- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes ProbInfoNCE, which uses a shared MLP to predict scaling components for query and reference images separately. These are then added to form a pairwise temperature. Under a conditional independence assumption, the analysis decomposes the expected squared distance between embeddings of the same location into query-side variation, reference-side variation, and cross-view mismatch. This provides motivation for the loss design. The authors also use synthetic appearance augmentation, dual-matrix training, and query-to-query alignment. They combine VIGOR and DRESS to construct CAV-Geo, which provides weather and day-night variants and a cross-continent protocol with training outside North America and testing in North America. The paper reports performance on several standard benchmarks and the new dataset.
Critical strengths
1.The method is simple and efficient.
ProbInfoNCE adds only a small MLP with little extra computation. Controlled experiments show that it improves R@1 from 64.74% to 68.07% on VIGOR Cross-Area with the same DINOv3 initialization.
2.The new benchmark is useful.
CAV-Geo covers 11 cities and 255,875 query locations, with synthetic weather and day-night changes. The authors also provide several checks to evaluate whether image editing preserves localization cues.
Critical weaknesses
1.The algorithmic novelty is limited.
Sample-dependent temperatures have already been studied. Table 8 shows improvement over query-side temperature scaling, but it is unclear whether the gain comes from adding reference-side information or using the additive form. More controlled comparisons are needed to support the specific contribution.
2.The robustness and generalization evidence is insufficient.
Both training and testing use FLUX-generated appearance changes, so performance on real weather or other distributions remains unclear. Also, CAV-Geo lacks a matched InfoNCE baseline to isolate the contribution of the new loss.
Questions for authors
Q1 Contribution of adaptive temperature
Could the authors add reference-side-only scaling and a few other ways to combine the query and reference scores to separate the effect of reference-side information from that of the additive form? Please explain the specific differences from Zhang et al. (2021) and Qiu et al. (2023), and why these differences matter.
Q2 External validity of appearance robustness
Could the authors evaluate the method on queries edited by a different generator, on an independent degradation benchmark, or on a small set of images captured in adverse weather? Cross-generator experiments could start with a representative subset.
Q3 Controlled experiments on CAV-Geo
In the Cross-Continent setting, could the authors match initialization, training data, and optimization settings, add both Dual Matrix and Dual Matrix + q2q configurations for InfoNCE, and report results for original and synthetic queries separately?
Q4 Stability of cross-continent results
Could the authors keep the full test reference gallery unchanged and provide R@1 for each of the five North American test cities? If results for other transfer directions are available, please also provide them.
7 comments
Response to Reviewer aTtE PART2
W2 / Q2. Do the gains hold with another editor, an independent degradation benchmark, or real adverse weather?
Yes—the gains persist on the full test split edited by another generator. Following cross-editor option, we re-edited VIGOR Cross-Area with Qwen-Image-2.1 and evaluated existing checkpoints on the same test locations and retrieval protocol. ProbInfoNCE retains its embedding advantage, and native scoring improves both edited conditions while reducing the drop (Table R3).
Table R3. Cross-editor evaluation and scoring gains on VIGOR Cross-Area (R@1, %).
| Queries | InfoNCE + cosine | Prob + cosine | Prob + native | Native gain (pp) | Prob drop: cosine / native (pp) |
|---|---|---|---|---|---|
| Original | 65.57 | 69.33 | 70.10 | +0.77 | — |
| FLUX edited | 61.80 | 64.56 | 66.69 | +2.13 | 4.77 / 3.41 |
| Qwen edited | 63.01 | 65.46 | 67.36 | +1.90 | 3.87 / 2.74 |
Both Prob columns use the same checkpoint. Native gain is relative to cosine. Drop is from original to edited queries. Original results are from submission Tables 7 and 9, FLUX combines submission Table 7 with cosine re-evaluation, and Qwen is the new full-test-set evaluation.
W2 / Q3. Can matched InfoNCE Dual and Dual+q2q baselines isolate the loss on original and edited CAV-Geo Cross-Continent queries?
ProbInfoNCE improves both original and edited Cross-Continent retrieval under both matched strategies (Table R4). As requested, InfoNCE includes Dual and Dual+q2q, with matched initialization, original/FLUX training images, optimization, and supervision. Complete Dual+q2q also improves both query conditions on Same-Area.
