One-Shot Segmentation in Clutter
arXiv:1803.09597
Abstract
We tackle the problem of one-shot segmentation: finding and segmenting a previously unseen object in a cluttered scene based on a single instruction example. We propose a novel dataset, which we call . Using a baseline architecture combining a Siamese embedding for detection with a U-net for segmentation we show that increasing levels of clutter make the task progressively harder. Using oracle models with access to various amounts of ground-truth information, we evaluate different aspects of the problem and show that in this kind of visual search task, detection and segmentation are two intertwined problems, the solution to each of which helps solving the other. We therefore introduce , an improved model that attends to multiple candidate locations, generates segmentation proposals to mask out background clutter and selects among the segmented objects. Our findings suggest that such image recognition models based on an iterative refinement of object detection and foreground segmentation may provide a way to deal with highly cluttered scenes.
arXiv commentTo appaer in: $\textit{Proceedings of the $\mathit{35}^{th}$ International Conference on Machine Learning}$, Stockholm, Sweden, PMLR 80, 2018
References in corpus (12)
- Adam: A Method for Stochastic Optimization
- Rethinking Atrous Convolution for Semantic Image Segmentation
- Prototypical Networks for Few-shot Learning
- Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
- CNN Features off-the-shelf: an Astounding Baseline for Recognition
- Learning Deconvolution Network for Semantic Segmentation
- Learning feed-forward one-shot learners
- Attentive Recurrent Comparators
- Few-Shot Learning Through an Information Retrieval Lens
- Deep Extreme Cut: From Extreme Points to Object Segmentation
- WebVision Challenge: Visual Learning and Understanding With Web Data
- One Shot Joint Colocalization and Cosegmentation