69 citations · 300 across the 25 of their papers we have counts for
26 papers
Branch-Centric Tokenization and Test-Time Augmentation for Skeleton Generation
Zhengyuan Li, Chuanyu Pan, Yuanming Hu +2
Automatic skeleton generation involves predicting both joint positions and skeletal connectivity. However, existing approaches struggle to encode branch structures into token seque…
Making Vision Transformers Truly Shift-Equivariant
Renan A. Rojas-Gomez, Teck-Yian Lim, Minh N. Do +1
For computer vision, Vision Transformers (ViTs) have become one of the go-to deep net architectures. Despite being inspired by Convolutional Neural Networks (CNNs), ViTs' output re…
GeoCode: Interpretable Shape Programs
Ofek Pearl, Itai Lang, Yuhua Hu +2
The task of crafting procedural programs capable of generating structurally valid 3D shapes easily and intuitively remains an elusive goal in computer vision and graphics. Within t…
Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation
Haochen Wang, Xiaodan Du, Jiahao Li +2
A diffusion model learns to predict a vector field of gradients. We propose to apply chain rule on the learned gradients, and back-propagate the score of a diffusion model through…
Learnable Polyphase Sampling for Shift Invariant and Equivariant Convolutional Networks
Renan A. Rojas-Gomez, Teck-Yian Lim, Alexander G. Schwing +2
We propose learnable polyphase sampling (LPS), a pair of learnable down/upsampling layers that enable truly shift-invariant and equivariant convolutional networks. LPS can be train…
TetGAN: A Convolutional Neural Network for Tetrahedral Mesh Generation
William Gao, April Wang, Gal Metzer +2
We present TetGAN, a convolutional neural network designed to generate tetrahedral meshes. We represent shapes using an irregular tetrahedral grid which encodes an occupancy and di…
Text-Free Learning of a Natural Language Interface for Pretrained Face Generators
Xiaodan Du, Raymond A. Yeh, Nicholas Kolkin +2
We propose Fast text2StyleGAN, a natural language interface that adapts pre-trained GANs for text-guided human face synthesis. Leveraging the recent advances in Contrastive Languag…
Adapting CLIP For Phrase Localization Without Further Training
Jiahao Li, Greg Shakhnarovich, Raymond A. Yeh
Supervised or weakly supervised methods for phrase localization (textual grounding) either rely on human annotations or some other supervised models, e.g., object detectors. Obtain…
Total Variation Optimization Layers for Computer Vision
Raymond A. Yeh, Yuan-Ting Hu, Zhongzheng Ren +1
Optimization within a layer of a deep-net has emerged as a new direction for deep-net layer design. However, there are two main challenges when applying these layers to computer vi…
Equivariance Discovery by Learned Parameter-Sharing
Raymond A. Yeh, Yuan-Ting Hu, Mark Hasegawa-Johnson +1
Designing equivariance as an inductive bias into deep-nets has been a prominent approach to build effective models, e.g., a convolutional neural network incorporates translation eq…
EH-DNAS: End-to-End Hardware-aware Differentiable Neural Architecture Search
Qian Jiang, Xiaofan Zhang, Deming Chen +2
In hardware-aware Differentiable Neural Architecture Search (DNAS), it is challenging to compute gradients of hardware metrics to perform architecture search. Existing works rely o…
Semantic Tracklets: An Object-Centric Representation for Visual Multi-Agent Reinforcement Learning
Iou-Jen Liu, Zhongzheng Ren, Raymond A. Yeh +1
Solving complex real-world tasks, e.g., autonomous fleet control, often involves a coordinated team of multiple agents which learn strategies from visual inputs via reinforcement l…
Cooperative Exploration for Multi-Agent Deep Reinforcement Learning
Iou-Jen Liu, Unnat Jain, Raymond A. Yeh +1
Exploration is critical for good results in deep reinforcement learning and has attracted much attention. However, existing multi-agent deep reinforcement learning algorithms still…
Inverting Adversarially Robust Networks for Image Synthesis
Renan A. Rojas-Gomez, Raymond A. Yeh, Minh N. Do +1
Despite unconditional feature inversion being the foundation of many image synthesis applications, training an inverter demands a high computational budget, large decoding capacity…
SAIL-VOS 3D: A Synthetic Dataset and Baselines for Object Detection and 3D Mesh Reconstruction from Video Data
Yuan-Ting Hu, Jiahong Wang, Raymond A. Yeh +1
Extracting detailed 3D information of objects from video data is an important goal for holistic scene understanding. While recent methods have shown impressive results when reconst…
High-Throughput Synchronous Deep RL
Iou-Jen Liu, Raymond A. Yeh, Alexander G. Schwing
Deep reinforcement learning (RL) is computationally demanding and requires processing of many data points. Synchronous methods enjoy training stability while having lower data thro…
Multi-Decoder DPRNN: High Accuracy Source Counting and Separation
Junzhe Zhu, Raymond Yeh, Mark Hasegawa-Johnson
We propose an end-to-end trainable approach to single-channel speech separation with unknown number of speakers. Our approach extends the MulCat source separation backbone with add…
Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning
Zhongzheng Ren, Raymond A. Yeh, Alexander G. Schwing
Existing semi-supervised learning (SSL) algorithms use a single weight to balance the loss of labeled and unlabeled examples, i.e., all unlabeled examples are equally weighted. But…
Chirality Nets for Human Pose Regression
Raymond A. Yeh, Yuan-Ting Hu, Alexander G. Schwing
We propose Chirality Nets, a family of deep nets that is equivariant to the "chirality transform," i.e., the transformation to create a chiral pair. Through parameter sharing, odd…
PIC: Permutation Invariant Critic for Multi-Agent Deep Reinforcement Learning
Iou-Jen Liu, Raymond A. Yeh, Alexander G. Schwing
Sample efficiency and scalability to a large number of agents are two important goals for multi-agent reinforcement learning systems. Recent works got us closer to those goals, add…
Learning Motion in Feature Space: Locally-Consistent Deformable Convolution Networks for Fine-Grained Action Detection
Khoi-Nguyen C. Mac, Dhiraj Joshi, Raymond A. Yeh +3
Fine-grained action detection is an important task with numerous applications in robotics and human-computer interaction. Existing methods typically utilize a two-stage approach in…
Interpretable and Globally Optimal Prediction for Textual Grounding using Image Concepts
Raymond A. Yeh, Jinjun Xiong, Wen-mei W. Hwu +2
Textual grounding is an important but challenging task for human-computer interaction, robotics and knowledge mining. Existing algorithms generally formulate the task as selection…
Unsupervised Textual Grounding: Linking Words to Image Concepts
Raymond A. Yeh, Minh N. Do, Alexander G. Schwing
Textual grounding, i.e., linking words to objects in images, is a challenging but important task for robotics and human-computer interaction. Existing techniques benefit from recen…
Video Frame Synthesis using Deep Voxel Flow
Ziwei Liu, Raymond A. Yeh, Xiaoou Tang +2
We address the problem of synthesizing new video frames in an existing video, either in-between existing frames (interpolation), or subsequent to them (extrapolation). This problem…