Search Results for author: Shiming Xiang

Found 52 papers, 20 papers with code

PackDet: Packed Long-Head Object Detector

1 code implementation ECCV 2020 Kun Ding, Guojin He, Huxiang Gu, Zisha Zhong, Shiming Xiang, Chunhong Pan

State-of-the-art object detectors exploit multi-branch structure and predict objects at several different scales, although substantially boosted accuracy is acquired, low efficiency is inevitable as fragmented structure is hardware unfriendly.


Weak Distribution Detectors Lead to Stronger Generalizability of Vision-Language Prompt Tuning

1 code implementation31 Mar 2024 Kun Ding, Haojian Zhang, Qiang Yu, Ying Wang, Shiming Xiang, Chunhong Pan

The idea is realized by exploiting out-of-distribution (OOD) detection to predict whether a sample belongs to a base distribution or a novel distribution and then using the score generated by a dedicated competition based scoring function to fuse the zero-shot and few-shot classifier.

Out of Distribution (OOD) Detection

SegICL: A Universal In-context Learning Framework for Enhanced Segmentation in Medical Imaging

no code implementations25 Mar 2024 Lingdong Shen, Fangxin Shang, Yehui Yang, Xiaoshuang Huang, Shiming Xiang

Extensive experimental validation of SegICL demonstrates a positive correlation between the number of prompt samples and segmentation performance on OOD modalities and tasks.

Image Segmentation In-Context Learning +3

Defying Imbalanced Forgetting in Class Incremental Learning

no code implementations22 Mar 2024 Shixiong Xu, Gaofeng Meng, Xing Nie, Bolin Ni, Bin Fan, Shiming Xiang

This intriguing phenomenon, discovered in replay-based Class Incremental Learning (CIL), highlights the imbalanced forgetting of learned classes, as their accuracy is similar before the occurrence of catastrophic forgetting.

Class Incremental Learning Disentanglement +1

Compositional Kronecker Context Optimization for Vision-Language Models

no code implementations18 Mar 2024 Kun Ding, Xiaohui Li, Qiang Yu, Ying Wang, Haojian Zhang, Shiming Xiang

Context Optimization (CoOp) has emerged as a simple yet effective technique for adapting CLIP-like vision-language models to downstream image recognition tasks.

PAD: Self-Supervised Pre-Training with Patchwise-Scale Adapter for Infrared Images

1 code implementation13 Dec 2023 Tao Zhang, Kun Ding, Jinyong Wen, Yu Xiong, Zeyu Zhang, Shiming Xiang, Chunhong Pan

Self-supervised learning (SSL) for RGB images has achieved significant success, yet there is still limited research on SSL for infrared images, primarily due to three prominent challenges: 1) the lack of a suitable large-scale infrared pre-training dataset, 2) the distinctiveness of non-iconic infrared images rendering common pre-training tasks like masked image modeling (MIM) less effective, and 3) the scarcity of fine-grained textures making it particularly challenging to learn general image features.

Self-Supervised Learning

Cooperation Does Matter: Exploring Multi-Order Bilateral Relations for Audio-Visual Segmentation

1 code implementation11 Dec 2023 Qi Yang, Xing Nie, Tong Li, Pengfei Gao, Ying Guo, Cheng Zhen, Pengfei Yan, Shiming Xiang

For the first time, our framework explores three types of bilateral entanglements within AVS: pixel entanglement, modality entanglement, and temporal entanglement.

Change Detection Methods for Remote Sensing in the Last Decade: A Comprehensive Review

no code implementations9 May 2023 Guangliang Cheng, Yunmeng Huang, Xiangtai Li, Shuchang Lyu, Zhaoyang Xu, Qi Zhao, Shiming Xiang

We first introduce some preliminary knowledge for the change detection task, such as problem definition, datasets, evaluation metrics, and transformer basics, as well as provide a detailed taxonomy of existing algorithms from three different perspectives: algorithm granularity, supervision modes, and learning frameworks in the methodology section.

Change Detection Change detection for remote sensing images

Free Lunch for Generating Effective Outlier Supervision

no code implementations17 Jan 2023 Sen Pei, Jiaxi Sun, Richard Yi Da Xu, Bin Fan, Shiming Xiang, Gaofeng Meng

Generally, existing approaches in dealing with out-of-distribution (OOD) detection mainly focus on the statistical difference between the features of OOD and in-distribution (ID) data extracted by the classifiers.

Out of Distribution (OOD) Detection

Prompt Tuning with Soft Context Sharing for Vision-Language Models

1 code implementation29 Aug 2022 Kun Ding, Ying Wang, Pengzhang Liu, Qiang Yu, Haojian Zhang, Shiming Xiang, Chunhong Pan

Inspired by the fact that modeling task relationship by multi-task learning can usually boost performance, we propose a novel method SoftCPT (Soft Context Sharing for Prompt Tuning) to tune pre-trained vision-language models on multiple target few-shot tasks jointly.

