Alan Yuille

Mitigating Adversarial Effects Through Randomization

2017 · arXiv (Cornell University)

Convolutional neural networks have demonstrated high accuracy on various tasks in recent years. However, they are extremely vulnerable to adversarial examples. For example, imperceptible perturbations added to clean images can cause convolutional neural networks to …

Intriguing properties of adversarial training at scale

2019 · arXiv (Cornell University)

Adversarial training is one of the main defenses against adversarial attacks. In this paper, we provide the first rigorous study on diagnosing elements of adversarial training, which reveals two intriguing properties. First, we study the …

CO2: Consistent Contrast for Unsupervised Visual Representation Learning

2020 · arXiv (Cornell University)

Contrastive learning has been adopted as a core method for unsupervised visual representation learning. Without human annotation, the common practice is to perform an instance discrimination task: Given a query image crop, this task labels …

Making Your First Choice: To Address Cold Start Problem in Vision Active Learning

2022 · arXiv (Cornell University)

Active learning promises to improve annotation efficiency by iteratively selecting the most important data to be annotated first. However, we uncover a striking contradiction to this promise: active learning fails to select data as efficiently …

Source-Free and Image-Only Unsupervised Domain Adaptation for Category Level Object Pose Estimation

2024 · arXiv (Cornell University)

We consider the problem of source-free unsupervised category-level pose estimation from only RGB images to a target domain without any access to source domain data or 3D annotations during adaptation. Collecting and annotating real-world 3D …

Generation and Comprehension of Unambiguous Object Descriptions

2016

We propose a method that can generate an unambiguous description (known as a referring expression) of a specific object or region in an image, and which can also comprehend or interpret such an expression to …

PreCo: A Large-scale Dataset in Preschool Vocabulary for Coreference Resolution

2018

We introduce PreCo, a large-scale English dataset for coreference resolution. The dataset is designed to embody the core challenges in coreference, such as entity representation, by alleviating the challenge of low overlap between training and …