Segmentation from Natural Language Expressions
Preprint
Abstract
In this paper we approach the novel problem of segmenting an image based on a natural language expression. This is different from traditional semantic segmentation over a predefined set of semantic classes, as e.g., the phrase "two men sitting on the right bench" requires segmenting only the two people on the right bench and no one standing or sitting on another bench. Previous approaches suitable for this task were limited to a fixed set of categories and/or rectangular regions. To produce pixelwise segmentation for the language expression, we propose an end-to-end trainable recurrent and convolutional network model that jointly learns to process visual and linguistic information. In our model, a recurrent LSTM network is used to encode the referential expression into a vector representation, and a fully convolutional network is used to a extract a spatial feature map from the image and output a spatial response map for the target object. We demonstrate on a benchmark dataset that our model can produce quality segmentation output from the natural language expression, and outperforms baseline methods by a large margin.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- Grounding of Textual Phrases in Images by Reconstruction2016
- Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering2016
- Natural Language Object Retrieval2016
- Stacked Attention Networks for Image Question Answering2016
- Generation and Comprehension of Unambiguous Object Descriptions2016
- Learning to Compose Neural Networks for Question Answering2016
- The Pascal Visual Object Classes Challenge: A RetrospectiveInternational Journal of Computer Vision, 2014
- On the Properties of Neural Machine Translation: Encoder–Decoder Approaches2014
- The segmented and annotated IAPR TC-12 benchmarkComputer Vision and Image Understanding, 2010