- Rating
- 4
- Confidence
- 4
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper addresses the problem of discovering new visual categories and proposes a framework for learning the relationship between known classes and new categories. The method combines label-guided multi-view matrix decomposition with relation modeling based on known class prototypes, and jointly utilizes distribution information and category relationship information for new category clustering. It has achieved good experimental results on multiple benchmark datasets.
Critical strengths
- To address the issue that the existing multi-view new category discovery methods do not adequately utilize the relationship between known categories and new categories, a targeted solution has been proposed.
- By using the prototype of the known category as the relationship anchor point and guiding the division of new categories through the consistency constraint of the relationship, an effective combination of distributed information and relationship information has been achieved.
Critical weaknesses
- The method requires the pre-determination of the number of new categories, and the applicability in cases where the number of categories is unknown has not been discussed.
- The performance improvement on some datasets is relatively limited. It is recommended to further analyze the role of the relationship learning module under different data features.
- The experiments lack the standard deviation reports from multiple runs. Adding statistical stability analysis will make the results more convincing.
Questions for authors
- When the feature correlation between the known class and the new category is weak, will the effect of the relationship learning module be affected?
- Can the experimental results under different random seeds be supplemented to further verify the stability of the performance improvement?
Response
W1. What if the number of novel classes is unknown?
Our experiments assume that the number of novel classes ku is given. Appendix F describes a possible extension. We would first estimate the count from labeled probe classes, following Han et al. (ICCV 2019), and then use the estimate to set the number of novel clusters and their relation prototypes.
W2. Why are the improvements smaller on some datasets?
On Reuters, our ACC is 0.24 percentage points above the strongest baseline in Table 2. Table 3 shows how much the relation branch contributes by keeping known-class supervision in both variants. On the original splits, adding the branch improves ACC by 2.50 points on Mfeat, 25.78 on Cora, and 29.10 on Citeseer. On Mfeat, the ablation already reaches 95.60% ACC, leaving less room for improvement.
We also compared the gain from the relation branch across known-class subsets with lower and higher similarity while keeping the novel samples fixed (see Q1 below).
W3. Report variability across runs.
We ran the full model and the relation-branch ablation on the original class splits using the same five seeds for both variants. For each dataset, we fixed the full model’s hyperparameters to the values used in Table 3. The ablation sets λ1=λ2=0 and retains known-class supervision.
ACC over five seeds (mean ± sample SD, %)
Q1. Does the relation branch still help when known and novel classes are weakly related?
For each dataset, we kept the novel samples fixed and matched the numbers of known classes and labeled samples across conditions. We used ground-truth labels to compute class centroids for this diagnostic. For each candidate subset of known classes, we averaged the cosine similarity of each known–novel centroid pair across views. We then took the highest similarity within that subset for each novel class and averaged these values across novel classes. We compared the lowest- and highest-scoring subsets using the same full-model hyperparameters.
Paired ACC gain from adding the relation branch (five seeds, mean ± SD, percentage points)
Under lower similarity, the branch improved mean ACC on four of the five datasets. The gain was larger in the higher-similarity condition on two datasets and smaller on three. On Wiki, the branch reduced mean ACC in both conditions. The subsets also differ in which known classes they contain, so these results describe how the branch behaved under the two choices of anchors. One possible explanation for the gains at lower similarity is that novel classes can still differ in their relation patterns across the full set of anchors.
Q2. Does the improvement hold across random seeds?
On each of the five datasets, the full model achieved higher mean ACC than the ablation over the five runs (see W3). The difference between the two means ranged from 2.50 percentage points on Mfeat to 29.10 on Citeseer.