147 citations · 1.2k across the 129 of their papers we have counts for
133 papers
DLIP: Distilling Language-Image Pre-training
Huafeng Kuang, Jie Wu, Xiawu Zheng +5
Vision-Language Pre-training (VLP) shows remarkable progress with the assistance of extremely heavy parameters, which challenges deployment in real applications. Knowledge distilla…
Continual Face Forgery Detection via Historical Distribution Preserving
Ke Sun, Shen Chen, Taiping Yao +3
Face forgery techniques have advanced rapidly and pose serious security threats. Existing face forgery detection methods try to learn generalizable features, but they still fall sh…
Systematic Investigation of Sparse Perturbed Sharpness-Aware Minimization Optimizer
Peng Mi, Li Shen, Tianhe Ren +6
Deep neural networks often suffer from poor generalization due to complex and non-convex loss landscapes. Sharpness-Aware Minimization (SAM) is a popular solution that smooths the…
Approximated Prompt Tuning for Vision-Language Pre-trained Models
Qiong Wu, Shubin Huang, Yiyi Zhou +4
Prompt tuning is a parameter-efficient way to deploy large-scale pre-trained models to downstream tasks by adding task-specific tokens. In terms of vision-language pre-trained (VLP…
MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models
Chaoyou Fu, Peixian Chen, Yunhang Shen +11
Multimodal Large Language Model (MLLM) relies on the powerful LLM to perform multimodal tasks, showing amazing emergent abilities in recent studies, such as writing poems based on…
Spatial Re-parameterization for N:M Sparsity
Yuxin Zhang, Mingbao Lin, Mingliang Xu +2
This paper presents a Spatial Re-parameterization (SpRe) method for the N:M sparsity. SpRe stems from an observation regarding the restricted variety in spatial sparsity of convolu…
Adapting Pre-trained Language Models to Vision-Language Tasks via Dynamic Visual Prompting
Shubin Huang, Qiong Wu, Yiyi Zhou +4
Pre-trained language models (PLMs) have played an increasing role in multimedia research. In terms of vision-language (VL) tasks, they often serve as a language encoder and still r…
DiffRate : Differentiable Compression Rate for Efficient Vision Transformers
Mengzhao Chen, Wenqi Shao, Peng Xu +6
Token compression aims to speed up large-scale vision transformers (e.g. ViTs) by pruning (dropping) or merging tokens. It is an important but challenging task. Although recent adv…
CamoDiffusion: Camouflaged Object Detection via Conditional Diffusion Models
Zhongxi Chen, Ke Sun, Xianming Lin +1
Camouflaged Object Detection (COD) is a challenging task in computer vision due to the high similarity between camouflaged objects and their surroundings. Existing COD methods prim…
Distribution-Flexible Subset Quantization for Post-Quantizing Super-Resolution Networks
Yunshan Zhong, Mingbao Lin, Jingjing Xie +3
This paper introduces Distribution-Flexible Subset Quantization (DFSQ), a post-training quantization method for super-resolution networks. Our motivation for developing DFSQ is bas…
Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models
Gen Luo, Yiyi Zhou, Tianhe Ren +3
Recently, growing interest has been aroused in extending the multimodal capability of large language models (LLMs), e.g., vision-language (VL) learning, which is regarded as the ne…
Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective
Yuexiao Ma, Huixia Li, Xiawu Zheng +6
Post-training quantization (PTQ) is widely regarded as one of the most efficient compression methods practically, benefitting from its data privacy and low computation costs. We ar…
Latent Feature Relation Consistency for Adversarial Robustness
Xingbin Liu, Huafeng Kuang, Hong Liu +3
Deep neural networks have been applied in many computer vision tasks and achieved state-of-the-art performance. However, misclassification will occur when DNN predicts adversarial…
CAT:Collaborative Adversarial Training
Xingbin Liu, Huafeng Kuang, Xianming Lin +2
Adversarial training can improve the robustness of neural networks. Previous methods focus on a single adversarial training strategy and do not consider the model property trained…
Towards Efficient Visual Adaption via Structural Re-parameterization
Gen Luo, Minglang Huang, Yiyi Zhou +4
Parameter-efficient transfer learning (PETL) is an emerging research spot aimed at inexpensively adapting large-scale pre-trained models to downstream tasks. Recent advances have a…
Active Teacher for Semi-Supervised Object Detection
Peng Mi, Jianghang Lin, Yiyi Zhou +7
In this paper, we study teacher-student learning from the perspective of data initialization and propose a novel algorithm called Active Teacher(Source code are available at: \url{…
Attention Disturbance and Dual-Path Constraint Network for Occluded Person Re-identification
Jiaer Xia, Lei Tan, Pingyang Dai +3
Occluded person re-identification (Re-ID) aims to address the potential occlusion problem when matching occluded or holistic pedestrians from different camera views. Many methods u…
Towards End-to-end Semi-supervised Learning for One-stage Object Detection
Gen Luo, Yiyi Zhou, Lei Jin +2
Semi-supervised object detection (SSOD) is a research hot spot in computer vision, which can greatly reduce the requirement for expensive bounding-box annotations. Despite great su…
Bi-directional Masks for Efficient N:M Sparse Training
Yuxin Zhang, Yiting Luo, Mingbao Lin +4
We focus on addressing the dense backward propagation issue for training efficiency of N:M fine-grained sparsity that preserves at most N out of M consecutive weights and achieves…
Real-Time Image Demoireing on Mobile Devices
Yuxin Zhang, Mingbao Lin, Xunchao Li +7
Moire patterns appear frequently when taking photos of digital screens, drastically degrading the image quality. Despite the advance of CNNs in image demoireing, existing networks…
Spectral Aware Softmax for Visible-Infrared Person Re-Identification
Lei Tan, Pingyang Dai, Qixiang Ye +3
Visible-infrared person re-identification (VI-ReID) aims to match specific pedestrian images from different modalities. Although suffering an extra modality discrepancy, existing m…
Exploring Invariant Representation for Visible-Infrared Person Re-Identification
Lei Tan, Yukang Zhang, Shengmei Shen +5
Cross-spectral person re-identification, which aims to associate identities to pedestrians across different spectra, faces a main challenge of the modality discrepancy. In this pap…
Discriminator-Cooperated Feature Map Distillation for GAN Compression
Tie Hu, Mingbao Lin, Lizhou You +2
Despite excellent performance in image generation, Generative Adversarial Networks (GANs) are notorious for its requirements of enormous storage and intensive computation. As an aw…
Exploring Content Relationships for Distilling Efficient GANs
Lizhou You, Mingbao Lin, Tie Hu +2
This paper proposes a content relationship distillation (CRD) to tackle the over-parameterized generative adversarial networks (GANs) for the serviceability in cutting-edge devices…