- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
To address the inconsistency between a model's masks and captions about the same change, the authors propose Chain-of-Change Detection (CoCD), which formulates each step of the CD process as an explicitly supervised task and passes the decoded prediction of each stage to the next as evidence. Specifically, the Semantic State Painter routes the observed semantic states to the comparison stage, and the Change Evidence Injector routes the localized change and its transitions to the description stage, thereby extending the CD-specific inductive bias beyond encoder-side feature interaction. Since no existing benchmark provides all three outputs for the same queried classes, the authors construct CoCD-Dataset from HRSCD and WUSU, containing aligned per-date semantic masks, change masks, and grounded captions. However, CoCD's core contribution is closer to an engineering combination, as components such as task chaining, evidence injection, and mask decoding have precedents in MLLM and remote-sensing change detection. Second, the experimental scope is narrow, with evaluation only on CoCD-Dataset constructed from HRSCD and WUSU, insufficient baseline adaptation, and captions synthesized by Qwen3-VL-32B, raising concerns about evaluation reliability. In addition, the method details and training protocol are incomplete.
Critical strengths
- An anonymous code link is provided, documenting data construction, training objectives, evaluation protocols, and the caption generation and verification pipeline.
- Based on HRSCD and WUSU, it provides aligned per-date semantic masks, change masks, and grounded captions, totaling 14,014 queries (11,898 / 510 / 1,606). Since no existing benchmark provides all three outputs simultaneously, CoCD-Dataset fills this gap and serves as a reusable resource.
- CoCD decomposes change detection into three stages—observe, compare, and describe—which aligns with the human cognitive process of analyzing changes and assigns clear responsibilities to each stage.
- The ablation experiments are relatively comprehensive, essentially covering the core design choices of the method.
Critical weaknesses
- Task chaining, visual CoT, evidence injection, and mask decoding all have precedents in MLLM and remote-sensing change detection.
- Training and evaluation are conducted only on CoCD-Dataset, which is constructed from HRSCD and WUSU, leaving it unclear whether the conclusions generalize to other remote-sensing datasets. A full comparison on standard benchmarks such as the original HRSCD, WUSU, LEVIR-CD+, and SECOND is recommended.
- The paper explicitly states that synthetic change captions are generated by Qwen3-VL-32B and then verified by rules. While this is reasonable, it introduces bias from the generative model.
- The operations in Equations 4 and 5 are written in a highly non-standard way, and the weight coefficients preceding the losses in Equation 9 appear without justification. A complete definition, along with convergence and sensitivity analyses, should be provided.
- Comparison with conventional CD methods is missing.
- The method mainly adopts common operations such as convolution, and its novelty is insufficient to support an ICLR main-conference paper.
Questions for authors
- Equation (3) for SSP is not fully given in the main text. Could the authors provide the complete formulation?
- The evidence construction in Equation (7) for CEI is only partially specified. Could the authors provide a complete definition?
- MMC and CMC only measure internal consistency, not correctness. A model can produce a fully consistent but incorrect mask-caption pair. Have the authors considered reporting correctness metrics alongside consistency metrics?
- The caption verification rules only check consistency with the fact tuples. Do they also check language naturalness, diversity, or semantic nuance?
- Training and evaluation are conducted only on CoCD-Dataset, which is constructed from HRSCD and WUSU. Can the conclusions generalize to other remote-sensing datasets?
- Could the authors provide a full comparison on standard benchmarks such as the original HRSCD, WUSU, LEVIR-CD+, and SECOND?
- Could the authors add comparisons with conventional methods in terms of mIoU, inference FLOPs, and parameter count?
- Provide a complete definition of Equation (9), along with corresponding convergence and sensitivity analyses.
- Standardize the notation in Equations (3) and (4).
9 comments
Response to Reviewer gGpK (2/6)
Q4 (and W3). "The caption verification rules only check consistency with the fact tuples" and "it introduces bias from the generative model" — Appendix B.14 [also: CJgm W1, Q4]
The rules verify the facts of each caption. For this response we also measured the quality of the wording, in naturalness and diversity.
Naturalness. An independent judge from a different family (OpenAI GPT-5.5) compared each of the 1,002 LLM-written test references with a template sentence built from the same facts, in random order. It preferred the LLM reference in 75.7% of pairs (naturalness 4.18 vs. 3.17 on a 1–5 scale).
