1 code implementation • 10 Jul 2024 • Lingzhi Pan, Tong Zhang, Bingyuan Chen, Qi Zhou, Wei Ke, Sabine Süsstrunk, Mathieu Salzmann
Our method searches latent spaces capable of generating inpainted regions that exhibit high fidelity to user-provided prompts while maintaining coherence with the background.
no code implementations • 24 May 2024 • Chak Fong Chong, Jielong Guo, Xu Yang, Wei Ke, Yapeng Wang
However, the powerful Mixup sample-mixing data augmentation cannot be well utilized to address this challenge, as it cannot perform linear interpolation on the unknown labels to construct augmented samples.
1 code implementation • CVPR 2024 • Yanhao Wu, Tong Zhang, Wei Ke, Congpei Qiu, Sabine Susstrunk, Mathieu Salzmann
Subsequently, we introduce a context-aware feature learning strategy, which encodes object patterns without relying on their specific context by aggregating object features across various scenes.
no code implementations • 13 Mar 2024 • ZiCheng Zhang, Tong Zhang, Yi Zhu, Jianzhuang Liu, Xiaodan Liang, Qixiang Ye, Wei Ke
To mitigate these issues, we propose a Language-Driven Visual Consensus (LDVC) approach, fostering improved alignment of semantic and visual information. Specifically, we leverage class embeddings as anchors due to their discrete and abstract nature, steering vision features toward class embeddings.
1 code implementation • 30 Jan 2024 • Chak Fong Chong, Xinyi Fang, Jielong Guo, Yapeng Wang, Wei Ke, Chan-Tong Lam, Sio-Kei Im
Large-scale image datasets are often partially labeled, where only a few categories' labels are known for each image.
1 code implementation • 29 Dec 2023 • Xiangyu Xiong, Yue Sun, Xiaohong Liu, Wei Ke, Chan-Tong Lam, Jiangang Chen, Mingfeng Jiang, Mingwei Wang, Hui Xie, Tong Tong, Qinquan Gao, Hao Chen, Tao Tan
Experimental results show that DisGAN consistently outperforms the GAN-based augmentation methods with explainable binary classification.
2 code implementations • International Conference on Neural Information Processing 2023 • Chak Fong Chong, Xu Yang, Tenglong Wang, Wei Ke, Yapeng Wang
A single model submitted to the competition server for the official evaluation achieves mAUC 91. 82% on the test set, which is the highest single model score in the leaderboard and literature.
Ranked #1 on
Multi-Label Classification
on CheXpert
1 code implementation • 24 Nov 2023 • Xiangyu Xiong, Yue Sun, Xiaohong Liu, Chan-Tong Lam, Tong Tong, Hao Chen, Qinquan Gao, Wei Ke, Tao Tan
Although current data augmentation methods are successful to alleviate the data insufficiency, conventional augmentation are primarily intra-domain while advanced generative adversarial networks (GANs) generate images remaining uncertain, particularly in small-scale datasets.
no code implementations • 19 Apr 2023 • Jie Hou, Jiakang Li, Xiaokang Peng, Wei Ke, Yonggang Lu
During the process of finding the next medoid, the RMS algorithm is based on a neighborhood defined by KNN, while the original Medoid-Shift is based on a neighborhood defined by a distance parameter.
no code implementations • 12 Apr 2023 • Shiwei Zhang, Zhengzheng Wang, Qing Liu, Fei Wang, Wei Ke, Tong Zhang
This paper presents a new annotation method called Sparse Annotation (SA) for crowd counting, which reduces human labeling efforts by sparsely labeling individuals in an image.
1 code implementation • 29 Mar 2023 • Congpei Qiu, Tong Zhang, Wei Ke, Mathieu Salzmann, Sabine Süsstrunk
Dense Self-Supervised Learning (SSL) methods address the limitations of using image-level feature representations when handling images with multiple objects.
