1 code implementation • CVPR 2024 • Chenming Shang, Shiji Zhou, Hengyuan Zhang, Xinzhe Ni, Yujiu Yang, Yuwang Wang
Concept Bottleneck Models (CBMs) map the black-box visual representations extracted by deep neural networks onto a set of interpretable concepts and use the concepts to make predictions, enhancing the transparency of the decision-making process.
no code implementations • 28 Feb 2024 • Meidai Xuanyuan, Yuwang Wang, Honglei Guo, Qionghai Dai
To achieve this, we provide a two-stage and cross-modal controllable video generation pipeline, taking facial landmarks as an explicit and compact control signal to bridge the driving audio, talking context and generated videos.
no code implementations • 11 Dec 2023 • Haozhe Jia, Yan Li, Hengfei Cui, Di Xu, Yuwang Wang, Tao Yu
We identify the key challenge as the exploration of disentangled conditional control between high-level semantics and explicit parameters (e. g., 3DMM) in the generation process, and accordingly propose a novel diffusion-based editing framework, named DisControlFace.
no code implementations • 12 Sep 2023 • Jingwen Fu, Tao Yang, Yuwang Wang, Yan Lu, Nanning Zheng
To study the mechanism behind the learning plateaus, we conceptually seperate a component within the model's internal representation that is exclusively affected by the model's weights.
no code implementations • 19 Jun 2023 • Jiaqi Xu, Yuwang Wang, Xuejin Chen
In this work, with the assumption that the gradients of a specific domain samples under the classification task could also reflect the property of the domain, we propose a Shape Guided Gradient Voting (SGGV) method for domain generalization.
no code implementations • 29 May 2023 • Tao Yang, Yuwang Wang, Cuiling Lan, Yan Lu, Nanning Zheng
In this paper, we study several typical disentangled representation learning works in terms of both disentanglement and compositional generalization abilities, and we provide an important insight: vector-based representation (using a vector instead of a scalar to represent a concept) is the key to empower both good disentanglement and strong compositional generalization.
no code implementations • 26 Apr 2023 • Yuqi Han, Tao Yu, Xiaohang Yu, Yuwang Wang, Qionghai Dai
Given multi-view low-resolution images, Super-NeRF constructs a consistency-controlling super-resolution module to generate view-consistent high-resolution details for NeRF.
no code implementations • 9 Apr 2023 • Meidai Xuanyuan, Yuwang Wang, Honglei Guo, Xiao Ma, Yuchen Guo, Tao Yu, Qionghai Dai
To support this novel task, we further collect a character centric multimodal dialogue dataset, named Deep Personalized Character Dataset (DPCD), from TV shows.
no code implementations • CVPR 2023 • Mude Hui, Zhizheng Zhang, Xiaoyi Zhang, Wenxuan Xie, Yuwang Wang, Yan Lu
Since different attributes have their individual semantics and characteristics, we propose to decouple the diffusion processes for them to improve the diversity of training samples and learn the reverse process jointly to exploit global-scope contexts for facilitating generation.
1 code implementation • NeurIPS 2023 • Tao Yang, Yuwang Wang, Yan Lv, Nanning Zheng
Targeting to understand the underlying explainable factors behind observations and modeling the conditional generation process on these factors, we connect disentangled representation learning to Diffusion Probabilistic Models (DPMs) to take advantage of the remarkable modeling ability of DPMs.
no code implementations • ICCV 2023 • Hewei Guo, Liping Ren, Jingjing Fu, Yuwang Wang, Zhizheng Zhang, Cuiling Lan, Haoqian Wang, Xinwen Hou
Targeting for detecting anomalies of various sizes for complicated normal patterns, we propose a Template-guided Hierarchical Feature Restoration method, which introduces two key techniques, bottleneck compression and template-guided compensation, for anomaly-free feature restoration.
Ranked #17 on
Anomaly Detection
on MVTec LOCO AD
no code implementations • 20 May 2022 • Tao Yang, Shenglong Zhou, Yuwang Wang, Yan Lu, Nanning Zheng
Deep neural networks often suffer the data distribution shift between training and testing, and the batch statistics are observed to reflect the shift.
2 code implementations • 20 May 2022 • Tao Yang, Yuwang Wang, Yan Lu, Nanning Zheng
We further propose a Concept Disentangling Loss to facilitate that different concept tokens represent independent visual concepts.
2 code implementations • ICLR 2022 • Dacheng Yin, Xuanchi Ren, Chong Luo, Yuwang Wang, Zhiwei Xiong, Wenjun Zeng
Last, an innovative link attention module serves as the decoder to reconstruct data from the decomposed content and style, with the help of the linking keys.
no code implementations • 25 May 2021 • Jingwen Fu, Xiaoyi Zhang, Yuwang Wang, Wenjun Zeng, Sam Yang, Grayson Hilliard
A dataset, RICO-PW, of screenshots with Pixel-Words annotations is built based on the public RICO dataset, which will be released to help to address the lack of high-quality training data in this area.
4 code implementations • CVPR 2021 • Xiaotian Chen, Yuwang Wang, Xuejin Chen, Wenjun Zeng
S2R-DepthNet consists of: a) a Structure Extraction (STE) module which extracts a domaininvariant structural representation from an image by disentangling the image into domain-invariant structure and domain-specific style components, b) a Depth-specific Attention (DSA) module, which learns task-specific knowledge to suppress depth-irrelevant structures for better depth estimation and generalization, and c) a depth prediction module (DP) to predict depth from the depth-specific representation.
2 code implementations • ICLR 2022 • Xuanchi Ren, Tao Yang, Yuwang Wang, Wenjun Zeng
Based on this observation, we argue that it is possible to mitigate the trade-off by $(i)$ leveraging the pretrained generative models with high generation quality, $(ii)$ focusing on discovering the traversal directions as factors for disentangled representation learning.
1 code implementation • 21 Feb 2021 • Xuanchi Ren, Tao Yang, Yuwang Wang, Wenjun Zeng
From the unsupervised disentanglement perspective, we rethink content and style and propose a formulation for unsupervised C-S disentanglement based on our assumption that different factors are of different importance and popularity for image reconstruction, which serves as a data bias.
1 code implementation • ICLR 2022 • Tao Yang, Xuanchi Ren, Yuwang Wang, Wenjun Zeng, Nanning Zheng
We then propose a model, based on existing VAE-based methods, to tackle the unsupervised learning problem of the framework.
no code implementations • 13 Apr 2020 • Wei Zhou, Qiuping Jiang, Yuwang Wang, Zhibo Chen, Weiping Li
Numerous image superresolution (SR) algorithms have been proposed for reconstructing high-resolution (HR) images from input images with lower spatial resolutions.
no code implementations • ICCV 2019 • Junsheng Zhou, Yuwang Wang, Kaihuai Qin, Wen-Jun Zeng
Our experimental evaluation demonstrates that the result of our method is comparable to fully supervised methods on the NYU Depth V2 benchmark.
no code implementations • ICCV 2019 • Junsheng Zhou, Yuwang Wang, Kaihuai Qin, Wen-Jun Zeng
Unsupervised depth learning takes the appearance difference between a target view and a view synthesized from its adjacent frame as supervisory signal.
Monocular Depth Estimation
Vocal Bursts Intensity Prediction
no code implementations • 4 Aug 2019 • Yixuan Liu, Yuwang Wang, Shengjin Wang
To this end, we first design a differentiable depth map warping operation, which is end-to-end trainable, and then propose a pose generator to generate novel views for a given image in an adversarial manner.