TLDR: Can Transformers ala BERT help VQA for #EO? Yes with fine-tuning!
LANGUAGE TRANSFORMERS FOR REMOTE SENSING VISUAL QUESTION ANSWERING by @Christel_Cha Chappuis @igarss2022@devistuia@SylvainLobry, I et students from @EPFL@ESA_EO
https://t.co/pvxRqLQV1h
@devistuia@EPFL_en@MarcCoru@b_kellenb In our contribution on interacting with remote sensing images using #NLP , we compared 2 language models that belong to two different families of deep learning architectures: Recurrent Neural Network (#RNN) and #Transformer, with and without fine-tuning, for the task of #RSVQA.
This week (tomorrow) @ESA_EO Φ-lab will be at @IEEE_GRSS@igarss2022#IGARSS2022 w/ 2 invited sessions on #AI4EO organised by @Dr_RSchneider and I
👉2/2: TU7.V21: ��𝐮𝐦𝐚𝐧-𝐜𝐞𝐧𝐭𝐫𝐢𝐜 𝐀𝐈4𝐄𝐎 𝐬𝐞𝐬𝐬𝐢𝐨𝐧
https://t.co/ib9IVpa7GS
𝐓𝐮𝐞 19/07 17:00CET / 23:00 Malaysia
Today @ESA_EO Φ-lab talked on #AI4EO at the 5th Columbian Summer School on #HPC!
👉dengue fever, #NLP for #EO, edge-, quantum-, neuromorphic and modular #supercomputing!
w/ R. Carmo G. Meoni and great talents from our network: @Christel_Cha@EPFL_en and Amer Delilbasic @fzj_jsc
"Prompt–RSVQA: Prompting visual context to a language model for Remote Sensing Visual Question Answering", Christel Chappuis; Valérie Zermatten; Sylvain Lobry; Bertrand Le Saux; Devis Tuia
https://t.co/R7RyJKItGp
On vous attend au stand #eceo à #scientastic à Sion, aujourd’hui et demain, pour parler de nos activités en conservation animale 🦓et #IA 🖥!
@val__zer , @Christel_Cha et Thien-Anh vous feront explorer la Savane de Namibie!
A l’EPFL valais!
@ScienceValais@EPFL_en@epflENAC
@esa newsletter highlights co-funded research projects selected through OSIP https://t.co/PdYLtZFkzL
👉includes PhD on Digital #AI Assistant for Earth Observation, by @Christel_Cha Chappuis at @EPFL_en with @devistuia@SylvainLobry and @ESA_EO Φ-lab
https://t.co/boJUbnJlpS
Job opportunity! Come work with me and @b_kellenb at @EPFL_en in beautiful Sion and study how to map species and their interactions at scale with #DeepLearning !
Two phd positions available, info here https://t.co/CpqcHr6lP5
@snf_ch@epflENAC
📢 Happening now: @ESA_EO@ECMWF ws on Machine Learning for Earth System Observation and Prediction!
https://t.co/0F4ag3kkVT
Today, @devistuia talked about (among other things) Visual Question & Answering #VQA for #EO, ongoing work with @Christel_Cha Chappuis (@EPFL_en & Φ-lab)
Impressive capstone work by @Christel_Cha -
classifying art pieces from the @metmuseum using heterogeneous data, predicting department and type with more than 97% accuracy using #machinelearning 💪
See more here⬇️
🔗 https://t.co/bp3uAbzDfO
#learningwithexts