Diversity. The references are more varied than a template and less varied than free-form human captions, by design: class names and location words are fixed to the dataset vocabulary.
| Metric | CoCD references | Template (same facts) | LEVIR-CC (human) |
|---|---|---|---|
| Vocabulary size | 399 | 41 | 592 |
| MATTR (window 50) | .541 | .448 | .643 |
| Bigram entropy (bits) | 7.13 | 5.69 | 8.89 |
| Unique sentences | 56.3% | 35.4% | 87.9% |
Each column uses 4,766 captions: one per scene and fact set for ours, one per changed image for LEVIR-CC [1]. MATTR is the share of distinct words within a window of 50 consecutive words, averaged over all windows, and higher values mean less repetition. Bigram entropy measures how evenly the pairs of consecutive words are distributed, and higher values mean more varied phrasing. LEVIR-CC captions are free-form human descriptions of a different domain and are shown only as a reference scale.
Bias from the generator. The facts come from the masks and only the wording comes from the 32B model, so as a scoring reference the wording can affect only the n-gram metrics. When the test references are rewritten by a non-Qwen generator (OpenAI GPT-5.4), the n-gram scores of every model drop, but CoCD stays above Parallel on all of them. The training captions remain Qwen-written, and for that side the evidence is that the gains hold with non-Qwen backbones (LLaVA-1.5-7B [2], InternVL3-2B [3], Appendix B.4). The tables are in our reply to Reviewer CJgm (Q4).
References
[1] Liu, C., Zhao, R., Chen, H., Zou, Z., and Shi, Z. Remote Sensing Image Change Captioning With Dual-Branch Transformers: A New Method and a Large-Scale Dataset. IEEE TGRS, 60:1–20, 2022. [2] Liu, H., Li, C., Li, Y., and Lee, Y. J. Improved Baselines with Visual Instruction Tuning. CVPR, 2024. [3] Zhu, J., Wang, W., Chen, Z., Liu, Z., et al. InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models. arXiv:2504.10479, 2025.
Response to Reviewer gGpK (3/6)
Q5, Q6 (and W2). "Can the conclusions generalize to other remote-sensing datasets?" and "a full comparison on standard benchmarks such as the original HRSCD, WUSU, LEVIR-CD+, and SECOND" — Appendix B.11 [also: YJYF Q2]
We trained CoCD and Parallel on each benchmark alone (SECOND [4], HRSCD [5], WUSU [6]), with the same backbone, decoder and schedule, and scored them with the standard SCD protocol. Each model is tested on the benchmark it was trained on, so these results show whether the gain reproduces on other benchmarks, not zero-shot transfer to an unseen domain.
Splits. These runs use the splits released with recent SCD work, not our CoCD-Dataset splits. For HRSCD this is the split of TaCo [7] and SemDINO [8] (256×256 patches, patches with less than 5% changed pixels removed, 9,463 training and 2,366 test patches). For WUSU it is the split of GSTM-SCD [9] (512×512 tiles of the 2015→2018 pair, 977 training and 137 test tiles), which, unlike Eq. 1 of the paper, also treats a pixel as changed when it is labelled at one date and unlabelled at the other. For SECOND we train on 2,671 of the 2,968 official training pairs, keep the remaining 297 out of training, and test on the official test set (1,694 pairs). Both models are trained for 10 epochs on SECOND and HRSCD, as in the paper, and for 30 epochs on WUSU, whose training set is about a third the size of SECOND's, and we report the final checkpoint of each run.
Labels. HRSCD and WUSU label every pixel at both dates, so no pseudo labels are needed. SECOND labels classes only inside the changed regions. CoCD observes the full scene at each date, and SSP passes that full-scene state to the change decoder, so training needs a semantic label for the unchanged area as well. We therefore trained a segmenter on the changed-region labels of the SECOND training set and used its prediction as a pseudo label outside the change mask, keeping the ground truth inside it. Both models are trained on the same labels, and the test set is not used. The standard protocol scores semantics only inside the changed regions, so the pseudo labels do not enter the reported metrics.
| Benchmark | Model | OA | mIoU | F_scd | SeK |
|---|---|---|---|---|---|
| SECOND | Parallel | 87.30 | 72.89 | 60.55 | 20.98 |
| CoCD | 87.70 | 73.31 | 61.25 | 21.82 | |
| HRSCD | Parallel | 82.30 | 67.67 | 64.03 | 16.94 |
| CoCD | 82.31 | 66.57 | 66.76 | 18.58 | |
| WUSU | Parallel | 93.90 | 75.71 | 54.01 | 17.23 |
| CoCD | 95.14 | 78.65 | 63.76 | 26.07 |
CoCD is above Parallel on F_scd and SeK, the two metrics that score the semantic change, on all three benchmarks. The gain is largest on WUSU (SeK 17.23 → 26.07) and smallest on SECOND. On HRSCD, mIoU is lower for CoCD (66.57 vs. 67.67) and OA is equal.
