activity
20132022
most citedZero-Shot Learning Through Cross-Modal Transfer

811 citations · 4.2k across the 47 of their papers we have counts for

collaborators
Showing cs.CVShow all

10 papers · 1 filter

cs.CV2020

Prototypical Contrastive Learning of Unsupervised Representations

Junnan Li, Pan Zhou, Caiming Xiong +1

This paper presents Prototypical Contrastive Learning (PCL), an unsupervised representation learning method that addresses the fundamental limitations of instance-wise contrastive…

cs.CV2020

Improving out-of-distribution generalization via multi-task self-supervised pretraining

Isabela Albuquerque, Nikhil Naik, Junnan Li +2

Self-supervised feature representations have been shown to be useful for supervised classification, few-shot learning, and adversarial robustness. We show that features obtained us…

cs.CV202015 cited

Towards Noise-resistant Object Detection with Noisy Annotations

Junnan Li, Caiming Xiong, Richard Socher +1

Training deep object detectors requires significant amount of human-annotated images with accurate object labels and bounding box coordinates, which are extremely expensive to acqu…

cs.CV2020500 cited

DivideMix: Learning with Noisy Labels as Semi-supervised Learning

Junnan Li, Richard Socher, Steven C. H. Hoi

Deep neural networks are known to be annotation-hungry. Numerous efforts have been devoted to reducing the annotation cost when learning with deep networks. Two prominent direction…

cs.CV2019

Learning from Noisy Anchors for One-stage Object Detection

Hengduo Li, Zuxuan Wu, Chen Zhu +3

State-of-the-art object detectors rely on regressing and classifying an extensive list of possible anchors, which are divided into positive and negative samples based on their inte…

cs.CV2019

WSLLN: Weakly Supervised Natural Language Localization Networks

Mingfei Gao, Larry S. Davis, Richard Socher +1

We propose weakly supervised language localization networks (WSLLN) to detect events in long, untrimmed videos given language queries. To learn the correspondence between visual se…