CondenseNet V2: Sparse Feature Reactivation for Deep Networks

Yang, Le; Jiang, Haojun; Cai, Ruojin; Wang, Yulin; Song, Shiji; Huang, Gao

doi:10.1109/cvpr46437.2021.00357

Cited by 54 publications

(23 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multiple studies about lightweight and efficient CNN architectures have been published over the last years [31,23,45,21,50]. These studies introduce different mechanisms.…”

Section: Lightweight and Efficient Architecturesmentioning

confidence: 99%

“…Next, Mo-bileNetV3 [23] combines automated network search techniques and optimized nonlinearities on an architecture based on inverted residual blocks. Afterward, GhostNet [21] introduces a novel Ghost module based on linear transformations and, CondenseNetV2 [50] relies on a new Sparse Feature Reactivation module which reuses a set of most important features from preceding layers.…”

Section: Lightweight and Efficient Architecturesmentioning

confidence: 99%

“…The number of trainable parameters is set at the level at which the best performing network (ResNet -see Section 5.1) does not show an increase in accuracy through the addition of new layers. Specifically, we used the authors' implementation of CondenseN-etV2 [50], MLSTM-FCN [26], ProtoPNet [10], XCM [20]. Moreover, we used the PyTorch Hub [36]/Torchvision [37] implementations of DenseNet [24], EfficientNet [45], GhostNet [21], MobileNetV3 [23], ResNet [22], and ShuffleNetV2 [31].…”

Section: Algorithmsmentioning

confidence: 99%

“…ProtoPNet consists of a regular CNN backbone which extracts discriminative features, then a prototype block computes similarities to the learned class-specific prototypes, and finally the classification is performed based on these similarity scores. Firstly, concerning the backbone, multiple work about lightweight and efficient CNN architectures have been published recently [31,23,45,21,50]. Most of these studies optimize a proxy metric to measure efficiency (number of floating-point operations -FLOPs), which is not always equivalent to the inference time [31].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Lightweight, Efficient and Explainable-by-Design Convolutional Neural Network for Internet Traffic Classification

Fauvel¹,

Finamore²,

Yang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Traffic classification, i.e. the identification of the type of applications flowing in a network, is a strategic task for numerous activities (e.g., intrusion detection, routing). This task faces some critical challenges that current deep learning approaches do not address. The design of current approaches do not take into consideration the fact that networking hardware (e.g., routers) often runs with limited computational resources. Further, they do not meet the need for faithful explainability highlighted by regulatory bodies. Finally, these traffic classifiers are evaluated on small datasets which fail to reflect the diversity of applications in real commercial settings.Therefore, this paper introduces a Lightweight, Efficient and eXplainable-by-design convolutional neural network (LEXNet) for Internet traffic classification, which relies on a new residual block (for lightweight and efficiency purposes) and prototype layer (for explainability). Based on a commercial-grade dataset, our evaluation shows that LEXNet succeeds to maintain the same accuracy as the best performing state-of-the-art neural network, while providing the additional features previously mentioned. Moreover, we demonstrate that LEXNet significantly reduces the model size and inference time compared to the state-of-the-art neural networks with explainability-by-design and post hoc explainability methods. Finally, we illustrate the explainability feature of our approach, which stems from the communication of detected application prototypes to the end-user, and we highlight the faithfulness of LEXNet explanations through a comparison with post hoc methods.

show abstract

“…Multiple studies about lightweight and efficient CNN architectures have been published over the last years [31,23,45,21,50]. These studies introduce different mechanisms.…”

Section: Lightweight and Efficient Architecturesmentioning

confidence: 99%

Section: Lightweight and Efficient Architecturesmentioning

confidence: 99%

Section: Algorithmsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Lightweight, Efficient and Explainable-by-Design Convolutional Neural Network for Internet Traffic Classification

Fauvel¹,

Finamore²,

Yang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Visual grounding (VG) task [13,24,40,65] has achieved great progress in recent years, with the advances in both computer vision [16,20,21,25,26,46,56,57,59] and natural language processing [4,14,41,50,53]. It aims to localize the objects referred by natural language queries, which is essential for various vision-language tasks, e.g., visual question answering [2] and visual commonsense reasoning [67].…”

Section: Introductionmentioning

confidence: 99%

Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding

Jiang¹,

Lin²,

Han³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Visual grounding, i.e., localizing objects in images according to natural language queries, is an important topic in visual language understanding. The most effective approaches for this task are based on deep learning, which generally require expensive manually labeled image-query or patch-query pairs. To eliminate the heavy dependence on human annotations, we present a novel method, named Pseudo-Q, to automatically generate pseudo language queries for supervised training. Our method leverages an off-the-shelf object detector to identify visual objects from unlabeled images, and then language queries for these objects are obtained in an unsupervised fashion with a pseudo-query generation module. Then, we design a task-related query prompt module to specifically tailor generated pseudo language queries for visual grounding tasks. Further, in order to fully capture the contextual relationships between images and language queries, we develop a visual-language model equipped with multi-level cross-modality attention mechanism. Extensive experimental results demonstrate that our method has two notable benefits: (1) it can reduce human annotation costs significantly, e.g., 31% on RefCOCO [65] without degrading original model's performance under the fully supervised setting, and (2) without bells and whistles, it achieves superior or comparable performance compared to state-of-theart weakly-supervised visual grounding methods on all the five datasets we have experimented. Code is available at https://github.com/LeapLabTHU/Pseudo-Q.* Equal contribution. † This work was done during an internship at Tsinghua.

show abstract