Cross-domain Open-world Discovery

1 code implementation • 17 Jun 2024 • Shuo Wen, Maria Brbic

In this work, we consider a cross-domain open-world discovery setting, where the goal is to assign samples to seen classes and discover unseen classes under a domain shift.

Image Classification

Let Go of Your Labels with Unsupervised Transfer

1 code implementation • International Conference on Machine Learning 2024 • Artyom Gadetsky, Yulun Jiang, Maria Brbic

In particular, TURTLE matches the average performance of CLIP zero-shot on 26 datasets by employing the same representation space, spanning a wide range of architectures and model sizes.

Image Clustering Unsupervised Image Classification

FIMP: Foundation Model-Informed Message Passing for Graph Neural Networks

no code implementations • 17 Oct 2022 • Syed Asad Rizvi, Nazreen Pallikkavaliyaveetil, David Zhang, Zhuoyang Lyu, Nhi Nguyen, Haoran Lyu, Benjamin Christensen, Josue Ortega Caro, Antonio H. O. Fonseca, Emanuele Zappala, Maryam Bagherian, Christopher Averill, Chadi G. Abdallah, Amin Karbasi, Rex Ying, Maria Brbic, Rahul Madhav Dhodapkar, David van Dijk

FIMP outperforms strong baselines, demonstrating that it can effectively leverage state-of-the-art foundation models in graph tasks.

Benchmarking Graph Neural Network +1

Leveraging the Cell Ontology to classify unseen cell types

1 code implementation • Nature Communications 2021 • Sheng Wang, Angela Oliveira Pisco, Aaron McGeever, Maria Brbic, Marinka Zitnik, Spyros Darmanis, Jure Leskovec, Jim Karkanias, Russ B. Altman

Single cell technologies are rapidly generating large amounts of data that enables us to understand biological systems at single-cell resolution.

Model-Agnostic Graph Regularization for Few-Shot Learning

no code implementations • 14 Feb 2021 • Ethan Shen, Maria Brbic, Nicholas Monath, Jiaqi Zhai, Manzil Zaheer, Jure Leskovec

In this paper, we present a comprehensive empirical study on graph embedded few-shot learning.

Few-Shot Image Classification Few-Shot Learning

Open-World Semi-Supervised Learning

1 code implementation • ICLR 2022 • Kaidi Cao, Maria Brbic, Jure Leskovec

Here, we introduce a novel open-world semi-supervised learning setting that formalizes the notion that novel classes may appear in the unlabeled test data.

Image Classification Novel Object Detection +1

Concept Learners for Few-Shot Learning

2 code implementations • ICLR 2021 • Kaidi Cao, Maria Brbic, Jure Leskovec

Developing algorithms that are able to generalize to a novel task given only a few labeled examples represents a fundamental challenge in closing the gap between machine- and human-level performance.

Few-Shot Learning Fine-Grained Image Classification

Selective Sampling-based Scalable Sparse Subspace Clustering

1 code implementation • NeurIPS 2019 • Shin Matsushima, Maria Brbic

Sparse subspace clustering (SSC) represents each data point as a sparse linear combination of other data points in the dataset.

Clustering Representation Learning

Multi-view Low-rank Sparse Subspace Clustering

2 code implementations • 29 Aug 2017 • Maria Brbic, Ivica Kopriva

Most existing approaches address multi-view subspace clustering problem by constructing the affinity matrix on each view separately and afterwards propose how to extend spectral clustering algorithm to handle multi-view data.

Clustering Multi-view Subspace Clustering