Search Results for author: Li Niu

Found 38 papers, 20 papers with code

Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similarity

1 code implementation NeurIPS 2021 Yan Liu, Zhijie Zhang, Li Niu, Junjie Chen, Liqing Zhang

Specifically, the ability of using mask prior to help detect objects is learned from base categories and transferred to novel categories.

Object Detection Semantic Similarity +1

Weak-shot Semantic Segmentation by Transferring Semantic Affinity and Boundary

no code implementations4 Oct 2021 Siyuan Zhou, Li Niu, Jianlou Si, Chen Qian, Liqing Zhang

As a result, we find that pixel-level annotation of base categories can facilitate affinity learning and propagation, leading to higher-quality CAMs of novel categories.

Weakly-Supervised Semantic Segmentation

HYouTube: Video Harmonization Dataset

1 code implementation18 Sep 2021 Xinyuan Lu, Shengyuan Huang, Li Niu, Wenyan Cong, Liqing Zhang

In this work, we construct a new video harmonization dataset HYouTube by adjusting the foreground of real videos to create synthetic composite videos.

Video Harmonization

High-Resolution Image Harmonization via Collaborative Dual Transformations

no code implementations14 Sep 2021 Wenyan Cong, Xinhao Tao, Li Niu, Jing Liang, Xuesong Gao, Qihao Sun, Liqing Zhang

Given a composite image, image harmonization aims to adjust the foreground to make it compatible with the background.

Visible Watermark Removal via Self-calibrated Localization and Background Refinement

1 code implementation8 Aug 2021 Jing Liang, Li Niu, Fengjun Guo, Teng Long, Liqing Zhang

In the refinement stage, we integrate multi-level features to improve the texture quality of watermarked area.

Multi-Task Learning

OPA: Object Placement Assessment Dataset

1 code implementation5 Jul 2021 Liu Liu, Bo Zhang, Jiangtong Li, Li Niu, Qingyang Liu, Liqing Zhang

Image composition aims to generate realistic composite image by inserting an object from one image into another background image, where the placement (e. g., location, size, occlusion) of inserted object may be unreasonable, which would significantly degrade the quality of the composite image.

Making Images Real Again: A Comprehensive Survey on Deep Image Composition

1 code implementation28 Jun 2021 Li Niu, Wenyan Cong, Liu Liu, Yan Hong, Bo Zhang, Jing Liang, Liqing Zhang

Datasets and codes for image composition are summarized at https://github. com/bcmi/Awesome-Image-Composition.

End-to-End Video Object Detection with Spatial-Temporal Transformers

no code implementations23 May 2021 Lu He, Qianyu Zhou, Xiangtai Li, Li Niu, Guangliang Cheng, Xiao Li, Wenxuan Liu, Yunhai Tong, Lizhuang Ma, Liqing Zhang

Recently, DETR and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors.

Optical Flow Estimation Video Object Detection

Shadow Generation for Composite Image in Real-world Scenes

1 code implementation21 Apr 2021 Yan Hong, Li Niu, Jianfu Zhang, Liqing Zhang

Then, we propose a novel shadow generation network SGRNet, which consists of a shadow mask prediction stage and a shadow filling stage.

Inharmonious Region Localization

2 code implementations19 Apr 2021 Jing Liang, Li Niu, Liqing Zhang

The advance of image editing techniques allows users to create artistic works, but the manipulated regions may be incompatible with the background.

Image Composition Assessment with Saliency-augmented Multi-pattern Pooling

1 code implementation7 Apr 2021 Bo Zhang, Li Niu, Liqing Zhang

Image composition assessment is crucial in aesthetic assessment, which aims to assess the overall composition quality of a given image.

Aesthetics Quality Assessment

Deep Image Harmonization by Bridging the Reality Gap

1 code implementation31 Mar 2021 Wenyan Cong, Junyan Cao, Li Niu, Jianfu Zhang, Xuesong Gao, Zhiwei Tang, Liqing Zhang

To leverage both real-world images and rendered images, we propose a cross-domain harmonization network CharmNet to bridge the domain gap between two domains.

Transfer Learning

Parallel Multi-Resolution Fusion Network for Image Inpainting

no code implementations ICCV 2021 Wentao Wang, Jianfu Zhang, Li Niu, Haoyu Ling, Xue Yang, Liqing Zhang

Conventional deep image inpainting methods are based on auto-encoder architecture, in which the spatial details of images will be lost in the down-sampling process, leading to the degradation of generated results.

