- Rating
- 1
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper proposes Hierarchical Dictionary Learning Tree (HDLT), which organizes sparse dictionaries into a tree based on Geometric Multi-Resolution Analysis (GMRA). The method passes sparse codes between tree levels and trains the dictionaries through differentiable sparse coding, with an optional classification loss. Experiments on CLIP image features show a WordNet-consistent concept hierarchy on a 30-class ImageNet subset. The authors also evaluate classification performance on CIFAR-100 and ImageNet.
Critical strengths
- The paper explores an interesting approach to hierarchical dictionary learning. Passing sparse codes between tree levels allows the model to represent patterns of atom activation rather than repeatedly processing the original features.
- The authors attempt to evaluate concept discovery using quantitative metrics, including leaf purity, cophenetic correlation, and atom–concept alignment.
- The experiments include comparisons between end-to-end and greedy training, as well as different ways of passing information between tree levels. These ablations are relevant for understanding the proposed design.
Critical weaknesses
- The main contribution is not clearly separated from the existing GMRA framework. The method starts with a tree constructed from the geometry of CLIP features, which may already capture much of the reported concept hierarchy. It is unclear how much the learned dictionaries actually contribute.
- The atom–concept alignment results are not convincing. Table 2 shows that the GMRA centroid baseline achieves a cosine similarity of 0.81, compared with only 0.32 for HDLT. The root dictionary alone achieves 0.30, suggesting that the additional learned layers contribute very little to this metric.
- The comparison with hierarchical clustering methods is not fully fair. The paper compares HDLT's cophenetic correlation with K-means and Ward using flat cluster assignments, even though Ward naturally produces a hierarchical tree. Using the full clustering hierarchy could substantially change the comparison.
- The paper does not include the appendices.
Questions for authors
Please see weakness.