35 citations · 147 across the 22 of their papers we have counts for
22 papers
BEV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentation
Miaoyu Li, Yachao Zhang, Xu MA +2
Cross-modal Unsupervised Domain Adaptation (UDA) aims to exploit the complementarity of 2D-3D data to overcome the lack of annotation in a new domain. However, UDA methods rely on…
Camouflaged Image Synthesis Is All You Need to Boost Camouflaged Detection
Haichao Zhang, Can Qin, Yu Yin +1
Camouflaged objects that blend into natural scenes pose significant challenges for deep-learning models to detect and synthesize. While camouflaged object detection is a crucial ta…
SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds
Yanyu Li, Huan Wang, Qing Jin +6
Text-to-image diffusion models can create stunning images from natural language descriptions that rival the work of professional artists and photographers. However, these models ar…
UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild
Can Qin, Shu Zhang, Ning Yu +10
Achieving machine autonomy and human control often represent divergent objectives in the design of interactive AI systems. Visual generative foundation models such as Stable Diffus…
Frame Flexible Network
Yitian Zhang, Yue Bai, Chang Liu +3
Existing video recognition algorithms always conduct different training pipelines for inputs with different frame numbers, which requires repetitive training operations and multipl…
Contrastive Alignment of Vision to Language Through Parameter-Efficient Transfer Learning
Zaid Khan, Yun Fu
Contrastive vision-language models (e.g. CLIP) are typically created by updating all the parameters of a vision model and language model through contrastive training. Can such mode…
Image as Set of Points
Xu Ma, Yuqian Zhou, Huan Wang +4
What is an image and how to extract latent features? Convolutional Networks (ConvNets) consider an image as organized pixels in a rectangular shape and extract features via convolu…
GlueGen: Plug and Play Multi-modal Encoders for X-to-image Generation
Can Qin, Ning Yu, Chen Xing +6
Text-to-image (T2I) models based on diffusion processes have achieved remarkable success in controllable image generation using user-provided captions. However, the tight coupling…
Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution
Jiamian Wang, Huan Wang, Yulun Zhang +2
Image super-resolution (SR) has witnessed extensive neural network designs from CNN to transformer architectures. However, prevailing SR models suffer from prohibitive memory footp…
Why is the State of Neural Network Pruning so Confusing? On the Fairness, Comparison Setup, and Trainability in Network Pruning
Huan Wang, Can Qin, Yue Bai +1
The state of neural network pruning has been noticed to be unclear and even confusing for a while, largely due to "a lack of standardized benchmarks and metrics" [3]. To standardiz…
Unveiling the Unseen: A Comprehensive Survey on Explainable Anomaly Detection in Images and Videos
Yizhou Wang, Dongliang Guo, Sheng Li +2
Anomaly detection and localization in visual data, including images and videos, are crucial in machine learning and real-world applications. Despite rapid advancements in visual an…
Making Reconstruction-based Method Great Again for Video Anomaly Detection
Yizhou Wang, Can Qin, Yue Bai +3
Anomaly detection in videos is a significant yet challenging problem. Previous approaches based on deep neural networks employ either reconstruction-based or prediction-based appro…
A Close Look at Spatial Modeling: From Attention to Convolution
Xu Ma, Huan Wang, Can Qin +4
Vision Transformers have shown great promise recently for many vision tasks due to the insightful architecture design and attention mechanism. By revisiting the self-attention resp…
Real-Time Neural Light Field on Mobile Devices
Junli Cao, Huan Wang, Pavlo Chemerys +6
Recent efforts in Neural Rendering Fields (NeRF) have shown impressive results on novel view synthesis by utilizing implicit neural representation to represent 3D scenes. Due to th…
Look More but Care Less in Video Recognition
Yitian Zhang, Yue Bai, Huan Wang +2
Existing action recognition methods typically sample a few frames to represent each video to avoid the enormous computation, which often limits the recognition performance. To tack…
Parameter-Efficient Masking Networks
Yue Bai, Huan Wang, Xu Ma +3
A deeper network structure generally handles more complicated non-linearity and performs more competitively. Nowadays, advanced network designs often contain a large number of repe…
Trainability Preserving Neural Pruning
Huan Wang, Yun Fu
Many recent works have shown trainability plays a central role in neural network pruning -- unattended broken trainability can lead to severe under-performance and unintentionally…
Dual Lottery Ticket Hypothesis
Yue Bai, Huan Wang, Zhiqiang Tao +2
Fully exploiting the learning capacity of neural networks requires overparameterized dense networks. On the other side, directly training sparse neural networks typically results i…
R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesis
Huan Wang, Jian Ren, Zeng Huang +4
Recent research explosion on Neural Radiance Field (NeRF) shows the encouraging potential to represent complex scenes with neural networks. One major drawback of NeRF is its prohib…
Hybrid Pixel-Unshuffled Network for Lightweight Image Super-Resolution
Bin Sun, Yulun Zhang, Songyao Jiang +1
Convolutional neural network (CNN) has achieved great success on image super-resolution (SR). However, most deep CNN-based SR models take massive computations to obtain high perfor…
Recent Advances on Neural Network Pruning at Initialization
Huan Wang, Can Qin, Yue Bai +2
Neural network pruning typically removes connections or neurons from a pretrained converged model; while a new pruning paradigm, pruning at initialization (PaI), attempts to prune…
What Makes a "Good" Data Augmentation in Knowledge Distillation -- A Statistical Perspective
Huan Wang, Suhas Lohit, Mike Jones +1
Knowledge distillation (KD) is a general neural network training approach that uses a teacher model to guide the student model. Existing works mainly study KD from the network outp…