Learning Dynamic Routing for Semantic Segmentation

Li, Yanwei; Lin, Song; Chen, Yukang; Li, Zeming; Zhang, Xiangyu; Wang, Xingang; Sun, Jian

doi:10.1109/cvpr42600.2020.00858

Cited by 140 publications

(98 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dynamic neural networks, which can adjust the network architectures or network parameters depending on the corresponding inputs, have been recently studied in the computer vision field. In early studies, these dynamic neural networks are proposed for the image classification and semantic segmentation tasks by dropping blocks [104−107] or pruning channels [73,108] for efficient inference. For example, in [109], a soft conditional gate is proposed to select scale transform paths for each layer.…”

Section: Dynamic Neural Networkmentioning

confidence: 99%

Advances in Deep Learning Methods for Visual Tracking: Literature Review and Fundamentals

Zhang

Jiang

Fan

et al. 2021

Int. J. Autom. Comput.

View full text Add to dashboard Cite

Recently, deep learning has achieved great success in visual tracking tasks, particularly in single-object tracking. This paper provides a comprehensive review of state-of-the-art single-object tracking algorithms based on deep learning. First, we introduce basic knowledge of deep visual tracking, including fundamental concepts, existing algorithms, and previous reviews. Second, we briefly review existing deep learning methods by categorizing them into data-invariant and data-adaptive methods based on whether they can dynamically change their model parameters or architectures. Then, we conclude with the general components of deep trackers. In this way, we systematically analyze the novelties of several recently proposed deep trackers. Thereafter, popular datasets such as Object Tracking Benchmark (OTB) and Visual Object Tracking (VOT) are discussed, along with the performances of several deep trackers. Finally, based on observations and experimental results, we discuss three different characteristics of deep trackers, i.e., the relationships between their general components, exploration of more effective tracking frameworks, and interpretability of their motion estimation components.

show abstract

Section: Dynamic Neural Networkmentioning

confidence: 99%

Advances in Deep Learning Methods for Visual Tracking: Literature Review and Fundamentals

Zhang

Jiang

Fan

et al. 2021

Int. J. Autom. Comput.

View full text Add to dashboard Cite

show abstract

“…Opposed to static ones, ANNs dynamically adjust structures according to input samples (Wang et al 2018; or constrained computation budgets (Yu et al 2018;Wang et al 2020b). More specifically, ANNs adjust structures from the perspective of depth (Wang et al 2018;, channel width (Yu et al 2018;Gao et al 2018), spatial resolution (Wang et al 2020b;Yang et al 2020) or dynamic routing (Li et al 2020). To answer the second question above (how to distill knowledge?…”

Section: Related Workmentioning

confidence: 99%

Partial to Whole Knowledge Distillation: Progressive Distilling Decomposed Knowledge Boosts Student Better

Zhang,

Sun

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Knowledge distillation field delicately designs various types of knowledge to shrink the performance gap between compact student and large-scale teacher. These existing distillation approaches simply focus on the improvement of knowledge quality, but ignore the significant influence of knowledge quantity on the distillation procedure. Opposed to the conventional distillation approaches, which extract knowledge from a fixed teacher computation graph, this paper explores a non-negligible research direction from a novel perspective of knowledge quantity to further improve the efficacy of knowledge distillation. We introduce a new concept of knowledge decomposition, and further put forward the Partial to Whole Knowledge Distillation (PWKD) paradigm. Specifically, we reconstruct teacher into weightsharing sub-networks with same depth but increasing channel width, and train sub-networks jointly to obtain decomposed knowledge (sub-networks with more channels represent more knowledge). Then, student extract partial to whole knowledge from the pre-trained teacher within multiple training stages where cyclic learning rate is leveraged to accelerate convergence. Generally, PWKD can be regarded as a plugin to be compatible with existing offline knowledge distillation approaches. To verify the effectiveness of PWKD, we conduct experiments on two benchmark datasets: CIFAR-100 and ImageNet, and comprehensive evaluation results reveal that PWKD consistently improve existing knowledge distillation approaches without bells and whistles.

show abstract

“…The concurrent trend of semantic segmentation concentrates on (i) bringing prior knowledge or features to particular scenarios, such as "cars cannot fly up in the sky" in urban scene segmentation [42], Fourier domain adaption [26], and model transfer (synthetic images to real images) [43], (ii) effective and efficient prediction, such as single-stage effective segmentation [44], boundary preserving segmentation [45], and very high-resolution segmentation [46], and (iii) novel network architecture, such as learnable dynamic architecture for semantic segmentation [23] and graph reasoning [27].…”

Section: Neural Image Segmentationmentioning

confidence: 99%

“…The convolutional neural network-based (CNN-based) feature encoders enable spatial and spectral feature extractions and output representative feature vectors, which can be used as the backbone for dense classification tasks. Learnable parameters [16][17][18][19][20][21] or network structures [22,23] push models to fit the feature space and reach the accurate pixel-wise classification results. Typical neural classifiers [4,24,25] have already been transferred to remote sensing segmentation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Refined UNet V2: End-to-End Patch-Wise Network for Noise-Free Cloud and Shadow Segmentation

Jiao

Huo

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

Cloud and shadow detection is an essential prerequisite for further remote sensing processing, whereas edge-precise segmentation remains a challenging issue. In Refined UNet, we considered the aforementioned task and proposed a two-stage pipeline to achieve the edge-precise segmentation. The isolated segmentation regions in Refined UNet, however, bring inferior visualization and should be sufficiently eliminated. Moreover, an end-to-end model is also expected to jointly predict and refine the segmentation results. In this paper, we propose the end-to-end Refined UNet v2 to achieve joint prediction and refinement of cloud and shadow segmentation, which is capable of visually neutralizing redundant segmentation pixels or regions. To this end, we inherit the pipeline of Refine UNet, revisit the bilateral message passing in the inference of conditional random field (CRF), and then develop a novel bilateral strategy derived from the Guided Gaussian filter. Derived from a local linear model of denoising, our v2 can considerably remove isolated segmentation pixels or regions, which is able to yield “cleaner” results. Compared to the high-dimensional Gaussian filter, the Guided Gaussian filter-based message-passing strategy is quite straightforward and easy to implement so that a brute-force implementation can be easily given in GPU frameworks, which is potentially efficient and facilitates embedding. Moreover, we prove that Guided Gaussian filter-based message passing is highly relevant to the Gaussian bilateral term in Dense CRF. Experiments and results demonstrate that our v2 is quantitatively comparable to Refined UNet, but can visually outperform that from the noise-free segmentation perspective. The comparison of time consumption also supports the potential efficiency of our v2.

show abstract

Learning Dynamic Routing for Semantic Segmentation

Cited by 140 publications

References 23 publications

Advances in Deep Learning Methods for Visual Tracking: Literature Review and Fundamentals

Advances in Deep Learning Methods for Visual Tracking: Literature Review and Fundamentals

Partial to Whole Knowledge Distillation: Progressive Distilling Decomposed Knowledge Boosts Student Better

Refined UNet V2: End-to-End Patch-Wise Network for Noise-Free Cloud and Shadow Segmentation

Contact Info

Product

Resources

About