342 citations · 2.4k across the 71 of their papers we have counts for
12 papers · 1 filter
CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet
Xiaoyi Dong, Jianmin Bao, Ting Zhang +7
Recent studies have shown that CLIP has achieved remarkable success in performing zero-shot inference while its fine-tuning performance is not satisfactory. In this paper, we ident…
X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion
Hanqing Zhao, Dianmo Sheng, Jianmin Bao +9
Copy-Paste is a simple and effective data augmentation strategy for instance segmentation. By randomly pasting object instances onto new background images, it creates new training…
Improving Commonsense in Vision-Language Models via Knowledge Graph Riddles
Shuquan Ye, Yujia Xie, Dongdong Chen +4
This paper focuses on analyzing and improving the commonsense ability of recent popular vision-language (VL) models. Despite the great success, we observe that existing VL-models s…
SinDiffusion: Learning a Diffusion Model from a Single Natural Image
Weilun Wang, Jianmin Bao, Wengang Zhou +4
We present SinDiffusion, leveraging denoising diffusion models to capture internal distribution of patches from a single natural image. SinDiffusion significantly improves the qual…
Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis
Wan-Cyuan Fan, Yen-Chun Chen, Dongdong Chen +3
Diffusion models (DMs) have shown great potential for high-quality image synthesis. However, when it comes to producing images with complex scenes, how to properly describe both im…
MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining
Xiaoyi Dong, Jianmin Bao, Yinglin Zheng +9
This paper presents a simple yet effective framework MaskCLIP, which incorporates a newly proposed masked self-distillation into contrastive language-image pretraining. The core id…
Bootstrapped Masked Autoencoders for Vision BERT Pretraining
Xiaoyi Dong, Jianmin Bao, Ting Zhang +6
We propose bootstrapped masked autoencoders (BootMAE), a new approach for vision BERT pretraining. BootMAE improves the original masked autoencoders (MAE) with two core designs: 1)…
Semantic Image Synthesis via Diffusion Models
Wengang Zhou, Weilun Wang, Jianmin Bao +4
Denoising Diffusion Probabilistic Models (DDPMs) have achieved remarkable success in various image generation tasks compared with Generative Adversarial Nets (GANs). Recent work on…
REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering
Yuanze Lin, Yujia Xie, Dongdong Chen +3
This paper revisits visual representation in knowledge-based visual question answering (VQA) and demonstrates that using regional information in a better way can significantly impr…
Large-Scale Pre-training for Person Re-identification with Noisy Labels
Dengpan Fu, Dongdong Chen, Hao Yang +6
This paper aims to address the problem of pre-training for person re-identification (Re-ID) with noisy labels. To setup the pre-training task, we apply a simple online multi-object…
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…
Online Multi-Object Tracking with Unsupervised Re-Identification Learning and Occlusion Estimation
Qiankun Liu, Dongdong Chen, Qi Chu +4
Occlusion between different objects is a typical challenge in Multi-Object Tracking (MOT), which often leads to inferior tracking results due to the missing detected objects. The c…