Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v3-stream-014-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v3-stream-014-alpha.b-cdn.net
      • sl-yoda-v3-stream-014-beta.b-cdn.net
      • 1978117156.rsc.cdn77.org
      • 1243944885.rsc.cdn77.org
      • Subtitles
      • Off
      • English
      • Playback rate
      • Quality
      • Subtitles size
      • Large
      • Medium
      • Small
      • Mode
      • Video Slideshow
      • Audio Slideshow
      • Slideshow
      • Video
      My playlists
        Bookmarks
          00:00:00
            Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning

            Dec 6, 2021

            Speakers

            YZ

            Yifan Zhang

            Speaker · 2 followers

            BH

            Bryan Hooi

            Speaker · 0 followers

            DH

            Dapeng Hu

            Speaker · 0 followers

            About

            Contrastive self-supervised learning (CSL) has attracted increasing attention for model pre-training via unlabeled data. The resulted CSL models provide instance-discriminative visual features that are uniformly scattered in the feature space. During deployment, the common practice is to directly fine-tune CSL models with cross-entropy, which however may not be the best strategy in practice. Although cross-entropy tends to separate inter-class features, the resulting models still have limited ca…

            Organizer

            N2
            N2

            NeurIPS 2021

            Account · 1.9k followers

            About NeurIPS 2021

            Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.

            Like the format? Trust SlidesLive to capture your next event!

            Professional recording and live streaming, delivered globally.

            Sharing

            Recommended Videos

            Presentations on similar topic, category or speaker

            Adversarial Robustness with Semi-Infinite Constrained Learning
            14:49

            Adversarial Robustness with Semi-Infinite Constrained Learning

            Alexander Robey, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Fitting summary statistics of neural data with a differentiable spiking network simulator
            13:07

            Fitting summary statistics of neural data with a differentiable spiking network simulator

            Guillaume Bellec, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            FIgLib & SmokeyNet: Dataset and Deep Learning Model for Real-Time Wildland Fire Smoke Detection
            05:05

            FIgLib & SmokeyNet: Dataset and Deep Learning Model for Real-Time Wildland Fire Smoke Detection

            Anshuman Dewangan, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Optimizing Functionals on the Space of Probabilities with Input Convex Neural Network
            03:46

            Optimizing Functionals on the Space of Probabilities with Input Convex Neural Network

            David Alvarez-Melis, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Self-Supervised Multi-Object Tracking with Cross-input Consistency
            14:59

            Self-Supervised Multi-Object Tracking with Cross-input Consistency

            Favyen Bastani, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Identification of Enzymatic Active Sites with Unsupervised Language Modelling
            09:33

            Identification of Enzymatic Active Sites with Unsupervised Language Modelling

            Loïc Kwate Dassi, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Interested in talks like this? Follow NeurIPS 2021