no code implementations • 19 Sep 2016 • Mengnan Shi, Fei Qin, Qixiang Ye, Zhenjun Han, Jianbin Jiao
In this paper, we explore the redundancy in convolutional neural network, which scales with the complexity of vision tasks.
1 code implementation • CVPR 2017 • Yanzhao Zhou, Qixiang Ye, Qiang Qiu, Jianbin Jiao
DCNNs using ARFs, referred to as Oriented Response Networks (ORNs), can produce within-class rotation-invariant deep features while maintaining inter-class discrimination for classification tasks.
Ranked #83 on Image Classification on CIFAR-100 (using extra training data)
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.
1 code implementation • ICCV 2017 • Yi Zhu, Yanzhao Zhou, Qixiang Ye, Qiang Qiu, Jianbin Jiao
Weakly supervised object localization remains challenging, where only image labels instead of bounding boxes are available during training.
Ranked #2 on Weakly Supervised Object Detection on MS COCO
2 code implementations • CVPR 2018 • Weijian Deng, Liang Zheng, Qixiang Ye, Guoliang Kang, Yi Yang, Jianbin Jiao
To this end, we propose to preserve two types of unsupervised similarities, 1) self-similarity of an image before and after translation, and 2) domain-dissimilarity of a translated source image and a target image.
1 code implementation • CVPR 2018 • Yanzhao Zhou, Yi Zhu, Qixiang Ye, Qiang Qiu, Jianbin Jiao
Motivated by this, we first design a process to stimulate peaks to emerge from a class response map.
Ranked #11 on Image-level Supervised Instance Segmentation on PASCAL VOC 2012 val (using extra training data)
General Classification Image-level Supervised Instance Segmentation +3
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.
no code implementations • 26 Nov 2018 • Weijian Deng, Liang Zheng, Qixiang Ye, Yi Yang, Jianbin Jiao
It first preserves two types of unsupervised similarity, namely, self-similarity of an image before and after translation, and domain-dissimilarity of a translated source image and a target image.
no code implementations • 3 Dec 2018 • Weijian Deng, Liang Zheng, Jianbin Jiao
When aligning the distributions in the embedding space, SCA enforces a similarity-preserving constraint to maintain class-level relations among the source and target images, i. e., if a source image and a target image are of the same class label, their corresponding embeddings are supposed to be aligned nearby, and vise versa.
1 code implementation • 2 Jan 2019 • Caijing Miao, Lingxi Xie, Fang Wan, Chi Su, Hongye Liu, Jianbin Jiao, Qixiang Ye
In particular, the advantage of CHR is more significant in the scenarios with fewer positive training samples, which demonstrates its potential application in real-world security inspection.
1 code implementation • CVPR 2018 • Fang Wan, Pengxu Wei, Zhenjun Han, Jianbin Jiao, Qixiang Ye
Weakly supervised object detection is a challenging task when provided with image category supervision but required to learn, at the same time, object locations and object detectors.
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.
1 code implementation • CVPR 2020 • Yi Zhu, Fengda Zhu, Zhaohuan Zhan, Bingqian Lin, Jianbin Jiao, Xiaojun Chang, Xiaodan Liang
Benefiting from the collaborative learning of the L-mem and the V-mem, our CMN is able to explore the memory about the decision making of historical navigation actions which is for the current step.
1 code implementation • 7 Jul 2020 • Yunjie Tian, Chang Liu, Lingxi Xie, Jianbin Jiao, Qixiang Ye
The search cost of neural architecture search (NAS) has been largely reduced by weight-sharing methods.
1 code implementation • ECCV 2020 • Boyu Yang, Chang Liu, Bohao Li, Jianbin Jiao, Qixiang Ye
Few-shot segmentation is challenging because objects within the support and query images could significantly differ in appearance and pose.
1 code implementation • 8 Nov 2020 • Chang Liu, Yunjie Tian, Jianbin Jiao, Qixiang Ye
Conventional networks for object skeleton detection are usually hand-crafted.
no code implementations • ICCV 2021 • Yi Zhu, Yue Weng, Fengda Zhu, Xiaodan Liang, Qixiang Ye, Yutong Lu, Jianbin Jiao
Vision-Dialog Navigation (VDN) requires an agent to ask questions and navigate following the human responses to find target objects.
