Search Results for author:
Found 15 papers, 3 papers with code
conv_einsum: A Framework for Representation and Fast Evaluation of Multilinear Operations in Convolutional Tensorial Neural Networks
Modern ConvNets continue to achieve state-of-the-art results over a vast array of vision and image classification tasks, but at the cost of increasing parameters.
End-to-end Rain Streak Removal with RAW Images
To be specific, we generate rainy RAW data by converting color rain streak into RAW space and design simple but efficient RAW processing algorithms to synthesize both rainy and clean color images.
LEMON: Lossless model expansion
Our empirical results demonstrate that LEMON reduces computational costs by 56. 7% for Vision Transformers and 33. 2% for BERT when compared to training from scratch.
Reviving Shift Equivariance in Vision Transformers
While the self-attention operator in vision transformers (ViT) is permutation-equivariant and thus shift-equivariant, patch embedding, positional encoding, and subsampled attention in ViT variants can disrupt this property, resulting in inconsistent predictions even under small shift perturbations.
Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach
In experiments, we show that our method consistently brings non-trivial improvements to the three aforementioned learning tasks from both efficiency and final performance, either or not combined with strong pre-defined augmentations, e. g., on medical images when domain knowledge is unavailable and the existing augmentation techniques perform poorly.
Scaling-up Diverse Orthogonal Convolutional Networks by a Paraunitary Framework
Some of these designs are not exactly orthogonal, while others only consider standard convolutional layers and propose specific classes of their realizations.
Tuformer: Data-Driven Design of Expressive Transformer by Tucker Tensor Representation
Guided by tensor diagram representations, we formulate a design space where we can analyze the expressive power of the network structure, providing new directions and possibilities for enhanced performance.
Certified Defense via Latent Space Randomized Smoothing with Orthogonal Encoders
Randomized Smoothing (RS), being one of few provable defenses, has been showing great effectiveness and scalability in terms of defending against $\ell_2$-norm adversarial perturbations.
Scaling-up Diverse Orthogonal Convolutional Networks with a Paraunitary Framework
To address this problem, we propose a theoretical framework for orthogonal convolutional layers, which establishes the equivalence between various orthogonal convolutional layers in the spatial domain and the paraunitary systems in the spectral domain.
Convolutional Tensor-Train LSTM for Spatio-temporal Learning
Learning from spatio-temporal data has numerous applications such as human-behavior analysis, object tracking, video compression, and physics simulation. However, existing methods still perform poorly on challenging video tasks such as long-term forecasting.
Ranked #1 on
Video Prediction
on KTH
(Cond metric)
ARMA Nets: Expanding Receptive Field for Dense Prediction
In this work, we propose to replace any traditional convolutional layer with an autoregressive moving-average (ARMA) layer, a novel module with an adjustable receptive field controlled by the learnable autoregressive coefficients.
Understanding Generalization in Deep Learning via Tensor Methods
Recently proposed complexity measures have provided insights to understanding the generalizability in neural networks from perspectives of PAC-Bayes, robustness, overparametrization, compression and so on.
Sampling-Free Learning of Bayesian Quantized Neural Networks
Bayesian learning of model parameters in neural networks is important in scenarios where estimates with well-calibrated uncertainty are important.
Convolutional Tensor-Train LSTM for Long-Term Video Prediction
Long-term video prediction is highly challenging since it entails simultaneously capturing spatial and temporal information across a long range of image frames. Standard recurrent models are ineffective since they are prone to error propagation and cannot effectively capture higher-order correlations.
Tensorial Neural Networks: Generalization of Neural Networks and Application to Model Compression
We propose tensorial neural networks (TNNs), a generalization of existing neural networks by extending tensor operations on low order operands to those on high order ones.
