SegSort: Segmentation by Discriminative Sorting of Segments

Abstract

Almost all existing deep learning approaches for semantic segmentation tackle this task as a pixel-wise classification problem. Yet humans understand a scene not in terms of pixels, but by decomposing it into perceptual groups and structures that are the basic building blocks of recognition. This motivates us to propose an end-to-end pixel-wise metric learning approach that mimics this process. In our approach, the optimal visual representation determines the right segmentation within individual images and associates segments with the same semantic classes across images. The core visual learning problem is therefore to maximize the similarity within segments and minimize the similarity between segments. Given a model trained this way, inference is performed consistently by extracting pixel-wise embeddings and clustering, with the semantic label determined by the majority vote of its nearest neighbors from an annotated set. As a result, we present the SegSort, as a first attempt using deep learning for unsupervised semantic segmentation, achieving $76\%$ performance of its supervised counterpart. When supervision is available, SegSort shows consistent improvements over conventional approaches based on pixel-wise softmax training. Additionally, our approach produces more precise boundaries and consistent region predictions. The proposed SegSort further produces an interpretable result, as each choice of label can be easily understood from the retrieved nearest segments.

arXiv commentIn ICCV 2019. Webpage & Code: https://jyhjinghwang.github.io/projects/segsort.html

References in corpus (13)

• Rethinking Atrous Convolution for Semantic Image Segmentation
• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• MobileNetV2: Inverted Residuals and Linear Bottlenecks
• ParseNet: Looking Wider to See Better
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• CosFace: Large Margin Cosine Loss for Deep Face Recognition
• Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination
• DeeperLab: Single-Shot Image Parser
• Learning a Discriminative Feature Network for Semantic Segmentation
• Pixel-wise Deep Learning for Contour Detection
• Stacked Deconvolutional Network for Semantic Segmentation
• ExFuse: Enhancing Feature Fusion for Semantic Segmentation
• Efficient Parameter-free Clustering Using First Neighbor Relations