27 citations · 46 across the 17 of their papers we have counts for
17 papers
Minimizing Layerwise Activation Norm Improves Generalization in Federated Learning
M Yashwanth, Gaurav Kumar Nayak, Harsh Rangwani +3
Federated Learning (FL) is an emerging machine learning framework that enables multiple clients (coordinated by a server) to collaboratively train a global model by aggregating the…
DynamicEval: Rethinking Evaluation for Dynamic Text-to-Video Synthesis
Nithin C. Babu, Aniruddha Mahapatra, Harsh Rangwani +2
Existing text-to-video (T2V) evaluation benchmarks, such as VBench and EvalCrafter, suffer from two limitations. (i) While the emphasis is on subject-centric prompts or static came…
Learning from Limited and Imperfect Data
Harsh Rangwani
The distribution of data in the world (eg, internet, etc.) significantly differs from the well-curated datasets and is often over-populated with samples from common categories. The…
Learning from Limited and Imperfect Data
Harsh Rangwani
The datasets used for Deep Neural Network training (e.g., ImageNet, MSCOCO, etc.) are often manually balanced across categories (classes) to facilitate learning of all the categori…
Composing Parts for Expressive Object Generation
Harsh Rangwani, Aishwarya Agarwal, Kuldeep Kulkarni +2
Image composition and generation are processes where the artists need control over various parts of the generated images. However, the current state-of-the-art generation models, l…
DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets
Harsh Rangwani, Pradipto Mondal, Mayank Mishra +2
Vision Transformer (ViT) has emerged as a prominent architecture for various computer vision tasks. In ViT, we divide the input image into patch tokens and process them through a s…
Selective Mixup Fine-Tuning for Optimizing Non-Decomposable Objectives
Shrinivas Ramasubramanian, Harsh Rangwani, Sho Takemori +3
The rise in internet usage has led to the generation of massive amounts of data, resulting in the adoption of various supervised and semi-supervised machine learning algorithms, wh…
Strata-NeRF : Neural Radiance Fields for Stratified Scenes
Ankit Dhiman, Srinath R, Harsh Rangwani +4
Neural Radiance Field (NeRF) approaches learn the underlying 3D representation of a scene and generate photo-realistic novel views with high fidelity. However, most proposed settin…
Cost-Sensitive Self-Training for Optimizing Non-Decomposable Metrics
Harsh Rangwani, Shrinivas Ramasubramanian, Sho Takemori +3
Self-training based semi-supervised learning algorithms have enabled the learning of highly accurate deep neural networks, using only a fraction of labeled data. However, the major…
Certified Adversarial Robustness Within Multiple Perturbation Bounds
Soumalya Nandi, Sravanti Addepalli, Harsh Rangwani +1
Randomized smoothing (RS) is a well known certified defense against adversarial attacks, which creates a smoothed classifier by predicting the most likely class under random noise…
NoisyTwins: Class-Consistent and Diverse Image Generation through StyleGANs
Harsh Rangwani, Lavish Bansal, Kartik Sharma +3
StyleGANs are at the forefront of controllable image generation as they produce a latent space that is semantically disentangled, making it suitable for image editing and manipulat…
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data
Harsh Rangwani, Sumukh K Aithal, Mayank Mishra +1
Real-world datasets exhibit imbalances of varying types and degrees. Several techniques based on re-weighting and margin adjustment of loss are often used to enhance the performanc…
Improving GANs for Long-Tailed Data through Group Spectral Regularization
Harsh Rangwani, Naman Jaswani, Tejan Karmali +2
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 sa…
Hierarchical Semantic Regularization of Latent Spaces in StyleGANs
Tejan Karmali, Rishubh Parihar, Susmit Agrawal +4
Progress in GANs has enabled the generation of high-resolution photorealistic images of astonishing quality. StyleGANs allow for compelling attribute modification on such images vi…
A Closer Look at Smoothness in Domain Adversarial Training
Harsh Rangwani, Sumukh K Aithal, Mayank Mishra +2
Domain adversarial training has been ubiquitous for achieving invariant representations and is used widely for various domain adaptation tasks. In recent times, methods converging…
SVAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptation
Harsh Rangwani, Arihant Jain, Sumukh K Aithal +1
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…
Class Balancing GAN with a Classifier in the Loop
Harsh Rangwani, Konda Reddy Mopuri, R. Venkatesh Babu
Generative Adversarial Networks (GANs) have swiftly evolved to imitate increasingly complex image distributions. However, majority of the developments focus on performance of GANs…