Search Results for author: Kecheng Zheng

Found 36 papers, 15 papers with code

Abstract Reasoning with Distracting Features

1 code implementation NeurIPS 2019 Kecheng Zheng, Zheng-Jun Zha, Wei Wei

Abstraction reasoning is a long-standing challenge in artificial intelligence.

Stacked Convolutional Deep Encoding Network for Video-Text Retrieval

no code implementations10 Apr 2020 Rui Zhao, Kecheng Zheng, Zheng-Jun Zha

Existing dominant approaches for cross-modal video-text retrieval task are to learn a joint embedding space to measure the cross-modal similarity.

Language Modelling Retrieval +2

Hierarchical Gumbel Attention Network for Text-based Person Search

no code implementations10 Oct 2020 Kecheng Zheng, Wu Liu, Jiawei Liu, Zheng-Jun Zha, Tao Mei

This hard selection strategy is able to fuse the strong-relevant multi-modality features for alleviating the problem of matching redundancy.

Image Retrieval Image-to-Text Retrieval +6

Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification

1 code implementation16 Dec 2020 Kecheng Zheng, Cuiling Lan, Wenjun Zeng, Zhizheng Zhang, Zheng-Jun Zha

Based on this finding, we propose to exploit the uncertainty (measured by consistency levels) to evaluate the reliability of the pseudo-label of a sample and incorporate the uncertainty to re-weight its contribution within various ReID losses, including the identity (ID) classification loss per sample, the triplet loss, and the contrastive loss.

Clustering Domain Adaptive Person Re-Identification +3

Group-aware Label Transfer for Domain Adaptive Person Re-identification

1 code implementation CVPR 2021 Kecheng Zheng, Wu Liu, Lingxiao He, Tao Mei, Jiebo Luo, Zheng-Jun Zha

In this paper, we propose a Group-aware Label Transfer (GLT) algorithm, which enables the online interaction and mutual promotion of pseudo-label prediction and representation learning.

Attribute Clustering +5

Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification

no code implementations25 Mar 2021 Zhizheng Zhang, Cuiling Lan, Wenjun Zeng, Quanzeng You, Zicheng Liu, Kecheng Zheng, Zhibo Chen

Each recomposed feature, obtained based on the domain-invariant feature (which enables a reliable inheritance of identity) and an enhancement from a domain specific feature (which enables the approximation of real distributions), is thus an "ideal" augmentation.

Disentanglement Domain Adaptive Person Re-Identification +2

Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization

1 code implementation CVPR 2022 Xin Jin, Tianyu He, Kecheng Zheng, Zhiheng Yin, Xu Shen, Zhen Huang, Ruoyu Feng, Jianqiang Huang, Xian-Sheng Hua, Zhibo Chen

Specifically, we introduce Gait recognition as an auxiliary task to drive the Image ReID model to learn cloth-agnostic representations by leveraging personal unique and cloth-independent gait information, we name this framework as GI-ReID.

Cloth-Changing Person Re-Identification Computational Efficiency +1

Memory Enhanced Embedding Learning for Cross-Modal Video-Text Retrieval

no code implementations29 Mar 2021 Rui Zhao, Kecheng Zheng, Zheng-Jun Zha, Hongtao Xie, Jiebo Luo

The cross-modal memory module is employed to record the instance embeddings of all the datasets for global negative mining.

Retrieval Text Retrieval +1

Adaptive Domain-Specific Normalization for Generalizable Person Re-Identification

no code implementations7 May 2021 Jiawei Liu, Zhipeng Huang, Kecheng Zheng, Dong Liu, Xiaoyan Sun, Zheng-Jun Zha

It describes unseen target domain as a combination of the known source ones, and explicitly learns domain-specific representation with target distribution to improve the model's generalization by a meta-learning pipeline.

Generalizable Person Re-identification Meta-Learning

Semi-Supervised Domain Generalizable Person Re-Identification

3 code implementations11 Aug 2021 Lingxiao He, Wu Liu, Jian Liang, Kecheng Zheng, Xingyu Liao, Peng Cheng, Tao Mei

Instead, we aim to explore multiple labeled datasets to learn generalized domain-invariant representations for person re-id, which is expected universally effective for each new-coming re-id scenario.

Ranked #16 on Person Re-Identification on Market-1501 (using extra training data)

Generalizable Person Re-identification Knowledge Distillation +1

Calibrated Feature Decomposition for Generalizable Person Re-Identification

1 code implementation27 Nov 2021 Kecheng Zheng, Jiawei Liu, Wei Wu, Liang Li, Zheng-Jun Zha

The calibrated person representation is subtly decomposed into the identity-relevant feature, domain feature, and the remaining entangled one.

