|
| 1 | +@techreport{DGMMC2024, |
| 2 | +title={Performance of Gaussian Mixture Model Classifiers on Embedded Feature Spaces}, |
| 3 | +author={Jeremy Chopin and Rozenn Dahyot}, |
| 4 | +year={2024}, |
| 5 | +eprint={2410.13421}, |
| 6 | +archivePrefix={arXiv}, |
| 7 | +primaryClass={cs.CV}, |
| 8 | +url={https://arxiv.org/pdf/2410.13421}, |
| 9 | +month={October}, |
| 10 | +doi={10.48550/arXiv.2410.13421}, |
| 11 | +abstract={Data embeddings with CLIP and ImageBind provide powerful features for the analysis of multimedia and/or multimodal data. We assess their performance here for classification using a Gaussian Mixture models (GMMs) based layer as an alternative to the standard Softmax layer. GMMs based classifiers have recently been shown to have interesting performances as part of deep learning pipelines trained end-to-end. Our first contribution is to investigate GMM based classification performance taking advantage of the embedded spaces CLIP and ImageBind. Our second contribution is in proposing our own GMM based classifier with a lower parameters count than previously proposed. Our findings are, that in most cases, on these tested embedded spaces, one gaussian component in the GMMs is often enough for capturing each class, and we hypothesize that this may be due to the contrastive loss used for training these embedded spaces that naturally concentrates features together for each class. We also observed that ImageBind often provides better performance than CLIP for classification of image datasets even when these embedded spaces are compressed using PCA.}, |
| 12 | +} |
| 13 | + |
| 14 | +@inbook{doi:10.1142/9789811289125_0011, |
| 15 | +author = {Jeremy Chopin and Jean-Baptiste Fasquel and Harold Mouchere and Rozenn Dahyot and Isabelle Bloch }, |
| 16 | +chapter = {Reinforcement Learning and Sequential QAP-Based Graph Matching for Semantic Segmentation of Images}, |
| 17 | +title = {Emerging Topics in Pattern Recognition and Artificial Intelligence}, |
| 18 | +publisher = {World Scientific}, |
| 19 | +pages = {259-294}, |
| 20 | +year ={2024}, |
| 21 | +doi = {10.1142/9789811289125_0011}, |
| 22 | +URL = {https://www.worldscientific.com/doi/abs/10.1142/9789811289125_0011}, |
| 23 | +eprint = {https://www.worldscientific.com/doi/pdf/10.1142/9789811289125_0011}, |
| 24 | +abstract = { This chapter addresses the fundamental task of semantic image analysis by exploiting structural information (spatial relationships between image regions). We propose to combine a deep neural network (DNN) with graph matching (formulated as a quadratic assignment problem (QAP)) where graphs encode efficiently structural information related to regions segmented by the DNN. Our novel approach solves the QAP sequentially for matching graphs, in the context of image semantic segmentation, where the optimal sequence for graph matching is conveniently defined using reinforcement learning (RL) based on the region membership probabilities produced by the DNN and their structural relationships. Our RL-based strategy for solving QAP sequentially allows us to significantly reduce the combinatorial complexity for graph matching. Two experiments are performed on two public datasets dedicated respectively to the semantic segmentation of face images and sub-cortical region of the brain. Results show that the proposed RL-based ordering performs better than using a random ordering, especially when using DNNs that have been trained on a limited number of samples. The open-source code and data are shared with the community. } |
| 25 | +} |
| 26 | + |
| 27 | + |
| 28 | +@ARTICLE{SmartHangar2024, |
| 29 | +AUTHOR={Luke Casey and John Dooley and Michael Codd and Rozenn Dahyot and Marco Cognetti and Thomas Mullarkey and Peter Redmond and Gerard Lacey}, |
| 30 | +TITLE={A real-time Digital Twin for active safety in an aircraft hangar}, |
| 31 | +JOURNAL={Frontiers in Virtual Reality}, |
| 32 | +VOLUME={5}, |
| 33 | +YEAR={2024}, |
| 34 | +URL={https://www.frontiersin.org/articles/10.3389/frvir.2024.1372923}, |
| 35 | +DOI={10.3389/frvir.2024.1372923}, |
| 36 | +ISSN={}, |
| 37 | +ABSTRACT={The aerospace industry prioritises safety protocols to prevent accidents that can result in injuries, fatalities, or aircraft damage. One of the potential hazards that can occur while manoeuvring aircraft in and out of a hangar is collisions with other aircraft or buildings, which can lead to operational disruption and costly repairs. To tackle this issue, we have developed the Smart Hangar project, which aims to alert personnel of increased risks and prevent incidents from happening. The Smart Hangar project uses computer vision, LiDAR, and ultra-wideband sensors to track all objects and individuals within the hangar space. These data inputs are combined to form a real-time 3D Digital Twin (DT) of the hangar environment. The Active Safety system then uses the DT to perform real-time path planning, collision prediction, and safety alerts for tow truck drivers and hangar personnel. This paper provides a detailed overview of the system architecture, including the technologies used, and highlights the system's performance. By implementing this system, we aim to reduce the risk of accidents in the aerospace industry and increase safety for all personnel involved. |
| 38 | + Additionally, we identify future research directions for the Smart Hangar project.} |
| 39 | +} |
| 40 | +
|
1 | 41 | @inproceedings{Panahi2023, |
2 | 42 | author= {Solmaz Panahi and Jeremy Chopin and Matej Ulicny and Rozenn Dahyot}, |
3 | 43 | title= {Improving GMM registration with class encoding}, |
|
0 commit comments