Search Results for author:
Found 14 papers, 5 papers with code
Deep Cross Modal Learning for Caricature Verification and Identification(CaVINet)
Further, recognizing the identity in the image by knowledge transfer using a combination of shared and modality specific representations, resulted in an unprecedented performance of 85% rank-1 accuracy for caricatures and 95% rank-1 accuracy for visual images.
Semantically Aligned Bias Reducing Zero Shot Learning
It overcomes the hubness problem by learning a latent space that preserves the semantic relationship between the labels while encoding the discriminating information about the classes.
Implicit Discriminator in Variational Autoencoder
In this work we introduce a novel hybrid architecture, Implicit Discriminator in Variational Autoencoder (IDVAE), that combines a VAE and a GAN, which does not need an explicit discriminator network.
Wheat Crop Yield Prediction Using Deep LSTM Model
An in-season early crop yield forecast before harvest can benefit the farmers to improve the production and enable various agencies to devise plans accordingly.
On Duality Gap as a Measure for Monitoring GAN Training
Further, we show that our estimate, with its ability to identify model convergence/divergence, is a potential performance measure that can be used to tune the hyperparameters of a GAN.
Stress Testing of Meta-learning Approaches for Few-shot Learning
Our results show a quick degradation in the performance of initialization strategies for ML (MAML, TAML, and MetaSGD), while surprisingly, approaches that use an optimization strategy (MetaLSTM) perform significantly better.
On Characterizing GAN Convergence Through Proximal Duality Gap
Finally, we validate experimentally the usefulness of proximal duality gap for monitoring and influencing GAN training.
Pho(SC)-CTC -- A Hybrid Approach Towards Zero-shot Word Image Recognition
Annotating words in a historical document image archive for word image recognition purpose demands time and skilled human resource (like historians, paleographers).
Task Attended Meta-Learning for Few-Shot Learning
The popular approaches for ML either learn a generalizable initial model or a generic parametric optimizer through episodic training.
Deep Geospatial Interpolation Networks
Spatio-Temporal interpolation is highly challenging due to the complex spatial and temporal relationships.
Efficient Algorithms For Fair Clustering with a New Fairness Notion
We revisit the problem of fair clustering, first introduced by Chierichetti et al., that requires each protected attribute to have approximately equal representation in every cluster; i. e., a balance property.
Towards Reducing Aleatoric Uncertainty for Medical Imaging Tasks
The proposed method was evaluated on a benchmark medical imaging dataset with image reconstruction as the self-supervised task and segmentation as the image analysis task.
Generalized Cross-domain Multi-label Few-shot Learning for Chest X-rays
Real-world application of chest X-ray abnormality classification requires dealing with several challenges: (i) limited training data; (ii) training and evaluation sets that are derived from different domains; and (iii) classes that appear during training may have partial overlap with classes of interest during evaluation.
Understanding Calibration of Deep Neural Networks for Medical Image Classification
We considered fully supervised training, which is the prevailing approach in the community, as well as rotation-based self-supervised method with and without transfer learning, across various datasets and architecture sizes.
