This paper presents FusionShot, a focal diversity optimized few-shot ensemble learning approach for boosting the robustness and generalization performance of pre-trained few-shot models. The paper makes three original contributions. First, we explore the unique characteristics of few-shot learning to ensemble multiple few-shot (FS) models by creating three alternative fusion channels. Second, we introduce the concept of focal error diversity to learn the most efficient ensemble teaming strategy, rather than assuming that an ensemble of a larger number of base models will outperform those sub-ensembles of smaller size. We develop a focal-diversity ensemble pruning method to effectively prune out the candidate ensembles with low ensemble error diversity and recommend top-$K$ FS ensembles with the highest focal error diversity. Finally, we capture the complex non-linear patterns of ensemble few-shot predictions by designing the learn-to-combine algorithm, which can learn the diverse weight assignments for robust ensemble fusion over different member models. Extensive experiments on representative few-shot benchmarks show that the top-K ensembles recommended by FusionShot can outperform the representative SOTA few-shot models on novel tasks (different distributions and unknown at training), and can prevail over existing few-shot learners in both cross-domain settings and adversarial settings. For reproducibility purposes, FusionShot trained models, results, and code are made available at https://github.com/sftekin/fusionshot
Soft Label Pruning and Quantization for Large-Scale Dataset Distillation
CFAR, Agency for Science, Technology and Research, Singapore（新加坡科技研究局应用科学与技术研究院）；IHPC, Agency for Science, Technology and Research, Singapore（新加坡科技研究局信息与通信技术研究院）；National University of Singapore（新加坡国立大学）
Unstructured neural network pruning algorithms have achieved impressive compression rates. However, the resulting - typically irregular - sparse matrices hamper efficient hardware implementations, leading to additional memory usage and complex control logic that diminishes the benefits of unstructured pruning. This has spurred structured coarse-grained pruning solutions that prune entire filters or even layers, enabling efficient implementation at the expense of reduced flexibility. Here we propose a flexible new pruning mechanism that facilitates pruning at different granularities (weights, k…
University of Science and Technology of China（中国科学技术大学）；Texas A&M University（得克萨斯农工大学）；WeBank（微众银行）
Neural architecture search (NAS) is gaining more and more attention in recent years due to its flexibility and remarkable capability to reduce the burden of neural network design. To achieve better performance, however, the searching process usually costs massive computations that might not be affordable for researchers and practitioners. While recent attempts have employed ensemble learning methods to mitigate the enormous computational cost, however, they neglect a key property of ensemble methods, namely diversity, which leads to collecting more similar sub-architectures with potential redu…
TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Models
University of North Carolina Chapel Hill（北卡罗来纳大学教堂山分校）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Massachusetts Institute of Technology（麻省理工学院）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Hong Kong University of Science and Technology（香港科学与技术大学）
Systematic Characterization of Minimal Deep Learning Architectures: A Unified Analysis of Convergence, Pruning, and Quantization
School of Computing, Newcastle University（新castle大学计算机学院）；VSB-Technical University of Ostrava（奥斯特拉瓦技术大学）；Queen Mary University of London（伦敦女王玛丽大学）；University of Florida（佛罗里达大学）；University of Catania（卡塔尼亚大学）
The advancement of convolutional neural networks (CNNs) on various vision applications has attracted lots of attention. Yet the majority of CNNs are unable to satisfy the strict requirement for real-world deployment. To overcome this, the recent popular network pruning is an effective method to reduce the redundancy of the models. However, the ranking of filters according to their "importance" on different pruning criteria may be inconsistent. One filter could be important according to a certain criterion, while it is unnecessary according to another one, which indicates that each criterion is…
RS-Prune: Training-Free Data Pruning at High Ratios for Efficient Remote Sensing Diffusion Foundation Models
