Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Detecting Out-of-distribution Data through In-distribution Class Prior
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-010-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-010-alpha.b-cdn.net
      • sl-yoda-v2-stream-010-beta.b-cdn.net
      • 1759419103.rsc.cdn77.org
      • 1016618226.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
            Detecting Out-of-distribution Data through In-distribution Class Prior
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Detecting Out-of-distribution Data through In-distribution Class Prior

            Jul 24, 2023

            Speakers

            XJ

            Xue Jiang

            Speaker · 1 follower

            FL

            Feng Liu

            Speaker · 0 followers

            ZF

            Zhen Fang

            Speaker · 0 followers

            About

            Given a pre-trained in-distribution (ID) model, the inference-time out-of-distribution (OOD) detection aims to recognize OOD data during the inference stage. However, some representative methods share an unproven assumption that the probability that OOD data belong to every ID class should be the same, i.e., these OOD-to-ID probabilities actually form a uniform distribution. In this paper, we show that this assumption makes the above methods incapable when the ID model is trained with class-imba…

            Organizer

            I2
            I2

            ICML 2023

            Account · 629 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

            On Investigating the Conservative Property of Score-Based Generative Models
            05:35

            On Investigating the Conservative Property of Score-Based Generative Models

            Chen-Hao Chao, …

            I2
            I2
            ICML 2023 2 years ago

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

            Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models
            04:50

            Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models

            Nikolaos Dimitriadis, …

            I2
            I2
            ICML 2023 2 years ago

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

            MoleculeSDE: A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretraining
            04:51

            MoleculeSDE: A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretraining

            Shengchao Liu, …

            I2
            I2
            ICML 2023 2 years ago

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

            Adversarially Robust PAC Learnability of Real-Valued Functions
            03:48

            Adversarially Robust PAC Learnability of Real-Valued Functions

            Idan Attias, …

            I2
            I2
            ICML 2023 2 years ago

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

            H-Likelihood Approach to Deep Neural Networks  with Temporal-Spatial Random Effects for High-Cardinality Categorical Features
            05:11

            H-Likelihood Approach to Deep Neural Networks with Temporal-Spatial Random Effects for High-Cardinality Categorical Features

            Hangbin Lee, …

            I2
            I2
            ICML 2023 2 years ago

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

            Improving Adversarial Robustness by Sample-Efficient Synthetic Data Generation
            04:51

            Improving Adversarial Robustness by Sample-Efficient Synthetic Data Generation

            Yidong Ouyang, …

            I2
            I2
            ICML 2023 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 ICML 2023