Search Results for author:
Found 11 papers, 9 papers with code
Tackling Structural Hallucination in Image Translation with Local Diffusion
We hypothesize such hallucinations result from local OOD regions in the conditional images.
An Image is Worth Multiple Words: Learning Object Level Concepts using Multi-Concept Prompt Learning
To address this challenge, we introduce a framework for Multi-Concept Prompt Learning (MCPL), where multiple new "words" are simultaneously learned from a single sentence-image pair.
Expectation Maximization Pseudo Labels
In the remainder of the paper, we showcase the applications of pseudo-labelling and its generalised form, Bayesian Pseudo-Labelling, in the semi-supervised segmentation of medical images.
Bayesian Pseudo Labels: Expectation Maximization for Robust and Efficient Semi-Supervised Segmentation
Secondly, we propose a semi-supervised medical image segmentation method purely based on the original pseudo labelling, namely SegPL.
Learning Morphological Feature Perturbations for Calibrated Semi-Supervised Segmentation
We propose MisMatch, a novel consistency-driven semi-supervised segmentation framework which produces predictions that are invariant to learnt feature perturbations.
MisMatch: Calibrated Segmentation via Consistency on Differential Morphological Feature Perturbations with Limited Labels
The state-of-the-art SSL methods in image classification utilise consistency regularisation to learn unlabelled predictions which are invariant to input level perturbations.
Learning to Downsample for Segmentation of Ultra-High Resolution Images
Many computer vision systems require low-cost segmentation algorithms based on deep learning, either because of the enormous size of input images or limited computational budget.
Bidirectional LSTM-CRF Attention-based Model for Chinese Word Segmentation
Chinese word segmentation (CWS) is the basic of Chinese natural language processing (NLP).
Disentangling Human Error from Ground Truth in Segmentation of Medical Images
In all cases, our method outperforms competing methods and relevant baselines particularly in cases where the number of annotations is small and the amount of disagreement is large.
Disentangling Human Error from the Ground Truth in Segmentation of Medical Images
Recent years have seen increasing use of supervised learning methods for segmentation tasks.
Foveation for Segmentation of Ultra-High Resolution Images
We demonstrate on three publicly available high-resolution image datasets that the foveation module consistently improves segmentation performance over the cases trained with patches of fixed FoV/resolution trade-off.
