Tips and Tricks for Visual Question Answering: Learnings from the 2017 Challenge
This paper presents a state-of-the-art model for visual question answering (VQA), which won the first place in the 2017 VQA Challenge. VQA is a task of significant importance for research in artificial intelligence, given its multimodal nature, clear evaluation protocol, and potential real-world applications. The performance of deep neural networks for VQA is very dependent on choices of architectures and hyperparameters. To help further research in the area, we describe in detail our high-performing, though relatively simple model. Through a massive exploration of architectures and hyperparameters representing more than 3,000 GPU-hours, we identified tips and tricks that lead to its success, namely: sigmoid outputs, soft training targets, image features from bottom-up attention, gated tanh activations, output embeddings initialized using GloVe and Google Images, large mini-batches, and smart shuffling of training data. We provide a detailed analysis of their impact on performance to assist others in making an appropriate selection.
Code (10)
Tasks
GPUVisual Question AnsweringVisual Question Answering (VQA)Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A guide to the dataset explosion in QA, NLI, and commonsense reasoning
Question answering, natural language inference and commonsense reasoning are increasingly popular as general NLP system benchmarks, driving both modeling and dataset work. Only for question answering we already have over…
Natural Language InferenceQuestion AnsweringTIPS Over Tricks: Simple Prompts for Effective Zero-shot Anomaly Detection
Anomaly detection identifies departures from expected behavior in safety-critical settings. When target-domain normal data are unavailable, zero-shot anomaly detection (ZSAD) leverages vision-language models (VLMs). Howe…
Anomaly DetectionTrajectory-Informed Memory Generation for Self-Improving Agent Systems
LLM-powered agents face a persistent challenge: learning from their execution experiences to improve future performance. While agents can successfully complete many tasks, they often repeat inefficient patterns, fail to …
The Answer is at your Fingertips: Improving Passage Retrieval for Web Question Answering with Search Behavior Data
TIPS: Turn-Level Information-Potential Reward Shaping for Search-Augmented LLMs
Search-augmented large language models (LLMs) trained with reinforcement learning (RL) have achieved strong results on open-domain question answering (QA), but training still remains a significant challenge. The optimiza…
Open-Domain Question AnsweringReinforcement Learning