cscribano / DCT-Former-Public
Public repository for "DCT-Former: Efficient Self-Attention withDiscrete Cosine Transform"
☆17Updated last year
Related projects ⓘ
Alternatives and complementary repositories for DCT-Former-Public
- ☆10Updated last year
- ☆11Updated 11 months ago
- ☆10Updated last year
- ☆41Updated 3 years ago
- Test-time adaptation for speech recognition model by single utterance. The official implementation of "Listen, Adapt, Better WER: Source-…☆15Updated 2 years ago
- Differentiable short-time Fourier transform (DSTFT): Gradient-based parameters tuning for adaptive time-frequency representation. DSTFT i…☆32Updated 6 months ago
- Code for the paper titled "Generalized Depthwise-Separable Convolutions for Adversarially Robust and Efficient Neural Networks" (NeurIPS…☆11Updated 2 years ago
- Transformer based Self-Attention for Complex Numbers☆11Updated 3 years ago
- Deep Learning Model for Signal Data☆84Updated 5 years ago
- Spiking Neural Network for computing the DFT and the CFAR on automotive radar☆20Updated 3 years ago
- [ICLR 2022] "Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice" by Peihao Wang, Wen…☆76Updated 10 months ago
- Position-based Scaled Gradient for Model Quantization and Pruning Code (NeurIPS 2020)☆26Updated 4 years ago
- ☆14Updated 6 months ago
- Hierarchical Group Sparse Regularization for Deep Convolutional Neural Networks☆11Updated 4 years ago
- WeightNet: Revisiting the Design Space of Weight Networks☆18Updated 3 years ago
- ☆17Updated 3 years ago
- ☆12Updated last year
- Complex tensor and complex functions for pytorch.☆47Updated 2 years ago
- Curse-of-memory phenomenon of RNNs in sequence modelling☆19Updated last week
- A pytorch implementation of DVIB(Deep Variational Information Bottleneck)☆9Updated 5 years ago
- Code for High-Capacity Expert Binary Networks (ICLR 2021).☆27Updated 2 years ago
- GBDT-NAS☆28Updated 3 years ago
- [CVPR'22] Parametric Scattering Networks☆23Updated 7 months ago
- ☆21Updated 2 years ago
- Code for the ICML 2021 and ICLR 2022 papers: Skew Orthogonal Convolutions, Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100☆18Updated 2 years ago
- ☆11Updated 2 months ago
- Source code for AAAI 22 paper: Hybrid Neural Networks for On-Device Directional Hearing☆14Updated 7 months ago
- Decoupled Kullback-Leibler Divergence Loss (DKL), NeurIPS 2024☆33Updated 3 weeks ago
- ICASSP 2024: Robust DOA estimation from deep acoustic imaging☆11Updated 7 months ago