1 code implementation • IEEE Transactions on Image Processing 2021 • Binghao Liu, Jianbin Jiao, Qixiang Ye
HFA is formulated as a bilinear model, which takes charge of the pixel-wise dense correlation (bilinear feature activation) between query and support images in a systematic way.
4 code implementations • ICCV 2021 • Zhiliang Peng, Wei Huang, Shanzhi Gu, Lingxi Xie, YaoWei Wang, Jianbin Jiao, Qixiang Ye
Within Convolutional Neural Network (CNN), the convolution operations are good at extracting local features but experience difficulty to capture global representations.
Ranked #325 on Image Classification on ImageNet
1 code implementation • CVPR 2021 • Binghao Liu, Yao Ding, Jianbin Jiao, Xiangyang Ji, Qixiang Ye
Encouraging progress in few-shot semantic segmentation has been made by leveraging features learned upon base classes with sufficient training data to represent novel classes with few-shot examples.
Ranked #68 on Few-Shot Semantic Segmentation on COCO-20i (1-shot)
2 code implementations • CVPR 2021 • Zonghao Guo, Chang Liu, Xiaosong Zhang, Jianbin Jiao, Xiangyang Ji, Qixiang Ye
Detecting oriented and densely packed objects remains challenging for spatial feature aliasing caused by the intersection of reception fields between objects.
Ranked #34 on Object Detection In Aerial Images on DOTA (using extra training data)
2 code implementations • 7 Jul 2021 • Xumeng Han, Xuehui Yu, Guorong Li, Jian Zhao, Gang Pan, Qixiang Ye, Jianbin Jiao, Zhenjun Han
While extensive research has focused on the framework design and loss function, this paper shows that sampling strategy plays an equally important role.
1 code implementation • 17 Sep 2021 • Weixi Zhao, Yunjie Tian, Qixiang Ye, Jianbin Jiao, Weiqiang Wang
Exploiting relations among 2D joints plays a crucial role yet remains semi-developed in 2D-to-3D pose estimation.
1 code implementation • 6 Oct 2021 • Zhiliang Peng, Wei Huang, Zonghao Guo, Xiaosong Zhang, Jianbin Jiao, Qixiang Ye
We propose to jointly optimize empirical risks of the unbalanced and balanced domains and approximate their domain divergence by intra-class and inter-class distances, with the aim to adapt models trained on the long-tailed distribution to general distributions in an interpretable way.
1 code implementation • 25 Nov 2021 • Yunjie Tian, Lingxi Xie, Xiaopeng Zhang, Jiemin Fang, Haohang Xu, Wei Huang, Jianbin Jiao, Qi Tian, Qixiang Ye
In this paper, we propose a self-supervised visual representation learning approach which involves both generative and discriminative proxies, where we focus on the former part by requiring the target network to recover the original image based on the mid-level features.
Ranked #63 on Semantic Segmentation on Cityscapes test
1 code implementation • 29 Nov 2021 • Mengnan Shi, Chang Liu, Qixiang Ye, Jianbin Jiao
Gating modules have been widely explored in dynamic network pruning to reduce the run-time computational cost of deep neural networks while preserving the representation of features.
no code implementations • 5 Dec 2021 • Yunjie Tian, Lingxi Xie, Jiemin Fang, Jianbin Jiao, Qixiang Ye, Qi Tian
In this paper, we build the search algorithm upon a complicated search space with long-distance connections, and show that existing weight-sharing search algorithms mostly fail due to the existence of \textbf{interleaved connections}.
no code implementations • 31 Dec 2021 • Xuehui Yu, Di wu, Qixiang Ye, Jianbin Jiao, Zhenjun Han
As a result, we propose a point self-refinement approach that iteratively updates point annotations in a self-paced way.
