6 papers
FeudalNav: A Simple Framework for Visual Navigation
Faith Johnson, Bryan Bo Cao, Shubham Jain +2
Visual navigation for robotics is inspired by the human ability to navigate environments using visual cues and memory, eliminating the need for detailed maps. In unseen, unmapped,…
YOPO-Nav: Visual Navigation using 3DGS Graphs from One-Pass Videos
Ryan Meegan, Adam D'Souza, Bryan Bo Cao +2
Visual navigation has emerged as a practical alternative to traditional robotic navigation pipelines that rely on detailed mapping and path planning. However, constructing and main…
StatsMerging: Statistics-Guided Model Merging via Task-Specific Teacher Distillation
Ranjith Merugu, Bryan Bo Cao, Shubham Jain
Model merging has emerged as a promising solution to accommodate multiple large models within constrained memory budgets. We present StatsMerging, a novel lightweight learning-base…
Few-Class Arena: A Benchmark for Efficient Selection of Vision Models and Dataset Difficulty Measurement
Bryan Bo Cao, Lawrence O'Gorman, Michael Coss +1
We propose Few-Class Arena (FCA), as a unified benchmark with focus on testing efficient image classification models for few classes. A wide variety of benchmark datasets with many…
A Lightweight Measure of Classification Difficulty from Application Dataset Characteristics
Bryan Bo Cao, Abhinav Sharma, Lawrence O'Gorman +2
Although accuracy and computation benchmarks are widely available to help choose among neural network models, these are usually trained on datasets with many classes, and do not gi…
Representation Similarity: A Better Guidance of DNN Layer Sharing for Edge Computing without Training
Bryan Bo Cao, Abhinav Sharma, Manavjeet Singh +3
Edge computing has emerged as an alternative to reduce transmission and processing delay and preserve privacy of the video streams. However, the ever-increasing complexity of Deep…