PPR-FCN: Weakly Supervised Visual Relation Detection via Parallel Pairwise R-FCN

Zhang, Hanwang; Kyaw, Zawlin; Yu, Jinyang; Chang, Shih-Fu

doi:10.48550/arxiv.1708.01956

Cited by 7 publications

(2 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep Convolutional Neural Networks (CNNs) have achieved substantial advances in a wide range of vision tasks, such as object detection and recognition Corresponding author. 4 Code is available on: https://github.com/liuzechun/Bi-Real-net arXiv:1808.00278v5 [cs.CV] 29 Sep 2018 [12,23,25,5,3,20], depth perception [2,16], visual relation detection [29,30], face tracking and alignment [24,32,34,28,27], object tracking [17], etc. However, the superior performance of CNNs usually requires powerful hardware with abundant computing and memory resources.…”

Section: Introductionmentioning

confidence: 99%

Bi-Real Net: Enhancing the Performance of 1-Bit CNNs with Improved Representational Capability and Advanced Training Algorithm

Liu

Luo

et al. 2018

Lecture Notes in Computer Science

432

591

View full text Add to dashboard Cite

In this work, we study the 1-bit convolutional neural networks (CNNs), of which both the weights and activations are binary. While being efficient, the classification accuracy of the current 1-bit CNNs is much worse compared to their counterpart real-valued CNN models on the large-scale dataset, like ImageNet. To minimize the performance gap between the 1-bit and real-valued CNN models, we propose a novel model, dubbed Bi-Real net, which connects the real activations (after the 1-bit convolution and/or BatchNorm layer, before the sign function) to activations of the consecutive block, through an identity shortcut. Consequently, compared to the standard 1-bit CNN, the representational capability of the Bi-Real net is significantly enhanced and the additional cost on computation is negligible. Moreover, we develop a specific training algorithm including three technical novelties for 1bit CNNs. Firstly, we derive a tight approximation to the derivative of the non-differentiable sign function with respect to activation. Secondly, we propose a magnitude-aware gradient with respect to the weight for updating the weight parameters. Thirdly, we pre-train the real-valued CNN model with a clip function, rather than the ReLU function, to better initialize the Bi-Real net. Experiments on ImageNet show that the Bi-Real net with the proposed training algorithm achieves 56.4% and 62.2% top-1 accuracy with 18 layers and 34 layers, respectively. Compared to the state-of-the-arts (e.g., XNOR Net), Bi-Real net achieves up to 10% higher top-1 accuracy with more memory saving and lower computational cost. 4

show abstract

Section: Introductionmentioning

confidence: 99%

Bi-Real Net: Enhancing the Performance of 1-Bit CNNs with Improved Representational Capability and Advanced Training Algorithm

Liu

Luo

et al. 2018

Lecture Notes in Computer Science

432

591

View full text Add to dashboard Cite

show abstract

“…Deep Convolutional Neural Networks (CNNs) have achieved substantial advances in a wide range of vision tasks, such as object detection and recognition [21,33,37,36,11,8,31], depth perception [6,26], visual relation detection [43,44], face tracking and alignment [34,48,50,40,39], object tracking [28], etc. However, the superior performance of CNNs usually requires powerful hardware with abundant computing and memory resources, for example, highend graphics processing units (GPUs).…”

Section: Introductionmentioning

confidence: 99%

Bi-Real Net: Binarizing Deep Network Towards Real-Network Performance

Liu

Luo

et al. 2019

Int J Comput Vis

View full text Add to dashboard Cite

In this paper, we study 1-bit convolutional neural networks (CNNs), of which both the weights and activations are binary. While being efficient, the lacking of a representational capability and the training difficulty impede 1-bit CNNs from performing as well as real-valued networks. To this end, we propose Bi-Real net with a novel training algorithm to tackle these two challenges. To enhance the representational capability, we propagate the real-valued activations generated by each 1-bit convolution via a parameter-free shortcut. To address the training difficulty, we propose a training algorithm using a tighter approximation to the derivative of the sign function, a magnitude-aware binarization for weight updating, a better initialization method, and a two-step scheme for training a deep network. Experiments on ImageNet show that an 18-layer Bi-Real net with the proposed training algorithm achieves 56.4% top-1 classification accuracy, which is 10% higher than the state-of-the-arts (e.g., 2Zechun Liu et al. XNOR-Net), with a greater memory saving and a lower computational cost. Bi-Real net is also the first to scale up 1-bit CNNs to an ultra-deep network with 152 layers, and achieves 64.5% top-1 accuracy on ImageNet. A 50-layer Bi-Real net shows comparable performance to a real-valued network on the depth estimation task with merely a 0.3% accuracy gap.

show abstract

Tackling the Challenges in Scene Graph Generation With Local-to-Global Interactions

Woo

Noh

Kim

2023

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

PPR-FCN: Weakly Supervised Visual Relation Detection via Parallel Pairwise R-FCN

Cited by 7 publications

References 37 publications

Bi-Real Net: Enhancing the Performance of 1-Bit CNNs with Improved Representational Capability and Advanced Training Algorithm

Bi-Real Net: Enhancing the Performance of 1-Bit CNNs with Improved Representational Capability and Advanced Training Algorithm

Bi-Real Net: Binarizing Deep Network Towards Real-Network Performance

Tackling the Challenges in Scene Graph Generation With Local-to-Global Interactions

Contact Info

Product

Resources

About