5 papers
Pooling Attention: Evaluating Pretrained Transformer Embeddings for Deception Classification
Sumit Mamtani, Abhijeet Bhure
This paper investigates fake news detection as a downstream evaluation of Transformer representations, benchmarking encoder-only and decoder-only pre-trained models (BERT, GPT-2, T…
Axial-UNet: A Neural Weather Model for Precipitation Nowcasting
Sumit Mamtani, Maitreya Sonawane
Accurately predicting short-term precipitation is critical for weather-sensitive applications such as disaster management, aviation, and urban planning. Traditional numerical weath…
Fine-Grained Classification: Connecting Metadata via Cross-Contrastive Pre-Training
Sumit Mamtani, Yash Thesia
Fine-grained visual classification aims to recognize objects belonging to many subordinate categories of a supercategory, where appearance alone often fails to distinguish highly s…
Enhancing Transformer-Based Vision Models: Addressing Feature Map Anomalies Through Novel Optimization Strategies
Sumit Mamtani
Vision Transformers (ViTs) have demonstrated superior performance across a wide range of computer vision tasks. However, structured noise artifacts in their feature maps hinder dow…
Token-free Models for Sarcasm Detection
Sumit Mamtani, Maitreya Sonawane, Kanika Agarwal +1
Tokenization is a foundational step in most natural language processing (NLP) pipelines, yet it introduces challenges such as vocabulary mismatch and out-of-vocabulary issues. Rece…