- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes Target-Centric Frequency Distillation (TCFDistill) for RGB-T Visual Grounding. The method consists of Dual-Frequency Spectral Distillation (DFSD) to transfer structural relations from an RGB-IR teacher model, and Spectral Alignment-Guided Representation Modulation (SARM) to fuse cross-modal features using local frequency consistency. The approach achieves state-of-the-art results on three benchmarks.
Critical strengths
- The topic is well-motivated, and addressing the limited IR semantic modeling in RGB-centric VLMs is highly relevant.
- The proposed DFSD is an elegant alternative to direct feature matching.
- The paper is well-written, and the experimental evaluation is comprehensive.
Critical weaknesses
- The paper broadly assumes that low frequencies capture coarse-scale structures, while high frequencies reflect fine-grained variations and applies this uniformly to both RGB and IR images. However, RGB and IR have fundamentally different imaging physics. The paper fails to analyze or discuss their distinct frequency distributions.
- In the SARM module, the authors use a consistency map to weight the RGB and refined IR spectral streams. However, there is no theoretical analysis of why and how they are complementary in the frequency domain. Without understanding their modality-specific frequency traits, the design of SARM appears additional learnable module.
- Real-world RGB-T systems frequently encounter modality missing. The proposed method mathematically relies on the simultaneous presence of both modalities to compute cross-modal frequency correspondence and consistency, lacking analysis of this complex scenario.
- While the authors claim to address the limited IR semantic modeling of VLMs via TCFDistill, this approach merely acts as a statistical shortcut. It relies heavily on the structural priors of a specific RGB-IR pretrained teacher (UNIV) rather than genuinely modeling the unique thermal semantics of IR images in the frequency domain.
- The table formats are inconsistent throughout the manuscript and appendix. Unlike standard grounding benchmarks (e.g., RefCOCO), the paper fails to report an Average metric across the 15 evaluation splits, forcing readers to manually aggregate the results to assess comprehensive performance. For example, in Table 8, the average score for LF-only is ~73.7%, HF-only is ~74.2%, and Full DFSD is ~74.6%. More critically, Full DFSD fails to achieve the best performance in nearly one-third of the splits, and on the Val sets of all three datasets, the Full model performs worse than at least one single-frequency variant. This indicates potential negative transfer between frequency bands.
Questions for authors
See weaknesses.
8 comments
Q3. Thanks for raising this concern. Our cross-modal correspondence and consistency modeling assumes paired RGB–IR observations. We have added missing-modality results and analysis across all three datasets in Appendix D.10, “Sensitivity to Missing Modalities,” and Table 20. Without retraining, we simulate modality absence by replacing the RGB or IR input with zeros after normalization.
On RefFLIR and RefM³FD Test, the model achieves 66.83% and 67.43% accuracy with IR missing, compared with 58.13% and 63.64% with RGB missing, respectively. Across all three datasets, Test-A accuracy is higher with IR missing, indicating greater dependence on RGB under normal illumination. On Test-B, IR becomes more important on RefFLIR and RefM³FD; on RefMFAD, accuracy remains higher with IR missing (61.99%) than with RGB missing (57.22%). Under missing inputs, Test-C accuracy ranges from 36.41% to 47.29%. These results quantify sensitivity to modality absence across datasets and test subsets and clarify the practical limitations of the paired-input design.
Results are [email protected] (%).
| Dataset | Input condition | Val | Test | Test-A | Test-B | Test-C |
|---|---|---|---|---|---|---|
| RefFLIR | RGB + IR (reference) | 77.13 | 75.00 | 91.88 | 69.84 | 55.57 |
| RefFLIR | Missing IR | 65.13 | 66.83 | 89.61 | 52.97 | 41.99 |
| RefFLIR | Missing RGB | 62.66 | 58.13 | 75.15 | 61.41 | 36.41 |
| RefM³FD | RGB + IR (reference) | 77.38 | 77.33 | 95.45 | 83.54 | 58.87 |
| RefM³FD | Missing IR | 65.48 | 67.43 | 93.34 | 67.73 | 42.69 |
| RefM³FD | Missing RGB | 55.36 | 63.64 | 78.81 | 73.95 | 44.81 |
| RefMFAD | RGB + IR (reference) | 72.05 | 70.40 | 91.64 | 67.33 | 55.72 |
| RefMFAD | Missing IR | 65.92 | 65.08 | 91.25 | 61.99 | 47.29 |
| RefMFAD | Missing RGB | 60.67 | 58.98 | 81.88 | 57.22 | 42.59 |
Full-input rows reproduce the main-table results for reference.
The corresponding revisions will be highlighted in red at Lines 1242–1248 and 1279–1289 of the manuscript.
Q4. Thanks for raising this concern. Our claim concerns improving query-relevant IR representations for grounding: text-conditioned targets and grounding supervision provide semantic guidance, while frequency decomposition organizes structural transfer across spatial scales.
Regarding the “statistical shortcut” concern, Appendix D.6, “Additional Analysis of Query Guidance,” and Table 16 report that spatially shuffling LF-TAD query weights, while preserving their distribution and retaining the same reinjection gate, reduces Avg.12 from 74.38% to 73.20%. This control demonstrates the importance of the correspondence between query weights and image locations, beyond the weight distribution alone.
