Unsupervised Semantic Segmentation
19 papers with code • 13 benchmarks • 8 datasets
Models that learn to segment each image (i.e. cluster the pixels into their ground truth classes) without seeing the ground truth labels.
( Image credit: SegSort: Segmentation by Discriminative Sorting of Segments )
In this work, we present DeepCluster, a clustering method that jointly learns the parameters of a neural network and the cluster assignments of the resulting features.
The method is not specialised to computer vision and operates on any paired dataset samples; in our experiments we use random transforms to obtain a pair from each image.
Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation
This paper focuses on the unsupervised domain adaptation of transferring the knowledge from the source domain to the target domain in the context of semantic segmentation.
To achieve this, we introduce a two-step framework that adopts a predetermined mid-level prior in a contrastive optimization objective to learn pixel embeddings.
The proposed SegSort further produces an interpretable result, as each choice of label can be easily understood from the retrieved nearest segments.
Qualitative and quantitative experiments on a real-world portrait shadow dataset demonstrate that our approach achieves comparable performance with supervised shadow removal methods.
Firstly, we design an enhancement factor extraction network using depthwise separable convolution for an efficient estimate of the pixel-wise light deficiency of an low-light image.
MFA basically considers three parallel information fusion strategies, i. e., the cross-model fusion, temporal fusion and a novel online-offline pseudo label fusion.