- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 2(+1)
Read review
Paper summary
This submission deals with the problem of identifying UXO: unexploded ordnance (ammunition that did not explode when originally fired, and may explode unexpectedly at some time in the present). The authors claim that UXO identification using Euclidean features is especially hard because of data scarcity and high intra-class variance even despite strong inter-class similarity. To address this, the paper proposes using hyperbolic features instead. It first studies the structure and dimensionality of UXO representations to argue that they exhibit a geometry resembling a hyperbolic space, compared to a null baseline. Using this motivation, it then proposes a transductive information maximization (TIM) strategy built on top of embeddings lifted into a hyperbolic space. The method, named LorentzTIM, implemented over frozen DINOv3 features, is evaluated on a benchmark for comparison against similar baselines.
Critical strengths
The experiments in the paper appear correctly implemented; the authors add several baselines to the rebuttal, which helps compare different classifiers on top of frozen image embeddings.
Critical weaknesses
W1. The geometric motivation is not empirically established.
The proposed method, LorentzTIM, introduces significant complexity (§4.2) motivated by the claim that UXO embeddings are "tree-like". But why are UXO embeddings special in this regard, i.e., in the presence of large foundation vision models, how can one motivate the development of considerable algorithmic machinery to tackle the specific problem of UXO identification, and how generalizable are the paper’s claims beyond the task of UXO identification? In addition,
-
Table 2 (row 1 in particular) seeks to establish that UXO embeddings are “tree-like”. I disagree that the current result supports this claim: the Gaussian control lacks class structure and is too weak of a control, therefore exhibiting higher tree-likeness in comparison to this baseline is not sufficiently informative. At minimum, a comparison with real image embeddings (e.g. Imagenet-1k) would be relevant.
-
Likewise, no evidence in the paper supports lines 425-426: “when the data are more intrinsically tree-like, hyperbolic methods tend to outperform flat Euclidean baselines.” This would require a correlation between the “tree-likeness” of embeddings and the advantage of LorentzTIM over the baselines; given that the paper only uses one dataset and one model in the current manuscript, it is unclear to me how this conclusion can be made from the current evidence. Even with the three additional datasets promised in the penultimate section (which are, importantly, missing), we would only have four data points in total. This would be far too small a sample size for making a general claim about the correlation between the geometry of the embeddings and the effectiveness of LorentzTIM on said embeddings.
W2. Very limited empirical strength towards the claimed advantages of LorentzTIM.
-
The comparison between TIM over Euclidean and hyperbolic embeddings is not sufficiently controlled. For instance, LorentzTIM uses Eqn. 21 as a regularizer. It is unclear to me whether this regularizer was used for the Euclidean version as well, but from the manuscript, the answer seems no. Likewise, the ablation in Table 4(a) does not satisfyingly isolate the benefit of hyperbolic embeddings: it looks like the curvature was set to zero while keeping the other hyperparameters at their LorentzTIM settings, which is potentially suboptimal for Euclidean TIM. As such, I find it hard to understand whether the 2-4 pp. gains from LorentzTIM (vs. tuned Euclidean TIM) come from the hyperbolic treatment or an improved TIM itself.
-
In particular, if the core claim is that UXO embeddings benefit from being lifted into a hyperbolic space, the benefit should plausibly occur independently of applying TIM. A simple experiment would compare linear and nonlinear classifiers trained over Euclidean and hyperbolic embeddings, with matched hyperparameter tuning budgets. This is perhaps attempted in SimpleShot vs Hyp-SimpleShot: Hyp-SimpleShot there has rather small improvements compared to SimpleShot (all less than 1 pp). Perhaps hyperbolic embeddings benefit especially from TIM, but the paper neither (i) provides an ablation showing the general superiority of hyperbolic embeddings nor (ii) clarifies the qualification that hyperbolic embeddings work well only under the specific, proposed modifications. If (ii) reduces to a really narrow setting (hyperparameter configuration, dataset and model), that brings us back to the generalizability issue from W1.
-
The only feature extractor presented in the manuscript is DINOv3; there is no justification as to why this model is suitable for the study, and no other models are considered. Even though the paper mentions CLIP was also considered in the Appendix, said Appendix is missing. Similarly, the three datasets promised in lines 471-473 are missing (evidently, because they were in the missing Appendix). Figure 5 is missing the baseline numbers, therefore, it currently remains inconclusive towards a proper assessment of the advantage of LorentzTIM. More broadly, though, even with DINOv3 and a single CLIP model, the study would have been far too limited for making a general claim about vision features.
Questions for authors
Please treat the points mentioned under Weaknesses as critical questions. In addition, for a potential re-assessment of my score,
Q1. I would appreciate seeing more ablations: in particular, a more direct ablation comparing Euclidean and hyperbolic embeddings under various downstream models (linear classifier, 2-layer MLP, and finetuning) would be really helpful.
Q2. Can the authors motivate why the task of UXO is especially suited to the proposed LorentzTIM? What do the current results tell us about which tasks will benefit from the proposed method? To make this question more concrete for the rebuttal, I would appreciate seeing results on the other three datasets from the missing appendix.
6 comments
Response to Reviewer VMSG (2/4)
W1. Geometric motivation.
-
Why geometry, given foundation models. LorentzTIM does not replace foundation models. It adapts class prototypes on their frozen features, and it improves on Euclidean TIM with both backbones we tested (Table A). The added cost is small: 197-199 ms per 5-way 5-shot episode on one RTX 4090 (Table 8);
-
Is UXO special? UXO motivated the work through scarce labels, a long tail, environmental degradation and visual similarity across categories, but the method is not UXO-specific. The same gains appear on CUB-200-2011, FGVC-Aircraft and tieredImageNet (Table D under W2);
-
Strength of the control and comparison with real image embeddings. We agree that the original Gaussian control has no class structure. We added a class-conditional and a full-covariance control, both generated in the full feature space and L2-normalised like Z (Table B). The UXO embeddings Z have the lowest δ_rel (.2453) and the highest cophenetic correlation (.768 / .613) of the four point sets. The class-conditional control comes close (δ_rel .2678, with overlapping confidence intervals; cophenetic .683 / .567), whereas the two controls without class structure are clearly less hierarchical (δ_rel .3070 and .4215; cophenetic at most .520 / .454). The tree-likeness of Z is therefore explained largely by its class structure. Following the suggestion, we also computed the diagnostics on ImageNet-derived embeddings (tieredImageNet): δ_rel is .147 with DINOv3 and .198 with CLIP, against .2453 and .284 for CTX-UXO. Natural-image embeddings are therefore also tree-like, which is consistent with LorentzTIM improving on all three additional datasets. We present tree-likeness as a general motivation for hyperbolic adaptation rather than as a property specific to UXO.
Table A. CTX-UXO, macro-F1 (%), 1,000 paired test episodes.
| Backbone | Method | 1-shot | 3-shot | 5-shot | 10-shot |
|---|---|---|---|---|---|
| DINOv3 | TIM (tuned) | 49.54 | 65.18 | 69.35 | 76.14 |
| LorentzTIM (tuned) | 53.83 | 67.10 | 72.10 | 80.51 | |
| CLIP | TIM (same ψ as LorentzTIM) | 34.46 | 43.07 | 47.52 | 52.52 |
| TIM (own random search) | 34.82 | 43.44 | 49.85 | 55.71 | |
| LorentzTIM (tuned) | 39.29 | 46.78 | 51.42 | 56.57 |
Table B. Geometric diagnostics for the UXO embeddings and three controls (DINOv3).
| Data | Participation ratio | δ_rel (tree-likeness), 95% CI | ρ_coph (Pearson / Spearman) |
|---|---|---|---|
| UXO embeddings Z | 29.04 | .2453 [.213, .274] | .768 / .613 |
| Single-Gaussian control (Eq. 11) | 12.88 | .4215 [.394, .462] | .520 / .454 |
| Full-covariance Gaussian, no class structure (new) | 35.29 | .3070 [.255, .355] | .505 / .411 |
| Class-conditional Gaussian (new) | 34.44 | .2678 [.233, .318] | .683 / .567 |
Response to Reviewer VMSG (3/4)
W2. Controls and empirical strength.
-
Was the regulariser of Eq. 21 used for Euclidean TIM? We added Euclidean TIM with the regulariser, tuned by its own random search with the same budget (Table C). Adding the regulariser changes Euclidean TIM by −0.82 / +0.67 / +1.38 / −0.81 points; LorentzTIM remains above it at every shot (by 5.11 / 1.25 / 1.37 / 5.18 points).
-
Table 4(a) keeps the LorentzTIM hyperparameters. This is correct, and the tuned Euclidean variant with the regulariser above is the comparison the reviewer asks for. In addition, the fixed-parameter row of Table 3 uses TIM's own hyperparameters, not ours, and still exceeds tuned TIM at every shot (+1.74 / +1.26 / +2.32 / +3.43).
-
Hyperbolic lifting alone. In the balanced protocol, Hyp-SimpleShot exceeds SimpleShot at every shot, by +0.69 / +0.57 / +0.69 / +0.41 points, while LorentzTIM exceeds tuned TIM by +4.29 / +1.92 / +2.75 / +4.37. Our claim is therefore the narrower one, option (ii) in the review: hyperbolic geometry helps in combination with transductive prototype adaptation.
-
Choice of DINOv3. Its self-supervised features are strong on fine-grained recognition with frozen backbones (Siméoni et al., 2025), which matches the UXO setting. CLIP is evaluated as a second backbone (Table A). The paper reports results for these two backbones and does not extend the claim to other vision features.
-
Three further datasets. LorentzTIM improves on Euclidean TIM run with the same hyperparameters in all 24 dataset × backbone × shot settings, by +1.31 to +3.67 points, and on the separately tuned TIM in all 24, by +1.34 to +3.43 points (Table D).
-
Figure 5. The baseline values behind Figure 5 are given in Table D.
Table C. CTX-UXO, DINOv3, macro-F1 (%), 1,000 paired test episodes.
| Method | 1-shot | 3-shot | 5-shot | 10-shot |
|---|---|---|---|---|
| TIM, tuned by random search | 49.54 | 65.18 | 69.35 | 76.14 |
| TIM + origin regulariser (Eq. 21), tuned by random search | 48.72 | 65.85 | 70.73 | 75.33 |
| LorentzTIM, c → 0 (Table 4(a); with regulariser, LorentzTIM settings) | 48.86 | 64.71 | 68.82 | 75.58 |
| LorentzTIM, TIM's fixed hyperparameters (no search) | 51.28 | 66.44 | 71.67 | 79.57 |
| LorentzTIM, tuned | 53.83 | 67.10 | 72.10 | 80.51 |
Table D. Values behind Figure 5, with both TIM protocols: macro-F1 (%) with DINOv3, 1,000 paired episodes per setting.
| Dataset | Method | 1-shot | 3-shot | 5-shot | 10-shot |
|---|---|---|---|---|---|
| CUB-200-2011 | TIM (same ψ as LorentzTIM) | 83.66 | 89.86 | 92.14 | 93.95 |
| TIM (own random search) | 83.83 | 90.36 | 91.90 | 93.88 | |
| LorentzTIM | 86.24 | 91.70 | 93.82 | 95.26 | |
| FGVC-Aircraft | TIM (same ψ as LorentzTIM) | 80.46 | 87.93 | 90.73 | 93.11 |
| TIM (own random search) | 80.66 | 88.53 | 90.44 | 93.03 | |
| LorentzTIM | 83.20 | 90.12 | 92.65 | 94.78 | |
| tieredImageNet | TIM (same ψ as LorentzTIM) | 78.86 | 86.12 | 88.99 | 91.52 |
| TIM (own random search) | 79.08 | 86.81 | 88.65 | 91.42 | |
| LorentzTIM | 82.41 | 88.77 | 91.22 | 93.36 |
Q1. Downstream classifiers.
We added the ablation in both geometries for two downstream models: a linear classifier (Euclidean logistic regression vs hyperbolic multinomial logistic regression) and a 2-layer MLP (ReLU hidden layer of 32-128 units; the hyperbolic version applies the hidden layer in the tangent space at the origin and uses the hyperbolic MLR as output layer). Each is trained on the support set with its own random search and the same budget (Table E). Together with SimpleShot versus Hyp-SimpleShot (inductive) and T = 0 (Table 4(b)), this separates the geometry from the transductive step.
Table E. CTX-UXO, DINOv3, macro-F1 (%).
| Method | 1-shot | 3-shot | 5-shot | 10-shot |
|---|---|---|---|---|
| Euclidean logistic regression (support set, tuned) | 46.70 | 61.04 | 67.79 | 75.20 |
| Hyperbolic MLR (support set, tuned) | 47.57 | 61.42 | 67.19 | 75.07 |
| Euclidean 2-layer MLP (support set, tuned) | 46.75 | 60.99 | 67.16 | 74.14 |
| Hyperbolic 2-layer MLP (support set, tuned) | 46.65 | 61.53 | 67.56 | 74.31 |
| SimpleShot | 46.90 | 60.50 | 66.45 | 72.99 |
| Hyp-SimpleShot | 47.59 | 61.07 | 67.14 | 73.40 |
| LorentzTIM | 53.83 | 67.10 | 72.10 | 80.51 |
With matched tuning budgets, the hyperbolic linear classifier shows no consistent advantage over the Euclidean one (+0.87 / +0.38 / −0.60 / −0.13 points at 1 / 3 / 5 / 10 shots), and neither does the hyperbolic MLP (−0.10 / +0.54 / +0.40 / +0.17 points). This matches option (ii) in the review: the hyperbolic advantage comes with transductive adaptation and is not a general property of the embeddings. We did not fine-tune the backbone: LorentzTIM is a training-free method over frozen features, and fine-tuning would change the embeddings whose geometry is being compared. All classifiers in Table E and all transductive methods operate on the same frozen features.
Response to Reviewer VMSG (1/4)
We thank the reviewer for the detailed feedback. The CLIP results and the three further datasets were in Appendix G (Tables 9-12), which was submitted as supplementary material. We report them directly below (Tables A and D).
Summary. (1) Controls that isolate the geometry within each method: Euclidean TIM with the regulariser and its own search, and linear and 2-layer MLP classifiers in both geometries.
(2) Results with CLIP and on three further datasets, against both a TIM with the same hyperparameters and a separately tuned TIM.