Correction: Lin, Y., et al. Road Extraction from Very-High-Resolution Remote Sensing Images via a Nested SE-Deeplab Model. Remote Sens. 2020, 12, 2985

The authors wish to make the following correction to this paper [1]:

Error in Figure/Table

1. In the original article, there was a mistake in Figure 9. as published. We found a spelling and color marking error in the original Figure 9B, the colors of the red curve and grey curve in the original figure should be exchanged, and ‘weightede’ should be replaced with ‘weighted’. The corrected ** Figure 9.** appears below. We wish to replace

with

Figure 9. Progression of loss values (A) and training accuracy (B) for four loss functions used with Nested SE-Deeplab during training. The loss functions are softmax cross entropy (softmax), weighted log loss, dice coefficient (dice), and dice coefficient added with binary cross entropy (bce).

Figure 9. Progression of loss values (A) and training accuracy (B) for four loss functions used with Nested SE-Deeplab during training. The loss functions are softmax cross entropy (softmax), weighted log loss, dice coefficient (dice), and dice coefficient added with binary cross entropy (bce).

The authors apologize for any inconvenience caused and state that the scientific conclusions are unaffected. The original article has been updated.

2. In the original article, there was a mistake in

Table 3. Quantitative comparison of three backbone networks for the testing dataset.

Experiment	Methods	Correctness	F1-Score	IoU 1
Figure 10a	ResNet	0.9100	0.9112	0.8385
	ResNext	0.9088	0.9161	0.8468
	SE-Net	0.9140	0.9167	0.8462
Figure 10b	ResNet	0.8152	0.8274	0.7179
	ResNext	0.8395	0.8447	0.7312
	SE-Net	0.8380	0.8541	0.7454
Figure 10c	ResNet	0.7941	0.8095	0.6957
	ResNext	0.8120	0.8190	0.7194
	SE-Net	0.8270	0.8254	0.7243

¹ The full name of IoU is Intersection over Union.

. as published. We are aware that some IoU values in the Table 3 were missed to be updated, so we wish to make this correction. The corrected ** Table 3.** appears below. We wish to replace

with

Table 3. Quantitative comparison of three backbone networks for the testing dataset.

Experiment	Methods	Correctness	F1-Score	IoU 1
Figure 10a	ResNet	0.9100	0.9112	0.8385
	ResNext	0.9088	0.9161	0.8455
	SE-Net	0.9140	0.9167	0.8462
Figure 10b	ResNet	0.8152	0.8274	0.7056
	ResNext	0.8395	0.8447	0.7312
	SE-Net	0.8380	0.8541	0.7454
Figure 10c	ResNet	0.7941	0.8095	0.6800
	ResNext	0.8120	0.8190	0.6935
	SE-Net	0.8270	0.8254	0.7027

¹ The full name of IoU is Intersection over Union.

Table 3. Quantitative comparison of three backbone networks for the testing dataset.

Experiment	Methods	Correctness	F1-Score	IoU 1
Figure 10a	ResNet	0.9100	0.9112	0.8385
	ResNext	0.9088	0.9161	0.8455
	SE-Net	0.9140	0.9167	0.8462
Figure 10b	ResNet	0.8152	0.8274	0.7056
	ResNext	0.8395	0.8447	0.7312
	SE-Net	0.8380	0.8541	0.7454
Figure 10c	ResNet	0.7941	0.8095	0.6800
	ResNext	0.8120	0.8190	0.6935
	SE-Net	0.8270	0.8254	0.7027

¹ The full name of IoU is Intersection over Union.

The authors apologize for any inconvenience caused and state that the scientific conclusions are unaffected. The original article has been updated.