@inproceedings{18258,
  abstract     = {Distance metric learning (DML) has been successfully applied to object classification, both in the standard regime of rich training data and in the few-shot scenario, where each category is represented by only a few examples. In this work, we propose a new method for DML that simultaneously learns the backbone network parameters, the embedding space, and the multi-modal distribution of each of the training categories in that space, in a single end-to-end training process. Our approach outperforms state-of-the-art methods for DML-based object classification on a variety of standard fine-grained datasets. Furthermore, we demonstrate the effectiveness of our approach on the problem of few-shot object detection, by incorporating the proposed DML architecture as a classification head into a standard object detection model. We achieve the best results on the ImageNet-LOC dataset compared to strong baselines, when only a few training examples are available. We also offer the community a new episodic benchmark based on the ImageNet dataset for the few-shot object detection task.},
  author       = {Karlinsky, Leonid and Shtok, Joseph and Harary, Sivan and Schwartz, Eli and Aides, Amit and Feris, Rogerio and Giryes, Raja and Bronstein, Alexander},
  booktitle    = {2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  isbn         = {9781728132945},
  issn         = {2575-7075},
  location     = {Long Beach, CA, United States},
  publisher    = {IEEE},
  title        = {{Repmet: Representative-based metric learning for classification and few-shot object detection}},
  doi          = {10.1109/cvpr.2019.00534},
  year         = {2020},
}

@inproceedings{18259,
  abstract     = {Example synthesis is one of the leading methods to tackle the problem of few-shot learning, where only a small number of samples per class are available. However, current synthesis approaches only address the scenario of a single category label per image. In this work, we propose a novel technique for synthesizing samples with multiple labels for the (yet unhandled) multi-label few-shot classification scenario. We propose to combine pairs of given examples in feature space, so that the resulting synthesized feature vectors will correspond to examples whose label sets are obtained through certain set operations on the label sets of the corresponding input pairs. Thus, our method is capable of producing a sample containing the intersection, union or set-difference of labels present in two input samples. As we show, these set operations generalize to labels unseen during training. This enables performing augmentation on examples of novel categories, thus, facilitating multi-label few-shot classifier learning. We conduct numerous experiments showing promising results for the label-set manipulation capabilities of the proposed approach, both directly (using the classification and retrieval metrics), and in the context of performing data augmentation for multi-label few-shot learning. We propose a benchmark for this new and challenging task and show that our method compares favorably to all the common baselines.},
  author       = {Alfassy, Amit and Karlinsky, Leonid and Aides, Amit and Shtok, Joseph and Harary, Sivan and Feris, Rogerio and Giryes, Raja and Bronstein, Alexander},
  booktitle    = {2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  isbn         = {9781728132945},
  issn         = {2575-7075},
  location     = {Long Beach, CA, United States},
  publisher    = {IEEE},
  title        = {{Laso: Label-set operations networks for multi-label few-shot learning}},
  doi          = {10.1109/cvpr.2019.00671},
  year         = {2020},
}

@inproceedings{18260,
  abstract     = {We introduce the first completely unsupervised correspondence learning approach for deformable 3D shapes. Key to our model is the understanding that natural deformations (such as changes in pose) approximately preserve the metric structure of the surface, yielding a natural criterion to drive the learning process toward distortion-minimizing predictions. On this basis, we overcome the need for annotated data and replace it by a purely geometric criterion. The resulting learning model is class-agnostic, and is able to leverage any type of deformable geometric data for the training phase. In contrast to existing supervised approaches which specialize on the class seen at training time, we demonstrate stronger generalization as well as applicability to a variety of challenging settings. We showcase our method on a wide selection of correspondence benchmarks, where we outperform other methods in terms of accuracy, generalization, and efficiency.},
  author       = {Halimi, Oshri and Litany, Or and Rodola, Emanuele Rodola and Bronstein, Alexander and Kimmel, Ron},
  booktitle    = {2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  isbn         = {9781728132945},
  issn         = {2575-7075},
  location     = {Long Beach, CA, United States},
  publisher    = {IEEE},
  title        = {{Unsupervised learning of dense shape correspondence}},
  doi          = {10.1109/cvpr.2019.00450},
  year         = {2020},
}