- Rating
- 1
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper proposes a two-phase approach to domain generalization without explicit domain or group labels during training. The key assumption is that the training data include label-preserving matched sets that share a class but differ in a nuisance variation the model should ignore. The training is done in multiple phases (2), each finetuning the feature extractor and then a classifier.
Critical strengths
- The papaer addresses DG under worst-group performance without requiring explicit domain/group labels for every training example.
Critical weaknesses
- In the method the combination of subspace projection, representation learning, and logit-margin regularization is established. But the specific benefit of the proposed integration lacks stronger motivation.
- Although the method does not require explicit domain IDs for every training example, it uses matched examples or counterfactual variations to identify nuisance changes. It is still considered as a meaniful supervision. There needs to be a comparison to test performance on how much and what types of matched examples are useful.
- The results from Table. 1 shows that LISA beats the proposed method in two out of three benchmarks. In the first two the margin is substantial.
- There is mismatch in the result presented in table 1, and that explaiend in section 4.2.
- The generalizability of the proposed method is shown limitedly. Its performance across other popular DG benchmarks such as DomainNet has not been established.
- The main design choice of this method: tolerances controlling within-class logit dispersion and worst-case class margins. These hyperparameters are not ablated.
Questions for authors
- How much of the improvement comes specifically from the proposed latent-geometry learning? Do you have any ablation done in this regard?
- What is the total training and tuning cost, including the geometry updates and the construction of matched examples compared with standard ERM and other baselines?
- Can authors clarify about how much matched data would be needed and how robust is the method when there are imperfect or noisy matches?
Response to Reviewer iVbH
During the rebuttal, (thanks to the reviewers’ comments) we realized that our formulation and experiments were inconsistent, making our “domain-label-free” claim overstated: although the algorithm takes neither domain label nor object-identity labels, during the experiments we utilized object information to construct the label-preserving pairs. This information leakage made our reported experimental comparison misleading, especially due to our choice of baselines that do not necessarily benefit from object-identify labels. During the rebuttal phase, we tried to address this gap: we evaluated label-preserving pair without any object-identity labels; matching our algorithm with the experimental results. Unfortunately, we observe a substantial amount of performance drop which we couldn’t resolve at the moment. We therefore agree with the reviewers’ shared opinion on this work that it should be rejected at least in this stage. We apologize again for our inconsistency; also for the delayed response. And most importantly, we appreciate the reviewers for their constructive comments/criticisms. In the following, we tried to provide point-by-point response to the reviewer’s comments, in case they are of the interest still.
Q1 Contribution of latent geometry learning
The ablation compares learning B on a fixed ERM representation with jointly updating B and the representation parameters in Eq. (7). All results below are measured right after projection, before adaptation. The gain persists when direct projection uses its natural rank, supporting joint representation learning beyond rank selection alone.
Q2 Training and data construction cost
The UrbanCars asset counts below include one label and one crop per car, with backgrounds and co-objects reused across rendered views. Beyond ERM, we learn the representation and adapt after projection; adaptation alone takes 69–148 minutes per UrbanCars sensitivity run.
Q3 Amount and type of useful matched data
On UrbanCars, reducing matched-set coverage to 10% lowers worst-group accuracy from 87.5% to 77.9%. Replacing views in 10% of the matched sets with views of different cars and different nuisance-source images lowers it to 49.3 ± 37.7%. Indeed, our algorithm is sensitive to such imperfect matches which we couldn’t resolve at the moment. Nonetheless, a good matched data for a new application might be obtained by cropping the object using some off-the-shelf object detection algorithm and then generate backgrounds using generative AI tools. Although this can be an interesting direction, it was beyond the scope of our revision; we will try to address the reviewer’s comments in our future work. Thanks again for raining important comments/criticisms.