- Rating
- 2
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper proposes Symmetry-Aware Region Representations (SRR) for two-stage oriented object detection. By modeling local axis reversals as a four-element symmetry group, the proposed GCA module constructs target-specific equivariant features, while SFL learns separate transformations for different feature types. Experiments across five remote sensing benchmarks demonstrate consistent improvements, particularly in localization accuracy.
Critical strengths
-
The paper introduces a well-motivated symmetry-based formulation for learning region representations in oriented object detection.
-
The proposed GCA and SFL modules provide a mathematically grounded architecture with explicitly enforced local equivariance.
Critical weaknesses
- Although the proposed architecture guarantees equivariance under axis reversals, the paper does not directly establish how this constraint translates into improved robustness or localization. Controlled experiments on equivalent frame representations, proposal perturbations, and different object orientations would better substantiate the central hypothesis.
2.The paper reports improvements in AP75 and average localization accuracy, but provides limited insight into which geometric configurations benefit most. A breakdown by object aspect ratio, orientation, proposal quality, and angle residual would help clarify whether the gains are specifically attributable to the proposed symmetry-aware representation.
- GCA combines four transformed RoI representations, which may itself improve feature robustness through implicit ensembling. Comparisons with unsigned multi-frame averaging, unconstrained multi-frame fusion, and alternative parameter-matched aggregation schemes would help determine the specific advantage of enforcing target-dependent transformation laws.
4.The reported FLOPs exclude certain operations, while latency measurements primarily focus on the detection head. End-to-end inference latency, memory consumption, and throughput under different numbers of RoIs are needed to establish the practical computational overhead of SRR.
Questions for authors
see the Weaknesses
3 comments
(2/2)
W3 / Q — Target signs and multi-frame fusion
All variants use the same four frames and hidden width with SFL disabled. GCA uses fixed equal signed weights. The table reports DOTA-v1.0 results.
| Aggregation | AP50 | AP75 | AP50:95 |
|---|---|---|---|
| Unsigned mean | 76.86 ± 0.30 | 50.98 ± 0.42 | 47.73 ± 0.27 |
| Learned fusion | 77.00 ± 0.15 | 51.95 ± 0.76 | 48.23 ± 0.14 |
| GCA | 77.03 ± 0.16 | 52.56 ± 0.66 | 48.60 ± 0.59 |
| Fixed nonuniform | 77.58 ± 0.08 | 52.17 ± 0.51 | 48.62 ± 0.18 |
Learned fusion optimizes 16 free coefficients, initialized uniformly. GCA achieves higher AP75 and AP50:95 than unsigned mean and learned fusion. On DIOR-R, mean AP50:95 is 41.93 ± 0.20 for GCA, compared with 40.70 ± 0.31 for unsigned averaging and 41.16 ± 0.25 for learned fusion with uniform initialization.
The fixed nonuniform variant retains the target signs but assigns weight 0.4 to the original frame and 0.2 to each reversed frame, with the same head parameter count as GCA. It favors AP50, whereas GCA achieves higher AP75, with similar AP50:95. GCA is our default because its equal signed weights preserve the prescribed transformation laws exactly.
W4 / Q — Latency, memory, and throughput
We measure patch-level detector latency, memory, and throughput across head architectures and RoI counts, including the FAA and Strip Head implementations compared in Table 6. The measurements cover the detector from backbone feature extraction through box decoding and NMS, including operations omitted from the FLOP counts.
