Traditional end-to-end deep learning models often enhance feature representation and overall performance by increasing the depth and complexity of the network during training. However, this approach inevitably introduces issues of parameter redundancy and resource inefficiency, especially in deeper networks. While existing works attempt to skip certain redundant layers to alleviate these problems, challenges related to poor performance, computational complexity, and inefficient memory usage remain. To address these issues, we propose an innovative training approach called Replacement Learning, which mitigates these limitations by completely replacing all the parameters of the frozen layers with only two learnable parameters. Specifically, Replacement Learning selectively freezes the parameters of certain layers, and the frozen layers utilize parameters from adjacent layers, updating them through a parameter integration mechanism controlled by two learnable parameters. This method leverages information from surrounding structures, reduces computation, conserves GPU memory, and maintains a balance between historical context and new inputs, ultimately enhancing overall model performance. We conducted experiments across four benchmark datasets, including CIFAR-10, STL-10, SVHN, and ImageNet, utilizing various architectures such as CNNs and ViTs to validate the effectiveness of Replacement Learning. Experimental results demonstrate that our approach reduces the number of parameters, training time, and memory consumption while completely surpassing the performance of end-to-end training.
FreeTransformSR: Efficient Lightweight Image Super-Resolution via Free Low-Rank Learnable Transform
Chinese Academy of Sciences Changchun Institute of Optics Fine Mechanics and Physics(中国科学院长春光学精密机械与物理研究所);University of the Chinese Academy of Sciences(中国科学院大学)
Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitives
Beijing Jiaotong University(北京交通大学);Sun Yat-sen University(中山大学);Beijing University of Posts and Telecommunications(北京邮电大学);Southern University of Science and Technology(南方科技大学);Michigan State University(密歇根州立大学)
OFVL-MS: Once for Visual Localization across Multiple Indoor Scenes
Harbin Institute of Technology(哈尔滨工业大学);China Coal Science and Technology Intelligent Storage Technology Co., Ltd.(中煤科工智能存储科技有限公司);Harbin Institute of Technology, Zhengzhou Research Institute(哈尔滨工业大学郑州研究院)
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)
Representing Prior Knowledge Using Randomly, Weighted Feature Networks for Visual Relationship Detection
School of Computing and Augmented Intelligence, Arizona State University(亚利桑那州立大学计算与增强智能学院);School of Sustainability, Arizona State University(亚利桑那州立大学可持续发展学院);School of Complex Adaptive Systems, Arizona State University(亚利桑那州立大学复杂适应系统学院);School of Life Sciences, Arizona State University(亚利桑那州立大学生命科学学院)