Online Machine Learning in Montpellier, Theory & Practice Machine Learning in Montpellier, Theory & Practice

Online Machine Learning in Montpellier, Theory & Practice Machine Learning in Montpellier, Theory & Practice

Room 02.124, Building 5, St Priest campus Machine Learning in Montpellier, Theory & Practice Deep generative models have made tremendous progress in modeling complex data, often exhibiting generation quality that surpasses a typical human's ability to discern the authenticity of samples. Undeniably, a key driver of this success is enabled by the massive amounts of web-scale data consumed by these models. Due to these models' striking performance and ease of availability, the web will inevitably be increasingly populated with synthetic content. Such a fact directly implies that future iterations of generative models will be trained on both clean and artificially generated data from past models. In addition, in practice, synthetic data is often subject to human feedback and curated by users before being used and uploaded online. For instance, many interfaces of popular text-to-image generative models, such as Stable Diffusion or Midjourney, produce several variations of an image for a given query which can eventually be curated by the users. In this talk we will discuss the impact of training generative models on mixed datasets---from classical training on real data to self-consuming generative models trained on purely synthetic curated data. Machine Learning in Montpellier, Theory & Practice

Room 02.124, Building 5, St Priest campus Machine Learning in Montpellier, Theory & Practice Computer vision tasks are frequently trained using distinctly annotated datasets although the tasks are often related to one another. Multi-task learning, on the other hand, is known to generally improve performance by leveraging the inter-task relationship but often at the high cost of maintaining all-task annotations for each training example. The multi-task partially supervised learning paradigm relaxes this requirement, allowing each input to be annotated only for one of the target tasks. This setting hinders learning joint-task representations yet is potentially helpful for data scarcity scenarios as datasets for individual tasks can be combined for training. In this presentation, we study multi-task relationships for better data exploitation under the partial supervision assumption for the two well-known computer vision tasks, namely object detection and semantic segmentation. Both of these tasks are designed for scene understanding yet differ in data structure and information level: object detection requires box coordinates for object instances while semantic segmentation requires pixel-wise regional categories. To that end, we propose Box-for-Mask and Mask-for-Box strategies to extract information from one task's annotations to train the other. Ablation studies and experimental results on VOC and COCO datasets show favorable results for the proposed idea. Machine Learning in Montpellier, Theory & Practice