133 citations · 510 across the 36 of their papers we have counts for
37 papers
Task-customized Masked AutoEncoder via Mixture of Cluster-conditional Experts
Zhili Liu, Kai Chen, Jianhua Han +4
Masked Autoencoder~(MAE) is a prevailing self-supervised learning method that achieves promising results in model pre-training. However, when the various downstream tasks have data…
Robust Outlier Bound Condition to Phase Retrieval with Adversarial Sparse Outliers
Gao Huang, Song Li, Hang Xu
We consider the problem of recovering an unknown signal from phaseless measurements. In this paper, we study the convex phase retrieval problem via Ph…
Policy Resilience to Environment Poisoning Attacks on Reinforcement Learning
Hang Xu, Xinghua Qu, Zinovi Rabinovich
This paper investigates policy resilience to training-environment poisoning attacks on reinforcement learning (RL) policies, with the goal of recovering the deployment performance…
Mixed Autoencoder for Self-supervised Visual Representation Learning
Kai Chen, Zhili Liu, Lanqing Hong +3
Masked Autoencoder (MAE) has demonstrated superior performance on various vision tasks via randomly masking image patches and reconstruction. However, effective data augmentation s…
Generative Negative Text Replay for Continual Vision-Language Pretraining
Shipeng Yan, Lanqing Hong, Hang Xu +4
Vision-language pre-training (VLP) has attracted increasing attention recently. With a large amount of image-text pairs, VLP models trained with contrastive loss have achieved impr…
DevNet: Self-supervised Monocular Depth Learning via Density Volume Construction
Kaichen Zhou, Lanqing Hong, Changhao Chen +4
Self-supervised depth learning from monocular images normally relies on the 2D pixel-wise photometric relation between temporally adjacent image frames. However, they neither fully…
CO^3: Cooperative Unsupervised 3D Representation Learning for Autonomous Driving
Runjian Chen, Yao Mu, Runsen Xu +5
Unsupervised contrastive learning for indoor-scene point clouds has achieved great successes. However, unsupervised learning point clouds in outdoor scenes remains challenging beca…
Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning
Jiahui Gao, Renjie Pi, Yong Lin +7
There is a rising interest in further exploring the zero-shot learning potential of large pre-trained language models (PLMs). A new paradigm called data-generation-based zero-shot…
Revisiting Over-smoothing in BERT from the Perspective of Graph
Han Shi, Jiahui Gao, Hang Xu +5
Recently over-smoothing phenomenon of Transformer-based models is observed in both vision and language fields. However, no existing work has delved deeper to further investigate th…
ZeroGen: Efficient Zero-shot Learning via Dataset Generation
Jiacheng Ye, Jiahui Gao, Qintong Li +5
There is a growing interest in dataset generation recently due to the superior generative capacity of large pre-trained language models (PLMs). In this paper, we study a flexible a…
AutoBERT-Zero: Evolving BERT Backbone from Scratch
Jiahui Gao, Hang Xu, Han Shi +5
Transformer-based pre-trained language models like BERT and its variants have recently achieved promising performance in various natural language processing (NLP) tasks. However, t…
One Million Scenes for Autonomous Driving: ONCE Dataset
Jiageng Mao, Minzhe Niu, Chenhan Jiang +10
Current perception models in autonomous driving have become notorious for greatly relying on a mass of annotated data to cover unseen cases and address the long-tail problem. On th…
Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation
Lewei Yao, Renjie Pi, Hang Xu +3
We propose Joint-DetNAS, a unified NAS framework for object detection, which integrates 3 key components: Neural Architecture Search, pruning, and Knowledge Distillation. Instead o…
TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Search
Yawen Duan, Xin Chen, Hang Xu +4
Recent breakthroughs of Neural Architecture Search (NAS) extend the field's research scope towards a broader range of vision tasks and more diversified search spaces. While existin…
BWCP: Probabilistic Learning-to-Prune Channels for ConvNets via Batch Whitening
Wenqi Shao, Hang Yu, Zhaoyang Zhang +3
This work presents a probabilistic channel pruning method to accelerate Convolutional Neural Networks (CNNs). Previous pruning methods often zero out unimportant channels in traini…
Effective Sparsification of Neural Networks with Global Sparsity Constraint
Xiao Zhou, Weizhong Zhang, Hang Xu +1
Weight pruning is an effective technique to reduce the model size and inference time for deep neural networks in real-world deployments. However, since magnitudes and relative impo…
Deeply Unsupervised Patch Re-Identification for Pre-training Object Detectors
Jian Ding, Enze Xie, Hang Xu +4
Unsupervised pre-training aims at learning transferable features that are beneficial for downstream tasks. However, most state-of-the-art unsupervised methods concentrate on learni…
Segmenting Transparent Object in the Wild with Transformer
Enze Xie, Wenjia Wang, Wenhai Wang +4
This work presents a new fine-grained transparent object segmentation dataset, termed Trans10K-v2, extending Trans10K-v1, the first large-scale transparent object segmentation data…
Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search
Peidong Liu, Gengwei Zhang, Bochao Wang +4
Designing proper loss functions for vision tasks has been a long-standing research direction to advance the capability of existing models. For object detection, the well-establishe…
DeepReduce: A Sparse-tensor Communication Framework for Distributed Deep Learning
Kelly Kostopoulou, Hang Xu, Aritra Dutta +3
Sparse tensors appear frequently in distributed deep learning, either as a direct artifact of the deep neural network's gradients, or as a result of an explicit sparsification proc…
SparseBERT: Rethinking the Importance Analysis in Self-attention
Han Shi, Jiahui Gao, Xiaozhe Ren +4
Transformer-based models are popularly used in natural language processing (NLP). Its core component, self-attention, has aroused widespread interest. To understand the self-attent…
DetCo: Unsupervised Contrastive Learning for Object Detection
Enze Xie, Jian Ding, Wenhai Wang +5
Unsupervised contrastive learning achieves great success in learning image representations with CNN. Unlike most recent methods that focused on improving accuracy of image classifi…
Ada-Segment: Automated Multi-loss Adaptation for Panoptic Segmentation
Gengwei Zhang, Yiming Gao, Hang Xu +3
Panoptic segmentation that unifies instance segmentation and semantic segmentation has recently attracted increasing attention. While most existing methods focus on designing novel…
OpenHoldem: A Benchmark for Large-Scale Imperfect-Information Game Research
Kai Li, Hang Xu, Enmin Zhao +2
Owning to the unremitting efforts by a few institutes, significant progress has recently been made in designing superhuman AIs in No-limit Texas Hold'em (NLTH), the primary testbed…