377 citations · 802 across the 20 of their papers we have counts for
20 papers
Large-scale Dataset Pruning with Dynamic Uncertainty
Muyang He, Shuo Yang, Tiejun Huang +1
The state of the art of many learning tasks, e.g., image classification, is advanced by collecting larger datasets and then training larger models on them. As the outcome, the incr…
Toward Moiré-Free and Detail-Preserving Demosaicking
Xuanchen Li, Yan Niu, Bo Zhao +2
3D convolutions are commonly employed by demosaicking neural models, in the same way as solving other image restoration problems. Counter-intuitively, we show that 3D convolutions…
Improving Convergence and Generalization Using Parameter Symmetries
Bo Zhao, Robert M. Gower, Robin Walters +1
In many neural networks, different values of the parameters may result in the same loss value. Parameter space symmetries are loss-invariant transformations that change the model p…
Symmetries, flat minima, and the conserved quantities of gradient flow
Bo Zhao, Iordan Ganev, Robin Walters +2
Empirical studies of the loss landscape of deep networks have revealed that many local minima are connected through low-loss valleys. Yet, little is known about the theoretical ori…
Privacy for Free: How does Dataset Condensation Help Privacy?
Tian Dong, Bo Zhao, Lingjuan Lyu
To prevent unintentional data leakage, research community has resorted to data generators that can produce differentially private data for model training. However, for the sake of…
FaceMAE: Privacy-Preserving Face Recognition via Masked Autoencoders
Kai Wang, Bo Zhao, Xiangyu Peng +5
Face recognition, as one of the most successful applications in artificial intelligence, has been widely used in security, administration, advertising, and healthcare. However, the…
Synthesizing Informative Training Samples with GAN
Bo Zhao, Hakan Bilen
Remarkable progress has been achieved in synthesizing photo-realistic images with generative adversarial networks (GANs). Recently, GANs are utilized as the training sample generat…
Makeup216: Logo Recognition with Adversarial Attention Representations
Junjun Hu, Yanhao Zhu, Bo Zhao +5
One of the challenges of logo recognition lies in the diversity of forms, such as symbols, texts or a combination of both; further, logos tend to be extremely concise in design whi…
Dataset Condensation with Distribution Matching
Bo Zhao, Hakan Bilen
Computational cost of training state-of-the-art deep models in many learning problems is rapidly increasing due to more sophisticated models and larger datasets. A recent promising…
Concentric Spherical GNN for 3D Representation Learning
James Fox, Bo Zhao, Sivasankaran Rajamanickam +2
Learning 3D representations that generalize well to arbitrarily oriented inputs is a challenge of practical importance in applications varying from computer vision to physics and c…
Dataset Condensation with Differentiable Siamese Augmentation
Bo Zhao, Hakan Bilen
In many machine learning problems, large-scale datasets have become the de-facto standard to train state-of-the-art deep networks at the price of heavy computation load. In this pa…
Augmented Bi-path Network for Few-shot Learning
Baoming Yan, Chen Zhou, Bo Zhao +5
Few-shot Learning (FSL) which aims to learn from few labeled training data is becoming a popular research topic, due to the expensive labeling cost in many real-world applications.…
Continual Representation Learning for Biometric Identification
Bo Zhao, Shixiang Tang, Dapeng Chen +2
With the explosion of digital data in recent years, continuously learning new tasks from a stream of data without forgetting previously acquired knowledge has become increasingly i…
Dataset Condensation with Gradient Matching
Bo Zhao, Konda Reddy Mopuri, Hakan Bilen
As the state-of-the-art machine learning methods in many fields rely on larger datasets, storing datasets and training models on them become significantly more expensive. This pape…
iDLG: Improved Deep Leakage from Gradients
Bo Zhao, Konda Reddy Mopuri, Hakan Bilen
It is widely believed that sharing gradients will not leak private training data in distributed learning systems such as Collaborative Learning and Federated Learning, etc. Recentl…
MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning
Bo Zhao, Xinwei Sun, Yanwei Fu +2
It is one typical and general topic of learning a good embedding model to efficiently learn the representation coefficients between two spaces/subspaces. To solve this task, $L_{1}…
A Large-scale Attribute Dataset for Zero-shot Learning
Bo Zhao, Yanwei Fu, Rui Liang +3
Zero-Shot Learning (ZSL) has attracted huge research attention over the past few years; it aims to learn the new concepts that have never been seen before. In classical ZSL algorit…
Zero-shot Learning via Shared-Reconstruction-Graph Pursuit
Bo Zhao, Xinwei Sun, Yuan Yao +1
Zero-shot learning (ZSL) aims to recognize objects from novel unseen classes without any training data. Recently, structure-transfer based methods are proposed to implement ZSL by…
AI Challenger : A Large-scale Dataset for Going Deeper in Image Understanding
Jiahong Wu, He Zheng, Bo Zhao +9
Significant progress has been achieved in Computer Vision by leveraging large-scale image datasets. However, large-scale datasets for complex Computer Vision tasks beyond classific…
Zero-Shot Learning posed as a Missing Data Problem
Bo Zhao, Botong Wu, Tianfu Wu +1
This paper presents a method of zero-shot learning (ZSL) which poses ZSL as the missing data problem, rather than the missing label problem. Specifically, most existing ZSL methods…