Search Results for author: Peike Li

Found 6 papers, 1 papers with code

Dynamic Gradient Reactivation for Backward Compatible Person Re-identification

no code implementations12 Jul 2022 Xiao Pan, Hao Luo, Weihua Chen, Fan Wang, Hao Li, Wei Jiang, Jianming Zhang, Jianyang Gu, Peike Li

To address this issue, we propose the Ranking-based Backward Compatible Learning (RBCL), which directly optimizes the ranking metric between new features and old features.

Person Re-Identification

M6-Fashion: High-Fidelity Multi-modal Image Generation and Editing

no code implementations24 May 2022 Zhikang Li, Huiling Zhou, Shuai Bai, Peike Li, Chang Zhou, Hongxia Yang

The fashion industry has diverse applications in multi-modal image generation and editing.

Image Generation

In-N-Out Generative Learning for Dense Unsupervised Video Segmentation

no code implementations29 Mar 2022 Xiao Pan, Peike Li, Zongxin Yang, Huiling Zhou, Chang Zhou, Hongxia Yang, Jingren Zhou, Yi Yang

As to pixel-level optimization, we perform in-view masked image modeling on patch tokens, which recovers the corrupted parts of an image via inferring its fine-grained structure, and we term it as in-generative learning.

Contrastive Learning Semantic Segmentation +3

Super-Resolving Cross-Domain Face Miniatures by Peeking at One-Shot Exemplar

no code implementations ICCV 2021 Peike Li, Xin Yu, Yi Yang

By iteratively updating the latent representations and our decoder, our DAP-FSR will be adapted to the target domain, thus achieving authentic and high-quality upsampled HR faces.

Super-Resolution

Consistent Structural Relation Learning for Zero-Shot Segmentation

no code implementations NeurIPS 2020 Peike Li, Yunchao Wei, Yi Yang

Concretely, by exploring the pair-wise and list-wise structures, we impose the relations of generated visual features to be consistent with their counterparts in the semantic word embedding space.

Semantic Segmentation Word Embeddings +1

Self-Correction for Human Parsing

2 code implementations22 Oct 2019 Peike Li, Yunqiu Xu, Yunchao Wei, Yi Yang

To tackle the problem of learning with label noises, this work introduces a purification strategy, called Self-Correction for Human Parsing (SCHP), to progressively promote the reliability of the supervised labels as well as the learned models.

Human Parsing Human Part Segmentation +1

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