9 citations · 24 across the 15 of their papers we have counts for
16 papers · 1 filter
Order Matters: Competition-Guided Query Ordering for RNN-Based Object Detection
Shengjian Wu, Li Sun, Yu Shangguan +1
DETR-style detectors use one-to-one bipartite matching during training to assign object queries to ground-truth objects, enabling end-to-end set prediction without non-maximum supp…
DragLoRA: Online Optimization of LoRA Adapters for Drag-based Image Editing in Diffusion Model
Siwei Xia, Li Sun, Tiantian Sun +1
Drag-based editing within pretrained diffusion model provides a precise and flexible way to manipulate foreground objects. Traditional methods optimize the input feature obtained f…
RefineStyle: Dynamic Convolution Refinement for StyleGAN
Siwei Xia, Xueqi Hu, Li Sun +1
In StyleGAN, convolution kernels are shaped by both static parameters shared across images and dynamic modulation factors specific to each image. Therefore, $…
OD-DETR: Online Distillation for Stabilizing Training of Detection Transformer
Shengjian Wu, Li Sun, Qingli Li
DEtection TRansformer (DETR) becomes a dominant paradigm, mainly due to its common architecture with high accuracy and no post-processing. However, DETR suffers from unstable train…
RecursiveDet: End-to-End Region-based Recursive Object Detection
Jing Zhao, Li Sun, Qingli Li
End-to-end region-based object detectors like Sparse R-CNN usually have multiple cascade bounding box decoding stages, which refine the current predictions according to their previ…
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels
Siyuan Li, Li Sun, Qingli Li
Pre-trained vision-language models like CLIP have recently shown superior performances on various downstream tasks, including image classification and segmentation. However, in fin…
IoU-Enhanced Attention for End-to-End Task Specific Object Detection
Jing Zhao, Shengjian Wu, Li Sun +1
Without densely tiled anchor boxes or grid points in the image, sparse R-CNN achieves promising results through a set of object queries and proposal boxes updated in the cascaded t…
Cross Attention Based Style Distribution for Controllable Person Image Synthesis
Xinyue Zhou, Mingyu Yin, Xinyuan Chen +3
Controllable person image synthesis task enables a wide range of applications through explicit control over body pose and appearance. In this paper, we propose a cross attention ba…
QS-Attn: Query-Selected Attention for Contrastive Learning in I2I Translation
Xueqi Hu, Xinyue Zhou, Qiusheng Huang +3
Unpaired image-to-image (I2I) translation often requires to maximize the mutual information between the source and the translated images across different domains, which is critical…
Style Transformer for Image Inversion and Editing
Xueqi Hu, Qiusheng Huang, Zhengyi Shi +4
Existing GAN inversion methods fail to provide latent codes for reliable reconstruction and flexible editing simultaneously. This paper presents a transformer-based image inversion…
Bridging the Gap between Label- and Reference-based Synthesis in Multi-attribute Image-to-Image Translation
Qiusheng Huang, Zhilin Zheng, Xueqi Hu +2
The image-to-image translation (I2IT) model takes a target label or a reference image as the input, and changes a source into the specified target domain. The two types of synthesi…
LSC-GAN: Latent Style Code Modeling for Continuous Image-to-image Translation
Qiusheng Huang, Xueqi Hu, Li Sun +1
Image-to-image (I2I) translation is usually carried out among discrete domains. However, image domains, often corresponding to a physical value, are usually continuous. In other wo…
ID-Unet: Iterative Soft and Hard Deformation for View Synthesis
Mingyu Yin, Li Sun, Qingli Li
View synthesis is usually done by an autoencoder, in which the encoder maps a source view image into a latent content code, and the decoder transforms it into a target view image a…
Novel View Synthesis on Unpaired Data by Conditional Deformable Variational Auto-Encoder
Mingyu Yin, Li Sun, Qingli Li
Novel view synthesis often needs the paired data from both the source and target views. This paper proposes a view translation model under cVAE-GAN framework without requiring the…
Disentangling the Spatial Structure and Style in Conditional VAE
Ziye Zhang, Li Sun, Zhilin Zheng +1
This paper aims to disentangle the latent space in cVAE into the spatial structure and the style code, which are complementary to each other, with one of them being label rel…
Disentangling Latent Space for VAE by Label Relevant/Irrelevant Dimensions
Zhilin Zheng, Li Sun
VAE requires the standard Gaussian distribution as a prior in the latent space. Since all codes tend to follow the same prior, it often suffers the so-called "posterior collapse".…