Search Results for author: Kehan Li

Found 13 papers, 5 papers with code

$L_2$BN: Enhancing Batch Normalization by Equalizing the $L_2$ Norms of Features

no code implementations6 Jul 2022 Zhennan Wang, Kehan Li, Runyi Yu, Yian Zhao, Pengchong Qiao, Chang Liu, Fan Xu, Xiangyang Ji, Guoli Song, Jie Chen

In this paper, we analyze batch normalization from the perspective of discriminability and find the disadvantages ignored by previous studies: the difference in $l_2$ norms of sample features can hinder batch normalization from obtaining more distinguished inter-class features and more compact intra-class features.

Acoustic Scene Classification Image Classification +1

Locality Guidance for Improving Vision Transformers on Tiny Datasets

1 code implementation20 Jul 2022 Kehan Li, Runyi Yu, Zhennan Wang, Li Yuan, Guoli Song, Jie Chen

Therefore, our locality guidance approach is very simple and efficient, and can serve as a basic performance enhancement method for VTs on tiny datasets.

ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentation

no code implementations CVPR 2023 Kehan Li, Zhennan Wang, Zesen Cheng, Runyi Yu, Yian Zhao, Guoli Song, Chang Liu, Li Yuan, Jie Chen

Recently, self-supervised large-scale visual pre-training models have shown great promise in representing pixel-level semantic relationships, significantly promoting the development of unsupervised dense prediction tasks, e. g., unsupervised semantic segmentation (USS).

Image Segmentation Unsupervised Semantic Segmentation

Position Embedding Needs an Independent Layer Normalization

1 code implementation10 Dec 2022 Runyi Yu, Zhennan Wang, Yinhuai Wang, Kehan Li, Yian Zhao, Jian Zhang, Guoli Song, Jie Chen

By analyzing the input and output of each encoder layer in VTs using reparameterization and visualization, we find that the default PE joining method (simply adding the PE and patch embedding together) operates the same affine transformation to token embedding and PE, which limits the expressiveness of PE and hence constrains the performance of VTs.

Position

Parallel Vertex Diffusion for Unified Visual Grounding

no code implementations13 Mar 2023 Zesen Cheng, Kehan Li, Peng Jin, Xiangyang Ji, Li Yuan, Chang Liu, Jie Chen

An intuitive materialization of our paradigm is Parallel Vertex Diffusion (PVD) to directly set vertex coordinates as the generation target and use a diffusion model to train and infer.

Visual Grounding

DiffusionRet: Generative Text-Video Retrieval with Diffusion Model

4 code implementations ICCV 2023 Peng Jin, Hao Li, Zesen Cheng, Kehan Li, Xiangyang Ji, Chang Liu, Li Yuan, Jie Chen

Existing text-video retrieval solutions are, in essence, discriminant models focused on maximizing the conditional likelihood, i. e., p(candidates|query).

Retrieval Video Retrieval

Multi-granularity Interaction Simulation for Unsupervised Interactive Segmentation

no code implementations ICCV 2023 Kehan Li, Yian Zhao, Zhennan Wang, Zesen Cheng, Peng Jin, Xiangyang Ji, Li Yuan, Chang Liu, Jie Chen

Interactive segmentation enables users to segment as needed by providing cues of objects, which introduces human-computer interaction for many fields, such as image editing and medical image analysis.

Interactive Segmentation

Forensic Histopathological Recognition via a Context-Aware MIL Network Powered by Self-Supervised Contrastive Learning

no code implementations27 Aug 2023 Chen Shen, Jun Zhang, Xinggong Liang, Zeyi Hao, Kehan Li, Fan Wang, Zhenyuan Wang, Chunfeng Lian

Forensic pathology is critical in analyzing death manner and time from the microscopic aspect to assist in the establishment of reliable factual bases for criminal investigation.

Contrastive Learning Domain Generalization +3

FreestyleRet: Retrieving Images from Style-Diversified Queries

1 code implementation5 Dec 2023 Hao Li, Curise Jia, Peng Jin, Zesen Cheng, Kehan Li, Jialu Sui, Chang Liu, Li Yuan

In this paper, we propose the Style-Diversified Query-Based Image Retrieval task, which enables retrieval based on various query styles.

Image Retrieval Retrieval

Instance Brownian Bridge as Texts for Open-vocabulary Video Instance Segmentation

1 code implementation18 Jan 2024 Zesen Cheng, Kehan Li, Hao Li, Peng Jin, Chang Liu, Xiawu Zheng, Rongrong Ji, Jie Chen

To mold instance queries to follow Brownian bridge and accomplish alignment with class texts, we design Bridge-Text Alignment (BTA) to learn discriminative bridge-level representations of instances via contrastive objectives.

Instance Segmentation Semantic Segmentation +1

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