اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدParameter Efficient Deep Neural Networks with Bilinear Projections
50
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Recent research on deep neural networks (DNNs) has primarily focused on improving the model accuracy. Given a proper deep learning framework, it is generally possible to increase the depth or layer width to achieve a higher level of accuracy. However, the huge number of model parameters imposes more computational and memory usage overhead and leads to the parameter redundancy. In this paper, we address the parameter redundancy problem in DNNs by replacing conventional full projections with bilinear projections. For a fully-connected layer with $D$ input nodes and $D$ output nodes, applying bilinear projection can reduce the model space complexity from $mathcal{O}(D^2)$ to $mathcal{O}(2D)$, achieving a deep model with a sub-linear layer size. However, structured projection has a lower freedom of degree compared to the full projection, causing the under-fitting problem. So we simply scale up the mapping size by increasing the number of output channels, which can keep and even boosts the model accuracy. This makes it very parameter-efficient and handy to deploy such deep models on mobile systems with memory limitations. Experiments on four benchmark datasets show that applying the proposed bilinear projection to deep neural networks can achieve even higher accuracies than conventional full DNNs, while significantly reduces the model size.
قيم البحث
اقرأ أيضاً
Channel pruning is a promising technique to compress the parameters of deep convolutional neural networks(DCNN) and to speed up the inference. This paper aims to address the long-standing inefficiency of channel pruning. Most channel pruning methods
recover the prediction accuracy by re-training the pruned model from the remaining parameters or random initialization. This re-training process is heavily dependent on the sufficiency of computational resources, training data, and human interference(tuning the training strategy). In this paper, a highly efficient pruning method is proposed to significantly reduce the cost of pruning DCNN. The main contributions of our method include: 1) pruning compensation, a fast and data-efficient substitute of re-training to minimize the post-pruning reconstruction loss of features, 2) compensation-aware pruning(CaP), a novel pruning algorithm to remove redundant or less-weighted channels by minimizing the loss of information, and 3) binary structural search with step constraint to minimize human interference. On benchmarks including CIFAR-10/100 and ImageNet, our method shows competitive pruning performance among the state-of-the-art retraining-based pruning methods and, more importantly, reduces the processing time by 95% and data usage by 90%.
The performance of Deep Neural Networks (DNNs) keeps elevating in recent years with increasing network depth and width. To enable DNNs on edge devices like mobile phones, researchers proposed several network compression methods including pruning, qua
ntization and factorization. Among the factorization-based approaches, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations. Several previous works attempted to directly approximate a pre-trained model by low-rank decomposition; however, small approximation errors in parameters can ripple a large prediction loss. As a result, performance usually drops significantly and a sophisticated fine-tuning is required to recover accuracy. We argue that it is not optimal to separate low-rank approximation from training. Unlike previous works, this paper integrates low rank approximation and regularization into the training. We propose Trained Rank Pruning (TRP), which iterates low rank approximation and training. TRP maintains the capacity of original network while imposes low-rank constraints during training. A stochastic sub-gradient descent optimized nuclear regularization is utilized to further encourage low rank in TRP. The TRP trained network has low-rank structure in nature, and can be approximated with negligible performance loss, eliminating fine-tuning after low rank approximation. The methods are comprehensively evaluated on CIFAR-10 and ImageNet, outperforming previous compression methods using low rank approximation. Code is available: https://github.com/yuhuixu1993/Trained-Rank-Pruning
To accelerate DNNs inference, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations. Several previous works attempted to directly approximate a pre-trained model by low-rank decomposit
ion; however, small approximation errors in parameters can ripple over a large prediction loss. Apparently, it is not optimal to separate low-rank approximation from training. Unlike previous works, this paper integrates low rank approximation and regularization into the training process. We propose Trained Rank Pruning (TRP), which alternates between low rank approximation and training. TRP maintains the capacity of the original network while imposing low-rank constraints during training. A nuclear regularization optimized by stochastic sub-gradient descent is utilized to further promote low rank in TRP. Networks trained with TRP has a low-rank structure in nature, and is approximated with negligible performance loss, thus eliminating fine-tuning after low rank approximation. The proposed method is comprehensively evaluated on CIFAR-10 and ImageNet, outperforming previous compression counterparts using low rank approximation. Our code is available at: https://github.com/yuhuixu1993/Trained-Rank-Pruning.
Recently, channel attention mechanism has demonstrated to offer great potential in improving the performance of deep convolutional neural networks (CNNs). However, most existing methods dedicate to developing more sophisticated attention modules for
achieving better performance, which inevitably increase model complexity. To overcome the paradox of performance and complexity trade-off, this paper proposes an Efficient Channel Attention (ECA) module, which only involves a handful of parameters while bringing clear performance gain. By dissecting the channel attention module in SENet, we empirically show avoiding dimensionality reduction is important for learning channel attention, and appropriate cross-channel interaction can preserve performance while significantly decreasing model complexity. Therefore, we propose a local cross-channel interaction strategy without dimensionality reduction, which can be efficiently implemented via $1D$ convolution. Furthermore, we develop a method to adaptively select kernel size of $1D$ convolution, determining coverage of local cross-channel interaction. The proposed ECA module is efficient yet effective, e.g., the parameters and computations of our modules against backbone of ResNet50 are 80 vs. 24.37M and 4.7e-4 GFLOPs vs. 3.86 GFLOPs, respectively, and the performance boost is more than 2% in terms of Top-1 accuracy. We extensively evaluate our ECA module on image classification, object detection and instance segmentation with backbones of ResNets and MobileNetV2. The experimental results show our module is more efficient while performing favorably against its counterparts.
Parameters in deep neural networks which are trained on large-scale databases can generalize across multiple domains, which is referred as transferability. Unfortunately, the transferability is usually defined as discrete states and it differs with d
omains and network architectures. Existing works usually heuristically apply parameter-sharing or fine-tuning, and there is no principled approach to learn a parameter transfer strategy. To address the gap, a parameter transfer unit (PTU) is proposed in this paper. The PTU learns a fine-grained nonlinear combination of activations from both the source and the target domain networks, and subsumes hand-crafted discrete transfer states. In the PTU, the transferability is controlled by two gates which are artificial neurons and can be learned from data. The PTU is a general and flexible module which can be used in both CNNs and RNNs. Experiments are conducted with various network architectures and multiple transfer domain pairs. Results demonstrate the effectiveness of the PTU as it outperforms heuristic parameter-sharing and fine-tuning in most settings.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
