- Rating
- 2(+1)
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes HyCoPro, which projects visual and textual features into role specific representations in the Poincaré ball that correspond respectively to states, objects, and compositions, and uses Möbius addition to construct compositional prototypes from primitive prototypes. The visual textual closure loss aligns the combined visual primitives with the text prototype obtained by encoding the complete prompt, while the bidirectional text text closure loss aligns, among candidate compositions, the prototype obtained by combining text primitives with the explicit compositional prototype. During training, the method uses Euclidean and hyperbolic classification losses, orthogonal regularization, and counterfactual regularization. At inference time, the model fuses explicit prototypes with prototypes formed by combining primitives, and primitive scores with composition scores, and further introduces Euclidean scores and feasibility priors depending on the dataset. The paper conducts closed world and open world evaluations on three standard datasets and presents three theoretical propositions. The method is plausible, and the reported MIT-States results are encouraging, but the submission has not yet sufficiently established its unique geometric contribution.
Critical strengths
-
The paper addresses a relevant and valuable limitation in composition-level recognition in the CZSL field. Explicitly establishing a connection between primitive representations and compositional prototypes is a reasonable route for recognizing compositions without training images. Emphasizing open-world CZSL also fits the characteristics of the problem, since the expansion of the candidate set makes prototype quality and seen-unseen calibration more important.
-
The two closure objectives provide a coherent mechanism for connecting primitives and compositions. The visual-textual and textual-textual objectives in Equations (3) to (6) connect complementary sources of supervision. In particular, the textual-side closure can regularize candidate compositions without introducing additional images. Retaining both the full-prompt prototype and the primitive-combination prototype also allows the model to combine holistic semantics with reusable semantic information.
-
The reported improvement on MIT-States is relatively large. In Table 1, open-world HM increases from 22.4 for the strongest baseline in the table to 27.3, and AUC increases from 8.7 to 12.5. These improvements are commendable. Conducting experiments on three datasets under two evaluation settings also provides valuable evaluation breadth, although baseline coverage still needs to be corrected.
Critical weaknesses
-
The contribution of the method is not clear. Troika [R1] adopts three-branch modeling for states, objects, and compositions. FlowComposer [R2] has studied explicit composition in embedding space. Pal et al. [R3] have studied compositional vision-language learning in hyperbolic space. These methods differ from this paper, but they make the contribution of this paper more focused on the specific closure form and the advantages verified for it. The introduction uses spatial packing capacity to argue for hyperbolic geometry and uses non-commutativity to argue for Möbius addition. However, neither argument proves that benchmark performance is limited by the packing capacity of Euclidean space, nor does either prove that this particular asymmetry can capture state-object semantics better than a learnable, role-aware Euclidean operator. The role-specific projection head itself already distinguishes the two types of input. The results in Figure 1 are noteworthy, but the definition of the operator and the control conditions in it are insufficiently explained and cannot yet resolve this issue. The paper needs to explain more clearly what contribution the proposed geometric structure brings beyond structured multi-branch learning and compositional consistency.
-
The theoretical analysis does not substantially support the core claim about unseen composition recognition. Propositions 1-3 provide background intuition and conditional score relationships, rather than an explanation or guarantee of compositional generalization for this method.
-
The ablation experiments do not sufficiently isolate the sources of improvement, nor do they explicitly verify the role of closure under the candidate scale emphasized in the paper. Table 2 removes inference scores, and removing hyperbolic scores is not equivalent to evaluating a Euclidean model retrained under matched adaptation, primitive supervision, closure losses, and regularization. The authors should conduct a controlled comparison at the training level. Likewise, the closure loss ablation is conducted only on UT-Zappos. In Figure 1, the full candidate set for this dataset contains only 192 compositions, whereas the larger datasets use sampled textual-side closure. On UT-Zappos, after removing text-to-text closure, open-world HM/AUC changes only from 53.4/37.8 to 53.0/37.1. These results support that closure yields gains in this setting, but they do not establish that it can explain the larger open-world improvements. The authors should conduct a matched Euclidean training comparison, closure ablations on larger benchmarks, and a control with and without the feasibility prior to resolve these attribution issues.
-
The results reported in the paper are attractive on MIT-States; however, important baselines are missing from the compared methods, including ClusPro (ICLR25) [R4], FlowComposer (CVPR26) [R2], and EVA (ICLR2026) [R5]. After including these baselines, the authors do not appear to be highly competitive on the two benchmarks UT-Zappos and C-GQA. It is recommended that the authors include these baselines and re-evaluate the results.
-
The writing of the entire paper should undergo a complete revision, especially Figure 1 and the writing and layout of the Method section. The presentation in Figure 1 is relatively unclear.
[R1] Huang, Siteng, et al. "Troika: Multi-path cross-modal traction for compositional zero-shot learning." 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2024.
[R2] He, Zhenqi, Lin Li, and Long Chen. "FlowComposer: Composable Flows for Compositional Zero-Shot Learning." 2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2026.
[R3] Pal, Avik, et al. "Compositional entailment learning for hyperbolic vision-language models." International Conference on Learning Representations. Vol. 2025. 2025.
[R4] Qu, Hongyu, et al. "Learning clustering-based prototypes for compositional zero-shot learning." International Conference on Learning Representations. Vol. 2025. 2025.
[R5] Zhang, Xiao, et al. "Decoupling primitive with experts: Dynamic feature alignment for compositional zero-shot learning." The Fourteenth International Conference on Learning Representations. 2026.
Questions for authors
Please address the above issues.