Image Inpainting

Disentangled Information Bottleneck

1 code implementation14 Dec 2020 Ziqi Pan, Li Niu, Jianfu Zhang, Liqing Zhang

The information bottleneck (IB) method is a technique for extracting information that is relevant for predicting the target random variable from the source random variable, which is typically implemented by optimizing the IB Lagrangian that balances the compression and prediction terms.

Adversarial Attack Out-of-Distribution Detection

From Pixel to Patch: Synthesize Context-aware Features for Zero-shot Semantic Segmentation

1 code implementation25 Sep 2020 Zhangxuan Gu, Siyuan Zhou, Li Niu, Zihan Zhao, Liqing Zhang

Thus, we focus on zero-shot semantic segmentation, which aims to segment unseen objects with only category-level semantic representations provided for unseen categories.

Image Classification Semantic Segmentation +1

BargainNet: Background-Guided Domain Translation for Image Harmonization

1 code implementation19 Sep 2020 Wenyan Cong, Li Niu, Jianfu Zhang, Jing Liang, Liqing Zhang

Therefore, we propose an image harmonization network with a novel domain code extractor and well-tailored triplet losses, which could capture the background domain information to guide the foreground harmonization.


Weak-shot Fine-grained Classification via Similarity Transfer

1 code implementation NeurIPS 2021 Junjie Chen, Li Niu, Liu Liu, Liqing Zhang

In this setting, we propose a method called SimTrans to transfer pairwise semantic similarity from base categories to novel categories.

Classification General Classification +2

DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta

no code implementations18 Sep 2020 Yan Hong, Li Niu, Jianfu Zhang, Jing Liang, Liqing Zhang

In this work, we propose a novel Delta Generative Adversarial Network (DeltaGAN), which consists of a reconstruction subnetwork and a generation subnetwork.

Image Generation

Context-aware Feature Generation for Zero-shot Semantic Segmentation

2 code implementations16 Aug 2020 Zhangxuan Gu, Siyuan Zhou, Li Niu, Zihan Zhao, Liqing Zhang

In this paper, we propose a novel context-aware feature generation method for zero-shot segmentation named CaGNet.

Semantic Segmentation Word Embeddings +1

F2GAN: Fusing-and-Filling GAN for Few-shot Image Generation

1 code implementation5 Aug 2020 Yan Hong, Li Niu, Jianfu Zhang, Weijie Zhao, Chen Fu, Liqing Zhang

In this paper, we propose a Fusing-and-Filling Generative Adversarial Network (F2GAN) to generate realistic and diverse images for a new category with only a few images.

Image Generation

Beyond without Forgetting: Multi-Task Learning for Classification with Disjoint Datasets

no code implementations15 Mar 2020 Yan Hong, Li Niu, Jianfu Zhang, Liqing Zhang

To address these issues, we propose our MTL with Selective Augmentation (MTL-SA) method to select the training samples in unlabeled datasets with confident pseudo labels and close data distribution to the labeled dataset.

Classification General Classification +1

MatchingGAN: Matching-based Few-shot Image Generation

1 code implementation7 Mar 2020 Yan Hong, Li Niu, Jianfu Zhang, Liqing Zhang

Matching generator can match random vectors with a few conditional images from the same category and generate new images for this category based on the fused features.

Image Generation

Exploiting Motion Information from Unlabeled Videos for Static Image Action Recognition

no code implementations1 Dec 2019 Yiyi Zhang, Li Niu, Ziqi Pan, Meichao Luo, Jianfu Zhang, Dawei Cheng, Liqing Zhang

Specifically, the VRE module includes a proxy task which imposes pseudo motion label constraint and temporal coherence constraint on unlabeled videos, while the MRA module could predict the motion information of a static action image by exploiting unlabeled videos.

Action Recognition Self-Supervised Learning

Zero-Shot Sketch-Based Image Retrieval with Structure-aware Asymmetric Disentanglement

no code implementations29 Nov 2019 Jiangtong Li, Zhixin Ling, Li Niu, Liqing Zhang

The goal of Sketch-Based Image Retrieval (SBIR) is using free-hand sketches to retrieve images of the same category from a natural image gallery.

Sketch-Based Image Retrieval Translation

DoveNet: Deep Image Harmonization via Domain Verification

1 code implementation CVPR 2020 Wenyan Cong, Jianfu Zhang, Li Niu, Liu Liu, Zhixin Ling, Weiyuan Li, Liqing Zhang

Image composition is an important operation in image processing, but the inconsistency between foreground and background significantly degrades the quality of composite image.

