Geographical region traceability of wild topmouth culter (Culter alburnus) from Xingkai Lake based on muscle quality and aroma profiles.

The wild topmouth culter (Culter alburnus) from Xingkai Lake (XKL) is highly regarded for its delicious taste and unique flavor. In this study, based on muscle quality and aroma analysis, we first differentiated the XKL population from three wild populations in Heilongjiang Province and one artificially cultured population (from Xingkai Lake). Compared with the other populations, the XKL population has a significantly higher crude protein content, essential amino acid content, delicious amino acid content, and n-3/n-6 PUFA ratio. Additionally, it exhibits superior hardness, elasticity, chewiness, recoverability, and viscosity. E-nose detection analysis revealed that W1S, W2S, and W3S were the potential sensors contributing the most to the differences among the five populations. HS-SPME-GC-MS and multivariate regression analysis showed that 21 volatile flavor compounds were identified as key markers for geographical identification of the Xingkai Lake region. These findings will provide guidance for the geographical traceability and identification of the XKL population.

Structured Domain Adaptation With Online Relation Regularization for Unsupervised Person Re-ID.

Unsupervised domain adaptation (UDA) aims at adapting the model trained on a labeled source-domain dataset to an unlabeled target-domain dataset. The task of UDA on open-set person reidentification (re-ID) is even more challenging as the identities (classes) do not have overlap between the two domains. One major research direction was based on domain translation, which, however, has fallen out of favor in recent years due to inferior performance compared with pseudo-label-based methods. We argue that domain translation has great potential on exploiting valuable source-domain data but the existing methods did not provide proper regularization on the translation process. Specifically, previous methods only focus on maintaining the identities of the translated images while ignoring the intersample relations during translation. To tackle the challenges, we propose an end-to-end structured domain adaptation framework with an online relation-consistency regularization term. During training, the person feature encoder is optimized to model intersample relations on-the-fly for supervising relation-consistency domain translation, which in turn improves the encoder with informative translated images. The encoder can be further improved with pseudo labels, where the source-to-target translated images with ground-truth identities and target-domain images with pseudo identities are jointly used for training. In the experiments, our proposed framework is shown to achieve state-of-the-art performance on multiple UDA tasks of person re-ID. With the synthetic→real translated images from our structured domain-translation network, we achieved second place in the Visual Domain Adaptation Challenge (VisDA) in 2020.