11 results on '"Shi, Hengcan"'
Search Results
2. Unpaired referring expression grounding via bidirectional cross-modal matching
- Author
-
Shi, Hengcan, Hayat, Munawar, and Cai, Jianfei
- Published
- 2023
- Full Text
- View/download PDF
3. Learning Offset Probability Distribution for Accurate Object Detection.
- Author
-
Qiu, Heqian, Li, Hongliang, Wu, Qingbo, Shi, Hengcan, Wang, Lanxiao, Meng, Fanman, and Xu, Linfeng
- Subjects
DISTRIBUTION (Probability theory) - Abstract
Object detection combines object classification and object localization problems. Current object detection methods heavily depend on regression networks to locate objects, which are optimized with various regression loss functions to predict offsets between candidate boxes and objects. However, these regression losses are difficult to assign the appropriate penalties for samples with large offset errors, resulting in suboptimal regression networks and inaccurate object offsets. In this article, we consider object location as offset bin classification problem, and propose a distance-aware offset bin classification network optimized with multiple binary cross entropy losses to learn various offset probability distribution, including single label distribution and distance-aware label distribution. On one hand, it provides gradient contributions for different samples based on the bounded probability instead of previous incalculable offset error. On the other hand, it explores the distance correlations between discrete offset bins to facilitate network learning. Specifically, we discretize the continuous offset into a number of bins, and predict the probability of each offset bin, in which the probability should be higher for the offset bin closer to the target offsets, and vice versa. Furthermore, we propose an expectation-based offset prediction and a hierarchical focusing method to improve the precision of prediction. We conduct extensive experiments to evaluate the effectiveness of our method. In addition, our method can be conveniently and flexibly inserted into existing object detection methods, which consistently achieves a large gain based on popular anchor-based and anchor-free methods on the PASCAL VOC, MS-COCO, KITTI, and CrowdHuman datasets. Code will be released at: https://github.com/QiuHeqian/DBC. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
4. Open-Vocabulary Object Detection via Scene Graph Discovery
- Author
-
Shi, Hengcan, Hayat, Munawar, and Cai, Jianfei
- Subjects
FOS: Computer and information sciences ,Computer Vision and Pattern Recognition (cs.CV) ,Computer Science - Computer Vision and Pattern Recognition - Abstract
In recent years, open-vocabulary (OV) object detection has attracted increasing research attention. Unlike traditional detection, which only recognizes fixed-category objects, OV detection aims to detect objects in an open category set. Previous works often leverage vision-language (VL) training data (e.g., referring grounding data) to recognize OV objects. However, they only use pairs of nouns and individual objects in VL data, while these data usually contain much more information, such as scene graphs, which are also crucial for OV detection. In this paper, we propose a novel Scene-Graph-Based Discovery Network (SGDN) that exploits scene graph cues for OV detection. Firstly, a scene-graph-based decoder (SGDecoder) including sparse scene-graph-guided attention (SSGA) is presented. It captures scene graphs and leverages them to discover OV objects. Secondly, we propose scene-graph-based prediction (SGPred), where we build a scene-graph-based offset regression (SGOR) mechanism to enable mutual enhancement between scene graph extraction and object localization. Thirdly, we design a cross-modal learning mechanism in SGPred. It takes scene graphs as bridges to improve the consistency between cross-modal embeddings for OV object classification. Experiments on COCO and LVIS demonstrate the effectiveness of our approach. Moreover, we show the ability of our model for OV scene graph detection, while previous OV scene graph generation methods cannot tackle this task.
- Published
- 2023
5. Improving object proposals with top-down cues
- Author
-
Li, Wei, Li, Hongliang, Luo, Bing, Shi, Hengcan, Wu, Qingbo, and Ngan, King Ngi
- Published
- 2017
- Full Text
- View/download PDF
6. Person re-identification based on multi-region-set ensembles
- Author
-
Li, Wei, Huang, Chao, Luo, Bing, Meng, Fanman, Song, Tiecheng, and Shi, Hengcan
- Published
- 2016
- Full Text
- View/download PDF
7. Class Enhancement Losses with Pseudo Labels for Zero-shot Semantic Segmentation
- Author
-
Dao, Son Duy, Shi, Hengcan, Phung, Dinh, and Cai, Jianfei
- Subjects
FOS: Computer and information sciences ,Computer Vision and Pattern Recognition (cs.CV) ,Computer Science - Computer Vision and Pattern Recognition - Abstract
Recent mask proposal models have significantly improved the performance of zero-shot semantic segmentation. However, the use of a `background' embedding during training in these methods is problematic as the resulting model tends to over-learn and assign all unseen classes as the background class instead of their correct labels. Furthermore, they ignore the semantic relationship of text embeddings, which arguably can be highly informative for zero-shot prediction as seen classes may have close relationship with unseen classes. To this end, this paper proposes novel class enhancement losses to bypass the use of the background embbedding during training, and simultaneously exploit the semantic relationship between text embeddings and mask proposals by ranking the similarity scores. To further capture the relationship between seen and unseen classes, we propose an effective pseudo label generation pipeline using pretrained vision-language model. Extensive experiments on several benchmark datasets show that our method achieves overall the best performance for zero-shot semantic segmentation. Our method is flexible, and can also be applied to the challenging open-vocabulary semantic segmentation problem.
