794 citations · 1.2k across the 17 of their papers we have counts for
18 papers
CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor
Shuyang Sun, Runjia Li, Philip Torr +2
Existing open-vocabulary image segmentation methods require a fine-tuning step on mask labels and/or image-text datasets. Mask labels are labor-intensive, which limits the number o…
Real-Fake: Effective Training Data Synthesis Through Distribution Matching
Jianhao Yuan, Jie Zhang, Shuyang Sun +2
Synthetic training data has gained prominence in numerous learning tasks and scenarios, offering advantages such as dataset augmentation, generalization evaluation, and privacy pre…
OxfordTVG-HIC: Can Machine Make Humorous Captions from Images?
Runjia Li, Shuyang Sun, Mohamed Elhoseiny +1
This paper presents OxfordTVG-HIC (Humorous Image Captions), a large-scale dataset for humour generation and understanding. Humour is an abstract, subjective, and context-dependent…
ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation
Shuyang Sun, Weijun Wang, Qihang Yu +3
This paper presents a new mechanism to facilitate the training of mask transformers for efficient panoptic segmentation, democratizing its deployment. We observe that due to its hi…
LUMix: Improving Mixup by Better Modelling Label Uncertainty
Shuyang Sun, Jie-Neng Chen, Ruifei He +3
Modern deep networks can be better generalized when trained with noisy samples and regularization techniques. Mixup and CutMix have been proven to be effective for data augmentatio…
Is synthetic data from generative models ready for image recognition?
Ruifei He, Shuyang Sun, Xin Yu +5
Recent text-to-image generation models have shown promising results in generating high-fidelity photo-realistic images. Though the results are astonishing to human eyes, how applic…
Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better Transferability
Ruifei He, Shuyang Sun, Jihan Yang +2
Large-scale pre-training has been proven to be crucial for various computer vision tasks. However, with the increase of pre-training data amount, model architecture amount, and the…
Slot-VPS: Object-centric Representation Learning for Video Panoptic Segmentation
Yi Zhou, Hui Zhang, Hana Lee +6
Video Panoptic Segmentation (VPS) aims at assigning a class label to each pixel, uniquely segmenting and identifying all object instances consistently across all frames. Classic so…
TransMix: Attend to Mix for Vision Transformers
Jie-Neng Chen, Shuyang Sun, Ju He +3
Mixup-based augmentation has been found to be effective for generalizing models during training, especially for Vision Transformers (ViTs) since they can easily overfit. However, p…
Vision Transformer with Progressive Sampling
Xiaoyu Yue, Shuyang Sun, Zhanghui Kuang +4
Transformers with powerful global relation modeling abilities have been introduced to fundamental computer vision tasks recently. As a typical example, the Vision Transformer (ViT)…
Visual Parser: Representing Part-whole Hierarchies with Transformers
Shuyang Sun, Xiaoyu Yue, Song Bai +1
Human vision is able to capture the part-whole hierarchical information from the entire scene. This paper presents the Visual Parser (ViP) that explicitly constructs such a hierarc…
Learning to Sample the Most Useful Training Patches from Images
Shuyang Sun, Liang Chen, Gregory Slabaugh +1
Some image restoration tasks like demosaicing require difficult training samples to learn effective models. Existing methods attempt to address this data training problem by manual…
Exploring the Hierarchy in Relation Labels for Scene Graph Generation
Yi Zhou, Shuyang Sun, Chao Zhang +2
By assigning each relationship a single label, current approaches formulate the relationship detection as a classification problem. Under this formulation, predicate categories are…
Robust Multi-Modality Multi-Object Tracking
Wenwei Zhang, Hui Zhou, Shuyang Sun +3
Multi-sensor perception is crucial to ensure the reliability and accuracy in autonomous driving system, while multi-object tracking (MOT) improves that by tracing sequential moveme…
MMDetection: Open MMLab Detection Toolbox and Benchmark
Kai Chen, Jiaqi Wang, Jiangmiao Pang +22
We present MMDetection, an object detection toolbox that contains a rich set of object detection and instance segmentation methods as well as related components and modules. The to…
FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction
Shuyang Sun, Jiangmiao Pang, Jianping Shi +2
The basic principles in designing convolutional neural network (CNN) structures for predicting objects on different levels, e.g., image-level, region-level, and pixel-level are div…
Hybrid Task Cascade for Instance Segmentation
Kai Chen, Jiangmiao Pang, Jiaqi Wang +9
Cascade is a classic yet powerful architecture that has boosted performance on various tasks. However, how to introduce cascade to instance segmentation remains an open question. A…
Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition
Shuyang Sun, Zhanghui Kuang, Wanli Ouyang +2
Motion representation plays a vital role in human action recognition in videos. In this study, we introduce a novel compact motion representation for video action recognition, name…