- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes Hierarchy-Aware Cross-Entropy (HACE), which expands the classifier over all hierarchy nodes, aggregates raw softmax mass upward through a reachability matrix, and distributes target mass from each true leaf toward its ancestors. The method is evaluated on CIFAR-100, FGVC Aircraft, and NABirds in end-to-end training across six architectures and in linear probing with frozen DINOv2-Large features. The paper reports improved leaf accuracy in most settings and stronger hierarchical operating metrics, with especially large gains on deeper fine-grained taxonomies.
Critical strengths
- HACE is a simple, broadly usable loss modification with a clear construction and negligible implementation burden. Combining ancestor targets with monotone aggregated predictions is conceptually coherent.
- The evaluation covers several architectures, datasets, training regimes, and hierarchical metrics, and it directly compares with relevant hierarchy-aware losses. Improvements in both leaf accuracy and mistake severity would be practically meaningful if they are robust.
Critical weaknesses
- The headline tables select the best result across dilution values and two learning-rate pairings, while HACE and SCE do not receive an equal number of effective model-selection opportunities (the paper states six HACE and four SCE models per architecture-dataset pair). This can bias the comparison, especially because some SCE runs diverge and the mean gain is much larger than the median.
- Results appear to come from single runs per configuration, without seed variability or a held-out hyperparameter-selection protocol. Consequently, the large reported average improvements cannot be separated cleanly from optimization instability and selection noise. The experiments also omit the important pretrained fine-tuning regime.
Questions for authors
- Under an equal tuning budget and a validation-selected dilution/learning-rate rule fixed before test evaluation, what are the paired HACE-versus-SCE results across multiple seeds? This answer could change my recommendation.
- How much of the gain remains when both losses are initialized from the same pretrained backbone and fine-tuned with identical schedules? The current from-scratch setting is unusually unstable for the fine-grained datasets and transformer models.
3 comments
We sincerely thank the reviewer once again for their thoughtful and constructive feedback. We believe that the additional experiments and clarifications prompted by their suggestions strengthen our work. We kindly ask for further feedback, and we are happy to engage in more discussion.
Response by Reviewer FCWs
Thank you for your responses. My concerns have been addressed. I will raise my socre.
We thank the reviewer for the constructive feedback and for recognizing the simplicity of HACE and the breadth of the experimental evaluation. We answer both questions below.
Regarding seeds, the original experiments used one seed per configuration. We have now run three seeds for DINOv2 linear probing on NABirds (see the table in our response to Reviewer JLqo) and for the new fine-tuning experiments described below.