93 citations · 476 across the 42 of their papers we have counts for
42 papers
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…
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…
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…
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…
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…
Designing a Better Asymmetric VQGAN for StableDiffusion
Zixin Zhu, Xuelu Feng, Dongdong Chen +5
StableDiffusion is a revolutionary text-to-image generator that is causing a stir in the world of image generation and editing. Unlike traditional methods that learn a diffusion mo…
PaintSeg: Training-free Segmentation via Painting
Xiang Li, Chung-Ching Lin, Yinpeng Chen +3
The paper introduces PaintSeg, a new unsupervised method for segmenting objects without any training. We propose an adversarial masked contrastive painting (AMCP) process, which cr…
Image as First-Order Norm+Linear Autoregression: Unveiling Mathematical Invariance
Yinpeng Chen, Xiyang Dai, Dongdong Chen +4
This paper introduces a novel mathematical property applicable to diverse images, referred to as FINOLA (First-Order Norm+Linear Autoregressive). FINOLA represents each image in th…
Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Label-Efficient Representations
Ziyu Jiang, Yinpeng Chen, Mengchen Liu +5
Recently, both Contrastive Learning (CL) and Mask Image Modeling (MIM) demonstrate that self-supervision is powerful to learn good representations. However, naively combining them…
Find Beauty in the Rare: Contrastive Composition Feature Clustering for Nontrivial Cropping Box Regression
Zhiyu Pan, Yinpeng Chen, Jiale Zhang +3
Automatic image cropping algorithms aim to recompose images like human-being photographers by generating the cropping boxes with improved composition quality. Cropping box regressi…
Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning
Rui Wang, Dongdong Chen, Zuxuan Wu +5
Benefiting from masked visual modeling, self-supervised video representation learning has achieved remarkable progress. However, existing methods focus on learning representations…
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…
Video Mobile-Former: Video Recognition with Efficient Global Spatial-temporal Modeling
Rui Wang, Zuxuan Wu, Dongdong Chen +6
Transformer-based models have achieved top performance on major video recognition benchmarks. Benefiting from the self-attention mechanism, these models show stronger ability of mo…
Design What You Desire: Icon Generation from Orthogonal Application and Theme Labels
Yinpeng Chen, Zhiyu Pan, Min Shi +3
Generative adversarial networks (GANs) have been trained to be professional artists able to create stunning artworks such as face generation and image style transfer. In this paper…
Should All Proposals be Treated Equally in Object Detection?
Yunsheng Li, Yinpeng Chen, Xiyang Dai +7
The complexity-precision trade-off of an object detector is a critical problem for resource constrained vision tasks. Previous works have emphasized detectors implemented with effi…
Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding
Lingchen Meng, Xiyang Dai, Yinpeng Chen +7
Combining multiple datasets enables performance boost on many computer vision tasks. But similar trend has not been witnessed in object detection when combining multiple datasets d…
Reduce Information Loss in Transformers for Pluralistic Image Inpainting
Qiankun Liu, Zhentao Tan, Dongdong Chen +6
Transformers have achieved great success in pluralistic image inpainting recently. However, we find existing transformer based solutions regard each pixel as a token, thus suffer f…
Residual Mixture of Experts
Lemeng Wu, Mengchen Liu, Yinpeng Chen +3
Mixture of Experts (MoE) is able to scale up vision transformers effectively. However, it requires prohibiting computation resources to train a large MoE transformer. In this paper…
The Overlooked Classifier in Human-Object Interaction Recognition
Ying Jin, Yinpeng Chen, Lijuan Wang +5
Human-Object Interaction (HOI) recognition is challenging due to two factors: (1) significant imbalance across classes and (2) requiring multiple labels per image. This paper shows…
Extremely Weak Supervision Inversion of Multi-physical Properties
Shihang Feng, Peng Jin, Xitong Zhang +4
Multi-physical inversion plays a critical role in geophysics. It has been widely used to infer various physical properties~(such as velocity and conductivity). Among those inversio…
The Overlooked Classifier in Human-Object Interaction Recognition
Ying Jin, Yinpeng Chen, Lijuan Wang +5
Human-Object Interaction (HOI) recognition is challenging due to two factors: (1) significant imbalance across classes and (2) requiring multiple labels per image. This paper shows…
Improving Vision Transformers for Incremental Learning
Pei Yu, Yinpeng Chen, Ying Jin +1
This paper proposes a working recipe of using Vision Transformer (ViT) in class incremental learning. Although this recipe only combines existing techniques, developing the combina…
BEVT: BERT Pretraining of Video Transformers
Rui Wang, Dongdong Chen, Zuxuan Wu +6
This paper studies the BERT pretraining of video transformers. It is a straightforward but worth-studying extension given the recent success from BERT pretraining of image transfor…
Unsupervised Finetuning
Suichan Li, Dongdong Chen, Yinpeng Chen +5
This paper studies "unsupervised finetuning", the symmetrical problem of the well-known "supervised finetuning". Given a pretrained model and small-scale unlabeled target data, uns…