相关论文: ImageNet Pre-training also Transfers Non-Robustnes…

Deep neural networks (DNNs) have been shown to be vulnerable to adversarial attacks -- subtle, perceptually indistinguishable perturbations of inputs that change the response of the model. In the context of vision, we hypothesize that an…

Pre-training models on Imagenet or other massive datasets of real images has led to major advances in computer vision, albeit accompanied with shortcomings related to curation cost, privacy, usage rights, and ethical issues. In this paper,…

Adversarial training is the industry standard for producing models that are robust to small adversarial perturbations. However, machine learning practitioners need models that are robust to other kinds of changes that occur naturally, such…

Recently, fine-tuning pre-trained language models (e.g., multilingual BERT) to downstream cross-lingual tasks has shown promising results. However, the fine-tuning process inevitably changes the parameters of the pre-trained model and…

Current state-of-the-art visual recognition systems usually rely on the following pipeline: (a) pretraining a neural network on a large-scale dataset (e.g., ImageNet) and (b) finetuning the network weights on a smaller, task-specific…

The pretrain-finetune paradigm has shown outstanding performance on many applications of deep learning, where a model is pre-trained on a upstream large dataset (e.g. ImageNet), and is then fine-tuned to different downstream tasks. Though…

The current mainstream and state-of-the-art anomaly detection (AD) methods are substantially established on pretrained feature networks yielded by ImageNet pretraining. However, regardless of supervised or self-supervised pretraining, the…

Robustness to natural distribution shifts has seen remarkable progress thanks to recent pre-training strategies combined with better fine-tuning methods. However, such fine-tuning assumes access to large amounts of labelled data, and the…

Deep neural networks are often considered opaque systems, prompting the need for explainability methods to improve trust and accountability. Existing approaches typically attribute test-time predictions either to input features (e.g.,…

Deep learning methods for chest X-ray interpretation typically rely on pretrained models developed for ImageNet. This paradigm assumes that better ImageNet architectures perform better on chest X-ray tasks and that ImageNet-pretrained…

Pre-training language models (LMs) on large-scale unlabeled text data makes the model much easier to achieve exceptional downstream performance than their counterparts directly trained on the downstream tasks. In this work, we study what…

Machine-learning models demand periodic updates to improve their average accuracy, exploiting novel architectures and additional data. However, a newly updated model may commit mistakes the previous model did not make. Such…

We introduce a framework to measure how biases change before and after fine-tuning a large scale visual recognition model for a downstream task. Deep learning models trained on increasing amounts of data are known to encode societal biases.…

The growing use of Machine Learning has produced significant advances in many fields. For image-based tasks, however, the use of deep learning remains challenging in small datasets. In this article, we review, evaluate and compare the…

Neural networks are susceptible to adversarial perturbations that are transferable across different models. In this paper, we introduce a novel model alignment technique aimed at improving a given source model's ability in generating…

Machine learning has demonstrated remarkable performance over finite datasets, yet whether the scores over the fixed benchmarks can sufficiently indicate the model's performance in the real world is still in discussion. In reality, an ideal…

Adversarial robustness refers to a model's ability to resist perturbation of inputs, while distribution robustness evaluates the performance of the model under data shifts. Although both aim to ensure reliable performance, prior work has…

The adversarial robustness of a neural network mainly relies on two factors: model capacity and anti-perturbation ability. In this paper, we study the anti-perturbation ability of the network from the feature maps of convolutional layers.…

In transfer learning, only the last part of the networks - the so-called head - is often fine-tuned. Representation similarity analysis shows that the most significant change still occurs in the head even if all weights are updatable.…

Neural networks have a number of shortcomings. Amongst the severest ones is the sensitivity to distribution shifts which allows models to be easily fooled into wrong predictions by small perturbations to inputs that are often imperceivable…