Deep Bayesian Active Learning for Multiple Correct Outputs

Abstract

Typical active learning strategies are designed for tasks, such as classification, with the assumption that the output space is mutually exclusive. The assumption that these tasks always have exactly one correct answer has resulted in the creation of numerous uncertainty-based measurements, such as entropy and least confidence, which operate over a model's outputs. Unfortunately, many real-world vision tasks, like visual question answering and image captioning, have multiple correct answers, causing these measurements to overestimate uncertainty and sometimes perform worse than a random sampling baseline. In this paper, we propose a new paradigm that estimates uncertainty in the model's internal hidden space instead of the model's output space. We specifically study a manifestation of this problem for visual question answer generation (VQA), where the aim is not to classify the correct answer but to produce a natural language answer, given an image and a question. Our method overcomes the paraphrastic nature of language. It requires a semantic space that structures the model's output concepts and that enables the usage of techniques like dropout-based Bayesian uncertainty. We build a visual-semantic space that embeds paraphrases close together for any existing VQA model. We empirically show state-of-art active learning results on the task of VQA on two datasets, being 5 times more cost-efficient on Visual Genome and 3 times more cost-efficient on VQA 2.0.

18 pages, 9 figures

References in corpus (9)

• Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models
• Weight Uncertainty in Neural Networks
• Deep Fragment Embeddings for Bidirectional Image Sentence Mapping
• Bayesian Active Learning for Classification and Preference Learning
• Exploring Models and Data for Image Question Answering
• Simple Baseline for Visual Question Answering
• A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input
• A Joint Model of Language and Perception for Grounded Attribute Learning
• Active Learning for Visual Question Answering: An Empirical Study

Cited by in corpus (4)

• Multimodal Intelligence: Representation Learning, Information Fusion, and Applications
• Deep Bayesian Active Learning, A Brief Survey on Recent Advances
• Bayesian Active Learning by Disagreements: A Geometric Perspective
• Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering