Decoupled Networks
Inner product-based convolution has been a central component of convolutional neural networks (CNNs) and the key to learning visual representations. Inspired by the observation that CNN-learned features are naturally decoupled with the norm of features corresponding to the intra-class variation and the angle corresponding to the semantic difference, we propose a generic decoupled learning framework which models the intra-class variation and semantic difference independently. Specifically, we first reparametrize the inner product to a decoupled form and then generalize it to the decoupled convolution operator which serves as the building block of our decoupled networks. We present several effective instances of the decoupled convolution operator. Each decoupled operator is well motivated and has an intuitive geometric interpretation. Based on these decoupled operators, we further propose to directly learn the operator from data. Extensive experiments show that such decoupled reparameterization renders significant performance gain with easier convergence and stronger robustness.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Spectral Efficiency Analysis of Uplink-Downlink Decoupled Access in C-V2X Networks
The uplink (UL)/downlink (DL) decoupled access has been emerging as a novel access architecture to improve the performance gains in cellular networks. In this paper, we investigate the UL/DL decoupled access performance …
Spectral Efficiency Analysis of Uplink-Downlink Decoupled Access in C-V2X NetworksFinite-Time Decoupled Convergence in Nonlinear Two-Time-Scale Stochastic Approximation
In two-time-scale stochastic approximation (SA), two iterates are updated at varying speeds using different step sizes, with each update influencing the other. Previous studies on linear two-time-scale SA have shown that…
Decoupled SGDA for Games with Intermittent Strategy Communication
We focus on reducing communication overhead in multiplayer games, where frequently exchanging strategies between players is not feasible and players have noisy or outdated strategies of the other players. We introduce De…
On the Equivalence of Decoupled Graph Convolution Network and Label Propagation
The original design of Graph Convolution Network (GCN) couples feature transformation and neighborhood aggregation for node representation learning. Recently, some work shows that coupling is inferior to decoupling, whic…
Node ClassificationPseudo LabelRepresentation LearningLearning to Merge Tokens via Decoupled Embedding for Efficient Vision Transformers
Recent token reduction methods for Vision Transformers (ViTs) incorporate token merging, which measures the similarities between token embeddings and combines the most similar pairs. However, their merging policies are d…
Token Reduction