Workshop
4th Workshop on Continual Learning in Computer Vision (CLVision)
Gido van de Ven · Pau Rodriguez · Vincenzo Lomonaco · Matthias De Lange · Dhireesha Kudithipudi · Xialei Liu · Rahaf Aljundi · Hava Siegelmann · Marc'Aurelio Ranzato · Hamed Hemati · Lorenzo Pellegrini
East 2
Keywords: Learning
Incorporating new knowledge in existing models to adapt to novel problems is a fundamental challenge of computer vision. Humans and animals continuously assimilate new experiences to survive in new environments and to improve in situations already encountered in the past. Moreover, while current computer vision models have to be trained with independent and identically distributed random variables, biological systems incrementally learn from non-stationary data distributions. This ability to learn from continuous streams of data, without interfering with previously acquired knowledge and exhibiting positive transfer is called Continual Learning. The CVPR Workshop on “Continual Learning in Computer Vision” (CLVision) aims to gather researchers and engineers from academia and industry to discuss the latest advances in Continual Learning. In this workshop, there are regular paper presentations, invited speakers, and a technical benchmark challenges to present the current state of the art, as well as the limitations and future directions for Continual Learning, arguably one of the most challenging milestones of AI.
Schedule
Sun 8:30 a.m. - 8:40 a.m.
|
Opening Remarks
(
Intro
)
|
Gido van de Ven · Pau Rodriguez 🔗 |
Sun 8:40 a.m. - 9:20 a.m.
|
Invited Talk
(
Talk
)
Zsolt Kira: “Continual Parameter-Efficient Fine-Tuning of Foundation Models” |
Zsolt Kira 🔗 |
Sun 9:20 a.m. - 10:00 a.m.
|
Invited Talk
(
Talk
)
Diane Larlus: “Lifelong visual representation learning” |
Diane Larlus 🔗 |
Sun 10:00 a.m. - 10:50 a.m.
|
Poster Session & Coffee Break
(
Posters
)
|
🔗 |
Sun 10:50 a.m. - 11:30 a.m.
|
Invited Talk
(
Talk
)
Adel Bibi: "The Uncomfortable Reality: The Need for Budgeted Computation in Continual Learning" |
🔗 |
Sun 11:30 a.m. - 11:45 a.m.
|
Oral Presentation
(
Oral
)
Mert Kilickaya: “Are Labels Needed for Incremental Instance Learning?” |
Mert Kilickaya 🔗 |
Sun 11:45 a.m. - 12:00 p.m.
|
Oral Presentation
(
Oral
)
Lama Alssum: “Just a Glimpse: Rethinking Temporal Information for Video Continual Learning” |
Alssum 🔗 |
Sun 12:00 p.m. - 1:00 p.m.
|
Lunch Break
|
🔗 |
Sun 1:00 p.m. - 1:40 p.m.
|
Invited Talk
(
Talk
)
Lucas Caccia: "Mitigating Task Interference in Continual and Multi-Task Learning" |
Lucas Caccia 🔗 |
Sun 1:40 p.m. - 2:20 p.m.
|
Invited Talk
(
Talk
)
Arslan Chaudhry: “On Forward Transfer in ML Development Cycle” |
🔗 |
Sun 2:20 p.m. - 3:00 p.m.
|
Panel Discussion
(
Panel
)
|
🔗 |
Sun 3:00 p.m. - 3:50 p.m.
|
Poster Session & Coffee Break
(
Posters
)
|
🔗 |
Sun 3:50 p.m. - 4:30 p.m.
|
Invited Talk
(
Talk
)
Xiaopeng Hong: “Incremental Knowledge Accumulation from Rehearsal to Prompt Learning” |
🔗 |
Sun 4:30 p.m. - 4:45 p.m.
|
Oral Presentation
(
Oral
)
Amir Nazemi: “CLVOS23: A Long Video Object Segmentation Dataset for Continual Learning” |
Amir Nazemi 🔗 |
Sun 4:45 p.m. - 5:20 p.m.
|
Challenge Presentations ( Challenge ) link | Hamed Hemati 🔗 |
Sun 5:20 p.m. - 5:30 p.m.
|
Award Announcement & Closing Remarks
(
Closing
)
|
Gido van de Ven · Pau Rodriguez 🔗 |