3 comments
Response to the Authors
I thank the authors for their response. I acknowledge that the authors have added fair comparison experiments with Euclidean methods, expanded the ablation studies, and updated the performance comparisons with recent methods. These results partially address my previous concerns about the effectiveness of the individual components of the method. Therefore, I am willing to raise my score from 1 to 2.
However, I still have some concerns. First, the authors still do not provide a sufficiently detailed analysis explaining why HyCoPro achieves particularly strong performance on MIT-States but fails to demonstrate comparable advantages on UT-Zappos and C-GQA. Moreover, the rebuttal does not provide convincing evidence of a consistent performance advantage over recent methods, such as EVA (ICLR'26) and VP-CMJL (ICCV'25). Considering that MIT-States is a dataset with relatively high label noise, the current results are not yet sufficient to fully demonstrate that the method has a stable and consistent advantage across different compositional recognition scenarios. Given that this paper emphasizes the advantages of hyperbolic geometry in large-scale compositional spaces, I suggest that the authors further provide experimental results on additional benchmarks such as VAW-CZSL, or conduct a more comprehensive analysis of candidate composition scale on C-GQA. Second, although the authors addressed the relevant issues in their response, I still believe that the overall writing and presentation of the current paper are not sufficiently polished. In particular, Figure 2 contains too many complex modules and connections, making the overall framework difficult to understand intuitively. In addition, the main text spends considerable space discussing theoretical propositions, but these analyses provide relatively limited help in explaining the actual generalization behavior of the method on unseen compositions. I suggest that the authors further streamline the related content and devote more space to clearly explaining the core design of the method or to supplementing relevant experimental content.
Rebuttal by Authors
We thank Reviewer kcpC for raising the score and for the constructive follow-up feedback. Below, we provide the requested candidate-scale analysis on C-GQA and outline our plan to further streamline the presentation.
1. Candidate-scale analysis on C-GQA and dataset-dependent gains
Following your suggestion, we evaluated full HyCoPro (A) and its matched Euclidean counterpart (C) on the same 5,098 C-GQA test images. We used fixed epoch-3 checkpoints from the seed-42 sensitivity run for A and the seed-42 Euclidean control run for C. Starting from the 6,515-pair closed-world vocabulary, we progressively added distractor compositions up to the full 278,362-pair open-world space. Throughout the sweep, both models used identical nested candidate pools, fixed inference weights, and the same open-world feasibility prior.
| Candidates | A HM / AUC | C HM / AUC | A−C HM | A−C AUC |
|---|---|---|---|---|
| 6,515 | 33.26 / 15.07 | 32.52 / 14.80 | +0.74 | +0.27 |
| 10,000 | 31.95 / 13.88 | 31.39 / 13.74 | +0.56 | +0.14 |
| 30,000 | 27.59 / 10.62 | 27.23 / 10.56 | +0.36 | +0.06 |
| 100,000 | 21.65 / 7.44 | 21.41 / 7.25 | +0.25 | +0.19 |
| 278,362 | 15.93 / 4.86 | 15.58 / 4.62 | +0.35 | +0.23 |
Differences are computed before rounding.
As the candidate pool grows, HM and AUC decline for both models. HyCoPro achieves higher mean HM and AUC at every tested scale, although the gaps are modest and do not widen consistently. At the full C-GQA scale, HyCoPro retains an advantage of 0.35 HM points and 0.23 AUC points over the matched Euclidean model. This experiment shows how the two models respond to a larger candidate pool within C-GQA. The extent to which candidate count explains the larger gains on MIT-States remains open. We will include this analysis and a concise discussion of dataset-dependent behavior in the revised manuscript.
2. Simplifying Figure 2 and streamlining the theory section
We appreciate your specific suggestions on the paper's presentation. In the revision, we will simplify Figure 2 by reducing visual clutter and explicitly highlighting the core visual–text and text–text closure paths so that the overall architecture is easier to follow at a glance. We will also condense the theoretical propositions in the main text, deferring extended details to the supplementary material, and reallocate the saved space to a clearer explanation of our core design and the additional experimental analyses.
Rebuttal by Authors
We thank the reviewer for recognizing our problem formulation, dual closure objectives, and open-world gains. Below we address Q1–Q5.
A1: Troika [R1] uses three-branch alignment, FlowComposer [R2] learns Euclidean velocity transport, and Pal et al. [R3] model entailment cones. Complementing them, HyCoPro formulates non-commutative algebraic closure (tsh⊕ctoh≈ts,oh) in the Poincare ball via visual-text and text-text supervision.
[state, object]composer in hyperbolic space (Variant B, +0.53M params) and a full ordered Euclidean model retrained from scratch (Variant C), confirming gains beyond role-specific heads and learnable Euclidean composition.Ord. Mobiusx⊕cy (51.8/35.9),Sym. Mobiusexp0c((log0c(x⊕cy)+log0c(y⊕cx))/2) (45.2/28.7),EuclideanN(x+y) (47.9/32.9), andOrd. EuclideanN(LN(W[x;y]+b)) (49.4/34.4).A2: Please see A3 to Reviewer 6X9h, where we connect Mobius closure to unseen generalization via the hyperbolic triangle inequality. Smoothness and closure of ⊕c ensure that accurate primitive alignment and small closure residuals bound an unseen image feature's distance to its explicit prototype, supporting Propositions 2–3 without unseen training images.
A3: All three controls are in our responses to Reviewers wQAb and 6X9h:
A4: We compare with [R4, R2, R5] below (HM / AUC):
A5: We clarified the Fig. 1 caption and revised Sections 3.3–3.6.