Bernt Schiele

Learning Deep Representations of Fine-grained Visual Descriptions

2016 · arXiv (Cornell University)

State-of-the-art methods for zero-shot visual recognition formulate learning as a joint embedding problem of images and side information. In these formulations the current best complement to visual features are attributes: manually encoded vectors describing shared …

On Fragile Features and Batch Normalization in Adversarial Training

2022 · arXiv (Cornell University)

Modern deep learning architecture utilize batch normalization (BN) to stabilize training and improve accuracy. It has been shown that the BN layers alone are surprisingly expressive. In the context of robustness against adversarial examples, however, …

$A^{4}NT$: Author Attribute Anonymity by Adversarial Training of Neural\n Machine Translation

2017 · arXiv (Cornell University)

Text-based analysis methods allow to reveal privacy relevant author\nattributes such as gender, age and identify of the text's author. Such methods\ncan compromise the privacy of an anonymous author even when the author tries to\nremove privacy …

SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learning

2023 · arXiv (Cornell University)

The critical challenge of Semi-Supervised Learning (SSL) is how to effectively leverage the limited labeled data and massive unlabeled data to improve the model's generalization performance. In this paper, we first revisit the popular pseudo-labeling …

Wakening Past Concepts without Past Data: Class-Incremental Learning from Online Placebos

2023 · arXiv (Cornell University)

Not forgetting old class knowledge is a key challenge for class-incremental learning (CIL) when the model continuously adapts to new classes. A common technique to address this is knowledge distillation (KD), which penalizes prediction inconsistencies …