Table R4. Matched CAV-Geo controls (R@1, %).
| CAV-Geo split | Training | InfoNCE original | InfoNCE edited | ProbInfoNCE original | ProbInfoNCE edited |
|---|---|---|---|---|---|
| Cross-Continent | Dual | 14.58 | 11.58 | 19.11 | 15.24 |
| Cross-Continent | Dual+q2q | 16.20 | 12.51 | 20.82 | 17.14 |
| Same-Area | Dual | 61.84 | 57.19 | 65.06 | 57.51 |
| Same-Area | Dual+q2q | 61.64 | 56.62 | 67.33 | 58.91 |
ProbInfoNCE Dual+q2q values are from submission Table 5. Table R5 is from the VIGOR Cross-Area ablation from submission Table 7, confirming the loss contribution under each training strategy, including original-only training. The effect of q2q depends on the objective, supporting its joint role with ProbInfoNCE in appearance-consistency learning.
Table R5. Matched training strategies on VIGOR Cross-Area (submission Table 7, R@1, %).
| Training setting | InfoNCE original | InfoNCE edited | ProbInfoNCE original | ProbInfoNCE edited | Gain, original / edited (pp) |
|---|---|---|---|---|---|
| Original only | 64.74 | 12.21 | 68.07 | 13.82 | +3.33 / +1.61 |
| MixBatch | 65.26 | 61.50 | 68.48 | 63.01 | +3.22 / +1.51 |
| Dual | 66.90 | 62.91 | 69.26 | 64.01 | +2.36 / +1.10 |
| Dual + q2q | 65.57 | 61.80 | 70.10 | 66.69 | +4.53 / +4.89 |
Q4(a). What is R@1 in each of the five cities with the full reference gallery?
The Cross-Continent improvement holds in all five test cities, for both original and edited queries (Table R6). As requested, city-wise evaluation retains the full 162,104-reference gallery for every query. Both models use matched Dual+q2q training.
Table R6. Five-city CAV-Geo Cross-Continent results with the full reference gallery (R@1, %).
| Test city | Queries | InfoNCE original | InfoNCE edited | ProbInfoNCE original | ProbInfoNCE edited |
|---|---|---|---|---|---|
| Chicago | 25,479 | 17.00 | 12.07 | 23.61 | 18.28 |
| New York | 27,769 | 12.39 | 9.81 | 14.94 | 13.02 |
| San Francisco | 28,215 | 18.26 | 15.43 | 20.67 | 18.75 |
| Seattle | 23,751 | 15.23 | 11.47 | 21.12 | 16.05 |
| Vancouver | 21,567 | 18.52 | 13.84 | 24.97 | 20.19 |
Q4(b). Are results for other transfer directions available?
CAV-Geo trains outside North America and tests within it. Table R6 establishes consistency across cities in that protocol. Additional transfer-direction results are not available for this response.
Response to Reviewer aTtE PART3
We would appreciate a prompt reply indicating whether our responses have resolved your concerns or whether any questions remain, so that we can further address any outstanding issues.
References
[1] Zhang et al. Temperature as Uncertainty in Contrastive Learning. NeurIPS Workshop on Self-Supervised Learning, 2021.
[2] Qiu et al. Not All Semantics are Created Equal: Contrastive Self-supervised Learning with Automatic Temperature Individualization. ICML, 2023.
[3] Qiu et al. To Cool or not to Cool? Temperature Network Meets Large Foundation Models via DRO. ICML, 2024.
[4] Manna et al. Dynamically Scaled Temperature in Self-Supervised Contrastive Learning. IEEE Transactions on Artificial Intelligence, 2025.
[5] Sheludzko et al. MM-TS: Multi-Modal Temperature and Margin Schedules for Contrastive Learning with Long-Tail Data. WACV, 2026.
[6] Duka et al. TeMo: Temperature Modulation for Multimodal Contrastive Learning. arXiv:2609.07540, 2026.
[7] Wang et al. Adaptive Multi-head Contrastive Learning. ECCV, 2024.
Response to Reviewer aTtE
We thank the reviewer for constructive feedback.
