<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-21T04:48:33Z</responseDate><request verb="GetRecord" identifier="oai:macsphere.mcmaster.ca:11375/33187" metadataPrefix="dim">https://prod-ms-be.lib.mcmaster.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:macsphere.mcmaster.ca:11375/33187</identifier><datestamp>2026-06-02T07:06:53Z</datestamp><setSpec>com_11375_271</setSpec><setSpec>col_11375_272</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:doc="http://www.lyncode.com/xoai" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="advisor">Giamou, Matthew</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author">Grandhi, Alaap</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="department">Computing and Software</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2026-06-01T20:33:03Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2026</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://hdl.handle.net/11375/33187</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://doi.org/10.71548/50</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract">Geometric data augmentation is widely used in autonomous driving 3D object
detection to improve robustness to transformations such as rotation,
translation, and scaling. While effective, this approach increases training
complexity and does not guarantee that the detector will respond predictably to transformations outside of those explicitly modelled. In this thesis, we investigate whether some of this robustness can instead be built directly into a BEVFusion-style detector through equivariance.

To study this, we introduce two architectures. The first, EquiFusion, applies
equivariant structure throughout the full detection pipeline. The second,
HybridFusion, combines an equivariant stream with a parallel non-equivariant
stream in order to balance geometric structure with feature flexibility. We also
evaluate the effects of representational depth, non-equivariant stream
placement, balanced resampling, and geometric data augmentation on the nuScenes
benchmark.

The results show that full equivariance alone does not work well. Across both augmentation and no-augmentation settings, EquiFusion performs consistently worse than the BEVFusion baseline, indicating that the fully equivariant constraint is too restrictive when imposed throughout the model. In contrast, HybridFusion performs much more strongly, especially in the no-augmentation setting. Most notably, unaugmented HybridFusion outperforms augmented BEVFusion in overall NDS.

These results show that equivariance can be useful in BEVFusion-style 3D object
detection, but that its strongest role is not as a full replacement for
non-equivariant processing. Instead, the best performance is obtained when
equivariant and non-equivariant features are combined within a hybrid
architecture.</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degreetype">Thesis</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degree">Master of Science (MSc)</dim:field>
   <dim:field mdschema="dc" element="rights" lang="en">Attribution 2.5 Canada</dim:field>
   <dim:field mdschema="dc" element="rights" qualifier="uri">http://creativecommons.org/licenses/by/2.5/ca/</dim:field>
   <dim:field mdschema="dc" element="subject">Geometric Deep Learning</dim:field>
   <dim:field mdschema="dc" element="subject">Deep Learning</dim:field>
   <dim:field mdschema="dc" element="subject">Machine Learning</dim:field>
   <dim:field mdschema="dc" element="subject">Computer Vision</dim:field>
   <dim:field mdschema="dc" element="subject">Autonomous Driving</dim:field>
   <dim:field mdschema="dc" element="subject">Equivariant Machine Learning</dim:field>
   <dim:field mdschema="dc" element="subject">Sensor Fusion</dim:field>
   <dim:field mdschema="dc" element="subject">Object Detection</dim:field>
   <dim:field mdschema="dc" element="title">Equivariant Sensor Fusion for Autonomous Driving Object Detection</dim:field>
   <dim:field mdschema="dc" element="type" lang="en">Thesis</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim></metadata></record></GetRecord></OAI-PMH>