Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Semantic Diffusion Network for Semantic Segmentation
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-006-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-006-alpha.b-cdn.net
      • sl-yoda-v2-stream-006-beta.b-cdn.net
      • 1549480416.rsc.cdn77.org
      • 1102696603.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
            Semantic Diffusion Network for Semantic Segmentation
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Semantic Diffusion Network for Semantic Segmentation

            Nov 28, 2022

            Speakers

            HT

            Haoru Tan

            Speaker · 0 followers

            SW

            Sitong Wu

            Speaker · 0 followers

            JP

            Jimin Pi

            Speaker · 0 followers

            About

            Precise and accurate segmentation over boundary areas is important in semantic segmentation. The commonly used convolutional operators tend to smooth and blur local detail cues, making it difficult for deep learning models to generate accurate boundary predictions. In this paper, we propose an efficient boundary-aware convolution operator to boost the boundary modeling capacity for semantic segmentation, named Semantic Difference Convolution (SDC). The SDC is sensitive to the inter-class boundar…

            Organizer

            N2
            N2

            NeurIPS 2022

            Account · 952 followers

            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

            What Makes Graph Neural Networks Miscalibrated?
            00:52

            What Makes Graph Neural Networks Miscalibrated?

            Hans Hao-Hsun Hsu, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            On The Fragility of Learned Reward Functions
            04:58

            On The Fragility of Learned Reward Functions

            Lev McKinney, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            On the Epistemic Limits of Personalized Prediction
            05:05

            On the Epistemic Limits of Personalized Prediction

            Lucas Monteiro Paes, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            Grounded Video Situation Recognition
            01:01

            Grounded Video Situation Recognition

            Zeeshan Khan, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            Unleashing The Potential of Data Sharing in Ensemble Deep Reinforcement Learning
            05:00

            Unleashing The Potential of Data Sharing in Ensemble Deep Reinforcement Learning

            Zhixuan Lin, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            On the inability of Gaussian process regression to optimally learn compositional functions
            04:28

            On the inability of Gaussian process regression to optimally learn compositional functions

            Matteo Giordano, …

            N2
            N2
            NeurIPS 2022 2 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 2022