activity
20182024
most citedDynamic Head: Unifying Object Detection Heads with Attentions

64 citations · 132 across the 16 of their papers we have counts for

collaborators
Showing cs.CVShow all

23 papers · 1 filter

cs.CV20243 cited

Efficient Modulation for Vision Networks

Xu Ma, Xiyang Dai, Jianwei Yang +4

In this work, we present efficient modulation, a novel design for efficient vision networks. We revisit the modulation mechanism, which operates input through convolutional context…

cs.CV20234 cited

Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection

Lingchen Meng, Xiyang Dai, Jianwei Yang +7

Long-tailed object detection (LTOD) aims to handle the extreme data imbalance in real-world datasets, where many tail classes have scarce instances. One popular strategy is to expl…

cs.CV2023

Exploring Invariance in Images through One-way Wave Equations

Yinpeng Chen, Dongdong Chen, Xiyang Dai +5

In this paper, we empirically reveal an invariance over images-images share a set of one-way wave equations with latent speeds. Each image is uniquely associated with a solution to…

cs.CV2023

Completing Visual Objects via Bridging Generation and Segmentation

Xiang Li, Yinpeng Chen, Chung-Ching Lin +6

This paper presents a novel approach to object completion, with the primary goal of reconstructing a complete object from its partially visible components. Our method, named MaskCo…

cs.CV2023

Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Prompting

Qidong Huang, Xiaoyi Dong, Dongdong Chen +5

In this paper, we investigate the adversarial robustness of vision transformers that are equipped with BERT pretraining (e.g., BEiT, MAE). A surprising observation is that MAE has…

cs.CV2022

Self-Supervised Learning based on Heat Equation

Yinpeng Chen, Xiyang Dai, Dongdong Chen +4

This paper presents a new perspective of self-supervised learning based on extending heat equation into high dimensional feature space. In particular, we remove time dependence by…