Department of Earth System Science, Tsinghua University（清华大学地球系统科学系）；School of Artificial Intelligence, Sun Yat-sen University（中山大学人工智能学院）；National Supercomputing Center in Shenzhen（深圳国家超算中心）；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生学院）；Department of Geography, The University of Hong Kong（香港大学地理系）；Wangxuan Institute of Computer Technology, Peking University（北京大学王轩计算机技术研究所）
In this paper, we first introduce batch normalization to the edRVFL network. This re-normalization method can help the network avoid divergence of the hidden features. Then we propose novel variants of Ensemble Deep Random Vector Functional Link (edRVFL). Weighted edRVFL (WedRVFL) uses weighting methods to give training samples different weights in different layers according to how the samples were classified confidently in the previous layer thereby increasing the ensemble's diversity and accuracy. Furthermore, a pruning-based edRVFL (PedRVFL) has also been proposed. We prune some inferior ne…
Malicious attackers can generate targeted adversarial examples by imposing tiny noises, forcing neural networks to produce specific incorrect outputs. With cross-model transferability, network models remain vulnerable even in black-box settings. Recent studies have shown the effectiveness of ensemble-based methods in generating transferable adversarial examples. To further enhance transferability, model augmentation methods aim to produce more networks participating in the ensemble. However, existing model augmentation methods are only proven effective in untargeted attacks. In this work, we p…
University of Science and Technology Beijing（北京科技大学）；Chinese Academy of Sciences（中国科学院）
Classifier ensemble generally should combine diverse component classifiers. However, it is difficult to give a definitive connection between diversity measure and ensemble accuracy. Given a list of available component classifiers, how to adaptively and diversely ensemble classifiers becomes a big challenge in the literature. In this paper, we argue that diversity, not direct diversity on samples but adaptive diversity with data, is highly correlated to ensemble accuracy, and we propose a novel technology for classifier ensemble, learning to diversify, which learns to adaptively combine classif…
University of New South Wales（新南威尔士大学）；Jiangnan University（江南大学）；University of Technology Sydney（悉尼科技大学）；University of California San Diego（加州大学圣地亚哥分校）；CSIRO’s Data61（澳大利亚联邦科学与工业研究组织Data61）
Zero-Shot Learning (ZSL) aims to transfer classification capability from seen to unseen classes. Recent methods have proved that generalization and specialization are two essential abilities to achieve good performance in ZSL. However, focusing on only one of the abilities may result in models that are either too general with degraded classification ability or too specialized to generalize to unseen classes. In this paper, we propose an end-to-end network, termed as BGSNet, which equips and balances generalization and specialization abilities at the instance and dataset level. Specifically, BG…
OTPrune: Distribution-Aligned Visual Token Pruning via Optimal Transport
Morgan Stanley（摩根士丹利）；Clemson University（克莱姆森大学）；Arizona State University（亚利桑那州立大学）；Washington University in St. Louis（圣路易斯华盛顿大学）；Texas A&M University（德克萨斯农工大学）；Rice University（莱斯大学）；Florida State University（佛罗里达州立大学）
Selectivity Drives Efficiency: Dataset Pruning for Visual Place Recognition
Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Shenzhen University of Advanced Technology（深圳先进技术研究院）
Which Layer Causes Distribution Deviation? Entropy-Guided Adaptive Pruning for Diffusion and Flow Models
Stanford University（斯坦福大学）；North China Electric Power University（华北电力大学）；University of Technology Sydney（悉尼科技大学）；Harvard University（哈佛大学）；University of Science and Technology of China（中国科学技术大学）
Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs
National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University（国家多媒体信息处理重点实验室，计算机学院，北京大学）；ByteDance（字节跳动）
EvoLattice: Persistent Internal-Population Evolution through Multi-Alternative Quality-Diversity Graph Representations for LLM-Guided Program Discovery
Sun Yat-sen University（中山大学）；NEC Laboratories, China（NEC中国研究院）
The aim of this study is to provide an automatic computational framework to assist clinicians in diagnosing Focal Liver Lesions (FLLs) in Contrast-Enhancement Ultrasound (CEUS). We represent FLLs in a CEUS video clip as an ensemble of Region-of-Interests (ROIs), whose locations are modeled as latent variables in a discriminative model. Different types of FLLs are characterized by both spatial and temporal enhancement patterns of the ROIs. The model is learned by iteratively inferring the optimal ROI locations and optimizing the model parameters. To efficiently search the optimal spatial and te…