Image Cropping with Composition and Saliency Aware Aesthetic Score Map

no code implementations24 Nov 2019 Yi Tu, Li Niu, Weijie Zhao, Dawei Cheng, Liqing Zhang

Aesthetic image cropping is a practical but challenging task which aims at finding the best crops with the highest aesthetic quality in an image.

Image Cropping

A Proposal-based Approach for Activity Image-to-Video Retrieval

no code implementations24 Nov 2019 Ruicong Xu, Li Niu, Jianfu Zhang, Liqing Zhang

Activity image-to-video retrieval task aims to retrieve videos containing the similar activity as the query image, which is a challenging task because videos generally have many background segments irrelevant to the activity.

Cross-Modal Retrieval Video Retrieval

Image Harmonization Dataset iHarmony4: HCOCO, HAdobe5k, HFlickr, and Hday2night

1 code implementation28 Aug 2019 Wenyan Cong, Jianfu Zhang, Li Niu, Liu Liu, Zhixin Ling, Weiyuan Li, Liqing Zhang

Image composition is an important operation in image processing, but the inconsistency between foreground and background significantly degrades the quality of composite image.

Learning from Web Data with Self-Organizing Memory Module

no code implementations CVPR 2020 Yi Tu, Li Niu, Junjie Chen, Dawei Cheng, Liqing Zhang

However, crawled web images usually have two types of noises, label noise and background noise, which induce extra difficulties in utilizing them effectively.

Image Classification

Hard Pixel Mining for Depth Privileged Semantic Segmentation

1 code implementation27 Jun 2019 Zhangxuan Gu, Li Niu, Haohua Zhao, Liqing Zhang

Specifically, we propose a novel Loss Weight Module, which outputs a loss weight map by employing two depth-related measurements of hard pixels: Depth Prediction Error and Depthaware Segmentation Error.

Curriculum Learning Depth Estimation +1

Fine-grained Classification using Heterogeneous Web Data and Auxiliary Categories

no code implementations19 Nov 2018 Li Niu, Ashok Veeraraghavan, Ashu Sabharwal

In the extreme case, given a set of test categories without any well-labeled training data, the majority of existing works can be grouped into the following two research directions: 1) crawl noisy labeled web data for the test categories as training data, which is dubbed as webly supervised learning; 2) transfer the knowledge from auxiliary categories with well-labeled training data to the test categories, which corresponds to zero-shot learning setting.

Classification General Classification +1

Webly Supervised Learning Meets Zero-Shot Learning: A Hybrid Approach for Fine-Grained Classification

no code implementations CVPR 2018 Li Niu, Ashok Veeraraghavan, Ashutosh Sabharwal

The drawbacks of the above two directions motivate us to design a new framework which can jointly leverage both web data and auxiliary labeled categories to predict the test categories that are not associated with any well-labeled training images.

Fine-Grained Image Classification General Classification +1

Learning from Noisy Web Data with Category-level Supervision

no code implementations CVPR 2018 Li Niu, Qingtao Tang, Ashok Veeraraghavan, Ashu Sabharwal

As tons of photos are being uploaded to public websites (e. g., Flickr, Bing, and Google) every day, learning from web data has become an increasingly popular research direction because of freely available web resources, which is also referred to as webly supervised learning.

General Classification

Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models

no code implementations CVPR 2018 Jiuxiang Gu, Jianfei Cai, Shafiq Joty, Li Niu, Gang Wang

Textual-visual cross-modal retrieval has been a hot research topic in both computer vision and natural language processing communities.

Cross-Modal Retrieval

Zero-Shot Learning via Category-Specific Visual-Semantic Mapping

no code implementations16 Nov 2017 Li Niu, Jianfei Cai, Ashok Veeraraghavan

Zero-Shot Learning (ZSL) aims to classify a test instance from an unseen category based on the training instances from seen categories, in which the gap between seen categories and unseen categories is generally bridged via visual-semantic mapping between the low-level visual feature space and the intermediate semantic space.

General Classification Image Classification +1

Multi-View Domain Generalization for Visual Recognition

no code implementations ICCV 2015 Li Niu, Wen Li, Dong Xu

Considering the recent works show the domain generalization capability can be enhanced by fusing multiple SVM classifiers, we build upon exemplar SVMs to learn a set of SVM classifiers by using one positive sample and all negative samples in the source domain each time.

Domain Generalization

Visual Recognition by Learning From Web Data: A Weakly Supervised Domain Generalization Approach

no code implementations CVPR 2015 Li Niu, Wen Li, Dong Xu

In this work, we formulate a new weakly supervised domain generalization problem for the visual recognition task by using loosely labeled web images/videos as training data.

Domain Generalization

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