1k citations · 1.1k across the 9 of their papers we have counts for
10 papers
i-WiViG: Interpretable Window Vision GNN
Ivica Obadic, Dmitry Kangin, Adrian Höhl +3
Vision graph neural networks have emerged as a popular approach for modeling the global and spatial context for image recognition. However, a significant drawback of these methods…
COMIX: Compositional Explanations using Prototypes
Sarath Sivaprasad, Dmitry Kangin, Plamen Angelov +1
Aligning machine representations with human understanding is key to improving interpretability of machine learning (ML) models. When classifying a new image, humans often explain t…
IMAFD: An Interpretable Multi-stage Approach to Flood Detection from time series Multispectral Data
Ziyang Zhang, Plamen Angelov, Dmitry Kangin +1
In this paper, we address two critical challenges in the domain of flood detection: the computational expense of large-scale time series change detection and the lack of interpreta…
Unsupervised Domain Adaptation within Deep Foundation Latent Spaces
Dmitry Kangin, Plamen Angelov
The vision transformer-based foundation models, such as ViT or Dino-V2, are aimed at solving problems with little or no finetuning of features. Using a setting of prototypical netw…
Towards interpretable-by-design deep learning algorithms
Plamen Angelov, Dmitry Kangin, Ziyang Zhang
The proposed framework named IDEAL (Interpretable-by-design DEep learning ALgorithms) recasts the standard supervised classification problem into a function of similarity to a set…
Imbedding Deep Neural Networks
Andrew Corbett, Dmitry Kangin
Continuous-depth neural networks, such as Neural ODEs, have refashioned the understanding of residual neural networks in terms of non-linear vector-valued optimal control problems.…
Skillful Precipitation Nowcasting using Deep Generative Models of Radar
Suman Ravuri, Karel Lenc, Matthew Willson +17
Precipitation nowcasting, the high-resolution forecasting of precipitation up to two hours ahead, supports the real-world socio-economic needs of many sectors reliant on weather-de…
A review of radar-based nowcasting of precipitation and applicable machine learning techniques
Rachel Prudden, Samantha Adams, Dmitry Kangin +4
A 'nowcast' is a type of weather forecast which makes predictions in the very short term, typically less than two hours - a period in which traditional numerical weather prediction…
On-Policy Trust Region Policy Optimisation with Replay Buffers
Dmitry Kangin, Nicolas Pugeault
Building upon the recent success of deep reinforcement learning methods, we investigate the possibility of on-policy reinforcement learning improvement by reusing the data from sev…
Aggregated Sparse Attention for Steering Angle Prediction
Sen He, Dmitry Kangin, Yang Mi +1
In this paper, we apply the attention mechanism to autonomous driving for steering angle prediction. We propose the first model, applying the recently introduced sparse attention m…