In this paper, we aim to alleviate this performance decay on multi-step incremental detection tasks by proposing a dilatable incremental object detector (DIODE).
To address this problem we present a method for performing BDL, namely Kernel Seed Networks (KSN), which does not require a 2-fold increase in the number of parameters.
Incremental learning requires a model to continually learn new tasks from streaming data.
To address this problem, incremental learning methods have been explored which preserve the old knowledge of deep learning models.
To achieve gradient alignment, we propose Forward-Backward Cyclic Adaptation, which iteratively computes adaptation from source to target via backward hopping and from target to source via forward passing.
Critical findings are observed: (1) The best balance between detection accuracy, detection speed and file size is achieved at 8 times downsampling captured with a $40\times$ objective; (2) compression which reduces the file size dramatically, does not necessarily have an adverse effect on overall accuracy; (3) reducing the amount of training data to some extents causes a drop in precision but has a negligible impact on the recall; (4) in most cases, Faster R-CNN achieves the best accuracy in the glomerulus detection task.
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. e, patches) and the task is to predict a single class label to the WSI.
This is because the system can ignore the attention mechanism by assigning equal weights for all members.
Our proposed framework, named Manifold Convex Class Model, represents each class on SPD manifolds using a convex model, and classification can be performed by computing distances to the convex models.
In order to address the quality assessment problem, we propose a deep neural network based framework to automatically assess the slide quality in a semantic way.
We show that existing adversarial perturbation methods are not effective to perform such an attack, especially when there are multiple faces in the input image.
While it can greatly increase the scope and benefits of the current security surveillance systems, performing such a task using thermal images is a challenging problem compared to face recognition task in the Visible Light Domain (VLD).
With this metric, automatic quantitative evaluation can be performed on the attribute sets; thus, reducing the enormous effort to perform manual evaluation.
In this paper, we propose a novel approach, based on the shared structure exhibited amongst meaningful attributes, that enables us to compare between different automatic attribute discovery approaches. We then validate our approach by comparing various attribute discovery methods such as PiCoDeS on two attribute datasets.
In our evaluation, we gleaned some insights that could be beneficial in developing automatic attribute discovery methods to generate meaningful attributes.
We then validate our framework on several computer vision applications by comparing against popular clustering methods on Riemannian manifolds.
In this paper we propose a novel approach to multi-action recognition that performs joint segmentation and classification.
In our work, a specimen image descriptor is represented by its overall cell attribute descriptors.
Robust foreground object segmentation via background modelling is a difficult problem in cluttered environments, where obtaining a clear view of the background to model is almost impossible.
Here, we propose to make better use of the structure of this manifold and rely on the distance on the manifold to compare the source and target distributions.
This paper describes a novel system for automatic classification of images obtained from Anti-Nuclear Antibody (ANA) pathology tests on Human Epithelial type 2 (HEp-2) cells using the Indirect Immunofluorescence (IIF) protocol.
For covariance-based image descriptors, taking into account the curvature of the corresponding feature space has been shown to improve discrimination performance.
Recent advances suggest that encoding images through Symmetric Positive Definite (SPD) matrices and then interpreting such matrices as points on Riemannian manifolds can lead to increased classification performance.
We then propose adaptive reference clustering (ARC) to constrain the clustering of each gallery image set by forcing the clusters to have resemblance to the clusters in the query image set.
A robust visual tracking system requires an object appearance model that is able to handle occlusion, pose, and illumination variations in the video stream.
Recent advances in computer vision and machine learning suggest that a wide range of problems can be addressed more appropriately by considering non-Euclidean geometry.
We show that by minimising the sparse representation reconstruction error, we approach the nearest point on a Grassmann manifold.
Recent advances suggest that a wide range of computer vision problems can be addressed more appropriately by considering non-Euclidean geometry.
While existing face recognition systems based on local features are robust to issues such as misalignment, they can exhibit accuracy degradation when comparing images of differing resolutions.
Furthermore, we propose the use of tracking performance as an unbiased approach for determining the practical usefulness of shadow detection methods.
In this paper, we propose a cell classification system comprised of a dual-region codebook-based descriptor, combined with the Nearest Convex Hull Classifier.
The motion and size features are modelled by an approximated version of kernel density estimation, which is computationally efficient even for large training datasets.
In video based face recognition, face images are typically captured over multiple frames in uncontrolled conditions, where head pose, illumination, shadowing, motion blur and focus change over the sequence.
This paper presents a video face recognition system based on probabilistic Multi-Region Histograms to characterise performance trade-offs in: (i) selecting a subset of faces compared to using all faces, and (ii) combining information from all faces via clustering.
We propose a new action and gesture recognition method based on spatio-temporal covariance descriptors and a weighted Riemannian locality preserving projection approach that takes into account the curved space formed by the descriptors.
Ranked #2 on Hand Gesture Recognition on Cambridge
In contrast to comparing faces via single exemplars, matching sets of face images increases robustness and discrimination performance.