Massey Documents by Type

Now showing 1 - 4 of 4

WBNet: Weakly-supervised salient object detection via scribble and pseudo-background priors
(Elsevier Ltd, 2024-10) Wang Y; Wang R; He X; Lin C; Wang T; Jia Q; Fan X
Weakly supervised salient object detection (WSOD) methods endeavor to boost sparse labels to get more salient cues in various ways. Among them, an effective approach is using pseudo labels from multiple unsupervised self-learning methods, but inaccurate and inconsistent pseudo labels could ultimately lead to detection performance degradation. To tackle this problem, we develop a new multi-source WSOD framework, WBNet, that can effectively utilize pseudo-background (non-salient region) labels combined with scribble labels to obtain more accurate salient features. We first design a comprehensive salient pseudo-mask generator from multiple self-learning features. Then, we pioneer the exploration of generating salient pseudo-labels via point-prompted and box-prompted Segment Anything Models (SAM). Then, WBNet leverages a pixel-level Feature Aggregation Module (FAM), a mask-level Transformer-decoder (TFD), and an auxiliary Boundary Prediction Module (EPM) with a hybrid loss function to handle complex saliency detection tasks. Comprehensively evaluated with state-of-the-art methods on five widely used datasets, the proposed method significantly improves saliency detection performance. The code and results are publicly available at https://github.com/yiwangtz/WBNet.
Fuzzy neural network interface : development and application : a thesis presented in partial fulfilment of the requirements for the degree of Master of Engineering in Information Engineering at Massey University, Palmerston North, New Zealand
(Massey University, 2003) Todd, Greg
This project is concerned with the development and application of an interface for a fuzzy neural network (FuNN). The original program, for which the interface was written, is a tool to research the mapping of problem knowledge to initialize the weights of a FuNN. The interface concentrates on allowing the user to efficiently manipulate network settings and to be able to easily perform large numbers of experiments. After the interface was completed, the new integrated application was used to investigate the use of problem knowledge on FuNN training in specific image processing problems.
Pattern formation in a neural field model : a thesis presented in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Mathematics at Massey University, Auckland, New Zealand
(Massey University, 2008) Elvin, Amanda Jane
In this thesis I study the effects of gap junctions on pattern formation in a neural field model for working memory. I review known results for the base model (the “Amari model”), then see how the results change for the “gap junction model”. I find steady states of both models analytically and numerically, using lateral inhibition with a step firing rate function, and a decaying oscillatory coupling function with a smooth firing rate function. Steady states are homoclinic orbits to the fixed point at the origin. I also use a method of piecewise construction of solutions by deriving an ordinary differential equation from the partial integro-differential formulation of the model. Solutions are found numerically using AUTO and my own continuation code in MATLAB. Given an appropriate level of threshold, as the firing rate function steepens, the solution curve becomes discontinuous and stable homoclinic orbits no longer exist in a region of parameter space. These results have not been described previously in the literature. Taking a phase space approach, the Amari model is written as a four-dimensional, reversible Hamiltonian system. I develop a numerical technique for finding both symmetric and asymmetric homoclinic orbits. I discover a small separate solution curve that causes the main curve to break as the firing rate function steepens and show there is a global bifurcation. The small curve and the global bifurcation have not been reported previously in the literature. Through the use of travelling fronts and construction of an Evans function, I show the existence of stable heteroclinic orbits. I also find asymmetric steady state solutions using other numerical techniques. Various methods of determining the stability of solutions are presented, including a method of eigenvalue analysis that I develop. I then find both stable and transient Turing structures in one and two spatial dimensions, as well as a Type-I intermittency. To my knowledge, this is the first time transient Turing structures have been found in a neural field model. In the Appendix, I outline numerical integration schemes, the pseudo-arclength continuation method, and introduce the software package AUTO used throughout the thesis.
Automatic Recognition of Light Microscope Pollen Images
(Massey University, 2006) Allen, Gary; Hodgson, Bob; Marsland, Stephen; Arnold, Greg; Flemmer, Rory; Flenley, John; Fountain, David
This paper is a progress report on a project aimed at the realization of a low-cost, automatic, trainable system "AutoStage" for recognition and counting of pollen. Previous work on image feature selection and classification has been extended by design and integration of an XY stage to allow slides to be scanned, an auto focus system, and segmentation software. The results of a series of classification tests are reported, and verified by comparison with classification performance by expert palynologists. A number of technical issues are addressed, including pollen slide preparation and slide sampling protocols.

Massey Documents by Type

Browse

Filters

Settings

Sort By

Results per page

Search Results