Few-Shot Learning Multi-Task Learning

Pro-tuning: Unified Prompt Tuning for Vision Tasks

no code implementations28 Jul 2022 Xing Nie, Bolin Ni, Jianlong Chang, Gaomeng Meng, Chunlei Huo, Zhaoxiang Zhang, Shiming Xiang, Qi Tian, Chunhong Pan

To this end, we propose parameter-efficient Prompt tuning (Pro-tuning) to adapt frozen vision models to various downstream vision tasks.

Adversarial Robustness Image Classification +4

Domain Decorrelation with Potential Energy Ranking

1 code implementation25 Jul 2022 Sen Pei, Jiaxi Sun, Richard Yi Da Xu, Shiming Xiang, Gaofeng Meng

PoER helps the neural networks to capture label-related features which contain the domain information first in shallow layers and then distills the label-discriminative representations out progressively, enforcing the neural networks to be aware of the characteristic of objects and background which is vital to the generation of domain-invariant features.

Domain Generalization

AME: Attention and Memory Enhancement in Hyper-Parameter Optimization

no code implementations CVPR 2022 Nuo Xu, Jianlong Chang, Xing Nie, Chunlei Huo, Shiming Xiang, Chunhong Pan

Training Deep Neural Networks (DNNs) is inherently subject to sensitive hyper-parameters and untimely feedbacks of performance evaluation.

Image Classification object-detection +2

Adversarial Gradient Driven Exploration for Deep Click-Through Rate Prediction

no code implementations21 Dec 2021 Kailun Wu, Zhangming Chan, Weijie Bian, Lejian Ren, Shiming Xiang, Shuguang Han, Hongbo Deng, Bo Zheng

We further show that such a process is equivalent to adding an adversarial perturbation to the model input, and thereby name our proposed approach as an the Adversarial Gradient Driven Exploration (AGE).

Click-Through Rate Prediction Recommendation Systems

Alleviating Mode Collapse in GAN via Diversity Penalty Module

no code implementations5 Aug 2021 Sen Pei, Richard Yi Da Xu, Shiming Xiang, Gaofeng Meng

We compare the proposed method with Unrolled GAN (Metz et al. 2016), BourGAN (Xiao, Zhong, and Zheng 2018), PacGAN (Lin et al. 2018), VEEGAN (Srivastava et al. 2017) and ALI (Dumoulin et al. 2016) on 2D synthetic dataset, and results show that the diversity penalty module can help GAN capture much more modes of the data distribution.

Data Augmentation

HAN: An Efficient Hierarchical Self-Attention Network for Skeleton-Based Gesture Recognition

no code implementations25 Jun 2021 Jianbo Liu, Ying Wang, Shiming Xiang, Chunhong Pan

Previous methods for skeleton-based gesture recognition mostly arrange the skeleton sequence into a pseudo picture or spatial-temporal graph and apply deep Convolutional Neural Network (CNN) or Graph Convolutional Network (GCN) for feature extraction.

Gesture Recognition

BoundarySqueeze: Image Segmentation as Boundary Squeezing

1 code implementation25 May 2021 Hao He, Xiangtai Li, Yibo Yang, Guangliang Cheng, Yunhai Tong, Lubin Weng, Zhouchen Lin, Shiming Xiang

This module is used to squeeze the object boundary from both inner and outer directions, which contributes to precise mask representation.

Image Segmentation Instance Segmentation +2

Knowledge Mining and Transferring for Domain Adaptive Object Detection

1 code implementation ICCV 2021 Kun Tian, Chenghao Zhang, Ying Wang, Shiming Xiang, Chunhong Pan

Specifically, KTNet is constructed on a base detector with intrinsic knowledge mining and relational knowledge constraints.

Attribute Domain Adaptation +4

CAN: Feature Co-Action for Click-Through Rate Prediction

no code implementations11 Nov 2020 Weijie Bian, Kailun Wu, Lejian Ren, Qi Pi, Yujing Zhang, Can Xiao, Xiang-Rong Sheng, Yong-Nan Zhu, Zhangming Chan, Na Mou, Xinchen Luo, Shiming Xiang, Guorui Zhou, Xiaoqiang Zhu, Hongbo Deng

For example, a simple attempt to learn the combination of feature A and feature B <A, B> as the explicit cartesian product representation of new features can outperform previous implicit feature interaction models including factorization machine (FM)-based models and their variations.

Click-Through Rate Prediction

Spatio-Temporal Graph Structure Learning for Traffic Forecasting

no code implementations AAAI 2020 Qi Zhang, Jianlong Chang, Gaofeng Meng, Shiming Xiang, Chunhong Pan

To address these issues, we propose a novel framework named Structure Learning Convolution (SLC) that enables to extend the traditional convolutional neural network (CNN) to graph domains and learn the graph structure for traffic forecasting.

