4 citations · 15 across the 12 of their papers we have counts for
12 papers
Images Speak Louder Than Scores: Failure Mode Escape for Enhancing Generative Quality
Jie Shao, Ke Zhu, Minghao Fu +2
Diffusion models have achieved remarkable progress in class-to-image generation. However, we observe that despite impressive FID scores, state-of-the-art models often generate dist…
QwT-v2: Practical, Effective and Efficient Post-Training Quantization
Ningyuan Tang, Minghao Fu, Hao Yu +1
Network quantization is arguably one of the most practical network compression approaches for reducing the enormous resource consumption of modern deep neural networks. They usuall…
Quantization without Tears
Minghao Fu, Hao Yu, Jie Shao +3
Deep neural networks, while achieving remarkable success across diverse tasks, demand significant resources, including computation, GPU memory, bandwidth, storage, and energy. Netw…
Unified Low-rank Compression Framework for Click-through Rate Prediction
Hao Yu, Minghao Fu, Jiandong Ding +2
Deep Click-Through Rate (CTR) prediction models play an important role in modern industrial recommendation scenarios. However, high memory overhead and computational costs limit th…
Minimal Interaction Separated Tuning: A New Paradigm for Visual Adaptation
Ningyuan Tang, Minghao Fu, Jianxin Wu
The rapid scaling of large vision pretrained models makes fine-tuning tasks more and more difficult on devices with low computational resources. We explore a new visual adaptation…
Low-rank Attention Side-Tuning for Parameter-Efficient Fine-Tuning
Ningyuan Tang, Minghao Fu, Ke Zhu +1
In finetuning a large pretrained model to downstream tasks, parameter-efficient fine-tuning (PEFT) methods can effectively finetune pretrained models with few trainable parameters,…
Rectify the Regression Bias in Long-Tailed Object Detection
Ke Zhu, Minghao Fu, Jie Shao +2
Long-tailed object detection faces great challenges because of its extremely imbalanced class distribution. Recent methods mainly focus on the classification bias and its loss func…
DTL: Disentangled Transfer Learning for Visual Recognition
Minghao Fu, Ke Zhu, Jianxin Wu
When pre-trained models become rapidly larger, the cost of fine-tuning on downstream tasks steadily increases, too. To economically fine-tune these models, parameter-efficient tran…
Multi-Label Self-Supervised Learning with Scene Images
Ke Zhu, Minghao Fu, Jianxin Wu
Self-supervised learning (SSL) methods targeting scene images have seen a rapid growth recently, and they mostly rely on either a dedicated dense matching mechanism or a costly uns…
ESTISR: Adapting Efficient Scene Text Image Super-resolution for Real-Scenes
Minghao Fu, Xin Man, Yihan Xu +1
While scene text image super-resolution (STISR) has yielded remarkable improvements in accurately recognizing scene text, prior methodologies have placed excessive emphasis on opti…
Instance-based Max-margin for Practical Few-shot Recognition
Minghao Fu, Ke Zhu, Jianxin Wu
In order to mimic the human few-shot learning (FSL) ability better and to make FSL closer to real-world applications, this paper proposes a practical FSL (pFSL) setting. pFSL is ba…
Worst Case Matters for Few-Shot Recognition
Minghao Fu, Yun-Hao Cao, Jianxin Wu
Few-shot recognition learns a recognition model with very few (e.g., 1 or 5) images per category, and current few-shot learning methods focus on improving the average accuracy over…