Journal Article•
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
TL;DR: This article introduced a unified framework that converts all text-based language problems into a text-to-text format and compared pre-training objectives, architectures, unlabeled data sets, transfer approaches, and other factors on dozens of language understanding tasks.
Abstract: Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has given rise to a diversity of approaches, methodology, and practice. In this paper, we explore the landscape of transfer learning techniques for NLP by introducing a unified framework that converts all text-based language problems into a text-to-text format. Our systematic study compares pre-training objectives, architectures, unlabeled data sets, transfer approaches, and other factors on dozens of language understanding tasks. By combining the insights from our exploration with scale and our new ``Colossal Clean Crawled Corpus'', we achieve state-of-the-art results on many benchmarks covering summarization, question answering, text classification, and more. To facilitate future work on transfer learning for NLP, we release our data set, pre-trained models, and code.
Citations
More filters
01 Nov 2020
TL;DR: A topic assistant (TA) including three modules is proposed that is compatible with various Transformer-based models and user-friendly since i) TA is a plug-and-play model that does not break any structure of the original Transformer network, making users easily fine-tune Transformer+TA based on a well pre-trained model.
Abstract: ive document summarization is a comprehensive task including document understanding and summary generation, in which area Transformer-based models have achieved the state-of-the-art performance. Compared with Transformers, topic models are better at learning explicit document semantics, and hence could be integrated into Transformers to further boost their performance. To this end, we rearrange and explore the semantics learned by a topic model, and then propose a topic assistant (TA) including three modules. TA is compatible with various Transformer-based models and user-friendly since i) TA is a plug-and-play model that does not break any structure of the original Transformer network, making users easily fine-tune Transformer+TA based on a well pre-trained model; ii) TA only introduces a small number of extra parameters. Experimental results on three datasets demonstrate that TA is able to improve the performance of several Transformer-based models.
40 citations
Posted Content•
TL;DR: This paper proposes a novel model-extraction attack, namely Hermes Attack, which is the first attack to fully steal the whole victim DNN model and shows that the stolen models have the same inference accuracy as the original ones (i.e., lossless inference accuracy).
Abstract: Deep Neural Networks (DNNs) models become one of the most valuable enterprise assets due to their critical roles in all aspects of applications. With the trend of privatization deployment of DNN models, the data leakage of the DNN models is becoming increasingly serious and widespread. All existing model-extraction attacks can only leak parts of targeted DNN models with low accuracy or high overhead. In this paper, we first identify a new attack surface -- unencrypted PCIe traffic, to leak DNN models. Based on this new attack surface, we propose a novel model-extraction attack, namely Hermes Attack, which is the first attack to fully steal the whole victim DNN model. The stolen DNN models have the same hyper-parameters, parameters, and semantically identical architecture as the original ones. It is challenging due to the closed-source CUDA runtime, driver, and GPU internals, as well as the undocumented data structures and the loss of some critical semantics in the PCIe traffic. Additionally, there are millions of PCIe packets with numerous noises and chaos orders. Our Hermes Attack addresses these issues by huge reverse engineering efforts and reliable semantic reconstruction, as well as skillful packet selection and order correction. We implement a prototype of the Hermes Attack, and evaluate two sequential DNN models (i.e., MINIST and VGG) and one consequential DNN model (i.e., ResNet) on three NVIDIA GPU platforms, i.e., NVIDIA Geforce GT 730, NVIDIA Geforce GTX 1080 Ti, and NVIDIA Geforce RTX 2080 Ti. The evaluation results indicate that our scheme is able to efficiently and completely reconstruct ALL of them with making inferences on any one image. Evaluated with Cifar10 test dataset that contains 10,000 images, the experiment results show that the stolen models have the same inference accuracy as the original ones (i.e., lossless inference accuracy).
40 citations
TL;DR: Wang et al. as discussed by the authors designed a local perception Swin transformer (LPSW) backbone to enhance the local perception of the network and to improve the detection accuracy of small-scale objects.
