Sharing Representations for Long Tail Computer Vision Problems

40 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Small Sample Learning in Big Data Era (2018, background): “The long tail phenomena appear in the dataset where a small number of objects/words/classes are very frequent, while many more are rare (Bengio, 2015).”
Learning to Model the Tail (2017, background): “This intrinsic long-tail property poses a multitude of open challenges for recognition in the wild [15], since the models will be largely dominated by those few head classes while degraded for many other tail classes.”
Distribution Alignment: A Unified Framework for Long-tail Visual Recognition (2021, background): “The intrinsic long-tail property of our visual data introduces a multitude of challenges for recognition in the wild [1], as a deep network model has to simultaneously cope with imbalanced annotations among the head and mediumsized classes, and few-shot learning in the tail classes.”
Feature Space Augmentation for Long-Tailed Data (2020, background): “In [2], the representation is shared in general with diﬀerent embedding approaches across diﬀerent classes.”
GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild (2018, background): “It is also a common phenomenon in the distributions of natural species and Internet data that is formally named Long-Tailed Distribution [39].”