Saurabh Sharma

Saurabh Sharma

Max-Planck-Institut für Informatik
Saarland Informatics Campus
Campus E1 4
66123 Saarbrücken
E1 4 - 621
+49 681 9325 2021
+49 681 9325 2099

Personal Information

  • Researcher at the Computer Vision and Machine Learning group in the Max Planck Institute for Informatics.
  • Masters student in Computer Science at Saarland University.
  • [Linkedin] [Github] [Google Scholar]


f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning
Y. Xian, S. Sharma, B. Schiele and Z. Akata
32nd IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019), 2019
(Accepted/in press)
When labeled training data is scarce, a promising data augmentation approach is to generate visual features of unknown classes using their attributes. To learn the class conditional distribution of CNN features, these models rely on pairs of image features and class attributes. Hence, they can not make use of the abundance of unlabeled data samples. In this paper, we tackle any-shot learning problems i.e. zero-shot and few-shot, in a unified feature generating framework that operates in both inductive and transductive learning settings. We develop a conditional generative model that combines the strength of VAE and GANs and in addition, via an unconditional discriminator, learns the marginal feature distribution of unlabeled images. We empirically show that our model learns highly discriminative CNN features for five datasets, i.e. CUB, SUN, AWA and ImageNet, and establish a new state-of-the-art in any-shot learning, i.e. inductive and transductive (generalized) zero- and few-shot learning settings. We also demonstrate that our learned features are interpretable: we visualize them by inverting them back to the pixel space and we explain them by generating textual arguments of why they are associated with a certain label.
Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking
S. Sharma, P. T. Varigonda, P. Bindal, A. Sharma and A. Jain
ICCV 2019, International Conference on Computer Vision, 2019
(Accepted/in press)
Monocular 3D Human Pose Estimation from static images is a challenging problem, due to the curse of dimensionality and the ill-posed nature of lifting 2D to 3D. In this paper, we propose a Deep Conditional Variational Autoencoder based model that synthesizes diverse 3D pose samples conditioned on the estimated 2D pose. Our experiments reveal that the CVAE generates significantly diverse 3D samples that are consistent with the 2D pose, thereby reducing the ambiguity in lifting from 2D-to-3D. We use two strategies for predicting the final 3D pose - (a) depth-ordering/ordinal relations to score and aggregate the final 3D pose, or OrdinalScore, and (b) with supervision from an Oracle. We report close to state of the art results on two benchmark datasets using OrdinalScore, and state-of-the-art results using the Oracle. We also show our pipeline gives competitive results without paired 3D supervision. We shall make the training and evaluation code available at