Graph structure learning Time Series +2

AugFPN: Improving Multi-scale Feature Learning for Object Detection

2 code implementations CVPR 2020 Chaoxu Guo, Bin Fan, Qian Zhang, Shiming Xiang, Chunhong Pan

In this paper, we begin by first analyzing the design defects of feature pyramid in FPN, and then introduce a new feature pyramid architecture named AugFPN to address these problems.

Object object-detection +1

Learning Where to Focus for Efficient Video Object Detection

1 code implementation ECCV 2020 Zhengkai Jiang, Yu Liu, Ceyuan Yang, Jihao Liu, Peng Gao, Qian Zhang, Shiming Xiang, Chunhong Pan

Transferring existing image-based detectors to the video is non-trivial since the quality of frames is always deteriorated by part occlusion, rare pose, and motion blur.

Object object-detection +1

FontGAN: A Unified Generative Framework for Chinese Character Stylization and De-stylization

no code implementations28 Oct 2019 Xiyan Liu, Gaofeng Meng, Shiming Xiang, Chunhong Pan

In our model, we decouple character images into style representation and content representation, which facilitates more precise control of these two types of variables, thereby improving the quality of the generated results.

Differentiable Architecture Search with Ensemble Gumbel-Softmax

no code implementations6 May 2019 Jianlong Chang, Xinbang Zhang, Yiwen Guo, Gaofeng Meng, Shiming Xiang, Chunhong Pan

For network architecture search (NAS), it is crucial but challenging to simultaneously guarantee both effectiveness and efficiency.

Neural Architecture Search

Deep Discriminative Clustering Analysis

no code implementations5 May 2019 Jianlong Chang, Yiwen Guo, Lingfeng Wang, Gaofeng Meng, Shiming Xiang, Chunhong Pan

Traditional clustering methods often perform clustering with low-level indiscriminative representations and ignore relationships between patterns, resulting in slight achievements in the era of deep learning.


LFFD: A Light and Fast Face Detector for Edge Devices

15 code implementations24 Apr 2019 Yonghao He, Dezhong Xu, Lifang Wu, Meng Jian, Shiming Xiang, Chunhong Pan

Under the new schema, the proposed method can achieve superior accuracy (WIDER FACE Val/Test -- Easy: 0. 910/0. 896, Medium: 0. 881/0. 865, Hard: 0. 780/0. 770; FDDB -- discontinuous: 0. 973, continuous: 0. 724).

Face Detection

Relation-Shape Convolutional Neural Network for Point Cloud Analysis

4 code implementations CVPR 2019 Yongcheng Liu, Bin Fan, Shiming Xiang, Chunhong Pan

Specifically, the convolutional weight for local point set is forced to learn a high-level relation expression from predefined geometric priors, between a sampled point from this point set and the others.

3D Part Segmentation 3D Point Cloud Classification +2

Progressive Sparse Local Attention for Video object detection

no code implementations ICCV 2019 Chaoxu Guo, Bin Fan, Jie Gu, Qian Zhang, Shiming Xiang, Veronique Prinet, Chunhong Pan

Instead of relying on optical flow, this paper proposes a novel module called Progressive Sparse Local Attention (PSLA), which establishes the spatial correspondence between features across frames in a local region with progressively sparser stride and uses the correspondence to propagate features.

Object object-detection +2

Structure-Aware Convolutional Neural Networks

1 code implementation NeurIPS 2018 Jianlong Chang, Jie Gu, Lingfeng Wang, Gaofeng Meng, Shiming Xiang, Chunhong Pan

Convolutional neural networks (CNNs) are inherently subject to invariable filters that can only aggregate local inputs with the same topological structures.

Action Recognition Activity Detection +5

Joint Neural Architecture Search and Quantization

no code implementations23 Nov 2018 Yukang Chen, Gaofeng Meng, Qian Zhang, Xinbang Zhang, Liangchen Song, Shiming Xiang, Chunhong Pan

Here our goal is to automatically find a compact neural network model with high performance that is suitable for mobile devices.

Model Compression Neural Architecture Search +1

Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection

1 code implementation16 Sep 2018 Yongcheng Liu, Lu Sheng, Jing Shao, Junjie Yan, Shiming Xiang, Chunhong Pan

Specifically, given the image-level annotations, (1) we first develop a weakly-supervised detection (WSD) model, and then (2) construct an end-to-end multi-label image classification framework augmented by a knowledge distillation module that guides the classification model by the WSD model according to the class-level predictions for the whole image and the object-level visual features for object RoIs.

