Xiaolin Wei

Xiaolin Wei

Auto-generated profile, based on publicly available information

Xiaolin Wei

Meituan Inc., Beijing, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 January 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
Weiqing MinWeiqing Min
Weiqing Min
ZWZhiling Wang
Zhiling Wang
YLYuxin Liu
Yuxin Liu
MLMengjiang Luo
Mengjiang Luo
LKLiping Kang
Liping Kang
SJShuqiang Jiang
Shuqiang Jiang
Food recognition plays an important role in food choice and intake, which is essential to the health and well‐being of humans. It is thus of importance to the computer vision community, and can further support many food-oriented vision and multimodal tasks, e.g., food detection and segmentation, cross-modal recipe retrieval and generation. Unfortunately, we have witnessed remarkable advancements in generic visual recognition for released large-scale datasets, yet largely lags in the food domain. In this paper, we introduce Food2K, which is the largest food recognition dataset with 2,000 categories and over 1 million images. Compared with existing food recognition datasets, Food2K bypasses them in both categories and images by one order of magnitude, and thus establishes a new challenging benchmark to develop advanced models for food visual representation learning. Furthermore, we propose a deep progressive region enhancement network for food recognition, which mainly consists of two components, namely progressive local feature learning and region feature enhancement. The former adopts improved progressive training to learn diverse and complementary local features, while the latter utilizes self-attention to incorporate richer context with multiple scales into local features for further local feature enhancement. Extensive experiments on Food2K demonstrate the effectiveness of our proposed method. More importantly, we have verified better generalization ability of Food2K in various tasks, including food image recognition, food image retrieval, cross-modal recipe retrieval, food detection and segmentation. Food2K can be further explored to benefit more food-relevant tasks including emerging and more complex ones (e.g., nutritional understanding of food), and the trained models on Food2K can be expected as backbones to improve the performance of more food-relevant tasks. We also hope Food2K can serve as a large scale fine-grained visual recognition benchmark, and contributes to the development of large scale fine-grained visual analysis.

18 February 2022 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
JLJinlong Li
Jinlong Li
ZJZequn Jie
Zequn Jie
XWXu Wang
Xu Wang
YZYu Zhou
Yu Zhou
XWXiaolin Wei
Xiaolin Wei
LMLin Ma
Lin Ma
Most of the existing semantic segmentation approaches with image-level class labels as supervision, highly rely on the initial class activation map (CAM) generated from the standard classification network. In this paper, a novel ‘`Progressive Patch Learning’' approach is proposed to improve the local details extraction of the classification, producing the CAM better covering the whole object rather than only the most discriminative regions as in CAMs obtained in conventional classification models. ‘`Patch Learning’' destructs the feature maps into patches and independently processes each local patch in parallel before the final aggregation. Such a mechanism enforces the network to find weak information from the scattered discriminative local parts, achieving enhanced local details sensitivity. ‘`Progressive Patch Learning’' further extends the feature destruction and patch learning to multi-level granularities in a progressive manner. Cooperating with a multi-stage optimization strategy, such a ‘`Progressive Patch Learning’' mechanism implicitly provides the model with the feature extraction ability across different locality-granularities. As an alternative to the implicit multi-granularity progressive fusion approach, we additionally propose an explicit method to simultaneously fuse features from different granularites in a single model, further enhancing the CAM quality on the full object coverage. Our proposed method achieves outstanding performance on the PASCAL VOC 2012 dataset e.g., with 69.6% mIoU on the test set), which surpasses most existing weakly supervised semantic segmentation methods.

