Search Results for author:
Found 20 papers, 7 papers with code
Semantic Segmentation by Semantic Proportions
Utilising semantic proportions suggested in this work offers a promising direction for future research in the field of semantic segmentation.
Generalisation and the Risk--Entropy Curve
In this paper we show that the expected generalisation performance of a learning machine is determined by the distribution of risks or equivalently its logarithm -- a quantity we term the risk entropy -- and the fluctuations in a quantity we call the training ratio.
Orthogonalising gradients to speed up neural network optimisation
The optimisation of neural networks can be sped up by orthogonalising the gradients before the optimisation step, ensuring the diversification of the learned representations.
On the Effects of Artificial Data Modification
Data distortion is commonly applied in vision models during both training (e. g methods like MixUp and CutMix) and evaluation (e. g. shape-texture bias and robustness).
GeoCLR: Georeference Contrastive Learning for Efficient Seafloor Image Interpretation
We demonstrate how the latent representations generated by GeoCLR can be used to efficiently guide human annotation efforts, where the semi-supervised framework improves classification accuracy by an average of 10. 2% compared to the state-of-the-art SimCLR using the same CNN and equivalent number of human annotations for training.
Language Models as Zero-shot Visual Semantic Learners
We find that contextual representations in language mod-els outperform static word embeddings, when the compositional chain of object is short.
What Remains of Visual Semantic Embeddings
Although different paradigms of visual semantic embedding models are designed to align visual features and distributed word representations, it is unclear to what extent current ZSL models encode semantic information from distributed word representations.
Object detection for crabs in top-view seabed imagery
This report presents the application of object detection on a database of underwater images of different species of crabs, as well as aerial images of sea lions and finally the Pascal VOC dataset.
RotLSTM: Rotating Memories in Recurrent Neural Networks
Long Short-Term Memory (LSTM) units have the ability to memorise and use long-term dependencies between inputs to generate predictions on time series data.
Quasi-Newton's method in the class gradient defined high-curvature subspace
Classification problems using deep learning have been shown to have a high-curvature subspace in the loss landscape equal in dimension to the number of classes.
FMix: Enhancing Mixed Sample Data Augmentation
Finally, we show that a consequence of the difference between interpolating MSDA such as MixUp and masking MSDA such as FMix is that the two can be combined to improve performance even further.
Ranked #3 on
Image Classification
on Fashion-MNIST
Rethinking Generalisation
In this paper, a new approach to computing the generalisation performance is presented that assumes the distribution of risks, $\rho(r)$, for a learning scenario is known.
Imagining the Latent Space of a Variational Auto-Encoders
Variational Auto-Encoders (VAEs) are designed to capture compressible information about a dataset.
Deep Set Prediction Networks
Current approaches for predicting sets from feature vectors ignore the unordered nature of sets and suffer from discontinuity issues as a result.
FSPool: Learning Set Representations with Featurewise Sort Pooling
Traditional set prediction models can struggle with simple datasets due to an issue we call the responsibility problem.
Probabilistic Semantic Embedding
We present an extension of a variational auto-encoder that creates semantically richcoupled probabilistic latent representations that capture the semantics of multiplemodalities of data.
Learning Representations of Sets through Optimized Permutations
Representations of sets are challenging to learn because operations on sets should be permutation-invariant.
Learning to Count Objects in Natural Images for Visual Question Answering
Visual Question Answering (VQA) models have struggled with counting objects in natural images so far.
Ranked #32 on
Visual Question Answering (VQA)
on VQA v2 test-std
Modifying memories in a Recurrent Neural Network Unit
Long Short-Term Memory (LSTM) units have the ability to memorise and use long-term dependencies between inputs to generate predictions on time series data.
