In this paper, we introduce a new building dataset and propose a novel domain generalization method to facilitate the development of building extraction from high-resolution remote sensing images. The problem with the current building datasets involves that they lack diversity, the quality of the labels is unsatisfactory, and they are hardly used to train a building extraction model with good generalization ability, so as to properly evaluate the real performance of a model in practical scenes. To address these issues, we built a diverse, large-scale, and high-quality building dataset named the WHU-Mix building dataset, which is more practice-oriented. The WHU-Mix building dataset consists of a training/validation set containing 43,727 diverse images collected from all over the world, and a test set containing 8402 images from five other cities on five continents. In addition, to further improve the generalization ability of a building extraction model, we propose a domain generalization method named batch style mixing (BSM), which can be embedded as an efficient plug-and-play module in the frond-end of a building extraction model, providing the model with a progressively larger data distribution to learn data-invariant knowledge. The experiments conducted in this study confirmed the potential of the WHU-Mix building dataset to improve the performance of a building extraction model, resulting in a 6-36% improvement in mIoU, compared to the other existing datasets. The adverse impact of the inaccurate labels in the other datasets can cause about 20% IoU decrease. The experiments also confirmed the high performance of the proposed BSM module in enhancing the generalization ability and robustness of a model, exceeding the baseline model without domain generalization by 13% and the recent domain generalization methods by 4-15% in mIoU.
相關內容
Annotating data for supervised learning is expensive and tedious, and we want to do as little of it as possible. To make the most of a given "annotation budget" we can turn to active learning (AL) which aims to identify the most informative samples in a dataset for annotation. Active learning algorithms are typically uncertainty-based or diversity-based. Both have seen success in image classification, but fall short when it comes to object detection. We hypothesise that this is because: (1) it is difficult to quantify uncertainty for object detection as it consists of both localisation and classification, where some classes are harder to localise, and others are harder to classify; (2) it is difficult to measure similarities for diversity-based AL when images contain different numbers of objects. We propose a two-stage active learning algorithm Plug and Play Active Learning (PPAL) that overcomes these difficulties. It consists of (1) Difficulty Calibrated Uncertainty Sampling, in which we used a category-wise difficulty coefficient that takes both classification and localisation into account to re-weight object uncertainties for uncertainty-based sampling; (2) Category Conditioned Matching Similarity to compute the similarities of multi-instance images as ensembles of their instance similarities. PPAL is highly generalisable because it makes no change to model architectures or detector training pipelines. We benchmark PPAL on the MS-COCO and Pascal VOC datasets using different detector architectures and show that our method outperforms the prior state-of-the-art. Code is available at //github.com/ChenhongyiYang/PPAL
Recently, data heterogeneity among the training datasets on the local clients (a.k.a., Non-IID data) has attracted intense interest in Federated Learning (FL), and many personalized federated learning methods have been proposed to handle it. However, the distribution shift between the training dataset and testing dataset on each client is never considered in FL, despite it being general in real-world scenarios. We notice that the distribution shift (a.k.a., out-of-distribution generalization) problem under Non-IID federated setting becomes rather challenging due to the entanglement between personalized and spurious information. To tackle the above problem, we elaborate a general dual-regularized learning framework to explore the personalized invariance, compared with the exsiting personalized federated learning methods which are regularized by a single baseline (usually the global model). Utilizing the personalized invariant features, the developed personalized models can efficiently exploit the most relevant information and meanwhile eliminate spurious information so as to enhance the out-of-distribution generalization performance for each client. Both the theoretical analysis on convergence and OOD generalization performance and the results of extensive experiments demonstrate the superiority of our method over the existing federated learning and invariant learning methods, in diverse out-of-distribution and Non-IID data cases.
