Search

Building robust and generic object detection frameworks requires scaling to larger label spaces and bigger training datasets. However, it is prohibitively costly to acquire annotations for thousands of categories at a large scale. We propose a novel method that leverages the rich semantics available in recent vision and language models to localize and classify objects in unlabeled images, effectively generating pseudo labels for object detection. Starting with a generic and class-agnostic region proposal mechanism, we use vision and language models to categorize each region of an image into any object category that is required for downstream tasks. We demonstrate the value of the generated pseudo labels in two specific tasks, open-vocabulary detection, where a model needs to generalize to unseen object categories, and semi-supervised object detection, where additional unlabeled images can be used to improve the model. Our empirical evaluation shows the effectiveness of the pseudo labels in both tasks, where we outperform competitive baselines and achieve a novel state-of-the-art for open-vocabulary object detection. Our code is available at https://github.com/xiaofeng94/VL-PLM., Comment: Accepted to ECCV 2022 (with the supplementary document)

We attempt to model magnetic reconnection during the two-ribbon flare in the gravitationally stratified solar atmosphere with the Lundquist number of $S=10^6$ using 2D simulations. We found that the tearing mode instability leads to the inhomogeneous turbulence inside the reconnecting current sheet (CS) and invokes the fast phase of reconnection. Fast reconnection brings an extra dissipation of magnetic field which enhances the reconnection rate in an apparent way. The energy spectrum in the CS shows the power-law pattern and the dynamics of plasmoids governs the associated spectral index. We noticed that the energy dissipation occurs at a scale $l_{ko}$ of 100-200~km, and the associated CS thickness ranges from 1500 to 2500~km, which follows the Taylor scale $l_T=l_{ko} S^{1/6}$. The termination shock(TS) appears in the turbulent region above flare loops, which is an important contributor to heating flare loops. Substantial magnetic energy is converted into both kinetic and thermal energies via TS, and the cumulative heating rate is greater than the rate of the kinetic energy transfer. In addition, the turbulence is somehow amplified by TS, of which the amplitude is related to the local geometry of the TS., Comment: 22 pages, 10 figures; Accepted for publication in Research in Astronomy and Astrophysics

Machine translation systems are expected to cope with various types of constraints in many practical scenarios. While neural machine translation (NMT) has achieved strong performance in unconstrained cases, it is non-trivial to impose pre-specified constraints into the translation process of NMT models. Although many approaches have been proposed to address this issue, most existing methods can not satisfy the following three desiderata at the same time: (1) high translation quality, (2) high match accuracy, and (3) low latency. In this work, we propose a template-based method that can yield results with high translation quality and match accuracy and the inference speed of our method is comparable with unconstrained NMT models. Our basic idea is to rearrange the generation of constrained and unconstrained tokens through a template. Our method does not require any changes in the model architecture and the decoding algorithm. Experimental results show that the proposed template-based approach can outperform several representative baselines in both lexically and structurally constrained translation tasks., Comment: Accepted by EMNLP 2022 (main conference)

Semi-supervised video object segmentation is a fundamental yet Challenging task in computer vision. Embedding matching based CFBI series networks have achieved promising results by foreground-background integration approach. Despite its superior performance, these works exhibit distinct shortcomings, especially the false predictions caused by little appearance instances in first frame, even they could easily be recognized by previous frame. Moreover, they suffer from object's occlusion and error drifts. In order to overcome the shortcomings , we propose Collaborative Attention Memory Network with an enhanced segmentation head. We introduce a object context scheme that explicitly enhances the object information, which aims at only gathering the pixels that belong to the same category as a given pixel as its context. Additionally, a segmentation head with Feature Pyramid Attention(FPA) module is adopted to perform spatial pyramid attention structure on high-level output. Furthermore, we propose an ensemble network to combine STM network with all these new refined CFBI network. Finally, we evaluated our approach on the 2021 Youtube-VOS challenge where we obtain 6th place with an overall score of 83.5\%., Comment: Technical Report. Proposed systems attain 6th in YouTube-VOS challenge 2021

Smart cities play a vital role in the growth of a nation. In recent years, several countries have made huge investments in developing smart cities to offer sustainable living. However, there are some challenges to overcome in smart city development, such as traffic and transportation man-agement, energy and water distribution and management, air quality and waste management monitoring, etc. The capabilities of the Internet of Things (IoT) and artificial intelligence (AI) can help to achieve some goals of smart cities, and there are proven examples from some cities like Singapore, Copenhagen, etc. However, the adoption of AI and the IoT in developing countries has some challenges. The analysis of challenges hindering the adoption of AI and the IoT are very limited. This study aims to fill this research gap by analyzing the causal relationships among the challenges in smart city development, and contains several parts that conclude the previous scholars work, as well as independent research and investigation, such as data collection and analysis based on DEMATEL. In this paper, we have reviewed the literature to extract key chal-lenges for the adoption of AI and the IoT. These helped us to proceed with the investigation and analyze the adoption status. Therefore, using the PRISMA method, 10 challenges were identified from the literature review. Subsequently, determination of the causal inter-relationships among the key challenges based on expert opinions using DEMATEL is performed. This study explored the driving and dependent power of the challenges, and causal relationships between the barriers were established.

