65 citations · 142 across the 15 of their papers we have counts for
15 papers
Improving Equivariance in State-of-the-Art Supervised Depth and Normal Predictors
Yuanyi Zhong, Anand Bhattad, Yu-Xiong Wang +1
Dense depth and surface normal predictors should possess the equivariant property to cropping-and-resizing -- cropping the input image should result in cropping the same output ima…
Do Pre-trained Models Benefit Equally in Continual Learning?
Kuan-Ying Lee, Yuanyi Zhong, Yu-Xiong Wang
Existing work on continual learning (CL) is primarily devoted to developing algorithms for models trained from scratch. Despite their encouraging performance on contrived benchmark…
Is Self-Supervised Learning More Robust Than Supervised Learning?
Yuanyi Zhong, Haoran Tang, Junkun Chen +2
Self-supervised contrastive learning is a powerful tool to learn visual representation without labels. Prior work has primarily focused on evaluating the recognition accuracy of va…
SIRfyN: Single Image Relighting from your Neighbors
D. A. Forsyth, Anand Bhattad, Pranav Asthana +2
We show how to relight a scene, depicted in a single image, such that (a) the overall shading has changed and (b) the resulting image looks like a natural image of that scene. Appl…
Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentation
Yuanyi Zhong, Bodi Yuan, Hong Wu +3
We present a novel semi-supervised semantic segmentation method which jointly achieves two desiderata of segmentation model regularities: the label-space consistency property betwe…
Coordinate-wise Control Variates for Deep Policy Gradients
Yuanyi Zhong, Yuan Zhou, Jian Peng
The control variates (CV) method is widely used in policy gradient estimation to reduce the variance of the gradient estimators in practice. A control variate is applied by subtrac…
DAP: Detection-Aware Pre-training with Weak Supervision
Yuanyi Zhong, Jianfeng Wang, Lijuan Wang +3
This paper presents a detection-aware pre-training (DAP) approach, which leverages only weakly-labeled classification-style datasets (e.g., ImageNet) for pre-training, but is speci…
Shaping Deep Feature Space towards Gaussian Mixture for Visual Classification
Weitao Wan, Jiansheng Chen, Cheng Yu +3
The softmax cross-entropy loss function has been widely used to train deep models for various tasks. In this work, we propose a Gaussian mixture (GM) loss function for deep neural…
Efficient Competitive Self-Play Policy Optimization
Yuanyi Zhong, Yuan Zhou, Jian Peng
Reinforcement learning from self-play has recently reported many successes. Self-play, where the agents compete with themselves, is often used to generate training data for iterati…
Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer
Yuanyi Zhong, Jianfeng Wang, Jian Peng +1
In this paper, we propose an effective knowledge transfer framework to boost the weakly supervised object detection accuracy with the help of an external fully-annotated source dat…
Disentangling Controllable Object through Video Prediction Improves Visual Reinforcement Learning
Yuanyi Zhong, Alexander Schwing, Jian Peng
In many vision-based reinforcement learning (RL) problems, the agent controls a movable object in its visual field, e.g., the player's avatar in video games and the robotic arm in…
Sequence Modeling of Temporal Credit Assignment for Episodic Reinforcement Learning
Yang Liu, Yunan Luo, Yuanyi Zhong +3
Recent advances in deep reinforcement learning algorithms have shown great potential and success for solving many challenging real-world problems, including Go game and robotic app…
Anchor Box Optimization for Object Detection
Yuanyi Zhong, Jianfeng Wang, Jian Peng +1
In this paper, we propose a general approach to optimize anchor boxes for object detection. Nowadays, anchor boxes are widely adopted in state-of-the-art detection frameworks. Howe…
Rethinking Feature Distribution for Loss Functions in Image Classification
Weitao Wan, Yuanyi Zhong, Tianpeng Li +1
We propose a large-margin Gaussian Mixture (L-GM) loss for deep neural networks in classification tasks. Different from the softmax cross-entropy loss, our proposal is established…
Towards End-to-End Face Recognition through Alignment Learning
Yuanyi Zhong, Jiansheng Chen, Bo Huang
Plenty of effective methods have been proposed for face recognition during the past decade. Although these methods differ essentially in many aspects, a common practice of them is…