Return of Frustratingly Easy Domain Adaptation
- Baochen Sun, Jiashi Feng, Kate Saenko
- Computer ScienceAAAI Conference on Artificial Intelligence
- 17 November 2015
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.
Deep Joint Rain Detection and Removal from a Single Image
- Wenhan Yang, R. Tan, Jiashi Feng, Jiaying Liu, Zongming Guo, Shuicheng Yan
- Computer ScienceComputer Vision and Pattern Recognition
- 25 September 2016
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.
Decoupling Representation and Classifier for Long-Tailed Recognition
- Bingyi Kang, Saining Xie, Yannis Kalantidis
- Computer ScienceInternational Conference on Learning…
- 21 October 2019
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.
Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
- Jian Liang, D. Hu, Jiashi Feng
- Computer ScienceInternational Conference on Machine Learning
- 20 February 2020
This work proposes a simple yet generic representation learning framework, named SHOT, which freezes the classifier module (hypothesis) of the source model and learns the target-specific feature extraction module by exploiting both information maximization and self-supervised pseudo-labeling to implicitly align representations from the target domains to the source hypothesis.
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
- Li Yuan, Yunpeng Chen, Shuicheng Yan
- Computer ScienceIEEE International Conference on Computer Vision
- 28 January 2021
A new Tokens-To-Token Vision Transformer (T2T-VTT), which incorporates an efficient backbone with a deep-narrow structure for vision transformer motivated by CNN architecture design after empirical study and reduces the parameter count and MACs of vanilla ViT by half.
PANet: Few-Shot Image Semantic Segmentation With Prototype Alignment
- Kaixin Wang, J. Liew, Yingtian Zou, Daquan Zhou, Jiashi Feng
- Computer ScienceIEEE International Conference on Computer Vision
- 18 August 2019
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.
Few-Shot Object Detection via Feature Reweighting
- Bingyi Kang, Zhuang Liu, Xin Wang, F. Yu, Jiashi Feng, Trevor Darrell
- Computer ScienceIEEE International Conference on Computer Vision
- 5 December 2018
This work develops a few-shot object detector that can learn to detect novel objects from only a few annotated examples, using a meta feature learner and a reweighting module within a one-stage detection architecture.
Tensor Robust Principal Component Analysis with a New Tensor Nuclear Norm
- Canyi Lu, Jiashi Feng, Yudong Chen, W. Liu, Zhouchen Lin, Shuicheng Yan
- Computer ScienceIEEE Transactions on Pattern Analysis and Machine…
- 10 April 2018
This paper considers the Tensor Robust Principal Component Analysis (TRPCA) problem, which aims to exactly recover the low-rank and sparse components from their sum, and proposes a model based on the recently proposed tensor-tensor product, which includes matrix RPCA as a special case.
Dual Path Networks
- Yunpeng Chen, Jianan Li, Huaxin Xiao, Xiaojie Jin, Shuicheng Yan, Jiashi Feng
- Computer ScienceNIPS
- 6 July 2017
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.
Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization
- Canyi Lu, Jiashi Feng, Yudong Chen, W. Liu, Zhouchen Lin, Shuicheng Yan
- Computer ScienceComputer Vision and Pattern Recognition
- 1 June 2016
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.
...
...