Timezone: »

Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization
Bruno Korbar · Du Tran · Lorenzo Torresani

Thu Dec 06 07:45 AM -- 09:45 AM (PST) @ Room 517 AB #None

There is a natural correlation between the visual and auditive elements of a video. In this work we leverage this connection to learn general and effective models for both audio and video analysis from self-supervised temporal synchronization. We demonstrate that a calibrated curriculum learning scheme, a careful choice of negative examples, and the use of a contrastive loss are critical ingredients to obtain powerful multi-sensory representations from models optimized to discern temporal synchronization of audio-video pairs. Without further fine-tuning, the resulting audio features achieve performance superior or comparable to the state-of-the-art on established audio classification benchmarks (DCASE2014 and ESC-50). At the same time, our visual subnet provides a very effective initialization to improve the accuracy of video-based action recognition models: compared to learning from scratch, our self-supervised pretraining yields a remarkable gain of +19.9% in action recognition accuracy on UCF101 and a boost of +17.7% on HMDB51.

Author Information

Bruno Korbar (Dartmouth Collegue)
Du Tran (Facebook)
Lorenzo Torresani (Dartmouth/Facebook)

Lorenzo Torresani is an Associate Professor with tenure in the Computer Science Department at Dartmouth College and a Research Scientist at Facebook AI. He received a Laurea Degree in Computer Science with summa cum laude honors from the University of Milan (Italy) in 1996, and an M.S. and a Ph.D. in Computer Science from Stanford University in 2001 and 2005, respectively. In the past, he has worked at several industrial research labs including Microsoft Research Cambridge, Like.com and Digital Persona. His research interests are in computer vision and deep learning. He is the recipient of several awards, including a CVPR best student paper prize, a National Science Foundation CAREER Award, a Google Faculty Research Award, three Facebook Faculty Awards, and a Fulbright U.S. Scholar Award.

More from the Same Authors