Abstract: Remote sensing image object detection and instance segmentation are widely valued research fields. A convolutional neural network (CNN) has shown defects in the object detection of remote sensing images. In recent years, the number of studies on transformer-based models increased, and these studies achieved good results. However, transformers still suffer from poor small object detection and unsatisfactory edge detail segmentation. In order to solve these problems, we improved the Swin transformer based on the advantages of transformers and CNNs, and designed a local perception Swin transformer (LPSW) backbone to enhance the local perception of the network and to improve the detection accuracy of small-scale objects. We also designed a spatial attention interleaved execution cascade (SAIEC) network framework, which helped to strengthen the segmentation accuracy of the network. Due to the lack of remote sensing mask datasets, the MRS-1800 remote sensing mask dataset was created. Finally, we combined the proposed backbone with the new network framework and conducted experiments on this MRS-1800 dataset. Compared with the Swin transformer, the proposed model improved the mask AP by 1.7%, mask APS by 3.6%, AP by 1.1% and APS by 4.6%, demonstrating its effectiveness and feasibility.
40 citations
01 Jun 2021
TL;DR: An improved video-and-language pre-training method that first adds automatically-extracted dense region captions from the video frames as auxiliary text input to alleviate the temporal misalignment issue and incorporates an entropy minimization-based constrained attention loss.
Abstract: Leveraging large-scale unlabeled web videos such as instructional videos for pre-training followed by task-specific finetuning has become the de facto approach for many video-and-language tasks. However, these instructional videos are very noisy, the accompanying ASR narrations are often incomplete, and can be irrelevant to or temporally misaligned with the visual content, limiting the performance of the models trained on such data. To address these issues, we propose an improved video-and-language pre-training method that first adds automatically-extracted dense region captions from the video frames as auxiliary text input, to provide informative visual cues for learning better video and language associations. Second, to alleviate the temporal misalignment issue, our method incorporates an entropy minimization-based constrained attention loss, to encourage the model to automatically focus on the correct caption from a pool of candidate ASR captions. Our overall approach is named DeCEMBERT (Dense Captions and Entropy Minimization). Comprehensive experiments on three video-and-language tasks (text-to-video retrieval, video captioning, and video question answering) across five datasets demonstrate that our approach outperforms previous state-of-the-art methods. Ablation studies on pre-training and downstream tasks show that adding dense captions and constrained attention loss help improve the model performance. Lastly, we also provide attention visualization to show the effect of applying the proposed constrained attention loss.
40 citations
TL;DR: A survey of text ranking with neural network architectures known as transformers can be found in this paper, where the authors provide a synthesis of existing work as a single point of entry for practitioners who wish to gain a better understanding of how to apply transformers to text ranking problems and researchers who desire to pursue work in this area.
Abstract: The goal of text ranking is to generate an ordered list of texts retrieved from a corpus in response to a query. Although the most common formulation of text ranking is search, instances of the task can also be found in many natural language processing applications. This survey provides an overview of text ranking with neural network architectures known as transformers, of which BERT is the best-known example. The combination of transformers and self-supervised pretraining has been responsible for a paradigm shift in natural language processing (NLP), information retrieval (IR), and beyond. In this survey, we provide a synthesis of existing work as a single point of entry for practitioners who wish to gain a better understanding of how to apply transformers to text ranking problems and researchers who wish to pursue work in this area. We cover a wide range of modern techniques, grouped into two high-level categories: transformer models that perform reranking in multi-stage architectures and dense retrieval techniques that perform ranking directly. There are two themes that pervade our survey: techniques for handling long documents, beyond typical sentence-by-sentence processing in NLP, and techniques for addressing the tradeoff between effectiveness (i.e., result quality) and efficiency (e.g., query latency, model and index size). Although transformer architectures and pretraining techniques are recent innovations, many aspects of how they are applied to text ranking are relatively well understood and represent mature techniques. However, there remain many open research questions, and thus in addition to laying out the foundations of pretrained transformers for text ranking, this survey also attempts to prognosticate where the field is heading.
40 citations