Domain Generalization Generalizable Person Re-identification

Unleashing the Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-Identification

1 code implementation1 Dec 2021 Zizheng Yang, Xin Jin, Kecheng Zheng, Feng Zhao

During the pre-training, we attempt to address two critical issues for learning fine-grained ReID features: (1) the augmentations in CL pipeline may distort the discriminative clues in person images.

Contrastive Learning Person Re-Identification +2

Unleashing Potential of Unsupervised Pre-Training With Intra-Identity Regularization for Person Re-Identification

no code implementations CVPR 2022 Zizheng Yang, Xin Jin, Kecheng Zheng, Feng Zhao

During the pre-training, we attempt to address two critical issues for learning fine-grained ReID features: (1) the augmentations in CL pipeline may distort the discriminative clues in person images.

Contrastive Learning Person Re-Identification +2

Modality-Adaptive Mixup and Invariant Decomposition for RGB-Infrared Person Re-Identification

no code implementations3 Mar 2022 Zhipeng Huang, Jiawei Liu, Liang Li, Kecheng Zheng, Zheng-Jun Zha

RGB-infrared person re-identification is an emerging cross-modality re-identification task, which is very challenging due to significant modality discrepancy between RGB and infrared images.

Person Re-Identification

Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-Identification

no code implementations3 Mar 2022 Jiawei Liu, Zhipeng Huang, Liang Li, Kecheng Zheng, Zheng-Jun Zha

In this paper, we propose a novel Debiased Batch Normalization via Gaussian Process approach (GDNorm) for generalizable person re-identification, which models the feature statistic estimation from BN layers as a dynamically self-refining Gaussian process to alleviate the bias to unseen domain for improving the generalization.

Generalizable Person Re-identification Representation Learning

FAMLP: A Frequency-Aware MLP-Like Architecture For Domain Generalization

no code implementations24 Mar 2022 Kecheng Zheng, Yang Cao, Kai Zhu, Ruijing Zhao, Zheng-Jun Zha

However, its generalization performance to heterogeneous tasks is inferior to other architectures (e. g., CNNs and transformers) due to the extensive retention of domain information.

Domain Generalization

Principled Knowledge Extrapolation with GANs

no code implementations21 May 2022 Ruili Feng, Jie Xiao, Kecheng Zheng, Deli Zhao, Jingren Zhou, Qibin Sun, Zheng-Jun Zha

Human can extrapolate well, generalize daily knowledge into unseen scenarios, raise and answer counterfactual questions.

counterfactual

Rank Diminishing in Deep Neural Networks

no code implementations13 Jun 2022 Ruili Feng, Kecheng Zheng, Yukun Huang, Deli Zhao, Michael Jordan, Zheng-Jun Zha

By virtue of our numerical tools, we provide the first empirical analysis of the per-layer behavior of network rank in practical settings, i. e., ResNets, deep MLPs, and Transformers on ImageNet.

Neural Dependencies Emerging from Learning Massive Categories

no code implementations CVPR 2023 Ruili Feng, Kecheng Zheng, Kai Zhu, Yujun Shen, Jian Zhao, Yukun Huang, Deli Zhao, Jingren Zhou, Michael Jordan, Zheng-Jun Zha

Through investigating the properties of the problem solution, we confirm that neural dependency is guaranteed by a redundant logit covariance matrix, which condition is easily met given massive categories, and that neural dependency is highly sparse, implying that one category correlates to only a few others.

Image Classification

Cones: Concept Neurons in Diffusion Models for Customized Generation

1 code implementation9 Mar 2023 Zhiheng Liu, Ruili Feng, Kai Zhu, Yifei Zhang, Kecheng Zheng, Yu Liu, Deli Zhao, Jingren Zhou, Yang Cao

Concatenating multiple clusters of concept neurons can vividly generate all related concepts in a single image.

Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detection

1 code implementation CVPR 2023 Fan Lu, Kai Zhu, Wei Zhai, Kecheng Zheng, Yang Cao

Semantically coherent out-of-distribution (SCOOD) detection aims to discern outliers from the intended data distribution with access to unlabeled extra set.

Out-of-Distribution Detection

Cones 2: Customizable Image Synthesis with Multiple Subjects

1 code implementation30 May 2023 Zhiheng Liu, Yifei Zhang, Yujun Shen, Kecheng Zheng, Kai Zhu, Ruili Feng, Yu Liu, Deli Zhao, Jingren Zhou, Yang Cao

Synthesizing images with user-specified subjects has received growing attention due to its practical applications.

