CUNet: A Compact Unsupervised Network for Image Classification

Dong, Le; He, Li; Mao, Mengdie; Kong, Gaipeng; Wu, Xi; Zhang, Qianni; Cao, Xiaochun; Izquierdo, Ebroul

doi:10.1109/tmm.2017.2788205

Cited by 19 publications

(8 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Early logo detection methods are established on hand-crafted visual features (e.g., SIFT and HOG) and conventional classification models (e.g., SVM). Inspired by the recent advances in object detection using deep learning methods [47], [48], remarkable progress has been made for logo detection. Some existing detectors often insert some network layers between the backbone and detection head, and these layers are usually used to collect feature maps from different levels.…”

Section: B Logo Detectionmentioning

confidence: 99%

Discriminative Semantic Feature Pyramid Network with Guided Anchoring for Logo Detection

Zhang

Min

Wang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Recently, logo detection has received more and more attention for its wide applications in the multimedia field, such as intellectual property protection, product brand management, and logo duration monitoring. Unlike general object detection, logo detection is a challenging task, especially for small logo objects and large aspect ratio logo objects in the real-world scenario. In this paper, we propose a novel approach, named Discriminative Semantic Feature Pyramid Network with Guided Anchoring (DSFP-GA), which can address these challenges via aggregating the semantic information and generating different aspect ratio anchor boxes. More specifically, our approach mainly consists of Discriminative Semantic Feature Pyramid (DSFP) and Guided Anchoring (GA). Considering that lowlevel feature maps that are used to detect small logo objects lack semantic information, we propose the DSFP, which can enrich more discriminative semantic features of low-level feature maps and can achieve better performance on small logo objects. Furthermore, preset anchor boxes are less efficient for detecting large aspect ratio logo objects. We therefore integrate the GA into our method to generate large aspect ratio anchor boxes to mitigate this issue. Extensive experimental results on four benchmarks demonstrate the effectiveness of our proposed DSFP-GA. Moreover, we further conduct visual analysis and ablation studies to illustrate the advantage of our method in detecting small and large aspect logo objects. The code and models can be found at https://github.com/Zhangbaisong/DSFP-GA.

show abstract

Section: B Logo Detectionmentioning

confidence: 99%

Discriminative Semantic Feature Pyramid Network with Guided Anchoring for Logo Detection

Zhang

Min

Wang³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…PCANet [23] and DCTNet [25] have also shown to work well in face recognition by processing input images with a layerwise convolution with PCA and DCT filters, followed by binarisation, block-wise histograming. Dong et al [26] proposed a compact unsupervised networks (CUNet), in which feature maps are derived by the K-means on image patches. The two-layer CUNet structure with weighted pooling has achieved performances comparable with the ScatNet, PCANet and DCTNet.…”

Section: Related Workmentioning

confidence: 99%

“…Despite these remarkable successes and state-of-theart performances by CNNs (e.g. in handwritten digit, face recognition and image categorisation [22,23,24,25,26]), their feature learning mechanism and optimal 40 configurations of their structures are not well understood [22]. These networks are often limited or tuned to specified applications and may not generalise well to other image classification tasks.…”

Section: Introductionmentioning

confidence: 99%

Data-Independent Feature Learning with Markov Random Fields in Convolutional Neural Networks

2020

View full text Add to dashboard Cite

In image classification, deriving robust image representations is a key process that determines the performance of vision systems. Numerous image features and descriptors have been developed manually over the years. As an alternative, however, deep neural networks, in particular convolutional neural networks (CNNs), have become popular for learning image features or representations from data and have demonstrated remarkable performance in many real-world applications. But CNNs often require huge amount of labelled data, which may be prohibitive in many applications, as well as long training times. This paper considers an alternative, data-independent means of obtaining features for CNNs. The proposed framework makes use of the Markov random field (MRF) and self-organising map (SOM) to generate basic features and model both intra-and inter-image dependencies. Various MRF textures are synthesised first, and are then clustered by a convolutional translation-invariant SOM, to form generic image features. These features can be directly applied as early convolutional filters of the CNN, leading to a new way of deriving effective features for image classification. The MRF framework also offers a theoretical and transparent way to examine and determine the influence of image features on performance of CNNs. Comprehensive experiments on the MNIST, rotated MNIST, CIFAR-10 and CIFAR-100 datasets were conducted with results outperforming most state-of-the-art models of similar complexity.

show abstract

“…In addition, cascaded of stacked U-Nets also gain enough attention. CU-Net [9] per-form dense connections of the same level among multiple U-Nets. However, these works fail to consider transforming the size of feature maps.…”

Section: Introductionmentioning

confidence: 99%

MDU-Net: Multi-scale Densely Connected U-Net for biomedical image segmentation

Zhang¹,

Jin²,

Xu³

et al. 2018

Preprint

View full text Add to dashboard Cite

Radiologist is "doctor's doctor", biomedical image segmentation plays a central role in quantitative analysis, clinical diagnosis, and medical intervention. In the light of the fully convolutional networks (FCN) and U-Net, deep convolutional networks (DNNs) have made significant contributions in biomedical image segmentation applications. In this paper, based on U-Net, we propose MDUnet, a multiscale densely connected U-net for biomedical image segmentation. we propose three different multi-scale dense connections for U shaped architectures encoder, decoder and across them. The highlights of our architecture is directly fuses the neighboring different scale feature maps from both higher layers and lower layers to strengthen feature propagation in current layer. Which can largely improves the information flow encoder, decoder and across them. Multi-scale dense connections, which means containing shorter connections between layers close to the input and output, also makes much deeper U-net possible. We adopt the optimal model based on the experiment and propose a novel Multi-scale Dense U-Net (MDU-Net) architecture with quantization. Which reduce overfitting in MDU-Net for better accuracy. We evaluate our purpose model on the MICCAI 2015 Gland Segmentation dataset (GlaS). The three multi-scale dense connections improve Unet performance by up to 1.8% on test A and 3.5% on test B in the MICCAI Gland dataset. Meanwhile the MDU-net with quantization achieves the superiority over U-Net performance by up to 3% on test A and 4.1% on test B.

show abstract

CUNet: A Compact Unsupervised Network for Image Classification

Cited by 19 publications

References 28 publications

Discriminative Semantic Feature Pyramid Network with Guided Anchoring for Logo Detection

Discriminative Semantic Feature Pyramid Network with Guided Anchoring for Logo Detection

Data-Independent Feature Learning with Markov Random Fields in Convolutional Neural Networks

MDU-Net: Multi-scale Densely Connected U-Net for biomedical image segmentation

Contact Info

Product

Resources

About