Guiguang Ding

papers

5,149

total citations

papers (26)

IMRAM: Iterative Matching With Recurrent Attention Memory for Cross-Modal Image-Text Retrieval

CVPR 2020arXiv

371

citations

Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification

ECCV 2020arXiv

327

citations

ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting

ICCV 2021arXiv

198

citations

One-dimensional Adapter to Rule Them All: Concepts Diffusion Models and Erasing Applications

CVPR 2024arXiv

119

citations

PANDA: A Gigapixel-Level Human-Centric Video Dataset

CVPR 2020arXiv

citations

RepMLPNet: Hierarchical Vision MLP With Re-Parameterized Locality

CVPR 2022arXiv

citations

YOLOE: Real-Time Seeing Anything

ICCV 2025arXiv

citations

PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation

ECCV 2024arXiv

citations

Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detection

CVPR 2025arXiv

citations

Box-Level Active Detection

CVPR 2023arXiv

citations

LSNet: See Large, Focus Small

CVPR 2025arXiv

citations

HEIE: MLLM-Based Hierarchical Explainable AIGC Image Implausibility Evaluator

CVPR 2025arXiv

citations

Scaffold-BPE: Enhancing Byte Pair Encoding for Large Language Models with Simple and Effective Scaffold Token Removal

AAAI 2025arXiv

citations

Confidence-based Visual Dispersal for Few-shot Unsupervised Domain Adaptation

ICCV 2023arXiv

citations

Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence

ECCV 2024arXiv

citations

Geometry-Guided Domain Generalization for Monocular 3D Object Detection

AAAI 2024

citations

Debiased Novel Category Discovering and Localization

AAAI 2024arXiv

citations

Quantized Prompt for Efficient Generalization of Vision-Language Models

ECCV 2024arXiv

citations

Promptable Anomaly Segmentation with SAM Through Self-Perception Tuning

AAAI 2025arXiv

citations

PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation

NEURIPS 2025arXiv

citations

DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval

CVPR 2025arXiv

citations

DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup

ICCV 2025arXiv

citations

Guiguang Ding

papers (26)

RepVGG: Making VGG-Style ConvNets Great Again

Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs

RepViT: Revisiting Mobile CNN From ViT Perspective

Diverse Branch Block: Building a Convolution as an Inception-Like Unit

IMRAM: Iterative Matching With Recurrent Attention Memory for Cross-Modal Image-Text Retrieval

Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification

ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting

One-dimensional Adapter to Rule Them All: Concepts Diffusion Models and Erasing Applications

PANDA: A Gigapixel-Level Human-Centric Video Dataset

RepMLPNet: Hierarchical Vision MLP With Re-Parameterized Locality

YOLOE: Real-Time Seeing Anything

PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation

Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detection

Box-Level Active Detection

LSNet: See Large, Focus Small

HEIE: MLLM-Based Hierarchical Explainable AIGC Image Implausibility Evaluator

Scaffold-BPE: Enhancing Byte Pair Encoding for Large Language Models with Simple and Effective Scaffold Token Removal

Confidence-based Visual Dispersal for Few-shot Unsupervised Domain Adaptation

Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence

Geometry-Guided Domain Generalization for Monocular 3D Object Detection

Debiased Novel Category Discovering and Localization

Quantized Prompt for Efficient Generalization of Vision-Language Models

Promptable Anomaly Segmentation with SAM Through Self-Perception Tuning

PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation

DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval

DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup

papers (26)

RepVGG: Making VGG-Style ConvNets Great Again

Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs

RepViT: Revisiting Mobile CNN From ViT Perspective

Diverse Branch Block: Building a Convolution as an Inception-Like Unit

IMRAM: Iterative Matching With Recurrent Attention Memory for Cross-Modal Image-Text Retrieval

Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification

ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting

One-dimensional Adapter to Rule Them All: Concepts Diffusion Models and Erasing Applications

PANDA: A Gigapixel-Level Human-Centric Video Dataset

RepMLPNet: Hierarchical Vision MLP With Re-Parameterized Locality

YOLOE: Real-Time Seeing Anything

PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation

Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detection

Box-Level Active Detection

LSNet: See Large, Focus Small

HEIE: MLLM-Based Hierarchical Explainable AIGC Image Implausibility Evaluator

Scaffold-BPE: Enhancing Byte Pair Encoding for Large Language Models with Simple and Effective Scaffold Token Removal

Confidence-based Visual Dispersal for Few-shot Unsupervised Domain Adaptation

Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence

Geometry-Guided Domain Generalization for Monocular 3D Object Detection

Debiased Novel Category Discovering and Localization

Quantized Prompt for Efficient Generalization of Vision-Language Models

Promptable Anomaly Segmentation with SAM Through Self-Perception Tuning

PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation

DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval

DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup