- Rating
- 2
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper aims to allocate computation more selectively without sacrificing detection performance. Specifically, CPSR uses Laplacian-based high-frequency scores to select informative regions for local zoom-in re-encoding and then reassembles them with global features to preserve contextual information. DA-AQA further adapts the number of decoder queries according to the confidence distribution of encoder proposals, allowing different images to use different decoding budgets based on their estimated object density.
Critical strengths
- The motivation is clear and well aligned with practical challenges in remote-sensing object detection, where high-resolution imagery, small objects, and large variations in object density make computational efficiency an important problem.
- The experimental section compares against a relatively broad set of recent and competitive baselines.
Critical weaknesses
-
The design of Context-Preserved Selective Reassembly (CPSR) is not sufficiently justified, and several important implementation choices remain unclear or heuristic. Specific concerns include:
- The relationship among the local crops introduced in the full local reassembly scheme, the fine-grained patches used in CPSR, and the subsequent packing operation is not clearly explained. These three partitioning schemes serve different purposes, but the current presentation makes their roles, magnification factors, and spatial correspondence difficult to follow. The authors should reorganize this part and explicitly clarify how these operations are related and how the packed observations are mapped back to the original image coordinate system.
- The use of a Laplacian-based high-frequency score for patch selection appears highly heuristic. High-frequency response does not necessarily correspond to object-rich or informative regions, particularly in remote-sensing imagery. The paper should provide direct evidence that the proposed score indeed prioritizes useful regions, e.g., by reporting GT coverage or small-object recall under different selection budgets.
- Packing spatially non-adjacent patches into the same local observation may introduce artificial spatial context. Since DINOv2 relies on global self-attention and positional embeddings, patches that are distant in the original image can interact after being packed next to each other, creating dependencies that do not exist in the original scene. Such effects cannot be removed simply by reassembling the encoded features back to their original locations. The paper should evaluate whether this artificial interaction affects representation quality, for example by comparing packed encoding with independent patch encoding or with full local reassembly.
- The direct reassembly of local and global features is insufficiently analyzed. CPSR replaces selected regions with zoomed-in local features while filling unselected regions with , although these two feature sources are produced under different spatial scales and contextual conditions and may therefore exhibit distribution mismatch or boundary discontinuities. Moreover, the final feature set still uses , while a large portion of is identical to , potentially introducing redundant computation. Additional ablations are needed to justify both the hard replacement strategy and the necessity of retaining and simultaneously.
-
The backbone configurations used in the experiments are not sufficiently specified, which raises concerns about the fairness of the comparisons. The implementation details only state that LiG-DETR uses a pretrained DINOv2 visual encoder, but the specific DINOv2 variant (e.g., ViT-S/14, ViT-B/14, or ViT-L/14) is not reported. More importantly, it is unclear whether all methods compared in Tables 1 and 2 use the same visual backbone and comparable model capacity. If different backbone variants are used across methods, the reported performance gains may partially originate from stronger pretrained representations rather than the proposed CPSR/DA-AQA modules. The authors should explicitly report the backbone, parameter count, and input resolution for every compared method, and ideally provide controlled comparisons under the same backbone and training setting to isolate the contribution of the proposed method.
Questions for authors
See Weakness
8 comments
R4. Global Feature Filling and the Complementarity of and
Joint optimization of cross-scale features. Zoomed-in local encoding and whole-image encoding operate at different scales and with different context, so the reassembled feature map may exhibit feature differences at region boundaries. To help the two feature streams work together, we use the same trainable visual encoder to extract both sets of features and align them with their original image locations after projection. When only a subset of patches is selected, the decoder receives composed of both types of features during training. Feature extraction and decoding are jointly optimized end to end under the same detection objective. This allows the decoder to learn how to combine cross-scale features on both sides of a boundary for detection.
Why we fill with . The decoder samples from a regular two-dimensional feature map, so needs to retain the spatial grid of the full image. Because and are spatially aligned, we can directly reuse the whole-image features from the corresponding locations in . This allows the decoder to access image information from unselected regions when sampling from . On the VisDrone-DET2019 validation set, we use the same model weights and change only how unselected regions are filled at inference. Compared with zero filling, filling with increases AP from 22.9 to 34.6 and APₛ from 16.5 to 25.3, corresponding to gains of 11.7 and 8.8 percentage points, respectively. This result supports reusing existing whole-image features to fill unselected regions.