Classification General Classification +4

Exploiting Vector Fields for Geometric Rectification of Distorted Document Images

no code implementations ECCV 2018 Gaofeng MENG, Yuanqi SU, Ying Wu, Shiming Xiang, Chunhong Pan

This paper proposes a segment-free method for geometric rectification of a distorted document image captured by a hand-held camera.

Reinforced Evolutionary Neural Architecture Search

1 code implementation1 Aug 2018 Yukang Chen, Gaofeng Meng, Qian Zhang, Shiming Xiang, Chang Huang, Lisen Mu, Xinggang Wang

To address this issue, we propose the Reinforced Evolutionary Neural Architecture Search (RE- NAS), which is an evolutionary method with the reinforced mutation for NAS.

Neural Architecture Search Semantic Segmentation

Semantic Labeling in Very High Resolution Images via a Self-Cascaded Convolutional Neural Network

1 code implementation30 Jul 2018 Yongcheng Liu, Bin Fan, Lingfeng Wang, Jun Bai, Shiming Xiang, Chunhong Pan

Specifically, for confusing manmade objects, ScasNet improves the labeling coherence with sequential global-to-local contexts aggregation.

AMVH: Asymmetric Multi-Valued Hashing

no code implementations CVPR 2017 Cheng Da, Shibiao Xu, Kun Ding, Gaofeng Meng, Shiming Xiang, Chunhong Pan

(2) A multi-integer-embedding is employed for compressing the whole database, which is modeled by binary sparse representation with fixed sparsity.

Do We Need Binary Features for 3D Reconstruction?

no code implementations14 Feb 2016 Bin Fan, Qingqun Kong, Wei Sui, Zhiheng Wang, Xinchao Wang, Shiming Xiang, Chunhong Pan, Pascal Fua

Binary features have been incrementally popular in the past few years due to their low memory footprints and the efficient computation of Hamming distance between binary descriptors.

3D Reconstruction

Segment Graph Based Image Filtering: Fast Structure-Preserving Smoothing

no code implementations ICCV 2015 Feihu Zhang, Longquan Dai, Shiming Xiang, Xiaopeng Zhang

In our SGF, we use the tree distance on the segment graph to define the internal weight function of the filtering kernel, which enables the filter to smooth out high-contrast details and textures while preserving major image structures very well.

Optical Flow Estimation Stereo Matching +1

Extraction of Virtual Baselines From Distorted Document Images Using Curvilinear Projection

no code implementations ICCV 2015 Gaofeng Meng, Zuming Huang, Yonghong Song, Shiming Xiang, Chunhong Pan

In this paper, we propose an efficient method for accurate extraction of these virtual visual cues from a curved document image.

Accurate Urban Road Centerline Extraction from VHR Imagery via Multiscale Segmentation and Tensor Voting

no code implementations25 Aug 2015 Guangliang Cheng, Feiyun Zhu, Shiming Xiang, Chunhong Pan

Finally, to overcome the ineffectiveness of current methods in the road intersection, a fitting based road centerline connection algorithm is proposed.

Road Segmentation

Cross-Modal Similarity Learning : A Low Rank Bilinear Formulation

no code implementations18 Nov 2014 Cuicui Kang, Shengcai Liao, Yonghao He, Jian Wang, Wenjia Niu, Shiming Xiang, Chunhong Pan

A new approach to the problem has been raised which intends to match features of different modalities directly.

Metric Learning Retrieval

10,000+ Times Accelerated Robust Subset Selection (ARSS)

no code implementations12 Sep 2014 Feiyun Zhu, Bin Fan, Xinliang Zhu, Ying Wang, Shiming Xiang, Chunhong Pan

Subset selection from massive data with noised information is increasingly popular for various applications.

Action Recognition Collaborative Filtering +16

Structured Sparse Method for Hyperspectral Unmixing

no code implementations19 Mar 2014 Feiyun Zhu, Ying Wang, Shiming Xiang, Bin Fan, Chunhong Pan

With this constraint, our method can learn a compact space, where highly similar pixels are grouped to share correlated sparse representations.

Hyperspectral Unmixing

Spectral Unmixing via Data-guided Sparsity

no code implementations13 Mar 2014 Feiyun Zhu, Ying Wang, Bin Fan, Gaofeng Meng, Shiming Xiang, Chunhong Pan

Hyperspectral unmixing, the process of estimating a common set of spectral bases and their corresponding composite percentages at each pixel, is an important task for hyperspectral analysis, visualization and understanding.

Hyperspectral Unmixing

Robust Hyperspectral Unmixing with Correntropy based Metric

no code implementations31 May 2013 Ying Wang, Chunhong Pan, Shiming Xiang, Feiyun Zhu

In addition, with sparsity constraints, our model can naturally generate sparse abundances.

Hyperspectral Unmixing

Cannot find the paper you are looking for? You can Submit a new open access paper.