arXiv subjects

Sumit Mamtani

Publications and source records attributed to Sumit Mamtani.

6 recordsLinked to original sources

arXiv2025

Pooling Attention: Evaluating Pretrained Transformer Embeddings for Deception Classification

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, Transformer-XL) as frozen embedders paired with lightweight classifiers. Through controlled preprocessing comparing pooling versus padding and neural versus linear heads, results demonstrate that contextual self-attention encodings consistently transfer effectively. BERT embeddings combined with logistic regression outperform neural baselines on LIAR dataset splits, while analyses of sequence length and aggregation reveal robustness to truncation and advantages from simple max or average pooling. This work positions attention-based token encoders as robust, architecture-centric foundations for veracity tasks, isolating Transformer contributions from classifier complexity.

cs.CL↗

arXiv2025

Enhancing Transformer-Based Vision Models: Addressing Feature Map Anomalies Through Novel Optimization Strategies

Vision Transformers (ViTs) have demonstrated superior performance across a wide range of computer vision tasks. However, structured noise artifacts in their feature maps hinder downstream applications such as segmentation and depth estimation. We propose two novel and lightweight optimisation techniques- Structured Token Augmentation (STA) and Adaptive Noise Filtering (ANF)- to improve interpretability and mitigate these artefacts. STA enhances token diversity through spatial perturbations during tokenisation, while ANF applies learnable inline denoising between transformer layers. These methods are architecture-agnostic and evaluated across standard benchmarks, including ImageNet, Ade20k, and NYUv2. Experimental results show consistent improvements in visual quality and task performance, highlighting the practical effectiveness of our approach.

cs.CV↗

arXiv2025

Token-free Models for Sarcasm Detection

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. Recent work has shown that models operating directly on raw text at the byte or character level can mitigate these limitations. In this paper, we evaluate two token-free models, ByT5 and CANINE, on the task of sarcasm detection in both social media (Twitter) and non-social media (news headlines) domains. We fine-tune and benchmark these models against token-based baselines and state-of-the-art approaches. Our results show that ByT5-small and CANINE outperform token-based counterparts and achieve new state-of-the-art performance, improving accuracy by 0.77% and 0.49% on the News Headlines and Twitter Sarcasm datasets, respectively. These findings underscore the potential of token-free models for robust NLP in noisy and informal domains such as social media.

cs.CL↗

arXiv2025

Fine-Grained Classification: Connecting Metadata via Cross-Contrastive Pre-Training

Fine-grained visual classification aims to recognize objects belonging to many subordinate categories of a supercategory, where appearance alone often fails to distinguish highly similar classes. We propose a unified framework that integrates image, text, and metadata via cross-contrastive pre-training. We first align the three modality encoders in a shared embedding space and then fine-tune the image and metadata encoders for classification. On NABirds, our approach improves over the baseline by 7.83% and achieves 84.44% top-1 accuracy, outperforming strong multimodal methods.

cs.CV↗

arXiv2025

Axial-UNet: A Neural Weather Model for Precipitation Nowcasting

Accurately predicting short-term precipitation is critical for weather-sensitive applications such as disaster management, aviation, and urban planning. Traditional numerical weather prediction can be computationally intensive at high resolution and short lead times. In this work, we propose a lightweight UNet-based encoder-decoder augmented with axial-attention blocks that attend along image rows and columns to capture long-range spatial interactions, while temporal context is provided by conditioning on multiple past radar frames. Our hybrid architecture captures both local and long-range spatio-temporal dependencies from radar image sequences, enabling fixed lead-time precipitation nowcasting with modest compute. Experimental results on a preprocessed subset of the HKO-7 radar dataset demonstrate that our model outperforms ConvLSTM, pix2pix-style cGANs, and a plain UNet in pixel-fidelity metrics, reaching PSNR 47.67 and SSIM 0.9943. We report PSNR/SSIM here; extending evaluation to meteorology-oriented skill measures (e.g., CSI/FSS) is left to future work. The approach is simple, scalable, and effective for resource-constrained, real-time forecasting scenarios.

cs.LG↗

arXiv2022

Deployment of ML Models using Kubeflow on Different Cloud Providers

This project aims to explore the process of deploying Machine learning models on Kubernetes using an open-source tool called Kubeflow [1] - an end-to-end ML Stack orchestration toolkit. We create end-to-end Machine Learning models on Kubeflow in the form of pipelines and analyze various points including the ease of setup, deployment models, performance, limitations and features of the tool. We hope that our project acts almost like a seminar/introductory report that can help vanilla cloud/Kubernetes users with zero knowledge on Kubeflow use Kubeflow to deploy ML models. From setup on different clouds to serving our trained model over the internet - we give details and metrics detailing the performance of Kubeflow.

cs.LG↗