Serge Belongie

Disentangling Nonlinear Perceptual Embeddings With Multi-Query Triplet Networks.

2016 · arXiv (Cornell University)

In typical perceptual tasks, higher-order concepts are inferred from visual features to assist with perceptual decision making. However, there is a multitude of visual concepts which can be inferred from a single stimulus. When learning …

Enhancing Adversarial Example Transferability With an Intermediate Level Attack

2019

Neural networks are vulnerable to adversarial examples, malicious inputs crafted to fool trained models. Adversarial examples often exhibit black-box transfer, meaning that adversarial examples for one model can fool another model. However, adversarial examples are …

Three New Validators and a Large-Scale Benchmark Ranking for Unsupervised Domain Adaptation

2022 · arXiv (Cornell University)

Changes to hyperparameters can have a dramatic effect on model accuracy. Thus, the tuning of hyperparameters plays an important role in optimizing machine-learning models. An integral part of the hyperparameter-tuning process is the evaluation of …

Collaborative Metric Learning

2017

Metric learning algorithms produce distance metrics that capture the important relationships among data. In this work, we study the connection between metric learning and collaborative filtering. We propose Collaborative Metric Learning (CML) which learns a …

Unbiased offline recommender evaluation for missing-not-at-random implicit feedback

2018

Implicit-feedback Recommenders (ImplicitRec) leverage positive only user-item interactions, such as clicks, to learn personalized user preferences. Recommenders are often evaluated and compared offline using datasets collected from online platforms. These platforms are subject to popularity …