551 citations · 2.3k across the 76 of their papers we have counts for
10 papers · 1 filter
Contrastive Learning for Label-Efficient Semantic Segmentation
Xiangyun Zhao, Raviteja Vemulapalli, Philip Mansfield +4
Collecting labeled data for the task of semantic segmentation is expensive and time-consuming, as it requires dense pixel-level annotations. While recent Convolutional Neural Netwo…
Ranking Neural Checkpoints
Yandong Li, Xuhui Jia, Ruoxin Sang +4
This paper is concerned with ranking many pre-trained deep neural networks (DNNs), called checkpoints, for the transfer learning to a downstream task. Thanks to the broad use of DN…
Spatiotemporal Contrastive Video Representation Learning
Rui Qian, Tianjian Meng, Boqing Gong +4
We present a self-supervised Contrastive Video Representation Learning (CVRL) method to learn spatiotemporal visual representations from unlabeled videos. Our representations are l…
Improving Object Detection with Selective Self-supervised Self-training
Yandong Li, Di Huang, Danfeng Qin +2
We study how to leverage Web images to augment human-curated object detection datasets. Our approach is two-pronged. On the one hand, we retrieve Web images by image-to-image searc…
Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds
Li Yi, Boqing Gong, Thomas Funkhouser
We study an unsupervised domain adaptation problem for the semantic labeling of 3D point clouds, with a particular focus on domain discrepancies induced by different LiDAR sensors.…
Smooth Adversarial Training
Cihang Xie, Mingxing Tan, Boqing Gong +2
It is commonly believed that networks cannot be both accurate and robust, that gaining robustness means losing accuracy. It is also generally believed that, unless making networks…
When Ensembling Smaller Models is More Efficient than Single Large Models
Dan Kondratyuk, Mingxing Tan, Matthew Brown +1
Ensembling is a simple and popular technique for boosting evaluation performance by training multiple models (e.g., with different initializations) and aggregating their prediction…
Neural Networks Are More Productive Teachers Than Human Raters: Active Mixup for Data-Efficient Knowledge Distillation from a Blackbox Model
Dongdong Wang, Yandong Li, Liqiang Wang +1
We study how to train a student deep neural network for visual recognition by distilling knowledge from a blackbox teacher model in a data-efficient manner. Progress on this proble…
Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective
Muhammad Abdullah Jamal, Matthew Brown, Ming-Hsuan Yang +2
Object frequency in the real world often follows a power law, leading to a mismatch between datasets with long-tailed class distributions seen by a machine learning model and our e…
MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radius
Runtian Zhai, Chen Dan, Di He +5
Adversarial training is one of the most popular ways to learn robust models but is usually attack-dependent and time costly. In this paper, we propose the MACER algorithm, which le…