• Publications
  • Influence
Return of Frustratingly Easy Domain Adaptation
TLDR
This work proposes a simple, effective, and efficient method for unsupervised domain adaptation called CORrelation ALignment (CORAL), which minimizes domain shift by aligning the second-order statistics of source and target distributions, without requiring any target labels. Expand
Deep Joint Rain Detection and Removal from a Single Image
TLDR
A recurrent rain detection and removal network that removes rain streaks and clears up the rain accumulation iteratively and progressively is proposed and a new contextualized dilated network is developed to exploit regional contextual information and to produce better representations for rain detection. Expand
Decoupling Representation and Classifier for Long-Tailed Recognition
TLDR
It is shown that it is possible to outperform carefully designed losses, sampling strategies, even complex modules with memory, by using a straightforward approach that decouples representation and classification. Expand
Dual Path Networks
TLDR
This work reveals the equivalence of the state-of-the-art Residual Network (ResNet) and Densely Convolutional Network (DenseNet) within the HORNN framework, and finds that ResNet enables feature re-usage while DenseNet enables new features exploration which are both important for learning good representations. Expand
Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization
TLDR
This work proves that under certain suitable assumptions, it can recover both the low-rank and the sparse components exactly by simply solving a convex program whose objective is a weighted combination of the tensor nuclear norm and the l1-norm. Expand
Online Robust PCA via Stochastic Optimization
TLDR
An Online Robust PCA (OR-PCA) is developed that processes one sample per time instance and hence its memory cost is independent of the number of samples, significantly enhancing the computation and storage efficiency. Expand
Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach
TLDR
This work investigates a principle way to progressively mine discriminative object regions using classification networks to address the weakly-supervised semantic segmentation problems and proposes a new adversarial erasing approach for localizing and expanding object regions progressively. Expand
Natural Language Object Retrieval
TLDR
Experimental results demonstrate that the SCRC model effectively utilizes both local and global information, outperforming previous baseline methods significantly on different datasets and scenarios, and can exploit large scale vision and language datasets for knowledge transfer. Expand
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
TLDR
A new TokensTo-Token Vision Transformers (T2T-ViT), which introduces an efficient backbone with a deep-narrow structure for vision transformers motivated by CNN architecture design after extensive study and reduces the parameter counts and MACs of vanilla ViT by 200%, while achieving more than 2.5% improvement when trained from scratch on ImageNet. Expand
PANet: Few-Shot Image Semantic Segmentation With Prototype Alignment
TLDR
This paper tackles the challenging few-shot segmentation problem from a metric learning perspective and presents PANet, a novel prototype alignment network to better utilize the information of the support set to better generalize to unseen object categories. Expand
...
1
2
3
4
5
...