Psycholinguistics meets Continual Learning: Measuring Catastrophic Forgetting in Visual Question Answering

06/10/2019
by   Claudio Greco, et al.
0

We study the issue of catastrophic forgetting in the context of neural multimodal approaches to Visual Question Answering (VQA). Motivated by evidence from psycholinguistics, we devise a set of linguistically-informed VQA tasks, which differ by the types of questions involved (Wh-questions and polar questions). We test what impact task difficulty has on continual learning, and whether the order in which a child acquires question types facilitates computational models. Our results show that dramatic forgetting is at play and that task difficulty and order matter. Two well-known current continual learning methods mitigate the problem only to a limiting degree.

READ FULL TEXT
research
04/04/2023

I2I: Initializing Adapters with Improvised Knowledge

Adapters present a promising solution to the catastrophic forgetting pro...
research
11/19/2022

CL-CrossVQA: A Continual Learning Benchmark for Cross-Domain Visual Question Answering

Visual Question Answering (VQA) is a multi-discipline research task. To ...
research
09/30/2022

Task Formulation Matters When Learning Continually: A Case Study in Visual Question Answering

Continual learning aims to train a model incrementally on a sequence of ...
research
08/24/2022

Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task

VQA is an ambitious task aiming to answer any image-related question. Ho...
research
06/26/2020

Continual Learning from the Perspective of Compression

Connectionist models such as neural networks suffer from catastrophic fo...
research
09/21/2022

Continual VQA for Disaster Response Systems

Visual Question Answering (VQA) is a multi-modal task that involves answ...
research
08/25/2020

Continual Domain Adaptation for Machine Reading Comprehension

Machine reading comprehension (MRC) has become a core component in a var...

Please sign up or login with your details

Forgot password? Click here to reset