25 citations · 147 across the 70 of their papers we have counts for
10 papers · 1 filter
Rethinking skip connection model as a learnable Markov chain
Dengsheng Chen, Jie Hu, Wenwen Qiang +2
Over past few years afterward the birth of ResNet, skip connection has become the defacto standard for the design of modern architectures due to its widespread adoption, easy optim…
MetaMask: Revisiting Dimensional Confounder for Self-Supervised Learning
Jiangmeng Li, Wenwen Qiang, Yanan Zhang +4
As a successful approach to self-supervised learning, contrastive learning aims to learn invariant information shared among distortions of the input sample. While contrastive learn…
Modeling Multiple Views via Implicitly Preserving Global Consistency and Local Complementarity
Jiangmeng Li, Wenwen Qiang, Changwen Zheng +4
While self-supervised learning techniques are often used to mining implicit knowledge from unlabeled data via modeling multiple views, it is unclear how to perform effective repres…
Disentangle and Remerge: Interventional Knowledge Distillation for Few-Shot Object Detection from A Conditional Causal Perspective
Jiangmeng Li, Yanan Zhang, Wenwen Qiang +5
Few-shot learning models learn representations with limited human annotations, and such a learning paradigm demonstrates practicability in various tasks, e.g., image classification…
Robust Causal Graph Representation Learning against Confounding Effects
Hang Gao, Jiangmeng Li, Wenwen Qiang +4
The prevailing graph neural network models have achieved significant progress in graph representation learning. However, in this paper, we uncover an ever-overlooked phenomenon: th…
Interventional Contrastive Learning with Meta Semantic Regularizer
Wenwen Qiang, Jiangmeng Li, Changwen Zheng +2
Contrastive learning (CL)-based self-supervised learning models learn visual representations in a pairwise manner. Although the prevailing CL model has achieved great progress, in…
Supporting Vision-Language Model Inference with Confounder-pruning Knowledge Prompt
Jiangmeng Li, Wenyi Mo, Wenwen Qiang +4
Vision-language models are pre-trained by aligning image-text pairs in a common space to deal with open-set visual concepts. To boost the transferability of the pre-trained models,…
Robust Local Preserving and Global Aligning Network for Adversarial Domain Adaptation
Wenwen Qiang, Jiangmeng Li, Changwen Zheng +2
Unsupervised domain adaptation (UDA) requires source domain samples with clean ground truth labels during training. Accurately labeling a large number of source domain samples is t…
MetAug: Contrastive Learning via Meta Feature Augmentation
Jiangmeng Li, Wenwen Qiang, Changwen Zheng +2
What matters for contrastive learning? We argue that contrastive learning heavily relies on informative features, or "hard" (positive or negative) features. Early works include mor…
Bootstrapping Informative Graph Augmentation via A Meta Learning Approach
Hang Gao, Jiangmeng Li, Wenwen Qiang +3
Recent works explore learning graph representations in a self-supervised manner. In graph contrastive learning, benchmark methods apply various graph augmentation approaches. Howev…