Scoring definitions. Retrieval tables report R@1 (%), and edited means FLUX unless specified. For L2-normalized query and reference embeddings qi,rj, cosine ranks satellite candidates by qi⊤rj. Native ranks them by ProbInfoNCE’s learned additive score (submission Eq. 11 and Appendix C, Eq. 32):
\qquad \epsilon=10^{-6}.$$ The two positive scales are predicted by the shared softplus MLP from the corresponding **pre-normalization features**. **Prob + cosine and Prob + native use the same ProbInfoNCE-trained checkpoint and embeddings, changing only inference scoring.** InfoNCE + cosine uses the separately InfoNCE-trained checkpoint. Prob abbreviates ProbInfoNCE, whose results use native scoring unless stated otherwise. --- **W1 / Q1(a). How does ProbInfoNCE differ from Zhang et al. [1] and Qiu et al. [2], and why do the differences matter?** **Our novelty concerns the observation model, matching objective, and their connection to CVGL.** Zhang et al. [1] use an input-dependent anchor temperature shared across its candidates. Qiu et al. [2] derive individualized temperatures through KL-distributionally robust optimization, with variables indexed by training examples. We model variation at both image endpoints and cross-view mismatch (Eq. 6), predicting scales from image features for unseen queries and references. Their sum preserves independent-perturbation covariance addition. Appendix C’s same-scale, zero-similarity ratio gives our exact logit (Eq. 32), followed by the specified contrastive NLL (Eqs. 34–37). These differences affect both learning and candidate-dependent retrieval scoring. **Our model, data, and training share this motivation:** editing supplies appearances of the same location, Dual aligns them with one reference, q2q enforces identity consistency, and CAV-Geo evaluates the challenge. A shared temperature-scaling operation does not establish equivalence between these formulations. Tables R1 and R2 test the parameterizations and compare the methods. --- **Q1(b). Do reference-only and alternative combinations separate reference information from the additive form?** As requested, we tested reference-only scaling and alternative combinations on VIGOR Cross-Area. **Addition outperforms every tested alternative on both query conditions (Table R1)**, including multiplication with both image scales. This is because addition is the only one that follows and is supported by Eq. 32 in our submission. **Table R1. Scale parameterizations on VIGOR Cross-Area (R@1, %).** | VIGOR Cross-Area variant | Scoring rule | Original R@1 (%) | FLUX-edited R@1 (%) | | --- | --- | ---: | ---: | | Query-only | One MLP scale per query | 66.27 | 62.10 | | Reference-only | One MLP scale per satellite candidate | 68.51 | 64.62 | | Multiplicative | Product of query and reference scales | 68.67 | 65.07 | | Learned pairwise similarity bias | Learned bias added to the similarity logit | 67.07 | 63.20 | | Additive (ProbInfoNCE, submission Table 7) | Sum of query and reference scales | **70.10** | **66.69** | The one-sided controls use the same MLP architecture on retrieval features. A query-dependent positive scale **changes training but preserves cosine ranks at fixed embeddings**, because it rescales all candidates for that query equally. Reference-only tests candidate information. Multiplication retains both scales and changes their combination. Query-only original is from submission Table 8. Its edited value is a confirmed re-evaluation. The query-only control implements the anchor-scaling idea of Zhang et al. [1]. The reference-only and multiplicative controls show that candidate information alone does not explain the full benefit. --- **Q1(c). How does ProbInfoNCE compare with iSogCLR and other adaptive-temperature methods?** Table R2 directly compares Qiu et al.’s iSogCLR objective [2] and additional alternatives [3, 4, 5, 6, 7], with matched DINOv3 initialization, training data, and optimization settings. **Table R2. Adaptive-temperature methods on VIGOR Cross-Area (R@1, %).** | Method | Mechanism | Original R@1 (%) | FLUX-edited R@1 (%) | | --- | --- | ---: | ---: | | TempNet [3] | Predicts anchor temperatures for a distributionally robust objective | 61.86 | 58.47 | | iSogCLR [2] | Optimizes per-training-example temperatures under that objective | 57.68 | 54.34 | | DySTreSS [4] | Pair-similarity modulation | 29.66 | 26.43 | | MM-TS [5] | Training schedule with a cluster-frequency shift | 48.34 | 42.95 | | TeMo [6] | Pair-similarity modulation with joint cross- and within-view alignment | 62.92 | 48.42 | | AMCL [7], three-head adaptation | Head-wise pair interactions | Training collapse | Training collapse | | ProbInfoNCE (submission Table 7) | Additive image scales | **70.10** | **66.69** |