| RoIs | Head | Median detector latency (ms) | Peak allocated memory (MiB) | Throughput (patches/s) |
|---|---|---|---|---|
| 128 | Baseline | 46.73 | 506.8 | 21.730 |
| 128 | GCA | 47.89 | 556.8 | 21.127 |
| 128 | SRR | 48.08 | 580.8 | 21.004 |
| 512 | Baseline | 48.80 | 506.8 | 20.844 |
| 512 | GCA | 50.31 | 556.8 | 20.077 |
| 512 | SRR | 50.69 | 580.8 | 19.910 |
| 2000 | Baseline | 54.40 | 506.8 | 18.700 |
| 2000 | GCA | 60.77 | 578.2 | 16.654 |
| 2000 | FAA | 70.12 | 888.1 | 14.503 |
| 2000 | Strip Head | 73.77 | 1087.9 | 13.875 |
| 2000 | SRR | 62.40 | 603.9 | 16.089 |
At the default 2,000 RoIs, SRR increases median detector latency by 8.00 ms (14.71%) and peak allocated memory by 97.1 MiB over Baseline. The latency overhead narrows to 1.89 ms at 512 RoIs and 1.35 ms at 128 RoIs. Although FAA and SRR have similar FLOPs in Table 6, SRR has 11.0% lower latency and 32.0% lower peak allocated memory. The reductions relative to Strip Head are 15.4% and 44.5%, respectively. SRR also has higher throughput than both heads. Table 6 reports mean AP75 gains of 1.61 points over FAA and 1.82 points over Strip Head, along with higher AP50:95.
We use final seed-0 checkpoints on the same 20 DOTA test patches with an RTX 2080 Ti, eager FP32 inference, and batch size 1. Latency is the median over synchronized patch calls; throughput is completed patch inferences divided by elapsed time in a separate measurement. Memory is peak GPU memory allocated by PyTorch, including model and input tensors. Data loading, preprocessing, host-to-device transfer, and whole-image splitting and merging are excluded. Table 16 in Appendix C.5 reports the comparison and measurement details.
As the discussion period is coming to a close, we wanted to kindly check whether there is anything further we can clarify or discuss. We hope our rebuttal and revisions have addressed your concerns, and we would be happy to answer any remaining questions. Thank you again for your time and feedback.
(1/2)
Thank you for your constructive feedback highlighting the need for direct geometric and computational comparisons. Your suggestions helped us substantially strengthen the manuscript. Unless specified otherwise, AP results use final checkpoints and report mean ± sample standard deviation over three training runs.
W1 / Q — Localization and perturbations
On shared baseline RPN proposals, three-run mean refined IoU increases from 0.8504 for Baseline to 0.8597 for SRR on HRSC2016. On DIOR-R, SRR achieves 0.8026, compared with 0.7966 for Baseline. Each model uses its own trained backbone. Table 5 in §4.3 of the revised manuscript reports these comparisons.
To assess sensitivity to proposal angles, we perturb the shared positive proposals by ±5° and evaluate final checkpoints from three training runs on all 11,738 DIOR-R test images. Within each run, the three models use the same Baseline RPN proposals with initial IoU ≥0.5. Original GT assignments and each model's image feature maps remain fixed; RoI features are extracted again at the perturbed proposals. We evaluate refined IoU before NMS, averaging within GT instances and then equally across instances. The table reports mean ± sample standard deviation across runs.
Relative to each model's natural condition, the mean IoU drop averaged equally over −5° and +5° is 0.00638 for Baseline, 0.00406 for GCA, and 0.00413 for SRR. GCA and SRR reduce this drop by 36.3% and 35.3%, respectively. The smaller perturbation loss is already present with GCA, while SFL improves absolute localization: SRR exceeds GCA in every run and condition. We have added the angle perturbation comparison to Appendix C.6 of the revised supplementary material.
We also examine the target transformation laws directly on 58,496 fixed pooled RoI features, comparing predictions after local axis reversals with the original predictions transformed by the target signs. Across GCA and SRR, maximum absolute differences are 3.81×10−6 for classification logits and 1.91×10−6 for regression outputs.
W2 / Q — Geometric configurations
For positive proposals with initial IoU ≥0.5 on DIOR-R, SRR improves refined IoU over Baseline across the groups below. Values are means over three runs. Aspect-ratio groups use GT boxes; quality groups use the common input proposals.
The following breakdowns use seed-0 final checkpoints. GT orientation uses the long-axis angle for AR≥1.2. Absolute initial coded angle residuals use
le90edge-swap targets across all aspect ratios. Each bin averages proposals within GTs, then equally across GTs.SRR improves refined IoU over both Baseline and GCA in all four orientation intervals, and its gains increase across the four coded-residual bins. Across three runs, the mean SRR−GCA gain within 5° of the coder's 45° width–height swap boundary is 0.00691 IoU, versus 0.00216 overall, with gains in every run. We have added the full breakdowns to Appendix C.6 of the revised supplementary material.