The rapid development of aspect-based sentiment analysis (ABSA) within recent decades shows great potential for real-world society. The current ABSA works, however, are mostly limited to the scenario of a single text piece, leaving the study in dialogue contexts unexplored. In this work, we introduce a novel task of conversational aspect-based sentiment quadruple analysis, namely DiaASQ, aiming to detect the sentiment quadruple of \emph{target-aspect-opinion-sentiment} in a dialogue. DiaASQ bridges the gap between fine-grained sentiment analysis and conversational opinion mining. We manually construct a large-scale high-quality DiaASQ dataset in both Chinese and English languages. We deliberately develop a neural model to benchmark the task, which advances in effectively performing end-to-end quadruple prediction, and manages to incorporate rich dialogue-specific and discourse feature representations for better cross-utterance quadruple extraction. We finally point out several potential future works to facilitate the follow-up research of this new task.
Generative models have recently started to outperform extractive models in Open Domain Question Answering, largely by leveraging their decoder to attend over multiple encoded passages and combining their information. However, generative models tend to be larger than extractive models due to the need for a decoder, run slower during inference due to auto-regressive decoder beam search, and their generated output often suffers from hallucinations. We propose to extend transformer encoders with the ability to fuse information from multiple passages, using global representation to provide cross-sample attention over all tokens across samples. Furthermore, we propose an alternative answer span probability calculation to better aggregate answer scores in the global space of all samples. Using our proposed method, we outperform the current state-of-the-art method by $2.5$ Exact Match score on the Natural Question dataset while using only $25\%$ of parameters and $35\%$ of the latency during inference, and $4.4$ Exact Match on WebQuestions dataset. When coupled with synthetic data augmentation, we outperform larger models on the TriviaQA dataset as well. The latency and parameter savings of our method make it particularly attractive for open-domain question answering, as these models are often compute-intensive.
Event Detection (ED) is the task of identifying and classifying trigger words of event mentions in text. Despite considerable research efforts in recent years for English text, the task of ED in other languages has been significantly less explored. Switching to non-English languages, important research questions for ED include how well existing ED models perform on different languages, how challenging ED is in other languages, and how well ED knowledge and annotation can be transferred across languages. To answer those questions, it is crucial to obtain multilingual ED datasets that provide consistent event annotation for multiple languages. There exist some multilingual ED datasets; however, they tend to cover a handful of languages and mainly focus on popular ones. Many languages are not covered in existing multilingual ED datasets. In addition, the current datasets are often small and not accessible to the public. To overcome those shortcomings, we introduce a new large-scale multilingual dataset for ED (called MINION) that consistently annotates events for 8 different languages; 5 of them have not been supported by existing multilingual datasets. We also perform extensive experiments and analysis to demonstrate the challenges and transferability of ED across languages in MINION that in all call for more research effort in this area.
Text-video retrieval is an important multi-modal learning task, where the goal is to retrieve the most relevant video for a given text query. Recently, pre-trained models, e.g., CLIP, show great potential on this task. However, as pre-trained models are scaling up, fully fine-tuning them on text-video retrieval datasets has a high risk of overfitting. Moreover, in practice, it would be costly to train and store a large model for each task. To overcome the above issues, we present a novel $\textbf{Cross-Modal Adapter}$ for parameter-efficient fine-tuning. Inspired by adapter-based methods, we adjust the pre-trained model with a few parameterization layers. However, there are two notable differences. First, our method is designed for the multi-modal domain. Secondly, it allows early cross-modal interactions between CLIP's two encoders. Although surprisingly simple, our approach has three notable benefits: (1) reduces $\textbf{99.6}\%$ of fine-tuned parameters, and alleviates the problem of overfitting, (2) saves approximately 30% of training time, and (3) allows all the pre-trained parameters to be fixed, enabling the pre-trained model to be shared across datasets. Extensive experiments demonstrate that, without bells and whistles, it achieves superior or comparable performance compared to fully fine-tuned methods on MSR-VTT, MSVD, VATEX, ActivityNet, and DiDeMo datasets. The code will be available at \url{//github.com/LeapLabTHU/Cross-Modal-Adapter}.
