Search Results for author: Xin-Yu Zhang

Found 22 papers, 11 papers with code

Error Bounds for Generalized Group Sparsity

no code implementations8 Aug 2020 Xin-Yu Zhang

In high-dimensional statistical inference, sparsity regularizations have shown advantages in consistency and convergence rates for coefficient estimation.

Learnable Cost Volume Using the Cayley Representation

1 code implementation ECCV 2020 Taihong Xiao, Jinwei Yuan, Deqing Sun, Qifei Wang, Xin-Yu Zhang, Kehan Xu, Ming-Hsuan Yang

Cost volume is an essential component of recent deep models for optical flow estimation and is usually constructed by calculating the inner product between two feature vectors.

Optical Flow Estimation

Exploit the potential of Multi-column architecture for Crowd Counting

2 code implementations11 Jul 2020 Junhao Cheng, Zhuojun Chen, Xin-Yu Zhang, Yizhou Li, Xiaoyuan Jing

To the best of our knowledge, PSNet is the first work to explicitly address scale limitation and feature similarity in multi-column design.

Crowd Counting

Semi-Supervised Learning with Meta-Gradient

1 code implementation8 Jul 2020 Xin-Yu Zhang, Taihong Xiao, HaoLin Jia, Ming-Ming Cheng, Ming-Hsuan Yang

In this work, we propose a simple yet effective meta-learning algorithm in semi-supervised learning.

Meta-Learning Pseudo Label

Safe Screening Rules for Generalized Double Sparsity Learning

no code implementations11 Jun 2020 Xin-Yu Zhang

In a high-dimensional setting, sparse model has shown its power in computational and statistical efficiency.

Optimization and Control Computation

Dependency Aware Filter Pruning

no code implementations6 May 2020 Kai Zhao, Xin-Yu Zhang, Qi Han, Ming-Ming Cheng

Convolutional neural networks (CNNs) are typically over-parameterized, bringing considerable computational overhead and memory footprint in inference.

Towards Embodied Scene Description

no code implementations30 Apr 2020 Sinan Tan, Huaping Liu, Di Guo, Xin-Yu Zhang, Fuchun Sun

Embodiment is an important characteristic for all intelligent agents (creatures and robots), while existing scene description tasks mainly focus on analyzing images passively and the semantic understanding of the scenario is separated from the interaction between the agent and the environment.

Imitation Learning reinforcement-learning +1

Dual-discriminator GAN: A GAN way of profile face recognition

no code implementations20 Mar 2020 Xin-Yu Zhang, Yang Zhao, Hao Zhang

A wealth of angle problems occur when facial recognition is performed: At present, the feature extraction network presents eigenvectors with large differences between the frontal face and profile face recognition of the same person in many cases.

Face Recognition

Structured Sparsification with Joint Optimization of Group Convolution and Channel Shuffle

1 code implementation19 Feb 2020 Xin-Yu Zhang, Kai Zhao, Taihong Xiao, Ming-Ming Cheng, Ming-Hsuan Yang

Recent advances in convolutional neural networks(CNNs) usually come with the expense of excessive computational overhead and memory footprint.

Network Pruning

DeepDualMapper: A Gated Fusion Network for Automatic Map Extraction using Aerial Images and Trajectories

no code implementations17 Feb 2020 Hao Wu, Hanyuan Zhang, Xin-Yu Zhang, Weiwei Sun, Baihua Zheng, Yuning Jiang

We propose a deep convolutional neural network called DeepDualMapper which fuses the aerial image and trajectory data in a more seamless manner to extract the digital map.

Memorizing Comprehensively to Learn Adaptively: Unsupervised Cross-Domain Person Re-ID with Multi-level Memory

no code implementations13 Jan 2020 Xin-Yu Zhang, Dong Gong, Jiewei Cao, Chunhua Shen

Due to the lack of supervision in the target domain, it is crucial to identify the underlying similarity-and-dissimilarity relationships among the unlabelled samples in the target domain.

Person Re-Identification

Diversity Transfer Network for Few-Shot Learning

1 code implementation31 Dec 2019 Mengting Chen, Yuxin Fang, Xinggang Wang, Heng Luo, Yifeng Geng, Xin-Yu Zhang, Chang Huang, Wenyu Liu, Bo wang

The learning problem of the sample generation (i. e., diversity transfer) is solved via minimizing an effective meta-classification loss in a single-stage network, instead of the generative loss in previous works.

Few-Shot Learning

Adversarial AutoAugment

no code implementations ICLR 2020 Xin-Yu Zhang, Qiang Wang, Jian Zhang, Zhao Zhong

The augmentation policy network attempts to increase the training loss of a target network through generating adversarial augmentation policies, while the target network can learn more robust features from harder examples to improve the generalization.

Data Augmentation Image Classification

AdaSample: Adaptive Sampling of Hard Positives for Descriptor Learning

no code implementations27 Nov 2019 Xin-Yu Zhang, Le Zhang, Zao-Yi Zheng, Yun Liu, Jia-Wang Bian, Ming-Ming Cheng

The effectiveness of the triplet loss heavily relies on the triplet selection, in which a common practice is to first sample intra-class patches (positives) from the dataset for batch construction and then mine in-batch negatives to form triplets.


Res2Net: A New Multi-scale Backbone Architecture

26 code implementations2 Apr 2019 Shang-Hua Gao, Ming-Ming Cheng, Kai Zhao, Xin-Yu Zhang, Ming-Hsuan Yang, Philip Torr

We evaluate the Res2Net block on all these models and demonstrate consistent performance gains over baseline models on widely-used datasets, e. g., CIFAR-100 and ImageNet.

Image Classification Instance Segmentation +4

DNA: Deeply-supervised Nonlinear Aggregation for Salient Object Detection

1 code implementation28 Mar 2019 Yun Liu, Ming-Ming Cheng, Xin-Yu Zhang, Guang-Yu Nie, Meng Wang

Recent progress on salient object detection mainly aims at exploiting how to effectively integrate multi-scale convolutional features in convolutional neural networks (CNNs).

object-detection RGB Salient Object Detection +2

Transferring Grasp Configurations using Active Learning and Local Replanning

no code implementations22 Jul 2018 Hao Tian, Changbo Wang, Dinesh Manocha, Xin-Yu Zhang

We compute a grasp space for each part of the example object using active learning.


A Design Methodology for Efficient Implementation of Deconvolutional Neural Networks on an FPGA

1 code implementation7 May 2017 Xin-Yu Zhang, Srinjoy Das, Ojash Neopane, Ken Kreutz-Delgado

In support of such applications, various FPGA accelerator architectures have been proposed for convolutional neural networks (CNNs) that enable high performance for classification tasks at lower power than CPU and GPU processors.

General Classification Image Classification +5

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