Qianru Sun

papers

3,482

total citations

papers (27)

Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection

CVPR 2023arXiv

125

citations

RMM: Reinforced Memory Management for Class-Incremental Learning

NEURIPS 2021arXiv

119

citations

Freestyle Layout-to-Image Synthesis

CVPR 2023arXiv

citations

Extracting Class Activation Maps From Non-Discriminative Features As Well

CVPR 2023arXiv

citations

Self-Supervised Learning Disentangled Group Representation as Feature

NEURIPS 2021arXiv

citations

Class-Incremental Exemplar Compression for Class-Incremental Learning

CVPR 2023arXiv

citations

Transporting Causal Mechanisms for Unsupervised Domain Adaptation

ICCV 2021arXiv

citations

Self-Regulation for Semantic Segmentation

ICCV 2021arXiv

citations

Equivariance and Invariance Inductive Bias for Learning from Insufficient Data

ECCV 2022arXiv

citations

Semantic Scene Completion With Cleaner Self

CVPR 2023arXiv

citations

Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognition

ICCV 2023arXiv

citations

Few-shot Learner Parameterization by Diffusion Time-steps

CVPR 2024arXiv

citations

On Mitigating Hard Clusters for Face Clustering

ECCV 2022arXiv

citations

Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization

ICCV 2025arXiv

citations

Class Is Invariant to Context and Vice Versa: On Learning Invariance for Out-of-Distribution Generalization

ECCV 2022arXiv

citations

Unleashing Network Potentials for Semantic Scene Completion

CVPR 2024arXiv

citations

Meta-Learning Hyperparameters for Parameter Efficient Fine-Tuning

CVPR 2025

citations

Qianru Sun

papers (27)

Causal Intervention for Weakly-Supervised Semantic Segmentation

Mnemonics Training: Multi-Class Incremental Learning Without Forgetting

Feature Pyramid Transformer

Visual Commonsense R-CNN

Interventional Few-Shot Learning

Adaptive Aggregation Networks for Class-Incremental Learning

Counterfactual Zero-Shot and Open-Set Visual Recognition

Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation

Causal Attention for Unbiased Visual Recognition

An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning

Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection

RMM: Reinforced Memory Management for Class-Incremental Learning

Freestyle Layout-to-Image Synthesis

Extracting Class Activation Maps From Non-Discriminative Features As Well

Self-Supervised Learning Disentangled Group Representation as Feature

Class-Incremental Exemplar Compression for Class-Incremental Learning

Transporting Causal Mechanisms for Unsupervised Domain Adaptation

Self-Regulation for Semantic Segmentation

Equivariance and Invariance Inductive Bias for Learning from Insufficient Data

Semantic Scene Completion With Cleaner Self

Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognition

Few-shot Learner Parameterization by Diffusion Time-steps

On Mitigating Hard Clusters for Face Clustering

Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization

Class Is Invariant to Context and Vice Versa: On Learning Invariance for Out-of-Distribution Generalization

Unleashing Network Potentials for Semantic Scene Completion

Meta-Learning Hyperparameters for Parameter Efficient Fine-Tuning

papers (27)

Causal Intervention for Weakly-Supervised Semantic Segmentation

Mnemonics Training: Multi-Class Incremental Learning Without Forgetting

Feature Pyramid Transformer

Visual Commonsense R-CNN

Interventional Few-Shot Learning

Adaptive Aggregation Networks for Class-Incremental Learning

Counterfactual Zero-Shot and Open-Set Visual Recognition

Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation

Causal Attention for Unbiased Visual Recognition

An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning

Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection

RMM: Reinforced Memory Management for Class-Incremental Learning

Freestyle Layout-to-Image Synthesis

Extracting Class Activation Maps From Non-Discriminative Features As Well

Self-Supervised Learning Disentangled Group Representation as Feature

Class-Incremental Exemplar Compression for Class-Incremental Learning

Transporting Causal Mechanisms for Unsupervised Domain Adaptation

Self-Regulation for Semantic Segmentation

Equivariance and Invariance Inductive Bias for Learning from Insufficient Data

Semantic Scene Completion With Cleaner Self

Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognition

Few-shot Learner Parameterization by Diffusion Time-steps

On Mitigating Hard Clusters for Face Clustering

Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization

Class Is Invariant to Context and Vice Versa: On Learning Invariance for Out-of-Distribution Generalization

Unleashing Network Potentials for Semantic Scene Completion

Meta-Learning Hyperparameters for Parameter Efficient Fine-Tuning