BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.4.0.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:357@isdm.umontpellier.fr
DTSTART;TZID=Europe/Paris:20250410T140000
DTEND;TZID=Europe/Paris:20250410T140000
DTSTAMP:20260828T093938Z
URL:https://isdm.umontpellier.fr/events/invariant-representation-learning-
 for-few-shot-bioacoustic-event-detection-and-classification-2/
SUMMARY:Invariant Representation Learning for Few-Shot Bioacoustic Event De
 tection and Classification
DESCRIPTION:Room 02.124\, Building 5\, St Priest campus\n\nMachine Learning
  in Montpellier\, Theory &amp\; Practice - Ilyass Moummad (Inria)\n\nBiodi
 versity monitoring has become increasingly popular as a way to better unde
 rstand and assess the health of surrounding ecosystems. Sound\, in particu
 lar\, plays a crucial role in biodiversity monitoring\, as many species re
 ly on vocalizations to communicate and navigate their environment. Recent 
 advancements in deep learning have improved our ability to automatically d
 etect and classify sounds. However deep learning often require large annot
 ated datasets\, which can be costly and time-consuming for manual labellin
 g\, and difficult to obtain for rare or endangered species. To address the
 se challenges\, we explore the potential of transfer learning\, where a fe
 ature extractor trained on one task is adapted to a new task. Specifically
 \, we investigate invariant learning as a pre-training strategy designed t
 o produce representations that are invariant to predefined transformations
 . In the unlabelled setting\, this involves mapping a data example and its
  transformed counterpart to similar latent representations (transformation
  invariance)\, whereas in the labelled setting\, examples sharing the same
  annotations are mapped to similar representations (label invariance). We 
 then apply these learned representations to downstream tasks\, focusing on
  the detection and classification of animal vocalizations in few-shot scen
 arios.\n\nMachine Learning in Montpellier\, Theory &amp\; Practice
ATTACH;FMTTYPE=image/jpeg:https://isdm.umontpellier.fr/wp-content/uploads/
 2026/06/ml-mtp-gC78d5.png
CATEGORIES:ML MTP
LOCATION:Room 02.124 Building 5\, St Priest Campus\, Montpellier\, 34000\, 
 France
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=St Priest Campus\, Montpell
 ier\, 34000\, France;X-APPLE-RADIUS=100;X-TITLE=Room 02.124 Building 5:geo
 :0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:DAYLIGHT
DTSTART:20250330T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR