Search Results for author:
Found 15 papers, 10 papers with code
NLPRL-IITBHU at SemEval-2018 Task 3: Combining Linguistic Features and Emoji pre-trained CNN for Irony Detection in Tweets
This paper describes our participation in SemEval 2018 Task 3 on Irony Detection in Tweets.
IIT (BHU) Submission for the ACL Shared Task on Named Entity Recognition on Code-switched Data
This paper describes the best performing system for the shared task on Named Entity Recognition (NER) on code-switched data for the language pair Spanish-English (ENG-SPA).
S3VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptation
Unsupervised domain adaptation (DA) methods have focused on achieving maximal performance through aligning features from source and target domains without using labeled data in the target domain.
Class Balancing GAN with a Classifier in the Loop
However, majority of the developments focus on performance of GANs on balanced datasets.
S$^3$VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptation
Unsupervised domain adaptation (DA) methods have focused on achieving maximal performance through aligning features from source and target domains without using labeled data in the target domain.
A Closer Look at Smoothness in Domain Adversarial Training
Based on the analysis, we introduce the Smooth Domain Adversarial Training (SDAT) procedure, which effectively enhances the performance of existing domain adversarial methods for both classification and object detection tasks.
Ranked #5 on
Domain Adaptation
on VisDA2017
Hierarchical Semantic Regularization of Latent Spaces in StyleGANs
The quality of the generated images is predicated on two assumptions; (a) The richness of the hierarchical representations learnt by the generator, and, (b) The linearity and smoothness of the style spaces.
Improving GANs for Long-Tailed Data through Group Spectral Regularization
Deep long-tailed learning aims to train useful deep networks on practical, real-world imbalanced distributions, wherein most labels of the tail classes are associated with a few samples.
Ranked #1 on
Image Generation
on LSUN
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data
Real-world datasets exhibit imbalances of varying types and degrees.
Ranked #1 on
Long-tail Learning
on CIFAR-10-LT (ρ=50)
NoisyTwins: Class-Consistent and Diverse Image Generation through StyleGANs
We find that one reason for degradation is the collapse of latents for each class in the $\mathcal{W}$ latent space.
Ranked #1 on
Conditional Image Generation
on ImageNet-LT
Certified Adversarial Robustness Within Multiple Perturbation Bounds
We further propose a novel \textit{training noise distribution} along with a \textit{regularized training scheme} to improve the certification within both $\ell_1$ and $\ell_2$ perturbation norms simultaneously.
Cost-Sensitive Self-Training for Optimizing Non-Decomposable Metrics
Using the proposed CSST framework, we obtain practical self-training methods (for both vision and NLP tasks) for optimizing different non-decomposable metrics using deep neural networks.
Strata-NeRF : Neural Radiance Fields for Stratified Scenes
We propose Strata-NeRF, a single neural radiance field that implicitly captures a scene with multiple levels.
Selective Mixup Fine-Tuning for Optimizing Non-Decomposable Objectives
We find that current state-of-the-art empirical techniques offer sub-optimal performance on these practical, non-decomposable performance objectives.
DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets
In DeiT-LT, we introduce an efficient and effective way of distillation from CNN via distillation DIST token by using out-of-distribution images and re-weighting the distillation loss to enhance focus on tail classes.
Ranked #1 on
Image Classification
on iNaturalist
(Overall metric)
