Timezone: »

Fine-Grained Zero-Shot Learning with DNA as Side Information
Sarkhan Badirli · Zeynep Akata · George Mohler · Christine Picard · Mehmet M Dundar

Wed Dec 08 04:30 PM -- 06:00 PM (PST) @

Fine-grained zero-shot learning task requires some form of side-information to transfer discriminative information from seen to unseen classes. As manually annotated visual attributes are extremely costly and often impractical to obtain for a large number of classes, in this study we use DNA as a side information for the first time for fine-grained zero-shot classification of species. Mitochondrial DNA plays an important role as a genetic marker in evolutionary biology and has been used to achieve near perfect accuracy in species classification of living organisms. We implement a simple hierarchical Bayesian model that uses DNA information to establish the hierarchy in the image space and employs local priors to define surrogate classes for unseen ones. On the benchmark CUB dataset we show that DNA can be equally promising, yet in general a more accessible alternative than word vectors as a side information. This is especially important as obtaining robust word representations for fine-grained species names is not a practicable goal when information about these species in free-form text is limited. On a newly compiled fine-grained insect dataset that uses DNA information from over a thousand species we show that the Bayesian approach outperforms state-of-the-art by a wide margin.

Author Information

Sarkhan Badirli (Purdue University)
Zeynep Akata (Max Planck Institute for Informatics)
George Mohler (Indiana University Purdue University Indianapolis)
Christine Picard (Indiana University Purdue University Indianapolis)
Mehmet M Dundar (Indiana University - Purdue University)

More from the Same Authors

  • 2021 : Revisiting Visual Product for Compositional Zero-Shot Learning »
    Shyamgopal Karthik · Massimiliano Mancini · Zeynep Akata
  • 2021 Poster: Robustness via Uncertainty-aware Cycle Consistency »
    Uddeshya Upadhyay · Yanbei Chen · Zeynep Akata
  • 2018 : Poster Session »
    Lorenzo Masoero · Tammo Rukat · Runjing Liu · Sayak Ray Chowdhury · Daniel Coelho de Castro · Claudia Wehrhahn · Feras Saad · Archit Verma · Kelvin Hsu · Irineo Cabreros · Sandhya Prabhakaran · Yiming Sun · Maxime Rischard · Linfeng Liu · Adam Farooq · Jeremiah Liu · Melanie F. Pradier · Diego Romeres · Neill Campbell · Kai Xu · Mehmet M Dundar · Tucker Keuter · Prashnna Gyawali · Eli Sennesh · Alessandro De Palma · Daniel Flam-Shepherd · Takatomi Kubo
  • 2016 Poster: Learning What and Where to Draw »
    Scott E Reed · Zeynep Akata · Santosh Mohan · Samuel Tenka · Bernt Schiele · Honglak Lee
  • 2016 Oral: Learning What and Where to Draw »
    Scott E Reed · Zeynep Akata · Santosh Mohan · Samuel Tenka · Bernt Schiele · Honglak Lee