17 citations · 58 across the 16 of their papers we have counts for
16 papers
Exploring Data Augmentations on Self-/Semi-/Fully- Supervised Pre-trained Models
Shentong Mo, Zhun Sun, Chao Li
Data augmentation has become a standard component of vision pre-trained models to capture the invariance between augmented views. In practice, augmentation techniques that mask reg…
What Can Simple Arithmetic Operations Do for Temporal Modeling?
Wenhao Wu, Yuxin Song, Zhun Sun +3
Temporal modeling plays a crucial role in understanding video content. To tackle this problem, previous studies built complicated temporal relations through time sequence thanks to…
Rethinking Prototypical Contrastive Learning through Alignment, Uniformity and Correlation
Shentong Mo, Zhun Sun, Chao Li
Contrastive self-supervised learning (CSL) with a prototypical regularization has been introduced in learning meaningful representations for downstream tasks that require strong se…
Design of the topology for contrastive visual-textual alignment
Zhun Sun
Cosine similarity is the common choice for measuring the distance between the feature representations in contrastive visual-textual alignment learning. However, empirically a learn…
Siamese Prototypical Contrastive Learning
Shentong Mo, Zhun Sun, Chao Li
Contrastive Self-supervised Learning (CSL) is a practical solution that learns meaningful visual representations from massive data in an unsupervised approach. The ordinary CSL emb…
Revisiting Classifier: Transferring Vision-Language Models for Video Recognition
Wenhao Wu, Zhun Sun, Wanli Ouyang
Transferring knowledge from task-agnostic pre-trained deep models for downstream tasks is an important topic in computer vision research. Along with the growth of computational cap…
On the Memory Mechanism of Tensor-Power Recurrent Models
Hejia Qiu, Chao Li, Ying Weng +3
Tensor-power (TP) recurrent model is a family of non-linear dynamical systems, of which the recurrence relation consists of a p-fold (a.k.a., degree-p) tensor product. Despite such…
Improving Head Pose Estimation with a Combined Loss and Bounding Box Margin Adjustment
Mingzhen Shao, Zhun Sun, Mete Ozay +1
We address a problem of estimating pose of a person's head from its RGB image. The employment of CNNs for the problem has contributed to significant improvement in accuracy in rece…
Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration
Xing Liu, Masanori Suganuma, Zhun Sun +1
In this paper, we study design of deep neural networks for tasks of image restoration. We propose a novel style of residual connections dubbed "dual residual connection", which exp…
Low-Rank Embedding of Kernels in Convolutional Neural Networks under Random Shuffling
Chao Li, Zhun Sun, Jinshi Yu +2
Although the convolutional neural networks (CNNs) have become popular for various image processing and computer vision task recently, it remains a challenging problem to reduce the…
Beyond Unfolding: Exact Recovery of Latent Convex Tensor Decomposition under Reshuffling
Chao Li, Mohammad Emtiyaz Khan, Zhun Sun +4
Exact recovery of tensor decomposition (TD) methods is a desirable property in both unsupervised learning and scientific data analysis. The numerical defects of TD methods, however…
HyperNetworks with statistical filtering for defending adversarial examples
Zhun Sun, Mete Ozay, Takayuki Okatani
Deep learning algorithms have been known to be vulnerable to adversarial perturbations in various tasks such as image classification. This problem was addressed by employing severa…
Linear Discriminant Generative Adversarial Networks
Zhun Sun, Mete Ozay, Takayuki Okatani
We develop a novel method for training of GANs for unsupervised and class conditional generation of images, called Linear Discriminant GAN (LD-GAN). The discriminator of an LD-GAN…
Improving Robustness of Feature Representations to Image Deformations using Powered Convolution in CNNs
Zhun Sun, Mete Ozay, Takayuki Okatani
In this work, we address the problem of improvement of robustness of feature representations learned using convolutional neural networks (CNNs) to image deformation. We argue that…
Information Potential Auto-Encoders
Yan Zhang, Mete Ozay, Zhun Sun +1
In this paper, we suggest a framework to make use of mutual information as a regularization criterion to train Auto-Encoders (AEs). In the proposed framework, AEs are regularized b…
Design of Kernels in Convolutional Neural Networks for Image Classification
Zhun Sun, Mete Ozay, Takayuki Okatani
Despite the effectiveness of Convolutional Neural Networks (CNNs) for image classification, our understanding of the relationship between shape of convolution kernels and learned r…