Curriculum Learning for Vision-and-Language Navigation
Dez 6, 2021
Sprecher:innen
Jiwen Zhang
Řečník · 0 sledujících
Zhongyu Wei
Řečník · 1 sledující
Jianqing Fan
Řečník · 0 sledujících
Jiajie Peng
Řečník · 0 sledujících
Über
Vision-and-Language Navigation (VLN) is a task where an agent navigates in an embodied indoor environment under human instructions. Previous works ignore the distribution of sample difficulty and we argue that this potentially degrade their agent performance. To tackle this issue, we propose a novel curriculum-based training paradigm for VLN tasks that can balance human prior knowledge and agent learning progress about training samples. We develop the principle of curriculum design and re-arrange the benchmark Room-to-Room (R2R) dataset to make it suitable for curriculum training. Experiments show that our method is model-agnostic and can significantly improve the performance, the generalizability, and the training efficiency of current state-of-the-art navigation agents without increasing model complexity.Vision-and-Language Navigation (VLN) is a task where an agent navigates in an embodied indoor environment under human instructions. Previous works ignore the distribution of sample difficulty and we argue that this potentially degrade their agent performance. To tackle this issue, we propose a novel curriculum-based training paradigm for VLN tasks that can balance human prior knowledge and agent learning progress about training samples. We develop the principle of curriculum design and re-arrang…
Organisator
NeurIPS 2021
Účet · 1,9k sledujících
Über 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.
Gefällt euch das Format? Vertraut auf SlidesLive, um euer nächstes Event festzuhalten!
Professionelle Aufzeichnung und Livestreaming – weltweit.
Freigeben
Empfohlene Videos
Präsentationen, deren Thema, Kategorie oder Sprecher:in ähnlich sind
Demonstrations 3
Zhlédnout později
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
Opening Remarks
Zhlédnout později
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
Canonical Noise Distributions and Private Hypothesis Tests
Zhlédnout později
Jordan Awan, …
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
Canonical Capsules: Self-Supervised Capsules in Canonical Pose
Zhlédnout později
Weiwei Sun, …
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
Addressing Content Selection Bias in Creating Datasets for Hate Speech Detection
Zhlédnout později
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation
Zhlédnout později
Pro uložení prezentace do věčného trezoru hlasovalo 2 diváků, což je 0.2 %