Image Generation

Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-trained Vision-Language Models

no code implementations ICCV 2023 Kecheng Zheng, Wei Wu, Ruili Feng, Kai Zhu, Jiawei Liu, Deli Zhao, Zheng-Jun Zha, Wei Chen, Yujun Shen

To bring the useful knowledge back into light, we first identify a set of parameters that are important to a given downstream task, then attach a binary mask to each parameter, and finally optimize these masks on the downstream data with the parameters frozen.

CoDeF: Content Deformation Fields for Temporally Consistent Video Processing

1 code implementation15 Aug 2023 Hao Ouyang, Qiuyu Wang, Yuxi Xiao, Qingyan Bai, Juntao Zhang, Kecheng Zheng, Xiaowei Zhou, Qifeng Chen, Yujun Shen

We present the content deformation field CoDeF as a new type of video representation, which consists of a canonical content field aggregating the static contents in the entire video and a temporal deformation field recording the transformations from the canonical image (i. e., rendered from the canonical content field) to each individual frame along the time axis. Given a target video, these two fields are jointly optimized to reconstruct it through a carefully tailored rendering pipeline. We advisedly introduce some regularizations into the optimization process, urging the canonical content field to inherit semantics (e. g., the object shape) from the video. With such a design, CoDeF naturally supports lifting image algorithms for video processing, in the sense that one can apply an image algorithm to the canonical image and effortlessly propagate the outcomes to the entire video with the aid of the temporal deformation field. We experimentally show that CoDeF is able to lift image-to-image translation to video-to-video translation and lift keypoint detection to keypoint tracking without any training. More importantly, thanks to our lifting strategy that deploys the algorithms on only one image, we achieve superior cross-frame consistency in processed videos compared to existing video-to-video translation approaches, and even manage to track non-rigid objects like water and smog. Project page can be found at https://qiuyu96. github. io/CoDeF/.

Image-to-Image Translation Keypoint Detection +1

Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis

1 code implementation7 Sep 2023 Jiapeng Zhu, Ceyuan Yang, Kecheng Zheng, Yinghao Xu, Zifan Shi, Yujun Shen

Due to the difficulty in scaling up, generative adversarial networks (GANs) seem to be falling from grace on the task of text-conditioned image synthesis.

Image Generation Philosophy +1

AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort

no code implementations19 Nov 2023 Wen Wang, Canyu Zhao, Hao Chen, Zhekai Chen, Kecheng Zheng, Chunhua Shen

We empirically find that sparse control conditions, such as bounding boxes, are suitable for layout planning, while dense control conditions, e. g., sketches and keypoints, are suitable for generating high-quality image content.

Image Generation Story Visualization

Likelihood-Aware Semantic Alignment for Full-Spectrum Out-of-Distribution Detection

1 code implementation4 Dec 2023 Fan Lu, Kai Zhu, Kecheng Zheng, Wei Zhai, Yang Cao

Full-spectrum out-of-distribution (F-OOD) detection aims to accurately recognize in-distribution (ID) samples while encountering semantic and covariate shifts simultaneously.

Out-of-Distribution Detection

Learning Naturally Aggregated Appearance for Efficient 3D Editing

1 code implementation11 Dec 2023 Ka Leong Cheng, Qiuyu Wang, Zifan Shi, Kecheng Zheng, Yinghao Xu, Hao Ouyang, Qifeng Chen, Yujun Shen

Neural radiance fields, which represent a 3D scene as a color field and a density field, have demonstrated great progress in novel view synthesis yet are unfavorable for editing due to the implicitness.

Novel View Synthesis

Contextual AD Narration with Interleaved Multimodal Sequence

no code implementations19 Mar 2024 Hanlin Wang, Zhan Tong, Kecheng Zheng, Yujun Shen, LiMin Wang

With video feature, text, character bank and context information as inputs, the generated ADs are able to correspond to the characters by name and provide reasonable, contextual descriptions to help audience understand the storyline of movie.

DreamLIP: Language-Image Pre-training with Long Captions

no code implementations25 Mar 2024 Kecheng Zheng, Yifei Zhang, Wei Wu, Fan Lu, Shuailei Ma, Xin Jin, Wei Chen, Yujun Shen

Motivated by this, we propose to dynamically sample sub-captions from the text label to construct multiple positive pairs, and introduce a grouping loss to match the embeddings of each sub-caption with its corresponding local image patches in a self-supervised manner.

Contrastive Learning Language Modelling +4

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