English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The deep neural networks (DNNs) have freed the synthetic aperture radarautomatic target recognition (SAR ATR) from expertise-based feature designingand demonstrated superiority over conventional solutions. There has been shownthe unique deficiency of ground vehicle benchmarks in shapes of strongbackground correlation results in DNNs overfitting the clutter and beingnon-robust to unfamiliar surroundings. However, the gap between fixedbackground model training and varying background application remainsunderexplored. Inspired by contrastive learning, this letter proposes asolution called Contrastive Feature Alignment (CFA) aiming to learn invariantrepresentation for robust recognition. The proposed method contributes a mixedclutter variants generation strategy and a new inference branch equipped withchannel-weighted mean square error (CWMSE) loss for invariant representationlearning. In specific, the generation strategy is delicately designed to betterattract clutter-sensitive deviation in feature space. The CWMSE loss is furtherdevised to better contrast this deviation and align the deep features activatedby the original images and corresponding clutter variants. The proposed CFAcombines both classification and CWMSE losses to train the model jointly, whichallows for the progressive learning of invariant target representation.Extensive evaluations on the MSTAR dataset and six DNN models prove theeffectiveness of our proposal. The results demonstrated that the CFA-trainedmodels are capable of recognizing targets among unfamiliar surroundings thatare not included in the dataset, and are robust to varying signal-to-clutterratios.

Learning Invariant Representation via Contrastive Feature Alignment for Clutter Robust SAR Target Recognition