30 citations · 74 across the 17 of their papers we have counts for
17 papers
Few-Shot Class-Incremental Learning from an Open-Set Perspective
Can Peng, Kun Zhao, Tianren Wang +2
The continual appearance of new objects in the visual world poses considerable challenges for current deep learning methods in real-world deployments. The challenge of new task lea…
DIODE: Dilatable Incremental Object Detection
Can Peng, Kun Zhao, Sam Maksoud +2
To accommodate rapid changes in the real world, the cognition system of humans is capable of continually learning concepts. On the contrary, conventional deep learning models lack…
Scalable Bayesian Deep Learning with Kernel Seed Networks
Sam Maksoud, Kun Zhao, Can Peng +1
This paper addresses the scalability problem of Bayesian deep neural networks. The performance of deep neural networks is undermined by the fact that these algorithms have poorly c…
Polynomial Trajectory Predictions for Improved Learning Performance
Ido Freeman, Kun Zhao, Anton Kummert
The rising demand for Active Safety systems in automotive applications stresses the need for a reliable short to mid-term trajectory prediction. Anticipating the unfolding path of…
SID: Incremental Learning for Anchor-Free Object Detection via Selective and Inter-Related Distillation
Can Peng, Kun Zhao, Sam Maksoud +2
Incremental learning requires a model to continually learn new tasks from streaming data. However, traditional fine-tuning of a well-trained deep neural network on a new task will…
PrognoseNet: A Generative Probabilistic Framework for Multimodal Position Prediction given Context Information
Thomas Kurbiel, Akash Sachdeva, Kun Zhao +1
The ability to predict multiple possible future positions of the ego-vehicle given the surrounding context while also estimating their probabilities is key to safe autonomous drivi…
SOS: Selective Objective Switch for Rapid Immunofluorescence Whole Slide Image Classification
Sam Maksoud, Kun Zhao, Peter Hobson +2
The difficulty of processing gigapixel whole slide images (WSIs) in clinical microscopy has been a long-standing barrier to implementing computer aided diagnostic systems. Since mo…
Faster ILOD: Incremental Learning for Object Detectors based on Faster RCNN
Can Peng, Kun Zhao, Brian C. Lovell
The human vision and perception system is inherently incremental where new knowledge is continually learned over time whilst existing knowledge is retained. On the other hand, deep…
To What Extent Does Downsampling, Compression, and Data Scarcity Impact Renal Image Analysis?
Can Peng, Kun Zhao, Arnold Wiliem +4
The condition of the Glomeruli, or filter sacks, in renal Direct Immunofluorescence (DIF) specimens is a critical indicator for diagnosing kidney diseases. A digital pathology syst…
Deep inspection: an electrical distribution pole parts study via deep neural networks
Liangchen Liu, Teng Zhang, Kun Zhao +3
Electrical distribution poles are important assets in electricity supply. These poles need to be maintained in good condition to ensure they protect community safety, maintain reli…
Visual analytics for team-based invasion sports with significant events and Markov reward process
Kun Zhao, Takayuki Osogami, Tetsuro Morimura
In team-based invasion sports such as soccer and basketball, analytics is important for teams to understand their performance and for audiences to understand matches better. The pr…
Deep Instance-Level Hard Negative Mining Model for Histopathology Images
Meng Li, Lin Wu, Arnold Wiliem +3
Histopathology image analysis can be considered as a Multiple instance learning (MIL) problem, where the whole slide histopathology image (WSI) is regarded as a bag of instances (i…
CORAL8: Concurrent Object Regression for Area Localization in Medical Image Panels
Sam Maksoud, Arnold Wiliem, Kun Zhao +3
This work tackles the problem of generating a medical report for multi-image panels. We apply our solution to the Renal Direct Immunofluorescence (RDIF) assay which requires a path…
Convex Class Model on Symmetric Positive Definite Manifolds
Kun Zhao, Arnold Wiliem, Shaokang Chen +1
The effectiveness of Symmetric Positive Definite (SPD) manifold features has been proven in various computer vision tasks. However, due to the non-Euclidean geometry of these featu…
SlideNet: Fast and Accurate Slide Quality Assessment Based on Deep Neural Networks
Teng Zhang, Johanna Carvajal, Daniel F. Smith +5
This work tackles the automatic fine-grained slide quality assessment problem for digitized direct smears test using the Gram staining protocol. Automatic quality assessment can pr…
Determining the best attributes for surveillance video keywords generation
Liangchen Liu, Arnold Wiliem, Shaokang Chen +2
Automatic video keyword generation is one of the key ingredients in reducing the burden of security officers in analyzing surveillance videos. Keywords or attributes are generally…
Efficient Clustering on Riemannian Manifolds: A Kernelised Random Projection Approach
Kun Zhao, Azadeh Alavi, Arnold Wiliem +1
Reformulating computer vision problems over Riemannian manifolds has demonstrated superior performance in various computer vision applications. This is because visual data often fo…