Reducing Deep Network Complexity via Sparse Hierarchical Fourier Interaction Networks
This paper presents a Sparse Hierarchical Fourier Interaction Networks, an architectural building block that unifies three complementary principles of frequency domain modeling: A hierarchical patch wise Fourier transform that affords simultaneous access to local detail and global context; A learnable, differentiable top K masking mechanism which retains only the most informative spectral coefficients, thereby exploiting the natural compressibility of visual and linguistic signals.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
On Recovering Higher-order Interactions from Protein Language Models
Protein language models leverage evolutionary information to perform state-of-the-art 3D structure and zero-shot variant prediction. Yet, extracting and explaining all the mutational interactions that govern model predic…
Language ModellingProtein Language ModelRobust Sparse Fourier Transform Based on The Fourier Projection-Slice Theorem
The state-of-the-art automotive radars employ multidimensional discrete Fourier transforms (DFT) in order to estimate various target parameters. The DFT is implemented using the fast Fourier transform (FFT), at sample an…
Efficiently Computing Sparse Fourier Transforms of $q$-ary Functions
Fourier transformations of pseudo-Boolean functions are popular tools for analyzing functions of binary sequences. Real-world functions often have structures that manifest in a sparse Fourier transform, and previous work…
Efficient Algorithm for Sparse Fourier Transform of Generalized $q$-ary Functions
Computing the Fourier transform of a $q$-ary function $f:\mathbb{Z}_{q}^n\rightarrow \mathbb{R}$, which maps $q$-ary sequences to real numbers, is an important problem in mathematics with wide-ranging applications in bio…
Accelerated Volumetric Compression without Hierarchies: A Fourier Feature Based Implicit Neural Representation Approach
Volumetric data compression is critical in fields like medical imaging, scientific simulation, and entertainment. We introduce a structure-free neural compression method combining Fourierfeature encoding with selective v…