Mehrtash Harandi

45

Papers

313

Total Citations

1

Affiliations

Affiliations

Monash University

Papers (45)

HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression

Museum Exhibit Identification Challenge for the Supervised Domain Adaptation and Beyond

How Far Can We Compress Instant-NGP-Based NeRF?

Erasing Undesirable Influence in Diffusion Models

Text-Enhanced Data-free Approach for Federated Class-Incremental Learning

Efficient Optimization for Linear Dynamical Systems with Applications to Clustering and Sparse Coding

Unleashing Diffusion Transformers for Visual Correspondence by Modulating Massive Activations

When VLAD Met Hilbert

Generalized Rank Pooling for Activity Recognition

Learning an Invariant Hilbert Space for Domain Adaptation

Geometry Aware Constrained Optimization Techniques for Deep Learning

Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective

Min-Max Statistical Alignment for Transfer Learning

Adaptive Subspaces for Few-Shot Learning

Learning to Optimize on SPD Manifolds

Reinforced Attention for Few-Shot Learning and Beyond

Semantic-Aware Knowledge Distillation for Few-Shot Class-Incremental Learning

On Learning the Geodesic Path for Incremental Learning

Implicit Motion Handling for Video Camouflaged Object Detection

On Generalizing Beyond Domains in Cross-Domain Continual Learning

Exploring Data Geometry for Continual Learning

Beyond Gauss: Image-Set Matching on the Riemannian Manifold of PDFs

Learning Discriminative ab-Divergences for Positive Definite Matrices

Siamese Networks: The Tale of Two Manifolds

Bilinear Attention Networks for Person Retrieval

Curvature Generation in Curved Spaces for Few-Shot Learning

Kernel Methods in Hyperbolic Spaces

Synthesized Feature Based Few-Shot Class-Incremental Learning on a Mixture of Subspaces

Hyperbolic Audio-visual Zero-shot Learning

Energy-based Self-Training and Normalization for Unsupervised Domain Adaptation

On Modulating the Gradient for Meta-Learning

Learning Instance and Task-Aware Dynamic Kernels for Few-Shot Learning

Riemannian Coding and Dictionary Learning: Kernels to the Rescue

MUNBa: Machine Unlearning via Nash Bargaining

A Good Teacher Adapts Their Knowledge for Distillation

LaViP: Language-Grounded Visual Prompting

Backpropagation-free Network for 3D Test-time Adaptation

NAYER: Noisy Layer Data Generation for Efficient and Effective Data-free Knowledge Distillation

Sparse Coding and Dictionary Learning With Linear Dynamical Systems

Hierarchical Neural Architecture Search for Deep Stereo Matching

Rethinking Generalization in Few-Shot Classification

On Enforcing Better Conditioned Meta-Learning for Rapid Few-Shot Adaptation

Hyperbolic Feature Augmentation via Distribution Estimation and Infinite Sampling on Manifolds

Joint Dimensionality Reduction and Metric Learning: A Geometric Take

Neural Collaborative Subspace Clustering