Place recognition or loop closure detection is one of the core components in a full SLAM system. In this paper, aiming at strengthening the relevancy of local neighboring points and the contextual dependency among global points simultaneously, we investigate the exploitation of transformer-based network for feature extraction, and propose a Hierarchical Transformer for Place Recognition (HiTPR). The HiTPR consists of four major parts: point cell generation, short-range transformer (SRT), long-range transformer (LRT) and global descriptor aggregation. Specifically, the point cloud is initially divided into a sequence of small cells by downsampling and nearest neighbors searching. In the SRT, we extract the local feature for each point cell. While in the LRT, we build the global dependency among all of the point cells in the whole point cloud. Experiments on several standard benchmarks demonstrate the superiority of the HiTPR in terms of average recall rate, achieving 93.71% at top 1% and 86.63% at top 1 on the Oxford RobotCar dataset for example., Comment: Accepted paper in ICRA 2022

With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm. Researchers have achieved various outcomes in the construction of BMs and the BM application in many fields. At present, there is a lack of research work that sorts out the overall progress of BMs and guides the follow-up research. In this paper, we cover not only the BM technologies themselves but also the prerequisites for BM training and applications with BMs, dividing the BM review into four parts: Resource, Models, Key Technologies and Application. We introduce 16 specific BM-related topics in those four parts, they are Data, Knowledge, Computing System, Parallel Training System, Language Model, Vision Model, Multi-modal Model, Theory&Interpretability, Commonsense Reasoning, Reliability&Security, Governance, Evaluation, Machine Translation, Text Generation, Dialogue and Protein Research. In each topic, we summarize clearly the current studies and propose some future research directions. At the end of this paper, we conclude the further development of BMs in a more general view., Comment: This report has been withdrawn by the authors due to critical issues in Section 2.3.1 of Article 2

Lexically constrained neural machine translation (NMT), which controls the generation of NMT models with pre-specified constraints, is important in many practical scenarios. Due to the representation gap between discrete constraints and continuous vectors in NMT models, most existing works choose to construct synthetic data or modify the decoding algorithm to impose lexical constraints, treating the NMT model as a black box. In this work, we propose to open this black box by directly integrating the constraints into NMT models. Specifically, we vectorize source and target constraints into continuous keys and values, which can be utilized by the attention modules of NMT models. The proposed integration method is based on the assumption that the correspondence between keys and values in attention modules is naturally suitable for modeling constraint pairs. Experimental results show that our method consistently outperforms several representative baselines on four language pairs, demonstrating the superiority of integrating vectorized lexical constraints., Comment: Accepted by ACL 2022 (main conference)

Optical flow estimation is a fundamental task in computer vision. Recent direct-regression methods using deep neural networks achieve remarkable performance improvement. However, they do not explicitly capture long-term motion correspondences and thus cannot handle large motions effectively. In this paper, inspired by the traditional matching-optimization methods where matching is introduced to handle large displacements before energy-based optimizations, we introduce a simple but effective global matching step before the direct regression and develop a learning-based matching-optimization framework, namely GMFlowNet. In GMFlowNet, global matching is efficiently calculated by applying argmax on 4D cost volumes. Additionally, to improve the matching quality, we propose patch-based overlapping attention to extract large context features. Extensive experiments demonstrate that GMFlowNet outperforms RAFT, the most popular optimization-only method, by a large margin and achieves state-of-the-art performance on standard benchmarks. Thanks to the matching and overlapping attention, GMFlowNet obtains major improvements on the predictions for textureless regions and large motions. Our code is made publicly available at https://github.com/xiaofeng94/GMFlowNet, Comment: Accepted to CVPR 2022 (with additional figures)

In this paper, we characterize the possible cofinalities of the least $\lambda$-strongly compact cardinal. We show that, on the one hand, for any regular cardinal, $\delta$, that carries a $\lambda$-complete uniform ultrafilter, it is consistent, relative to the existence of a supercompact cardinal above $\delta$, that the least $\lambda$-strongly compact cardinal has cofinality $\delta$. On the other hand, provably the cofinality of the least $\lambda$-strongly compact cardinal always carries a $\lambda$-complete uniform ultrafilter., Comment: 15 pages