- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The authors propose an intrinsic feature decomposition framework for low-light object detection. The approach decomposes detector features into intrinsic, illumination, and noise components during pretraining, encouraging illumination-invariant representation learning. The authors also introduce auxiliary decomposition modules that are removed after pretraining. Therefore, they introduce no additional inference overhead. Experiments across multiple benchmarks and detector architectures demonstrate consistent improvements over standard pretraining models and existing baselines.
Critical strengths
-
The proposed method achieves consistent improvements on multiple low-light object detection benchmarks and also performs well on nighttime driving benchmarks. Its effectiveness across YOLO variants and RT-DETR further supports the approach's generalizability.
-
The feature decomposition is introduced only during pretraining, allowing the detector to benefit from illumination-robust representations without additional inference-time computation. This makes the framework practical for real-world applications where inference efficiency and speed are important.
Critical weaknesses
-
The proposed approach builds upon Retinex decomposition and illumination-invariant representation learning. Previous studies such as MAET [1] and DAI-Net [2] have applied similar ideas for low-light object detection. Although applying decomposition directly to the detector's feature space is a meaningful design choice, the paper could more clearly distinguish the conceptual innovation beyond these closely related approaches.
-
The ablation study provides valuable information for the effectiveness of feature-level decomposition. However, it is still unclear how much of the improvement comes from the proposed Retinex-inspired formulation, instead of the additional introduced reconstruction supervision during pretraining. A comparison with a similarly sized auxiliary reconstruction objective without explicit decomposition would help answer this question and strengthen the innovation.
[1]. https://openaccess.thecvf.com/content/ICCV2021/papers/Cui_Multitask_AET_With_Orthogonal_Tangent_Regularity_for_Dark_Object_Detection_ICCV_2021_paper.pdf [2]. https://openaccess.thecvf.com/content/CVPR2024/papers/Du_Boosting_Object_Detection_with_Zero-Shot_Day-Night_Domain_Adaptation_CVPR_2024_paper.pdf
Questions for authors
- How much additional computational cost (e.g., GPU hours or FLOPs) is introduced by the auxiliary decomposition modules during pretraining, compared with the vanilla model?
4 comments
Official Comment to Reviewer hyEs (2/3)
Q2: Whether the Gains Come from the Retinex-Based Formulation or from the Added Reconstruction Supervision
We thank the reviewer for the careful and constructive feedback. As suggested, we conducted a control experiment that provides only an auxiliary reconstruction task of matched capacity, without the decomposition structure. In all settings, pretraining is conducted with the same Dark ISP pairs and the same schedule, and the resulting detectors are subsequently fine-tuned on LOD.
This control uses the same auxiliary encoder and decoder as our method, but simply adds the encoder output to the first-layer feature before reconstructing the input image (D(I + E(S))). It has no multiplicative structure, no distinction between L and N, and no smoothness constraint, and the number of parameters of the auxiliary modules is identical to that of our method. In other words, it provides reconstruction supervision with the same capacity but without the decomposition structure.
Table R11. Separating the contributions of reconstruction supervision and the decomposition structure (LOD, YOLOv8-m)
| Pretraining setting | Auxiliary module | Decomposition structure | mAP |
|---|---|---|---|
| COCO baseline | – | – | 55.8 |
| Dark ISP pair training only | – | – | 58.1 |
| ↳ + paired feature alignment (consistency) only | – | – | 58.4 |
| ↳ + capacity-matched reconstruction (no decomposition structure) | Encoder + decoder | None | 59.0 |
| ↳ + image-level Retinex decomposition | Encoder + decoder | Image space | 57.2 |
| ↳ + feature-level decomposition (without N) | Encoder + decoder | Feature space | 62.5 |
| ↳ + feature-level decomposition + N (Ours) | Encoder + decoder | Feature space | 63.7 |
The results can be summarized as follows.
- Reconstruction supervision by itself is helpful, but its gain is limited to +0.9 over Dark ISP pair training (from 58.1 to 59.0).
- Compared with this control, whose auxiliary-module capacity is matched exactly to ours (59.0), the feature-level decomposition structure brings an additional +4.7.
Therefore, most of the improvement comes not from the added reconstruction supervision but from the Retinex-style decomposition structure in which the detector feature serves as a factor.
We also examined the role of each loss term within the decomposition structure through additional ablation.
Table R12. Loss-term ablation (LOD, YOLOv8-m)
| Setting | mAP |
|---|---|
| Ours (full) | 63.7 |
| Without the noise term N | 62.5 |
| Without the cross-reconstruction loss | 63.0 |
| Without the illumination smoothness loss | 61.9 |
| Without the intrinsic consistency loss | 59.3 |
Every term contributes to the performance. Removing the intrinsic consistency loss causes the largest drop (−4.4 mAP), followed by the illumination smoothness loss (−1.8), the noise term (−1.2), and the cross-reconstruction loss (−0.7). In particular, removing the smoothness loss allows the illumination factor L to absorb structural information, which reduces the role of I, and removing the consistency loss eliminates the direct constraint that aligns I across the pair. The fact that performance drops in both cases supports that the gains arise when the decomposition behaves as intended. We are grateful to the reviewer for the constructive comment, which allowed us to further strengthen our work through this control experiment and the additional ablations.
