- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes EiT, a U-shaped Transformer with channel compression. The authors analyze three-stage representation dynamics using SPR and Noise Fraction, and introduce a DWT-based frequency-weighted loss. Experiments show that EiT outperforms JiT and some PixelU configurations on ImageNet-256/512, and also improves performance in latent diffusion.
Critical strengths
-
Channel compression is a simple and reasonable design. With comparable parameter counts and computational budgets, EiT achieves clear improvements over JiT, showing the practical value of this approach.
-
The experiments cover ImageNet-256/512, different model sizes, and latent diffusion. The paper also includes ablations on different channel compression configurations and frequency loss weights, making the evaluation relatively comprehensive.
-
The analysis using SPR and Noise Fraction offers a new perspective on how representations evolve inside diffusion Transformers. This is an interesting direction worth exploring further.
Critical weaknesses
-
The contribution of channel compression is not clearly isolated. Compared with JiT and PixelU, EiT changes not only the compression dimension but also the network depth and skip connection design. For example, EiT-B uses 24 layers, while PixelU-B has only 12. Without comparisons at matched depth and compute, it is unclear whether the improvements mainly come from channel compression or from the deeper network and other architectural changes.
-
The evidence for the three-stage representation dynamics is not fully convincing. A lower Noise Fraction does not necessarily mean better denoising, and a higher SPR does not always indicate more useful features. The lack of comparison with PixelU also makes it unclear whether these patterns are specific to channel compression or common to U-shaped architectures.
-
The novelty and empirical gains of the frequency-domain component are relatively limited. The equivalence between pixel-space and frequency-space diffusion mainly follows from the fact that orthogonal transforms preserve the L2 norm, while the DWT loss essentially gives more weight to low-frequency errors. Similar frequency-weighted losses have already been used in DeCo, so the novelty over prior work is unclear. The FID improvements are also relatively small.
Questions for authors
-
Could you directly compare channel compression, spatial compression, and a Transformer without compression under matched depth, similar FLOPs, and the same skip connection design? This would help clarify the core architectural contribution of EiT.
-
Could you compare the layer-wise SPR and Noise Fraction of EiT and PixelU under comparable settings? This would help clarify whether earlier denoising and longer basis lift-up are specific to channel compression.
-
What are the key differences between EiT's DWT loss and DeCo's Frequency-Aware FM loss? A comparison using the same model and training setup would help determine whether the DWT loss achieves better results.