1 code implementation • 27 Mar 2022 • Yunjie Tian, Lingxi Xie, Jiemin Fang, Mengnan Shi, Junran Peng, Xiaopeng Zhang, Jianbin Jiao, Qi Tian, Qixiang Ye
The past year has witnessed a rapid development of masked image modeling (MIM).
1 code implementation • CVPR 2023 • Yunjie Tian, Lingxi Xie, Jihao Qiu, Jianbin Jiao, YaoWei Wang, Qi Tian, Qixiang Ye
iTPN is born with two elaborated designs: 1) The first pre-trained feature pyramid upon vision transformer (ViT).
no code implementations • 16 Dec 2022 • Wei Sun, Chengao Liu, Linyan Zhang, Yu Li, Pengxu Wei, Chang Liu, Jialing Zou, Jianbin Jiao, Qixiang Ye
Optimizing a convolutional neural network (CNN) for camouflaged object detection (COD) tends to activate local discriminative regions while ignoring complete object extent, causing the partial activation issue which inevitably leads to missing or redundant regions of objects.
1 code implementation • CVPR 2023 • Wei Huang, Zhiliang Peng, Li Dong, Furu Wei, Jianbin Jiao, Qixiang Ye
Lightweight ViT models limited by the model capacity, however, benefit little from those pre-training mechanisms.
1 code implementation • ICCV 2023 • Di wu, Pengfei Chen, Xuehui Yu, Guorong Li, Zhenjun Han, Jianbin Jiao
Object detection via inaccurate bounding boxes supervision has boosted a broad interest due to the expensive high-quality annotation data or the occasional inevitability of low annotation quality (\eg tiny objects).
no code implementations • 22 Nov 2023 • Guangming Cao, Xuehui Yu, Wenwen Yu, Xumeng Han, Xue Yang, Guorong Li, Jianbin Jiao, Zhenjun Han
In this study, we introduce the P2RBox network, which leverages point annotations and a mask generator to create mask proposals, followed by filtration through our Inspector Module and Constrainer Module.
1 code implementation • 19 Dec 2023 • Jing Cui, Yufei Han, Yuzhe ma, Jianbin Jiao, Junge Zhang
Our algorithm, BadRL, strategically chooses state observations with high attack values to inject triggers during training and testing, thereby reducing the chances of detection.
no code implementations • 26 Dec 2023 • Zhaoyang Wei, Pengfei Chen, Xuehui Yu, Guorong Li, Jianbin Jiao, Zhenjun Han
In this paper, we introduce a cost-effective category-specific segmenter using SAM.
no code implementations • 29 Dec 2023 • Xiaoqian Liu, Jianbin Jiao, Junge Zhang
Decision-making is a dynamic process requiring perception, memory, and reasoning to make choices and find optimal policies.
no code implementations • 18 Jan 2024 • Zipeng Wang, Xuehui Yu, Xumeng Han, Wenwen Yu, Zhixun Huang, Jianbin Jiao, Zhenjun Han
Nevertheless, weakly supervised semantic segmentation methods are proficient in utilizing intra-class feature consistency to capture the boundary contours of the same semantic regions.
1 code implementation • 24 Jan 2024 • Yunjie Tian, Tianren Ma, Lingxi Xie, Jihao Qiu, Xi Tang, Yuan Zhang, Jianbin Jiao, Qi Tian, Qixiang Ye
In this study, we establish a baseline for a new task named multimodal multi-round referring and grounding (MRG), opening up a promising direction for instance-level multimodal dialogues.
2 code implementations • 30 Jan 2024 • Xuehui Yu, Pengfei Chen, Kuiran Wang, Xumeng Han, Guorong Li, Zhenjun Han, Qixiang Ye, Jianbin Jiao
CPR reduces the semantic variance by selecting a semantic centre point in a neighbourhood region to replace the initial annotated point.
1 code implementation • 30 Jan 2024 • Jianbin Jiao, Xina Cheng, WeiJie Chen, Xiaoting Yin, Hao Shi, Kailun Yang
Due to the challenges in data collection, mainstream datasets of 3D human pose estimation are primarily composed of multi-view video data collected in laboratory environments, which contains rich spatial-temporal correlation information besides the image frame content.