Official Comment to Reviewer hyEs (3/3)
Q3: Additional Pretraining Cost Introduced by the Auxiliary Decomposition Modules
As the reviewer notes, the auxiliary encoder-decoder increases the computation of the pretraining stage, which we also stated as a limitation in the Conclusion of the submission. To quantify this cost, we measured the parameters and computation of the three auxiliary architectures compared in Appendix A.4 (Table 6).
Table R8. Additional pretraining cost by auxiliary encoder-decoder architecture (YOLOv8-m, per 640×640 input image; LOD mAP from Table 6 in the appendix of the submission)
| Auxiliary encoder-decoder | Parameters (enc + dec) | Relative to the detector (25.9M) | GFLOPs (enc + dec) | Relative to the detector (78.9) | LOD mAP |
|---|---|---|---|---|---|
| MLP-based | 41.6K (32.0K + 9.6K) | 0.16% | 8.38 (6.37 + 2.01) | 10.6% | 63.3 |
| Convolutional (Ours) | 89.5K (67.4K + 22.1K) | 0.35% | 19.05 (13.74 + 5.31) | 24.1% | 63.7 |
| Light Transformer-based | 146.6K (105.5K + 41.1K) | 0.57% | 37.57 (26.09 + 11.48) | 47.6% | 64.3 |
The results can be summarized as follows.
- Magnitude of the additional cost. The three-layer convolutional architecture that we use has 89.5K parameters (0.35% of the detector) and requires 19.05 GFLOPs per image (24.1% of the detector). The computation is large relative to the parameter count because the auxiliary modules operate at the same high resolution as the first-layer feature of the backbone.
- Cost and performance across architectures. The computation varies from 10.6% to 47.6% of the detector depending on the architecture, whereas the LOD mAP differs only slightly, ranging from 63.3 to 64.3. The convolutional architecture that we adopt is therefore a reasonable choice that offers a favorable balance between performance and cost, as discussed in Appendix A.4. When the pretraining cost is more critical, the MLP architecture can be used instead, which reduces the computation to less than half at a cost of only 0.4 mAP.
- The cost is incurred only once, during COCO pretraining. Starting from COCO-pretrained weights and fine-tuning them on multiple target datasets is a widely adopted practice for training detectors, and our pretrained weights can be used in exactly the same manner. We performed pretraining only once per detector and used the same weights for all six target datasets. We also plan to release the code and the pretrained weights, so that users of the released weights will not need to bear this cost again.
- There is no additional cost in fine-tuning or inference. The auxiliary encoder-decoder is removed after pretraining. Fine-tuning therefore proceeds at the same cost as with the standard COCO-pretrained weights, and the parameters (25.9M), computation (78.9 GFLOPs), and latency at inference are identical to those of the baseline.
In summary, the additional cost is confined to a one-time pretraining, and the subsequent fine-tuning and inference are performed at the same cost as the baseline.
We thank the reviewer once again for the constructive comments. We hope that the additional experiments and clarifications have helped to address the concerns, and we will incorporate all of them into the final version of the paper.
Dear Reviewer,
The authors have responded to your review. Could you please take a moment to review their responses and engage in the discussion?
Thank you for your time and valuable contributions.
Kind regards, AC
Official Comment to Reviewer hyEs (1/3)
Dear Reviewer hyEs,
We sincerely thank the reviewer for the careful review of our paper and for the positive assessment of the consistent improvements across multiple benchmarks and detector architectures, as well as the practicality of a design that adds no inference cost. In particular, the suggestion to isolate the source of the gains was of great help in verifying the central claim of our paper. We respond to each point below.
Q1: Conceptual Innovation That Distinguishes Our Work from MAET and DAI-Net
We appreciate the reviewer's assessment that applying the decomposition directly in the detector's feature space is a meaningful design choice. To explain the differences from prior work more clearly, we have added a conceptual comparison of the training pipelines of MAET, DAI-Net, and our method (Fig. 8) to Appendix D of the revised version, and we summarize the differences along three axes.
F = (I + N) ⊙ L. What is exchanged in cross-reconstruction is also the detector feature itself.These conceptual differences translate into differences in performance. With the same detector, the same Dark ISP synthesis, and the same fine-tuning schedule, the proposed method consistently outperforms MAET and DAI-Net.
Moreover, within our framework, the variant that defines the decomposition in the image space reaches only 57.2 mAP, whereas defining it in the feature space reaches 62.5 mAP (Table 3). This result shows that "where the decomposition is defined" is the key.