Why we retain both and . The two levels share features in unselected regions, and retaining both increases the amount of feature data processed by the decoder. In selected regions, provides local details from zoomed-in encoding, and the complete preserves the representation of the same locations in the context of the whole image. Joint decoding can therefore use both local details and global context at the same location. Table 6 shows that adding as a separate feature level to increases AP from 32.9 to 35.5 and APₛ from 23.3 to 26.4, supporting the use of both feature levels.
R5. Backbone Configurations and Same-Backbone Comparison
On VisDrone-DET2019, LiG-DETR and RF-DETR-L both use a windowed DINOv2-Small backbone with a patch size of 16, with the same pretrained weights, inputs, training data, number of training epochs, learning rate, and effective batch size. In this comparison, LiG-DETR improves AP from 29.4 to 37.1 (+7.7 percentage points) and small-object AP from 18.6 to 27.6 (+9.0 percentage points). Table 6 further shows that adding only the reassembled local feature raises AP from 29.4 to 32.9, directly quantifying the benefit of local feature reassembly with the same backbone.
The other compared methods retain their respective backbones and detection architectures. Table 2 of the revised manuscript lists the backbone and parameter count of each method compared on VisDrone, and Section 4.1 describes the input resolution settings. The new matched-resolution comparison shows that at , LiG-DETR achieves an overall AP of 37.1, compared with 36.0 for Dome-DETR-L, and leads by 3.4 percentage points in medium-object AP (49.9 vs. 46.5).
Thank you for the clarifications and additional experiments. They partially address my concerns about the experimental setup and comparison fairness. However, I believe the methodological novelty remains limited, as the contribution appears primarily to be an engineering integration of local cropping, feature reassembly, and adaptive query allocation. The gains over the original RF-DETR baseline entail substantially greater computation and lower inference throughput. I acknowledge the improved trade-off relative to the slicing baseline, but the incremental accuracy advantage remains modest and does not sufficiently strengthen the contribution in my assessment. I note the commitment to release code in the responses to other reviewers, but a future release promise cannot substitute for reproducibility materials available during review.
We thank the reviewer for the careful reading and constructive suggestions. We have revised the manuscript accordingly.
R1. Local Patch Selection, Packing, and Feature Reassembly
Given a full-image input of size H×W, the global branch encodes the full image, and the local branch proceeds in three steps.
If you find this explanation clearer, we will revise the final manuscript accordingly.
R2. Laplacian Patch Selection Prioritizes Small-Object Coverage
On the VisDrone-DET2019 validation set, selecting only 25% of the patches in each image using Laplacian scores covers 48.3% of small objects, 1.93 times the expected coverage of uniform random selection under the same budget. We evaluated 26,588 small objects across all validation images, counting an object as covered if the center of its ground-truth bounding box fell within a selected patch. Coverage reaches 79.9% and 94.0% when the selection budget increases to 50% and 75% of the patches, respectively. Across the three budgets, coverage exceeds the random-selection expectation by 23.3, 29.9, and 19.0 percentage points, respectively. These results show that, under the same local encoding budget, Laplacian scoring allows regions containing more small objects to receive high-resolution encoding.
Laplacian scoring is a replaceable patch selection strategy within the Local-in-Global Reassembly framework. The core contribution of this work is to reassemble high-resolution local features from the selected regions at their original image locations and jointly decode them with the global features.
R3. Laplacian Score-Based Packing Achieves Detection Accuracy Comparable to Spatially Adjacent Packing
On the VisDrone-DET2019 validation set, we use the same model weights and vary only the packing layout at inference. Both settings use the same 16 patches and encode four local inputs per image (B=4), each upscaled by a factor of 2 along both height and width.
Under the same encoding budget, the default score-based packing achieves 37.12 AP and 27.56 APₛ, differing from spatially adjacent packing by only 0.32 and 0.29 percentage points, respectively. These results support CPSR's ability to pack patches from different parts of the original image into a single local input while maintaining detection accuracy comparable to that of spatially adjacent packing.