- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes BandDiT, which applies frequency-specific supervision at different Transformer depths based on the observation that low-frequency information is decoded earlier than high-frequency details. Experiments on ImageNet-256 show modest improvements in FID, 5-crop FID, and hFWD over JiT, with faster convergence in terms of training epochs.
Critical strengths
-
Supervising different layers according to their frequency characteristics is an intuitive idea. The method does not require a pretrained teacher or changes to the original generation architecture or sampling procedure, making it relatively easy to adopt.
-
The evaluation is fairly comprehensive. In addition to FID, the authors report 5-crop FID and hFWD to assess local structure and texture quality, and evaluate the method at multiple model scales.
Critical weaknesses
-
The motivation is not fully supported by Figure 3. The authors use the final output head to decode intermediate features, but this head was trained on the final layer. Poor high-frequency decodability in shallow layers may simply come from this mismatch rather than missing information.
-
It's still unclear whether band-depth alignment is the main reason for the improvements. In Table 3, G0 alone achieves an FID of 4.23, while adding all bands slightly worsens it to 4.25. A comparison with standard intermediate supervision is also missing. Some gains are quite small, such as the H model improving FID from 1.91 to just 1.90, though with fewer training epochs. The extra adapters also make the actual training efficiency unclear.
Questions for authors
-
If a separate linear probe were trained for each intermediate layer, rather than reusing the final output head, would the same frequency hierarchy still be observed? Does this trend hold across different noise levels?
-
Given the three additional adapters used during training, does BandDiT require fewer GPU-hours or training FLOPs than JiT to reach the same FID?