Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Rangwani, Harsh"'
Autor:
Rangwani, Harsh
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 categories. This curation process is often expensive and requires throwing awa
Externí odkaz:
http://arxiv.org/abs/2411.07229
Autor:
Rangwani, Harsh, Agarwal, Aishwarya, Kulkarni, Kuldeep, Babu, R. Venkatesh, Karanam, Srikrishna
Text-to-image generation from large generative models like Stable Diffusion, DALLE-2, etc., have become a common base for various tasks due to their superior quality and extensive knowledge bases. As image composition and generation are creative proc
Externí odkaz:
http://arxiv.org/abs/2406.10197
Autor:
Rangwani, Harsh, Mondal, Pradipto, Mishra, Mayank, Asokan, Ashish Ramayee, Babu, R. Venkatesh
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 stack of self attention blocks. However, unlike Convolutional Neural Ne
Externí odkaz:
http://arxiv.org/abs/2404.02900
Autor:
Ramasubramanian, Shrinivas, Rangwani, Harsh, Takemori, Sho, Samanta, Kunal, Umeda, Yuhei, Radhakrishnan, Venkatesh Babu
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, which can effectively utilize the colossal amount of data to train model
Externí odkaz:
http://arxiv.org/abs/2403.18301
Autor:
Dhiman, Ankit, R, Srinath, Rangwani, Harsh, Parihar, Rishubh, Boregowda, Lokesh R, Sridhar, Srinath, Babu, R Venkatesh
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 settings concentrate on modelling a single object or a single level of a sce
Externí odkaz:
http://arxiv.org/abs/2308.10337
Autor:
Rangwani, Harsh, Ramasubramanian, Shrinivas, Takemori, Sho, Takashi, Kato, Umeda, Yuhei, Radhakrishnan, Venkatesh Babu
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 majority of work on self-training has focused on the objective of improving
Externí odkaz:
http://arxiv.org/abs/2304.14738
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 perturbations of inputs during inference. While initial work focused o
Externí odkaz:
http://arxiv.org/abs/2304.10446
Autor:
Rangwani, Harsh, Bansal, Lavish, Sharma, Kartik, Karmali, Tejan, Jampani, Varun, Babu, R. Venkatesh
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 manipulation. However, the performance of StyleGANs severely degrades when trai
Externí odkaz:
http://arxiv.org/abs/2304.05866
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 performance of neural networks, particularly on minority classes. In this work,
Externí odkaz:
http://arxiv.org/abs/2212.13827
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. There has been a large body of work to train discriminative mod
Externí odkaz:
http://arxiv.org/abs/2208.09932