Correction to: The Visual Computer https://doi.org/10.1007/s00371-023-02925-8

The publication of this article unfortunately contained mistakes. The email addresses of to authors and Figs. 1, 3 and 4 were not correct. Electonical supplementary material was missing. The corrected addresses and figures are given below. ESM is added.

Fig. 1
figure 1

Different tasks of image segmentation. For a given input image a that contains both known (“person”, “dog” and “vegetation”) and unknown objects (“sheep”, “rail” and “grass”), we show: b open-set semantic segmentation (OSS) by pixel identification, c generic segmentation (GS) by pixel clustering, and d generalized open-set semantic segmentation (GOSS)

Full size image
Fig. 3
figure 3

The framework of the baseline and GOSS Segmentor. a Baseline. The input image is fed into the encoder for feature extraction. The dual-branch heads are jointly trained for pixel classification and clustering. Furthermore, pixel-wise contrastive learning is leveraged to learn discriminative feature embeddings. The pixel identification module is designed to recognize sets of pixels of the unknown class from the semantic prediction. The final GOSS output is generated by fusing the identified semantic and grou** predictions. b GOSS Segmentor (GST). Confidence adjustment and pixel contrastive learning modules are included

Full size image
Fig. 4
figure 4

Visualized segmentation results from GST (N+1-model+CA+CL) on COCO-Stuff-GOSS. The GOSS prediction (f) merges the OSS prediction (c) and the grou** prediction (d). Hence, within GOSS prediction (f), “objects” inside identified unknown regions can be segmented out. For example, unknown objects, “paper” in the 1st row, “dog/grass” in the 2nd row, and “bottle” in the 3rd row are correctly outlined even though their classes are not known. We also have some zoom-in images to show the effectiveness of the GST

Full size image

The original article has been corrected.