paper-with-me

Papers

Non-iterative recomputation of dense layers for performance improvement of DCNN

2018-09-14 · Yimin Yang, Q. M. Jonathan Wu, Xiexing Feng, Thangarajah Akilan

An iterative method of learning has become a paradigm for training deep convolutional neural networks (DCNN). However, utilizing a non-iterative learning strategy can accelerate the training process of the DCNN and surprisingly such approach has been rarely explored by the deep learning (DL) community. It motivates this paper to introduce a non-iterative learning strategy that eliminates the backpropagation (BP) at the top dense or fully connected (FC) layers of DCNN, resulting in, lower training time and higher performance. The proposed method exploits the Moore-Penrose Inverse to pull back the current residual error to each FC layer, generating well-generalized features. Then using the recomputed features, i.e., the new generalized features the weights of each FC layer is computed according to the Moore-Penrose Inverse. We evaluate the proposed approach on six widely accepted object recognition benchmark datasets: Scene-15, CIFAR-10, CIFAR-100, SUN-397, Places365, and ImageNet. The experimental results show that the proposed method obtains significant improvements over 30 state-of-the-art methods. Interestingly, it also indicates that any DCNN with the proposed method can provide better performance than the same network with its original training based on BP.

📄 PDF Abstract BibTeX arXiv:1809.05606

Code (0)

등록된 구현이 없습니다.

Tasks

Object Recognition

Methods 이 논문이 사용한 방법론

DCNN Diffusion-convolutional neural networks (DCNN) is a model for graph-structured data. Through the introduction of a diffusion-convolution operation, diffusion-based representations…

Similar Papers 제목 키워드 기반

Deep Networks with Fast Retraining

2020-08-13 · Wandong Zhang, Yimin Yang, Jonathan Wu

Recent work [1] has utilized Moore-Penrose (MP) inverse in deep convolutional neural network (DCNN) learning, which achieves better generalization performance over the DCNN with a stochastic gradient descent (SGD) pipeli…

Image Classification

Echo: Compiler-based GPU Memory Footprint Reduction for LSTM RNN Training

2018-05-22 · Bojian Zheng, Abhishek Tiwari, Nandita Vijaykumar, Gennady Pekhimenko

The Long-Short-Term-Memory Recurrent Neural Networks (LSTM RNNs) are a popular class of machine learning models for analyzing sequential data. Their training on modern GPUs, however, is limited by the GPU memory capacity…

GPUMachine TranslationNMT

VLCache: Computing 2% Vision Tokens and Reusing 98% for Vision-Language Inference

2025-12-15 · Shengling Qin, Hao Yu, Chenxin Wu, Zheng Li 외 arxiv

This paper presents VLCache, a cache reuse framework that exploits both Key-Value (KV) cache and encoder cache from prior multimodal inputs to eliminate costly recomputation when the same multimodal inputs recur. Unlike …

Adacc: An Adaptive Framework Unifying Compression and Activation Recomputation for LLM Training

2025-08-01 · Ping Chen, Zhuohong Deng, Ping Li, Shuibing He 외 arxiv

Training large language models (LLMs) is often constrained by GPU memory limitations. To alleviate memory pressure, activation recomputation and data compression have been proposed as two major strategies. However, both …

HERO: Hierarchical Extrapolation and Refresh for Efficient World Models

2025-08-25 · Quanjian Song, Xinyu Wang, Donghao Zhou, Jingyu Lin 외 arxiv

Generation-driven world models create immersive virtual environments but suffer slow inference due to the iterative nature of diffusion models. While recent advances have improved diffusion model efficiency, directly app…