63 citations · 87 across the 12 of their papers we have counts for
13 papers
Rethinking Few-Shot Object Detection on a Multi-Domain Benchmark
Kibok Lee, Hao Yang, Satyaki Chakraborty +4
Most existing works on few-shot object detection (FSOD) focus on a setting where both pre-training and few-shot learning datasets are from a similar domain. However, few-shot algor…
Omni-DETR: Omni-Supervised Object Detection with Transformers
Pei Wang, Zhaowei Cai, Hao Yang +4
We consider the problem of omni-supervised object detection, which can use unlabeled, fully labeled and weakly labeled annotations, such as image tags, counts, points, etc., for ob…
Rethinking Feature Uncertainty in Stochastic Neural Networks for Adversarial Robustness
Hao Yang, Min Wang, Zhengfei Yu +1
It is well-known that deep neural networks (DNNs) have shown remarkable success in many fields. However, when adding an imperceptible magnitude perturbation on the model input, the…
ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment
Yangyu Huang, Hao Yang, Chong Li +2
The recent progress of CNN has dramatically improved face alignment performance. However, few works have paid attention to the error-bias with respect to error distribution of faci…
Learning from Noisy Labels via Dynamic Loss Thresholding
Hao Yang, Youzhi Jin, Ziyin Li +4
Numerous researches have proved that deep neural networks (DNNs) can fit everything in the end even given data with noisy labels, and result in poor generalization performance. How…
Rethinking the Hyperparameters for Fine-tuning
Hao Li, Pratik Chaudhari, Hao Yang +4
Fine-tuning from pre-trained ImageNet models has become the de-facto standard for various computer vision tasks. Current practices for fine-tuning typically involve selecting an ad…