- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes FHAW (Funk–Hecke Adaptive Weighting), a lightweight patch gating module for visual Transformers. It projects and normalizes patch features onto a sphere, generates weights using Gegenbauer polynomials based on their similarity to learnable reference directions, and then modulates the patch features to improve performance on visual tasks.
Critical strengths
-
Each module has approximately 25k parameters, making it easy to integrate into existing ViTs.
-
The spherical angular frequency interpretation and orthogonal basis selection are mathematically supported.
-
Some results have been validated with multiple seeds, and failure conditions and negative results are also reported.
Critical weaknesses
-
Gegenbauer gating has not yet been proven to outperform conventional MLP gating within the same budget.
-
Most improvements are small and dependent on training methods, insertion positions, and output formats.
Questions for authors
-
With fixed projection, reference direction, and output format, and only replaced with an MLP of the same budget, can FHAW still maintain its leading position?
-
Can the gains be retained on a strong baseline with sufficient training? Especially since Swin-B's current results are still below the official checkpoint.