1k citations · 1.5k across the 81 of their papers we have counts for
83 papers
When Muon Meets Task Interference: A Spectral Perspective on Continual Learning and Model Merging
Shangge Liu, Yuehan Yin, Yinghuan Shi +2
Continual learning (CL) and model merging (MM) both aim to obtain a single model that performs well across multiple tasks, challenged respectively by catastrophic forgetting and we…
Towards the Connection between Activation Sparsity and Flat Minima
Ze Peng, Jian Zhang, Lei Qi +2
The observation that activation sparsity emerges in MLP blocks of standardly trained Transformers offers an opportunity to drastically reduce computation costs without sacrificing…
CLASP: Class-Adaptive Layer Fusion and Dual-Stage Pruning for Multimodal Large Language Models
Yunkai Dang, Yizhu Jiang, Yifan Jiang +4
Multimodal Large Language Models (MLLMs) suffer from substantial computational overhead due to the high redundancy in visual token sequences. Existing approaches typically address…
Understanding and Enforcing Weight Disentanglement in Task Arithmetic
Shangge Liu, Yuehan Yin, Lei Wang +5
Task arithmetic provides an efficient, training-free way to edit pre-trained models, yet lacks a fundamental theoretical explanation for its success. The existing concept of ``weig…
DeferredSeg:A Multi-Expert Deferral Framework for Medical Image Segmentation
Qiuyu Tian, Haoliang Sun, Yunshan Wang +2
Segmentation models based on deep neural networks demonstrate strong generalization for medical image segmentation. However, they often exhibit overconfidence or underconfidence, l…
Diffusion-Based Data Augmentation for Image Recognition: A Systematic Analysis and Evaluation
Zekun Li, Yinghuan Shi, Yang Gao +1
Diffusion-based data augmentation (DiffDA) has emerged as a promising approach to improving classification performance under data scarcity. However, existing works vary significant…
Leveraging Flatness to Improve Information-Theoretic Generalization Bounds for SGD
Ze Peng, Jian Zhang, Yisen Wang +3
Information-theoretic (IT) generalization bounds have been used to study the generalization of learning algorithms. These bounds are intrinsically data- and algorithm-dependent so…
LibContinual: A Comprehensive Library towards Realistic Continual Learning
Wenbin Li, Shangge Liu, Borui Kang +7
A fundamental challenge in Continual Learning (CL) is catastrophic forgetting, where adapting to new tasks degrades the performance on previous ones. While the field has evolved wi…
An Adaptor for Triggering Semi-Supervised Learning to Out-of-Box Serve Deep Image Clustering
Yue Duan, Lei Qi, Yinghuan Shi +1
Recently, some works integrate SSL techniques into deep clustering frameworks to enhance image clustering performance. However, they all need pretraining, clustering learning, or a…
Mamba-Sea: A Mamba-based Framework with Global-to-Local Sequence Augmentation for Generalizable Medical Image Segmentation
Zihan Cheng, Jintao Guo, Jian Zhang +4
To segment medical images with distribution shifts, domain generalization (DG) has emerged as a promising setting to train models on source domains that can generalize to unseen ta…
Balancing Multi-Target Semi-Supervised Medical Image Segmentation with Collaborative Generalist and Specialists
You Wang, Zekun Li, Lei Qi +3
Despite the promising performance achieved by current semi-supervised models in segmenting individual medical targets, many of these models suffer a notable decrease in performance…
Text and Image Are Mutually Beneficial: Enhancing Training-Free Few-Shot Classification with CLIP
Yayuan Li, Jintao Guo, Lei Qi +2
Contrastive Language-Image Pretraining (CLIP) has been widely used in vision tasks. Notably, CLIP has demonstrated promising performance in few-shot learning (FSL). However, existi…
Dual-Teacher Ensemble Models with Double-Copy-Paste for 3D Semi-Supervised Medical Image Segmentation
Zhan Fa, Shumeng Li, Jian Zhang +3
Semi-supervised learning (SSL) techniques address the high labeling costs in 3D medical image segmentation, with the teacher-student model being a common approach. However, using a…
START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation
Jintao Guo, Lei Qi, Yinghuan Shi +1
Domain Generalization (DG) aims to enable models to generalize to unseen target domains by learning from multiple source domains. Existing DG methods primarily rely on convolutiona…
PC: Pseudo-Classification Based Pseudo-Captioning for Noisy Correspondence Learning in Cross-Modal Retrieval
Yue Duan, Zhangxuan Gu, Zhenzhe Ying +3
In the realm of cross-modal retrieval, seamlessly integrating diverse modalities within multimedia remains a formidable challenge, especially given the complexities introduced by n…
The Devil is in the Statistics: Mitigating and Exploiting Statistics Difference for Generalizable Semi-supervised Medical Image Segmentation
Muyang Qiu, Jian Zhang, Lei Qi +3
Despite the recent success of domain generalization in medical image segmentation, voxel-wise annotation for all source domains remains a huge burden. Semi-supervised domain genera…
Learn to Preserve and Diversify: Parameter-Efficient Group with Orthogonal Regularization for Domain Generalization
Jiajun Hu, Jian Zhang, Lei Qi +2
Domain generalization (DG) aims to avoid the performance degradation of the model when the distribution shift between the limited training data and unseen test data occurs. Recentl…
Constructing and Exploring Intermediate Domains in Mixed Domain Semi-supervised Medical Image Segmentation
Qinghe Ma, Jian Zhang, Lei Qi +3
Both limited annotation and domain shift are prevalent challenges in medical image segmentation. Traditional semi-supervised segmentation and unsupervised domain adaptation methods…
SETA: Semantic-Aware Token Augmentation for Domain Generalization
Jintao Guo, Lei Qi, Yinghuan Shi +1
Domain generalization (DG) aims to enhance the model robustness against domain shifts without accessing target domains. A prevalent category of methods for DG is data augmentation,…
Stitching, Fine-tuning, Re-training: A SAM-enabled Framework for Semi-supervised 3D Medical Image Segmentation
Shumeng Li, Lei Qi, Qian Yu +3
Segment Anything Model (SAM) fine-tuning has shown remarkable performance in medical image segmentation in a fully supervised manner, but requires precise annotations. To reduce th…
Learning Generalizable Models via Disentangling Spurious and Enhancing Potential Correlations
Na Wang, Lei Qi, Jintao Guo +2
Domain generalization (DG) intends to train a model on multiple source domains to ensure that it can generalize well to an arbitrary unseen target domain. The acquisition of domain…
PG-LBO: Enhancing High-Dimensional Bayesian Optimization with Pseudo-Label and Gaussian Process Guidance
Taicai Chen, Yue Duan, Dong Li +3
Variational Autoencoder based Bayesian Optimization (VAE-BO) has demonstrated its excellent performance in addressing high-dimensional structured optimization problems. However, cu…
Roll With the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained Learning
Yue Duan, Zhen Zhao, Lei Qi +3
While semi-supervised learning (SSL) has yielded promising results, the more realistic SSL scenario remains to be explored, in which the unlabeled data exhibits extremely high reco…
A Theoretical Explanation of Activation Sparsity through Flat Minima and Adversarial Robustness
Ze Peng, Lei Qi, Yinghuan Shi +1
A recent empirical observation (Li et al., 2022b) of activation sparsity in MLP blocks offers an opportunity to drastically reduce computation costs for free. Although having attri…