4 citations · 5 across the 5 of their papers we have counts for
5 papers · 1 filter
Mix-QVLA: Task-Evidence-Aware Mixed-Precision Quantization of Vision-Language-Action Models
Navin Ranjan, Andreas Savakis
We propose Mix-QVLA, a task-evidence-aware mixed-precision PTQ framework for VLA models. Mix-QVLA anchors each quantized variant to the full-precision action-token reference decisi…
Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model
Navin Ranjan, Andreas Savakis
The Segment Anything Model (SAM) is a popular vision foundation model; however, its high computational and memory demands make deployment on resource-constrained devices challengin…
Mix-QViT: Mixed-Precision Vision Transformer Quantization Driven by Layer Importance and Quantization Sensitivity
Navin Ranjan, Andreas Savakis
In this paper, we propose Mix-QViT, an explainability-driven MPQ framework that systematically allocates bit-widths to each layer based on two criteria: layer importance, assessed…
Waterfall Transformer for Multi-person Pose Estimation
Navin Ranjan, Bruno Artacho, Andreas Savakis
We propose the Waterfall Transformer architecture for Pose estimation (WTPose), a single-pass, end-to-end trainable framework designed for multi-person pose estimation. Our framewo…
LRP-QViT: Mixed-Precision Vision Transformer Quantization via Layer-wise Relevance Propagation
Navin Ranjan, Andreas Savakis
Vision transformers (ViTs) have demonstrated remarkable performance across various visual tasks. However, ViT models suffer from substantial computational and memory requirements,…