22 October 2022
Verified
Book Chapter
Closed access
PDF file
TWTong Wu
Tong Wu
GGGuangyu Gao
Guangyu Gao
JHJunshi Huang
Junshi Huang
XWXiaolin Wei
Xiaolin Wei
XWXiaoming Wei
Xiaoming Wei
CLChi Harold Liu
Chi Harold Liu

7 October 2024 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
BLBo Li
Bo Li
FPFengguang Peng
Fengguang Peng
THTianrui Hui
Tianrui Hui
XWXiaoming Wei
Xiaoming Wei
XWXiaolin Wei
Xiaolin Wei
SLSi Liu
Si Liu
The goal of RGB-Thermal (RGB-T) tracking is to utilize the synergistic and complementary strengths of RGB and TIR modalities to enhance tracking in diverse situations, with cross-modal interaction being a crucial element. Earlier methods often simply combine the features of the RGB and TIR search frames, leading to a coarse interaction that also introduced unnecessary background noise. Many other approaches sample candidate boxes from search frames and apply different fusion techniques to individual pairs of RGB and TIR boxes, which confines cross-modal interactions to local areas and results in insufficient context modeling. Additionally, mining video temporal contexts is also under-explored in RGB-T tracking. To alleviate these limitations, we propose a novel Template-Bridged Search region Interaction (TBSI) module that exploits templates as the medium to bridge the cross-modal interaction between RGB and TIR search regions by gathering and distributing target-relevant object and environment contexts. An Illumination Guided Fusion (IGF) module is designed to adaptively fuse RGB and TIR search region tokens with a global illumination factor. Furthermore, in the inference stage, we also propose an efficient Target-Preserved Template Updating (TPTU) strategy, leveraging the temporal context within video sequences to accommodate the target’s appearance change. Our proposed modules are integrated into a ViT backbone for joint feature extraction, search-template matching, and cross-modal interaction. Extensive experiments on three popular RGB-T tracking benchmarks demonstrate our method achieves new state-of-the-art performances.

26 June 2023 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
ZFZhengcong Fei
Zhengcong Fei
MFMingyuan Fan
Mingyuan Fan
LZLi Zhu
Li Zhu
JHJunshi Huang
Junshi Huang
XWXiaoming Wei
Xiaoming Wei
XWXiaolin Wei
Xiaolin Wei
It is well believed that the higher uncertainty in a word of the caption, the more inter-correlated context information is required to determine it. However, current image captioning methods usually consider the generation of all words in a sentence sequentially and equally. In this paper, we propose an uncertainty-aware image captioning framework, which parallelly and iteratively operates insertion of discontinuous candidate words between existing words from easy to difficult until converged. We hypothesize that high-uncertainty words in a sentence need more prior information to make a correct decision and should be produced at a later stage. The resulting non-autoregressive hierarchy makes the caption generation explainable and intuitive. Specifically, we utilize an image-conditioned bag-of-word model to measure the word uncertainty and apply a dynamic programming algorithm to construct the training pairs. During inference, we devise an uncertainty-adaptive parallel beam search technique that yields an empirically logarithmic time complexity. Extensive experiments on the MS COCO benchmark reveal that our approach outperforms the strong baseline and related methods on both captioning quality as well as decoding speed.

30 September 2021 in arXiv
Verified
Preprint
Open access
PDF file
XCXiangxiang Chu
Xiangxiang Chu
ZTZhi Tian
Zhi Tian
YWYuqing Wang
Yuqing Wang
BZBo Zhang
Bo Zhang
HRHaibing Ren
Haibing Ren
CSChunhua Shen
Chunhua Shen
Very recently, a variety of vision transformer architectures for dense prediction tasks have been proposed and they show that the design of spatial attention is critical to their success in these tasks. In this work, we revisit the design of the spatial attention and demonstrate that a carefully-devised yet simple spatial attention mechanism performs favourably against the state-of-the-art schemes. As a result, we propose two vision transformer architectures, namely, Twins-PCPVT and Twins-SVT. Our proposed architectures are highly-efficient and easy to implement, only involving matrix multiplications that are highly optimized in modern deep learning frameworks. More importantly, the proposed architectures achieve excellent performance on a wide range of visual tasks, including image level classification as well as dense detection and segmentation. The simplicity and strong performance suggest that our proposed architectures may serve as stronger backbones for many vision tasks. Our code is released at https://github.com/Meituan-AutoML/Twins .