July - December, 2018
High-level vision stuff with deep learning. Mentor: David Eigen
Sep 2015 - now
Ph.D. Student, Chinese Univ. of Hong Kong
Mitacs Research Internship at University of Victoria
Devise an algorithm to alleviate the server bandwidth consumption in a P2P VoD system.
Bachelor Degree at Dalian University of Technology
Electronic and Information Engineering.
How to pronounce my name Hongyang? It's Home
Pinned: I am actively searching for industry/academia internships and jobs all over the globe, as I am about to graduate in June 2019.
- My Academic Blog. A good (probably best) way of sharing ideas than bustling around like most people do in conferences.
- Jun. 2018: We are organizing a workshop on machine learning reproducibility (RML) in conjunction with ICML 2018.
I am currently the third-year (2017.8 - 2018.7) PhD student at The Chinese University of Hong Kong
My research covers a wide span of deep learning, computer vision (high-level stuff) and machine learning.
In particular, I am interested in object detection, generic deep learning algorithms and capsule research. I used to do some research on salient object detection.
Neat first-author versoin. For a full list, check the Google Scholar page.
Zoom Out-and-In Network with Map Attention Decision for Region Proposal and Object Detection
We propose a zoom-out-and-in network for generating object proposals.
A key observation is that it is difficult to classify anchors of different sizes
with the same set of features. A map attention decision (MAD) unit is further proposed
to aggressively search for neuron activations among two streams and
attend the most contributive ones on the feature learning of the final loss.
The unit serves as a decision maker to adaptively activate maps along certain channels
with the solely purpose of optimizing the overall training loss.
One advantage of MAD is that the learned weights enforced on each feature channel
is predicted on-the-fly based on the input context,
which is more suitable than the fixed enforcement of a convolutional kernel.
Hongyang Li, Yu Liu, Wanli Ouyang, Xiaogang Wang
International Journal of Computer Vision (IJCV) 2018
Rethinking Feature Discrimination and Polymerization for Large-scale Recognition
Feature matters. How to train a deep network to acquire discriminative features
across categories and polymerized features within classes has always been
at the core of many computer vision tasks.
In this paper, we address this problem based on the simple intuition that
the cosine distance of features in high-dimensional space should be
close enough within one class and far away across categories.
To this end, we proposed the congenerous cosine (COCO) algorithm to
simultaneously optimize the cosine similarity among data.
It inherits the softmax property to make inter-class features discriminative
as well as shares the idea of class centroid in metric learning.
Yu Liu*, Hongyang Li*, Xiaogang Wang (* equal contribution)
NIPS 2017 deep learning
Do We Really Need More Training Data for Object Localization
New dataset proposed! ImageNet-3k
where the total number of classes is around 2700, including the original 1000 classes from the standard ILSVRC CLS challenge. Source image is provided from official webiste and we annotate each category with instance-level bounding boxes. [abstract]
As more datasets are available nowadays, one may wonder whether
the success of deep learning descends from data augmentation only.
In this paper, we propose a new dataset, namely, Extended
ImageNet Classification (EIC) dataset to investigate if
more training data is crucial. We find more data could enhance
average recall, but a more balanced data distribution among categories
could obtain better results at the cost of fewer training samples.
Multi-Bias Non-linear Activation in Deep Neural Networks
In this paper, we propose a multi-bias non-linear activation (MBA) layer
to explore the information hidden in the magnitudes of responses.
It is placed after the convolution layer to decouple the responses
to a convolution kernel into multiple maps by multi-thresholding magnitudes,
thus generating more patterns in the feature space at a low computational cost.
It provides great flexibility of selecting responses to different visual patterns
in different magnitude ranges to form rich representations in higher layers.
Hongyang Li, Wanli Ouyang, Xiaogang Wang
Inner and Inter Label Propagation: Salient Object Detection in the Wild
We propose a novel label propagation based method for saliency detection.
A key observation is that saliency in an image can be estimated by
propagating the labels extracted from the most certain background and object regions.
A co-transduction algorithm is devised to fuse both boundary and objectness labels
based on an inter propagation scheme to effectively improve the saliency accuracy.
Hongyang Li, Huchuan Lu, Zhe Lin, Xiaohui Shen, Brian Price
IEEE Trans. on Image Processing (TIP) 2015
Missioner on the Road
As a Student Researcher reviewing the following conferences
ECCV 2018, NIPS 2018, ICLR 2018.
BMVC 2017-2018, AAAI 2018, ICCV 2017.
As a Graduate Student learning the following courses
Foundations of Optimization.
Big Data Analytics
Pattern Recognition. Computer Vision. Advanced Machine Learning.