BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium: Computer Vision for Global-Scale Biodiversity Monit
 oring
DTSTART:20220411T100000
DTEND:20220411T110000
DTSTAMP:20260406T171938Z
UID:d28a2532647b9e430399bd8bd4f1699110ee90a83c0e262836f563aa
CATEGORIES:Conferences - Seminars
DESCRIPTION:By: Sara Beery - Caltech\nIC Faculty candidate\n\nAbstract\nWe
  require a real-time\, modular earth observation system that unites effort
 s across research groups in order to provide the vital information necessa
 ry for global-scale impact in sustainability and conservation in the face 
 of climate change. The development of such systems requires collaborative\
 , interdisciplinary approaches that translate diverse sources of raw infor
 mation into accessible scientific insight. For example\, we need to monito
 r species in real time and in greater detail to quickly understand which c
 onservation efforts are most effective and take corrective action. Current
  ecological monitoring systems generate data far faster than researchers c
 an analyze it\, making scaling up impossible without automated data proces
 sing. However\, ecological data collected in the field presents a number o
 f challenges that current methods\, like deep learning\, are not designed 
 to tackle. These include strong spatiotemporal correlations\, imperfect da
 ta quality\, fine-grained categories\, and long-tailed distributions. My w
 ork seeks to overcome these challenges\, and includes methods which can le
 arn from imperfect data\, systematic frameworks for measuring and overcomi
 ng performance drops due to domain shift\, and the deployment of efficient
  human-AI systems that have made significant real-world conservation impac
 t. My future research agenda will expand upon the strong foundation built 
 by my past and current research. It will seek to make effective use of all
  available modalities of data\, incorporate expert knowledge systematicall
 y\, and ensure these systems are equitable and ethical – all fundamental
  and unresolved challenges for CV&ML.\n\nBio\nSara Beery is a final-year P
 hD Candidate in Computing and Mathematical Sciences at Caltech\, advised b
 y Pietro Perona. She has always loved the natural world and has seen a gro
 wing need for technology-based approaches to conservation and sustainabili
 ty challenges. Her research focuses on building computer vision methods th
 at enable efficient\, accessible\, and equitable global-scale biodiversity
  monitoring. She was honored to be awarded both the PIMCO Data Science Fel
 lowship and the Amazon AI4Science Fellowship\, which recognize senior grad
 uate students that have had a remarkable impact in machine learning and da
 ta science\, and in their application to fields beyond computer science. H
 er work is funded in part by an NSF Graduate Research Fellowship and the C
 altech Resnick Sustainability Institute. She seeks to break down knowledge
  barriers between fields: she founded the successful AI for Conservation s
 lack community (with almost 800 members)\, and she is the founding directo
 r of the Caltech Summer School on Computer Vision Methods for Ecology. She
  works closely with Microsoft AI for Earth\, Google Research\, and Wildlif
 e Insights where she helps turn her research into usable tools for the eco
 logical community. Sara's experiences as a professional ballerina\, a nont
 raditional student\, and a queer woman have taught her the value of unique
  and diverse perspectives\, both inside and outside of the research commun
 ity. She is passionate about increasing diversity and inclusion in STEM th
 rough mentorship\, teaching\, and outreach.\n\nMore information
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420 https://epfl.zoom.us/
 j/68125803805?pwd=WDhZZDMyNHlNV0Z5Z1E0UC84RTZZdz09
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR