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 comparative losses (typically, triplet loss) are appealing choices forlearning person re-identification (ReID) features. However, the triplet loss iscomputationally much more expensive than the (practically more popular)classification loss, limiting their wider usage in massive datasets. Moreover,the abundance of label noise and outliers in ReID datasets may also put themargin-based loss in jeopardy. This work addresses the above two shortcomingsof triplet loss, extending its effectiveness to large-scale ReID datasets withpotentially noisy labels. We propose a fast-approximated triplet (FAT) loss,which provably converts the point-wise triplet loss into its upper bound form,consisting of a point-to-set loss term plus cluster compactness regularization.It preserves the effectiveness of triplet loss, while leading to linearcomplexity to the training set size. A label distillation strategy is furtherdesigned to learn refined soft-labels in place of the potentially noisy labels,from only an identified subset of confident examples, through teacher-studentnetworks. We conduct extensive experiments on three most popular ReIDbenchmarks (Market-1501, DukeMTMC-reID, and MSMT17), and demonstrate that FATloss with distilled labels lead to ReID features with remarkable accuracy,efficiency, robustness, and direct transferability to unseen datasets.

In Defense of the Triplet Loss Again: Learning Robust Person Re-Identification with Fast Approximated Triplet Loss and Label Distillation