These splits have much larger changed areas than CoCD-Dataset, which keeps scenes with little or no change and pairs adjacent years for WUSU: the median changed area per test scene is 20.0% (HRSCD) and 7.2% (WUSU) here, against 3.7% and 1.8% in CoCD-Dataset. The absolute values here are therefore not comparable with those in our reply to Reviewer YJYF (Q2), where the same protocol is applied to CoCD-Dataset.
References
[4] Yang, K., Xia, G.-S., Liu, Z., Du, B., Yang, W., Pelillo, M., and Zhang, L. Asymmetric Siamese Networks for Semantic Change Detection in Aerial Images. IEEE TGRS, 60:1–18, 2022. [5] Daudt, R. C., Le Saux, B., Boulch, A., and Gousseau, Y. Multitask Learning for Large-Scale Semantic Change Detection. Computer Vision and Image Understanding, 187:102783, 2019. [6] Shi, S., Zhong, Y., Liu, Y., Wang, J., Wan, Y., Zhao, J., Lv, P., Zhang, L., and Li, D. Multi-Temporal Urban Semantic Understanding Based on GF-2 Remote Sensing Imagery: From Tri-Temporal Datasets to Multi-Task Mapping. International Journal of Digital Earth, 16(1):3321–3347, 2023. [7] Guo, H., Liu, C., Zhang, H., Chen, B., Zou, Z., and Shi, Z. TaCo: Capturing Spatio-Temporal Semantic Consistency in Remote Sensing Change Detection. arXiv:2511.20306, 2025. [8] Tong, X., Zhou, M., Sun, J., Tang, Y., and Wang, L. SemDINO: A DINOv3-Driven Network for Cross-Temporal Semantic Alignment in Change Detection. arXiv:2606.09772, 2026. [9] Liu, X., Dai, C., Ding, L., Zhang, Z., Li, Y., Zuo, X., Li, M., Wang, H., and Miao, Y. GSTM-SCD: Graph-Enhanced Spatio-Temporal State Space Model for Semantic Change Detection in Multi-Temporal Remote Sensing Images. ISPRS Journal of Photogrammetry and Remote Sensing, 230:73–91, 2025.
Response to Reviewer gGpK (1/6)
We thank Reviewer gGpK. We provide the complete equations, the standard-benchmark comparison, model size and inference cost, and clarify the contribution.
Q1. "Equation (3) for SSP is not fully given in the main text" — Sec. 3.3.1, Appendix A.2
The SSP formulation is spread over Eq. 2–5, so Eq. 3 alone does not show the full path from class probabilities to the decoder prompt. The revision presents it as one connected derivation, which we summarize here.
Each class name is embedded as u_k = W_e e_k, with e_k the mean LLM input embedding of its tokens (Eq. 2). The state of date t is F_t(x) = Σ_k P_{t,k}(x) u_k + τ_t, a 64-dimensional vector per pixel at 128×128 (Eq. 3). The two states are concatenated, resized to 64×64, and passed through the state adapter (3×3 conv 128→256, LayerNorm, GELU, 1×1 conv 256→256) to give Z_S (Eq. 4), which is added to the visual prompt of the change decoder (Eq. 5). W_e, τ_t and the adapter are the only trained parameters (0.52 M).
Q2. "The evidence construction in Equation (7) for CEI is only partially specified" — Sec. 3.3.2, Appendix A.2
We agree that the selection rules and the text format were missing. They are now in Appendix A.2.
The evidence reads "Changed (top-right, right): <IMG> Transitions: excavation -> low building (top-right); grassland -> road (right)."
Q3. "MMC and CMC only measure internal consistency, not correctness"
We agree, which is why every table pairs them with correctness metrics (oIoU, sem-mIoU, BLEU/CIDEr) and Appendix B.1 reports caption accuracy against ground truth (Cap-Acc). The two do come apart in our results: in Table 2, Naive-Chain raises MMC from 37.98 to 48.74 and CMC from 35.18 to 45.11 over Parallel, while oIoU (25.00 → 25.59) and BLEU-4 (21.98 → 21.96) stay similar. Consistency alone is therefore not taken as evidence of correctness in the paper.