Search Results for author:
Found 11 papers, 6 papers with code
Deep Learning for Single-View Instance Recognition
We show that feedforward neural networks outperform state-of-the-art methods for recognizing objects from novel viewpoints even when trained from just a single image per object.
Learning to Track at 100 FPS with Deep Regression Networks
We propose a method for offline training of neural networks that can track novel objects at test-time at 100 fps.
Skin Cancer Detection and Tracking using Data Synthesis and Deep Learning
Dense object detection and temporal tracking are needed across applications domains ranging from people-tracking to analysis of satellite imagery over time.
BanditPAM: Almost Linear Time $k$-Medoids Clustering via Multi-Armed Bandits
Current state-of-the-art $k$-medoids clustering algorithms, such as Partitioning Around Medoids (PAM), are iterative and are quadratic in the dataset size $n$ for each iteration, being prohibitively expensive for large datasets.
BanditPAM: Almost Linear Time k-Medoids Clustering via Multi-Armed Bandits
In these experiments, we observe that BanditPAM returns the same results as state-of-the-art PAM-like algorithms up to 4x faster while performing up to 200x fewer distance computations.
Faster Maximum Inner Product Search in High Dimensions
We provide theoretical guarantees that BanditMIPS returns the correct answer with high probability, while improving the complexity in $d$ from $O(\sqrt{d})$ to $O(1)$.
MABSplit: Faster Forest Training Using Multi-Armed Bandits
We present an algorithm that accelerates the training of random forests and other popular tree-based learning methods.
Bayesian Decision Trees via Tractable Priors and Probabilistic Context-Free Grammars
Once the posterior has been learned, trees can be sampled efficiently (linearly in the number of nodes).
MAPTree: Beating "Optimal" Decision Trees with Bayesian Decision Trees
We first demonstrate a connection between maximum a posteriori inference of decision trees and AND/OR search.
In-Context Learning for Few-Shot Molecular Property Prediction
In this paper, we adapt the concepts underpinning in-context learning to develop a new algorithm for few-shot molecular property prediction.
Context-Aware Meta-Learning
Large Language Models like ChatGPT demonstrate a remarkable capacity to learn new concepts during inference without any fine-tuning.
Ranked #1 on
Few-Shot Image Classification
on Mini-Imagenet 5-way (5-shot)
(using extra training data)
