7 papers
HilDA: Hierarchical Distillation with Diffusion for Advancing Self-Supervised LiDAR Pre-training
Maciej Wozniak, Jesper Ericsson, Hariprasath Govindarajan +4
Leveraging Vision Foundation Models (VFMs) for camera-to-LiDAR knowledge distillation offers a promising solution to the scarcity of annotated data needed to represent the immense…
QUEST: A robust attention formulation using query-modulated spherical attention
Hariprasath Govindarajan, Per Sidén, Jacob Roll +1
The Transformer model architecture has become one of the most widely used in deep learning and the attention mechanism is at its core. The standard attention formulation uses a sof…
CleverDistiller: Simple and Spatially Consistent Cross-modal Distillation
Hariprasath Govindarajan, Maciej K. Wozniak, Marvin Klingner +3
Vision foundation models (VFMs) such as DINO have led to a paradigm shift in 2D camera-based perception towards extracting generalized features to support many downstream tasks. Re…
Understanding Ice Crystal Habit Diversity with Self-Supervised Learning
Joseph Ko, Hariprasath Govindarajan, Fredrik Lindsten +4
Ice-containing clouds strongly impact climate, but they are hard to model due to ice crystal habit (i.e., shape) diversity. We use self-supervised learning (SSL) to learn latent re…
S3PT: Scene Semantics and Structure Guided Clustering to Boost Self-Supervised Pre-Training for Autonomous Driving
Maciej K. Wozniak, Hariprasath Govindarajan, Marvin Klingner +3
Recent self-supervised clustering-based pre-training techniques like DINO and Cribo have shown impressive results for downstream detection and segmentation tasks. However, real-wor…
On Partial Prototype Collapse in the DINO Family of Self-Supervised Methods
Hariprasath Govindarajan, Per Sidén, Jacob Roll +1
A prominent self-supervised learning paradigm is to model the representations as clusters, or more generally as a mixture model. Learning to map the data samples to compact represe…