Completed
Intro
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Responsible Computer Vision - Model Failures and Solutions
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Standard Visual Recognition Pipeline
- 3 Visual Recognition Benchmark
- 4 Benchmark Performance
- 5 Dataset Bias
- 6 Adversarial Examples
- 7 Benchmark Challenge Adversar
- 8 RobustNav Dynamics Corruptid
- 9 Domain Adaptation: Train on Source Test on
- 10 Domain Adversarial Adaptatio
- 11 Adapting to Imbalanced Data
- 12 Adaptation with Self-Training Entropy Minimization for UDA
- 13 SENTRY: Selective Entropy Optimization Selective Entropy Minimization
- 14 Selective Entropy Loss
- 15 SENTRY Results: Image Classification
- 16 SENTRY Results: MiniDomainNet
- 17 Extension to Semantic Segmentation
- 18 Performance Degradation from Bias
- 19 Geographic Bias
- 20 Does object recognition work for everyone?
- 21 Can domain adaptation make obj rec work for everyone?
- 22 Geographically diverse data
- 23 Additional challenges in GeoDA
- 24 Summary: Responsible Vision
