Prevalent semantic segmentation solutions, despite their different network designs (FCN
based or attention based) and mask decoding strategies (parametric softmax based or pixel …

Self-supervised learning algorithms based on instance discrimination train encoders to be
invariant to pre-defined transformations of the same instance. While most methods treat …

Abstract We present MaX-DeepLab, the first end-to-end model for panoptic segmentation.
Our approach simplifies the current pipeline that depends heavily on surrogate sub-tasks …

Continually learning new classes from fresh data without forgetting previous knowledge of
old classes is a very challenging research problem. Moreover, it is imperative that such …

Contrastive learning applied to self-supervised representation learning has seen a
resurgence in recent years, leading to state of the art performance in the unsupervised …

Contrastive learning between multiple views of the data has recently achieved state of the
art performance in the field of self-supervised representation learning. Despite its success …

Semi-supervised learning on class-imbalanced data, although a realistic problem, has been
under studied. While existing semi-supervised learning (SSL) methods are known to perform …

We devise deep nearest centroids (DNC), a conceptually elegant yet surprisingly effective
network for large-scale visual recognition, by revisiting Nearest Centroids, one of the most …

This paper considers the domain adaptive person re-identification (re-ID) problem: learning
a re-ID model from a labeled source domain and an unlabeled target domain. Conventional …

This paper introduces a negative margin loss to metric learning based few-shot learning
methods. The negative margin loss significantly outperforms regular softmax loss, and …