baselines because the branch computes a second attention map in each block. SV-RoPE is therefore parameter efficient; its cost is in compute and memory, and we will state this in the revision (Table 2).
Table 2. Trainable parameters and computation costs.