Instance Embedding Transfer to Unsupervised Video Object Segmentation
We propose a method for unsupervised video object segmentation by transferring the knowledge encapsulated in image-based instance embedding networks. The instance embedding network produces an embedding vector for each pixel that enables identifying all pixels belonging to the same object. Though trained on static images, the instance embeddings are stable over consecutive video frames, which allows us to link objects together over time. Thus, we adapt the instance networks trained on static images to video object segmentation and incorporate the embeddings with objectness and optical flow features, without model retraining or online fine-tuning. The proposed method outperforms state-of-the-art unsupervised segmentation methods in the DAVIS dataset and the FBMS dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
ObjectOptical Flow EstimationSegmentationSemantic SegmentationUnsupervised Video Object SegmentationVideo Object SegmentationVideo Semantic SegmentationSimilar Papers 제목 키워드 기반
Unsupervised Learning from Video with Deep Neural Embeddings
Because of the rich dynamical structure of videos and their ubiquity in everyday life, it is a natural idea that video data could serve as a powerful unsupervised learning signal for training visual representations in de…
Action RecognitionObject RecognitionLocal Aggregation for Unsupervised Learning of Visual Embeddings
Unsupervised approaches to learning in neural networks are of substantial interest for furthering artificial intelligence, both because they would enable the training of networks without the need for large numbers of exp…
ClusteringContrastive Learningobject-detectionObject Detection+4Unsupervised Video Object Segmentation with Motion-based Bilateral Networks
In this work, we study the unsupervised video object segmentation problem where moving objects are segmented without prior knowledge of these objects. First, we propose a motion-based bilateral network to estimate the ba…
ObjectSegmentationSemantic SegmentationUnsupervised Video Object Segmentation+3Exploring Instance Relations for Unsupervised Feature Embedding
Despite the great progress achieved in unsupervised feature embedding, existing contrastive learning methods typically pursue view-invariant representations through attracting positive sample pairs and repelling negative…
Contrastive Learningimage-classificationImage ClassificationRelation+1Unsupervised Part-Based Disentangling of Object Shape and Appearance
Large intra-class variation is the result of changes in multiple object characteristics. Images, however, only show the superposition of different variable factors such as appearance or shape. Therefore, learning to dise…
Appearance TransferImage GenerationObjectPose Prediction+3