activity
20182023
most citeddipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs

325 citations · 1.2k across the 58 of their papers we have counts for

collaborators

77 papers

cs.LG20231 cited

Regularly Truncated M-estimators for Learning with Noisy Labels

Xiaobo Xia, Pengqian Lu, Chen Gong +3

The sample selection approach is very popular in learning with noisy labels. As deep networks learn pattern first, prior methods built on sample selection share a similar training…

cs.LG2023

Continual Learning From a Stream of APIs

Enneng Yang, Zhenyi Wang, Li Shen +5

Continual learning (CL) aims to learn new tasks without forgetting previous tasks. However, existing CL methods require a large amount of raw data, which is often unavailable due t…

cs.LG2023

Late Stopping: Avoiding Confidently Learning from Mislabeled Examples

Suqin Yuan, Lei Feng, Tongliang Liu

Sample selection is a prevalent method in learning with noisy labels, where small-loss data are typically considered as correctly labeled data. However, this method may not effecti…

cs.CV20234 cited

Point-Query Quadtree for Crowd Counting, Localization, and More

Chengxin Liu, Hao Lu, Zhiguo Cao +1

We show that crowd counting can be viewed as a decomposable point querying process. This formulation enables arbitrary points as input and jointly reasons whether the points are cr…

cs.CV20231 cited

ALIP: Adaptive Language-Image Pre-training with Synthetic Caption

Kaicheng Yang, Jiankang Deng, Xiang An +5

Contrastive Language-Image Pre-training (CLIP) has significantly boosted the performance of various vision-language tasks by scaling up the dataset with image-text pairs collected…

cs.LG20231 cited

Channel-Wise Contrastive Learning for Learning with Noisy Labels

Hui Kang, Sheng Liu, Huaxi Huang +1

In real-world datasets, noisy labels are pervasive. The challenge of learning with noisy labels (LNL) is to train a classifier that discerns the actual classes from given instances…