Regarding dependence on UNIV, Appendix D.7, “Additional Analysis of Teacher Selection,” and Table 17 report Avg.12 scores of 74.38%, 73.63%, and 73.17% with UNIV, M-SpecGene, and InfMAE, respectively. These results show that the framework can use different teachers, while teacher selection affects transfer effectiveness. Our contribution is to transfer query-relevant structural knowledge across frequency bands, with the query-weight shuffling control assessing the spatial relevance of this guidance.
The corresponding revisions will be highlighted in red at Lines 1198–1204 and 1208–1220 of the manuscript.
Q5. Thanks for highlighting the need for consistent presentation and explicit aggregate metrics. We have standardized the presentation of the multi-dataset ablation tables and added Avg.12 and Avg.15 to report aggregate performance. As defined in Appendix A.1, these are unweighted means over the 12 test columns and all 15 evaluation columns, including Val, respectively. For the dual-frequency ablation in Appendix D.2 and Table 9, the results are:
| Variant | Avg.12 (%) | Avg.15 (%) |
|---|---|---|
| LF-only | 73.18 | 73.65 |
| HF-only | 73.74 | 74.20 |
| LF + HF, MSE | 73.42 | 73.79 |
| Full DFSD | 74.38 | 74.61 |
Regarding potential negative transfer, under the same SmoothL1 objective, Full outperforms both single-frequency variants on the overall Test and Test-C splits of all three datasets. Among these SmoothL1 variants, Full achieves the highest accuracy on 11 of the 12 test columns, sharing the best result with HF-only on RefMFAD Test-B. The exception is RefFLIR Test-B, with 69.84% versus 70.15% for HF-only. The RefM³FD Test-A comparison against the MSE variant changes the regression loss while retaining both frequency objectives, so it does not isolate the effect of combining frequency bands.
The lower validation scores indicate that improvements vary across splits, but these single-run comparisons alone do not establish systematic interference between the frequency objectives. Considering aggregate scores together with results on different test subsets provides a more comprehensive assessment of overall performance. Full DFSD’s highest Avg.12 and Avg.15, together with its improvements on the overall Test splits, demonstrate the overall benefit of joint frequency supervision.
The corresponding revisions will be highlighted in red at Lines 737–740 and 930–937 of the manuscript.
We sincerely appreciate the careful and constructive suggestions from Reviewer PvMc. We will explain the major concerns point-by-point as follows:
Q1. Thanks for highlighting this issue. Fig. 1(b) illustrates the spatial content of the low- and high-frequency components of RGB and IR images. To further characterize the cross-modal differences, we have added Fig. 1(c), presenting normalized two-dimensional Fourier spectra and radial RGB–IR spectral differences in dB. The comparison shows relatively stronger low-frequency responses in IR and stronger high-frequency responses in RGB.
We further provide additional examples in Fig. 6. The left panels visualize paired RGB–IR images and their two-dimensional spectra. In the campus example, RGB spectral responses extend farther toward the high-frequency periphery, whereas IR responses are more concentrated around the low-frequency center. The right panels present radial spectral differences for a separate set of image pairs, illustrating how relative RGB–IR responses vary across frequency bands. Together, these observations clarify the modality-specific frequency characteristics and motivate separate modeling of cross-modal structural relations across spatial scales.
We have revised the Introduction to explain this connection. Appendix A.4, “Image Spectral Analysis,” details the computation, and Appendix B.1, “RGB–IR Spatial-Frequency Distributions,” and Fig. 6 provide the additional examples and analysis.
The corresponding revisions will be highlighted in red at Lines 80–82, 89–98, 787–826, and 882–898 of the manuscript.
Q2. Thanks for raising this concern. As discussed in Q1, Fig. 1(b) illustrates the spatial content of different frequency components, while the added Fig. 1(c) shows modality-specific frequency distributions. Related studies also exploit RGB–IR frequency complementarity through wavelet fusion (WaveMamba [1]), frequency-driven feature decomposition (FD²-Net [2]), and dual-frequency enhancement (DCFusion [3]). These observations and prior studies motivate modeling shared structures and modality-specific responses in the frequency domain.
We have strengthened this rationale at the beginning of Section 3.3. SARM measures cross-modal agreement at corresponding spatial locations and local DCT frequencies using channel-wise cosine similarity. The consistency weight emphasizes RGB components shared with IR, while its complementary weight emphasizes discrepant responses from the DFSD-refined IR stream. These responses offer potentially complementary information, whose relevance to localization is learned through subsequent modulation under the grounding objective. This explains the two-stream weighting and its local frequency-dependent operation.
Moreover, the ablations with the same number of parameters in Appendix D.3 and Table 10 show that full SARM exceeds the spatial-neighborhood and IR-only variants by 0.98 and 1.23 percentage points, respectively, averaged over the 12 test splits. These comparisons demonstrate the benefit of local cross-modal spectral interaction beyond increasing model capacity. We have revised the Introduction and Section 3.3 to clarify the motivation and mechanism.
[1] WaveMamba: Wavelet-Driven Mamba Fusion for RGB-Infrared Object Detection, ICCV 2025.
[2] FD²-Net: Frequency-Driven Feature Decomposition Network for Infrared-Visible Object Detection, AAAI 2025.
[3] DCFusion: A Dual-Frequency Cross-Enhanced Fusion Network for Infrared and Visible Image Fusion, IEEE TIM 2023.
The corresponding revisions will be highlighted in red at Lines 89–98, 299–310, 972–981, and 1002–1017 of the manuscript.