Explainable Action Prediction through Self-Supervision on Scene Graphs
This work explores scene graphs as a distilled representation of high-level information for autonomous driving, applied to future driver-action prediction. Given the scarcity and strong imbalance of data samples, we propose a self-supervision pipeline to infer representative and well-separated embeddings. Key aspects are interpretability and explainability; as such, we embed in our architecture attention mechanisms that can create spatial and temporal heatmaps on the scene graphs. We evaluate our system on the ROAD dataset against a fully-supervised approach, showing the superiority of our training regime.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous DrivingPredictionSimilar Papers 제목 키워드 기반
Better Self-training for Image Classification through Self-supervision
Self-training is a simple semi-supervised learning approach: Unlabelled examples that attract high-confidence predictions are labelled with their predictions and added to the training set, with this process being repeate…
Classificationimage-classificationImage ClassificationTowards Self-Explainable Document Visual Question Answering with Chain-of-Explanation Predictions
Document Visual Question Answering (DocVQA) requires vision-language models to reason not only about what information in a document is relevant to a question, but also where the answer is grounded on the page. Existing D…
Visual Question AnsweringGFM4MPM: Towards Geospatial Foundation Models for Mineral Prospectivity Mapping
Machine Learning (ML) for Mineral Prospectivity Mapping (MPM) remains a challenging problem as it requires the analysis of associations between large-scale multi-modal geospatial data and few historical mineral commodity…
Explainable artificial intelligenceAdvancing Melanoma Diagnosis with Self-Supervised Neural Networks: Evaluating the Effectiveness of Different Techniques
We investigate the potential of self-supervision in improving the accuracy of deep learning models trained to classify melanoma patches. Various self-supervision techniques such as rotation prediction, missing patch pred…
Contrastive LearningMelanoma DiagnosisHOP, UNION, GENERATE: Explainable Multi-hop Reasoning without Rationale Supervision
Explainable multi-hop question answering (QA) not only predicts answers but also identifies rationales, i. e. subsets of input sentences used to derive the answers. This problem has been extensively studied under the sup…
Multi-hop Question AnsweringQuestion Answering