DSC ADRIA’s Post

Towards autonomous shotcrete construction: semantic 3D reconstruction for concrete deposition using stereo vision and deep learning Paper ID 156 - ISARC 2024 by Patrick Schmidt IAARC https://lnkd.in/gVphrU9E

I’m happy to share that our paper “Continual Domain Randomization” was accepted at the IROS 2024 conference in Abu Dhabi. I want to thank the co-authors Sayantan Auddy, Mohammadhossein Malmir, Justus Piater, Alois Knoll and Nicolás Navarro-Guerrero, whose contribution and support made this possible. Summary: Domain randomization is often used in sim2real transfer of reinforcement learning policies for robotic tasks, but the combined randomization of many parameters might increase the task difficulty and the convergence to a suitable policy. We propose Continual Domain Randomization (CDR) to address this problem and to provide a more flexible training process in simulation. CDR combines domain randomization with continual learning to enable sequential training on a subset of randomization parameters at a time and subsequent sim2real transfer. A preprint of the paper, as well as the code and supplementary video are available at https://lnkd.in/dh-BHtQ5

If you're seeking valuable insights and innovative ideas in data science, we have something special for you! Whether you missed the event or just want more, DSC ADRIA 24 talks are here for you! Today we’re sharing Miloš Košprdić’s talk: Verif.ai: A Trustworthy Scientific Generative Search Engine Milos Kosprdic presents Verif.ai, an innovative open-source scientific question-answering system designed to deliver referenced and verifiable answers. This pioneering system employs a dual-stage process, combining robust information retrieval techniques with fine-tuned generative models and advanced verification engines to ensure answer accuracy and reliability. By integrating semantic and lexical search techniques over scientific papers and utilizing a Retrieval-Augmented Generation (RAG) module, Verif.ai generates claims with references to source materials, bolstering answer credibility. Additionally, a Verification Engine cross-checks generated claims against original articles, identifying any potential inaccuracies. This speech by Milos Kosprdic was held on May 23rd at DSC Adria 2024 in Zagreb. Don't miss next year's DSC ADRIA 25 – it's set to be the biggest AI&Data conference in Croatia! 🤫 For the entire video just click the link below  https://lnkd.in/dyKUrqXD #ai #datascience #generative #search #engine #verifAI #ml #dscadria

A few days ago I had the honor to present the joint work together with Nick Rossenbach: „On the Effect of Purely Synthetic Training Data for Different Automatic Speech Recognition Architectures“ at the SynData4GenAI 2024 workshop at #Interspeech2024 on Kos Island. In the follow-up work of our last paper (https://lnkd.in/ek83mucz) we looked at different ASR architectures and compared their behavior on synthetic only data. Through varying model parameters we found that the indicated overfitting shown in the train loss does not reflect in the final ASR performance. Furthermore, we saw that pre-trained speaker embeddings did only help the model in specific cases, while the baseline embeddings already showed a decent performance in this low resource scenario. If you are interested give the paper a read at: https://lnkd.in/ezRECAvP

Bootstrapping our way to AGI: JEPA vs. APD (Action Perception Divergence). Two methods that are being discussed (and sometimes, used) as AGI precursors are (1) JEPA (Joint Embedding Predictive Architecture), espoused by Yann LeCun, and (2) APD (Action Perception Divergence), offered by Hafner et al. (2020, rev. 2022), which is an evolution of Friston's active inference. The latter method (APD) frames the notions of AGI agents that can "act" and "sense/perceive" via minimizing a (reverse) Kullback-Leibler divergence between a set of potential random (actual) distributions (potentially generated via a parameter vector "phi") versus a target distribution "tau." In yesterday's YouTube, I went through that crucial derivation to reach Eqn. 3 in the APD paper. #ai #agi #artificialintelligence #artificialgeneralintelligence #aieducation #machinelearning #APD #actionperceptiondivergence #activeinference #kullbackleibler #KLdivergence https://lnkd.in/gypuvMq5

🚀 Transforming Object Detection with DETR 🔍 The DETR (DEtection TRansformers) model is a game-changer in object detection, leveraging transformers and CNNs to simplify the process and boost accuracy. By eliminating the need for traditional post-processing steps like anchor boxes and non-maximum suppression (NMS), DETR introduces a more efficient, end-to-end detection pipeline. In my latest blog, I break down DETR's transformer-driven architecture, explain how it achieves state-of-the-art performance, and discuss why it’s a significant leap forward in computer vision. Let’s explore how DETR is reshaping the future of object detection! #AI #ObjectDetection #DETR #DeepLearning #Transformers #MachineLearning #CVPR

Our great presenter Miloš discusses the Verif.ai project - a system uniquely designed for question-answering with verification in the biomedical field.

📢 #HighlyCited 1.  Automated Arabic Long-Tweet Classification Using Transfer Learning with BERT https://lnkd.in/geADXYmk 2. Edge-YOLO: Lightweight Infrared Object Detection Method Deployed on Edge Devices https://lnkd.in/gFm-W_WK 3. Adaptive Driver Face Feature Fatigue Detection Algorithm Research https://lnkd.in/g34YmR-j 4. A Financial Time-Series Prediction Model Based on Multiplex Attention and Linear Transformer Structure https://lnkd.in/gXMCPWZu

Interesting approach to use iterative micro-segmentation, combination and a smoothing technique to generate the final segment to detect subtle junctures where topics shift and can be chunked meaningfully.

#11 Seg-Eval Choosing the proper ground sampling distance is a pivotal decision in remote sensing downstream applications. In this work, the authors try to set out a clear ensemble of guidelines for fairly comparing semantic segmentation results obtained at various spatial resolutions. They also propose region-based pixel-wise metrics, allowing for a more detailed analysis of the model performance. what I liked: very practical and important problem paper: https://lnkd.in/gFfUE35v #50papers #AI4EO #remotesensing #deeplearning #GeoAI