“Tokenizers face an odd compute issue. Since they're part of the pre-processing pipeline, you can't quickly test them out for effectiveness. You have to restart a pretraining run to test downstream effectiveness. Separately, As much as an attention module can do universal nonlinear transformations....I wonder if it makes sense to add specifuc modules fo…”
Inferring and Executing Programs for Visual Reasoning
Existing methods for visual reasoning attempt to directly map inputs to outputs using black-box architectures without explicitly modeling the underlying reasoning processes. As a result, these black-box models often learn to exploit biases in the data rather than learning to perform visual reasoning. Inspired by module networks, this paper proposes a model for visual reasoning that consists of a program generator that constructs an explicit representation of the reasoning process to be performed, and an execution engine that executes the resulting program to produce an answer. Both the program generator and the execution engine are implemented by neural networks, and are trained using a combination of backpropagation and REINFORCE. Using the CLEVR benchmark for visual reasoning, we show that our model significantly outperforms strong baselines and generalizes better in a variety of settings.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及- Inferring and Executing Programs for Visual Reasoning ↗Abtin88 · 2017-05-11 · 1 分