6 papers
FlexPooling with Simple Auxiliary Classifiers in Deep Networks
Muhammad Ali, Omar Alsuwaidi, Salman Khan
In computer vision, the basic pipeline of most convolutional neural networks consists of multiple feature extraction layers, where the input signal is downsampled to a lower resolu…
Waste-Bench: A Comprehensive Benchmark for Evaluating VLLMs in Cluttered Environments
Muhammad Ali, Salman Khan
Recent advancements in Large Language Models (LLMs) have paved the way for Vision Large Language Models (VLLMs) capable of performing a wide range of visual understanding tasks. Wh…
COSNet: A Novel Semantic Segmentation Network using Enhanced Boundaries in Cluttered Scenes
Muhammad Ali, Mamoona Javaid, Mubashir Noman +2
Automated waste recycling aims to efficiently separate the recyclable objects from the waste by employing vision-based systems. However, the presence of varying shaped objects havi…
Underwater Object Detection Enhancement via Channel Stabilization
Muhammad Ali, Salman Khan
The complex marine environment exacerbates the challenges of object detection manifold. Marine trash endangers the aquatic ecosystem, presenting a persistent challenge. Accurate de…
FANet: Feature Amplification Network for Semantic Segmentation in Cluttered Background
Muhammad Ali, Mamoona Javaid, Mubashir Noman +2
Existing deep learning approaches leave out the semantic cues that are crucial in semantic segmentation present in complex scenarios including cluttered backgrounds and translucent…
CLIP-Decoder : ZeroShot Multilabel Classification using Multimodal CLIP Aligned Representation
Muhammad Ali, Salman Khan
Multi-label classification is an essential task utilized in a wide variety of real-world applications. Multi-label zero-shot learning is a method for classifying images into multip…