1 code implementation • CVPR 2023 • Yanhao Wu, Tong Zhang, Wei Ke, Sabine Süsstrunk, Mathieu Salzmann
In this paper, we introduce an SSL strategy that leverages positive pairs in both the spatial and temporal domain.
no code implementations • 4 Dec 2022 • ZiCheng Zhang, Yi Zhu, Jianzhuang Liu, Xiaodan Liang, Wei Ke
Then in the Sentence-Mask Alignment (SMA) module, the masks are weighted by the sentence embedding to localize the referred object, and finally projected back to aggregate the pixels for the target.
1 code implementation • CVPR 2022 • Tong Zhang, Congpei Qiu, Wei Ke, Sabine Süsstrunk, Mathieu Salzmann
In essence, this strategy ignores the fact that two crops may truly contain different image information, e. g., background and small objects, and thus tends to restrain the diversity of the learned representations.
1 code implementation • 30 Oct 2021 • Qing Liu, Haotian Liu, Wei Ke, Yixiong Liang
It reassembles features in a dimension-reduced feature space and simultaneously aggregates multiple features inside a large predefined region into multiple target features.
no code implementations • 18 Oct 2021 • Shiwei Zhang, Wei Ke, Lin Yang
Weakly supervised object detection (WSOD) is a challenging task that requires simultaneously learn object classifiers and estimate object locations under the supervision of image category labels.
no code implementations • 14 Jan 2021 • Ka-Hou Chan, Sio-Kei Im, Wei Ke
This article introduces a multiple classifier method to improve the performance of concatenate-designed neural networks, such as ResNet and DenseNet, with the purpose to alleviate the pressure on the final classifier.
1 code implementation • ECCV 2020 • Zhekun Luo, Devin Guillory, Baifeng Shi, Wei Ke, Fang Wan, Trevor Darrell, Huijuan Xu
Weakly-supervised action localization requires training a model to localize the action segments in the video given only video level action label.
Ranked #9 on
Weakly Supervised Action Localization
on THUMOS’14
3 code implementations • CVPR 2020 • Wei Ke, Tianliang Zhang, Zeyi Huang, Qixiang Ye, Jianzhuang Liu, Dong Huang
In this paper, we propose a Multiple Instance Learning (MIL) approach that selects anchors and jointly optimizes the two modules of a CNN-based object detector.
Ranked #119 on
Object Detection
on COCO test-dev
no code implementations • 18 Apr 2019 • Qing Liu, Xiaopeng Hong, Wei Ke, Zailiang Chen, Beiji Zou
In this paper, we propose a novel segmentation approach, named Cartesian-polar dual-domain network (DDNet), which for the first time considers the complementary of the Cartesian domain and the polar domain.
1 code implementation • CVPR 2019 • Fang Wan, Chang Liu, Wei Ke, Xiangyang Ji, Jianbin Jiao, Qixiang Ye
Weakly supervised object detection (WSOD) is a challenging task when provided with image category supervision but required to simultaneously learn object locations and object detectors.
Ranked #15 on
Weakly Supervised Object Detection
on PASCAL VOC 2007
1 code implementation • 28 Mar 2019 • Zeyi Huang, Wei Ke, Dong Huang
Our approach (1) operates along both the spatial and channels dimensions of the feature maps; (2) requires no extra training on hard samples, no extra network parameters for attention estimation, and no testing overheads.
no code implementations • ECCV 2018 • Chang Liu, Wei Ke, Fei Qin, Qixiang Ye
Hinted by this, we formalize a Linear Span framework, and propose Linear Span Network (LSN) modified by Linear Span Units (LSUs), which minimize the reconstruction error of convolutional network.
1 code implementation • 17 Jul 2018 • Wei Ke, Jie Chen, Jianbin Jiao, Guoying Zhao, Qixiang Ye
The end-to-end deep learning approach, referred to as a side-output residual network (SRN), leverages the output residual units (RUs) to fit the errors between the object ground-truth symmetry and the side-outputs of multiple stages.
1 code implementation • CVPR 2017 • Wei Ke, Jie Chen, Jianbin Jiao, Guoying Zhao, Qixiang Ye
By stacking RUs in a deep-to-shallow manner, SRN exploits the 'flow' of errors among multiple scales to ease the problems of fitting complex outputs with limited layers, suppressing the complex backgrounds, and effectively matching object symmetry of different scales.