Learning Co-segmentation by Segment Swapping for Retrieval and Discovery

The goal of this work is to efficiently identify visually similar patterns from a pair of images, e.g. identifying an artwork detail copied between an engraving and an oil painting, or matching a night-time photograph with its daytime counterpart. Lack of training data is a key challenge for this co-segmentation task. We present a simple yet surprisingly effective approach to overcome this difficulty: we generate synthetic training pairs by selecting object segments in an image and copy-pasting them into another image. We then learn to predict the repeated object masks. We find that it is crucial to predict the correspondences as an auxiliary task and to use Poisson blending and style transfer on the training pairs to generalize on real data. We analyse results with two deep architectures relevant to our joint image analysis task: a transformer-based [64] architecture and Sparse Nc-Net [45], a recent network designed to predict coarse correspondences using 4D convolutions. We show our approach provides clear improvements for artwork details retrieval on the Brueghel dataset [1, 53] and achieves competitive performance on two place recognition benchmarks, Tokyo247 [58] and Pitts30K [59]. We then demonstrate the potential of our approach by performing object discovery on the Internet object discovery dataset [48] and the Brueghel dataset [1, 53]. Our code and data are available at http://imagine.enpc. fr/~shenx/SegSwap/.