You are currently viewing a new version of our website. To view the old version click .
by
  • Xiaodian Zhang1,
  • Kun Gao1,* and
  • Junwei Wang1
  • et al.

Reviewer 1: Anonymous Reviewer 2: Anonymous

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

This manuscript proposes the Implicit Contrastive Learning Module (ICLM) and the Local Spectral Similarity Constraint Loss (LSSC) to implement an Implicit Contrastive Learning-based Target Detector (ICLTD). Detailed experiments and derivations compellingly illustrate the effectiveness of the proposed method. Nonetheless, a few minor issues merit attention:

1.     As an improvement of BN, whether ICLM can play a role in other HSI detection methods. Can it be used as a plug-and-play method and be widely used in other DL-based HTD methods?

2.     In Figure 12, compared with GT, we notice that the proposed method LSSC also enhances some noise (A1, B2, U1). Is this an inherent flaw in the approach?

3.     Given the relatively innovative nature of Implicit Contrastive Learning, could you provide a brief prospect to foster the development of Implicit Contrastive Learning in the HTD domain?

4.     The slashes in the headers of Tables 6,7 and 8 may need to be corrected.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

See attached file.

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

Comments and Suggestions for Authors

The authors answered all my questions.