- Published
- 2023
8. Transformer Scale Gate for Semantic Segmentation
- Author
-
Shi, Hengcan, Hayat, Munawar, and Cai, Jianfei
- Subjects
FOS: Computer and information sciences ,Computer Vision and Pattern Recognition (cs.CV) ,Computer Science - Computer Vision and Pattern Recognition - Abstract
Effectively encoding multi-scale contextual information is crucial for accurate semantic segmentation. Existing transformer-based segmentation models combine features across scales without any selection, where features on sub-optimal scales may degrade segmentation outcomes. Leveraging from the inherent properties of Vision Transformers, we propose a simple yet effective module, Transformer Scale Gate (TSG), to optimally combine multi-scale features.TSG exploits cues in self and cross attentions in Vision Transformers for the scale selection. TSG is a highly flexible plug-and-play module, and can easily be incorporated with any encoder-decoder-based hierarchical vision Transformer architecture. Extensive experiments on the Pascal Context and ADE20K datasets demonstrate that our feature selection strategy achieves consistent gains.
- Published
- 2022
9. Hierarchical Context Features Embedding for Object Detection.
- Author
-
Qiu, Heqian, Li, Hongliang, Wu, Qingbo, Meng, Fanman, Xu, Linfeng, Ngan, King Ngi, and Shi, Hengcan
- Abstract
Pixel-level segmentation has been widely used to improve object detection. Most of the existing methods refine detection features by adding the constraint of the segmentation branch or by simply embedding high-level segmentation features into detection features within the local receptive field. However, noisy segmentation features are unavoidable in real-word applications and can easily cause false positives. To address this problem, we propose a novel hierarchical context embedding module to effectively embed segmentation features into detection features. The idea of this module is to capture hierarchical context information that includes local objects or parts and nonlocal context features by learning multiple attention maps, and subsequently utilize interdependencies between features to recalibrate noisy segmentation features. Furthermore, we use this module in the proposed gated encoder-decoder network that adaptively aggregates feature maps of different resolutions based on the gate mechanism so that we can embed multiscale segmentation feature maps into detection features for more accurate detection of objects of all sizes. Experimental results demonstrate the effectiveness of the proposed method on the Pascal VOC 2012Seg dataset, the Pascal VOC dataset and the MS COCO dataset. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
10. Hierarchical Parsing Net: Semantic Scene Parsing From Global Scene to Objects.
- Author
-
Shi, Hengcan, Li, Hongliang, Meng, Fanman, Wu, Qingbo, Xu, Linfeng, and Ngan, King Ngi
- Abstract
This paper proposes a novel Hierarchical Parsing Net (HPN) for semantic scene parsing. Unlike previous methods, which separately classify each object, HPN leverages global scene semantic information and the context among multiple objects to enhance scene parsing. On the one hand, HPN uses the global scene category to constrain the semantic consistency between the scene and each object. On the other hand, the context among all objects is also modeled to avoid incompatible object predictions. Specifically, HPN consists of four steps. In the first step, we extract scene and local appearance features. Based on these appearance features, the second step is to encode a contextual feature for each object, which models both the scene-object context (the context between the scene and each object) and the interobject context (the context among different objects). In the third step, we classify the global scene and then use the scene classification loss and a backpropagation algorithm to constrain the scene feature encoding. In the fourth step, a label map for scene parsing is generated from the local appearance and contextual features. Our model outperforms many state-of-the-art deep scene parsing networks on five scene parsing databases. [ABSTRACT FROM AUTHOR]
- Published
- 2018
- Full Text
- View/download PDF
11. A2RMNet: Adaptively Aspect Ratio Multi-Scale Network for Object Detection in Remote Sensing Images.
- Author
-
Qiu, Heqian, Li, Hongliang, Wu, Qingbo, Meng, Fanman, Ngan, King Ngi, and Shi, Hengcan
- Subjects
REMOTE sensing ,IMAGE analysis ,ART & state ,OPTICAL remote sensing - Abstract
Object detection is a significant and challenging problem in the study area of remote sensing and image analysis. However, most existing methods are easy to miss or incorrectly locate objects due to the various sizes and aspect ratios of objects. In this paper, we propose a novel end-to-end Adaptively Aspect Ratio Multi-Scale Network (A 2 RMNet) to solve this problem. On the one hand, we design a multi-scale feature gate fusion network to adaptively integrate the multi-scale features of objects. This network is composed of gate fusion modules, refine blocks and region proposal networks. On the other hand, an aspect ratio attention network is leveraged to preserve the aspect ratios of objects, which alleviates the excessive shape distortions of objects caused by aspect ratio changes during training. Experiments show that the proposed A 2 RMNet significantly outperforms the previous state of the arts on the DOTA dataset, NWPU VHR-10 dataset, RSOD dataset and UCAS-AOD dataset by 5.73 % , 7.06 % , 3.27 % and 2.24 % , respectively. [ABSTRACT FROM AUTHOR]
- Published
- 2019
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.