The Zero-Shot Learning (ZSL) task attempts to learn concepts without any labeled data. Unlike traditional classification/detection tasks, the evaluation environment is provided unseen classes never encountered during training. As such, it remains both challenging, and promising on a variety of fronts, including unsupervised concept learning, domain adaptation, and dataset drift detection. Recently, there have been a variety of approaches towards solving ZSL, including improved metric learning methods, transfer learning, combinations of semantic and image domains using, e.g. word vectors, and generative models to model the latent space of known classes to classify unseen classes. We find many approaches require intensive training augmentation with attributes or features that may be commonly unavailable (attribute-based learning) or susceptible to adversarial attacks (generative learning). We propose combining approaches from the related person re-identification task for ZSL, with key modifications to ensure sufficiently improved performance in the ZSL setting without the need for feature or training dataset augmentation. We are able to achieve state-of-the-art performance on the CUB200 and Cars196 datasets in the ZSL setting compared to recent works, with NMI (normalized mutual inference) of 63.27 and top-1 of 61.04 for CUB200, and NMI 66.03 with top-1 82.75% in Cars196. We also show state-of-the-art results in the Generalized Zero-Shot Learning (GZSL) setting, with Harmonic Mean R-1 of 66.14% on the CUB200 dataset.
Knowledge enhanced pre-trained language models (K-PLMs) are shown to be effective for many public tasks in the literature but few of them have been successfully applied in practice. To address this problem, we propose K-AID, a systematic approach that includes a low-cost knowledge acquisition process for acquiring domain knowledge, an effective knowledge infusion module for improving model performance, and a knowledge distillation component for reducing the model size and deploying K-PLMs on resource-restricted devices (e.g., CPU) for real-world application. Importantly, instead of capturing entity knowledge like the majority of existing K-PLMs, our approach captures relational knowledge, which contributes to better-improving sentence-level text classification and text matching tasks that play a key role in question answering (QA). We conducted a set of experiments on five text classification tasks and three text matching tasks from three domains, namely E-commerce, Government, and Film&TV, and performed online A/B tests in E-commerce. Experimental results show that our approach is able to achieve substantial improvement on sentence-level question answering tasks and bring beneficial business value in industrial settings.
This paper introduces video domain generalization where most video classification networks degenerate due to the lack of exposure to the target domains of divergent distributions. We observe that the global temporal features are less generalizable, due to the temporal domain shift that videos from other unseen domains may have an unexpected absence or misalignment of the temporal relations. This finding has motivated us to solve video domain generalization by effectively learning the local-relation features of different timescales that are more generalizable, and exploiting them along with the global-relation features to maintain the discriminability. This paper presents the VideoDG framework with two technical contributions. The first is a new deep architecture named the Adversarial Pyramid Network, which improves the generalizability of video features by capturing the local-relation, global-relation, and cross-relation features progressively. On the basis of pyramid features, the second contribution is a new and robust approach of adversarial data augmentation that can bridge different video domains by improving the diversity and quality of augmented data. We construct three video domain generalization benchmarks in which domains are divided according to different datasets, different consequences of actions, or different camera views, respectively. VideoDG consistently outperforms the combinations of previous video classification models and existing domain generalization methods on all benchmarks.
Invariant approaches have been remarkably successful in tackling the problem of domain generalization, where the objective is to perform inference on data distributions different from those used in training. In our work, we investigate whether it is possible to leverage domain information from the unseen test samples themselves. We propose a domain-adaptive approach consisting of two steps: a) we first learn a discriminative domain embedding from unsupervised training examples, and b) use this domain embedding as supplementary information to build a domain-adaptive model, that takes both the input as well as its domain into account while making predictions. For unseen domains, our method simply uses few unlabelled test examples to construct the domain embedding. This enables adaptive classification on any unseen domain. Our approach achieves state-of-the-art performance on various domain generalization benchmarks. In addition, we introduce the first real-world, large-scale domain generalization benchmark, Geo-YFCC, containing 1.1M samples over 40 training, 7 validation, and 15 test domains, orders of magnitude larger than prior work. We show that the existing approaches either do not scale to this dataset or underperform compared to the simple baseline of training a model on the union of data from all training domains. In contrast, our approach achieves a significant improvement.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191