The content based image retrieval aims to find the similar images from a large scale dataset against a query image. Generally, the similarity between the representative features of the query image and dataset images is used to rank the images for retrieval. In early days, various hand designed feature descriptors have been investigated based on the visual cues such as color, texture, shape, etc. that represent the images. However, the deep learning has emerged as a dominating alternative of hand-designed feature engineering from a decade. It learns the features automatically from the data. This paper presents a comprehensive survey of deep learning based developments in the past decade for content based image retrieval. The categorization of existing state-of-the-art methods from different perspectives is also performed for greater understanding of the progress. The taxonomy used in this survey covers different supervision, different networks, different descriptor type and different retrieval type. A performance analysis is also performed using the state-of-the-art methods. The insights are also presented for the benefit of the researchers to observe the progress and to make the best choices. The survey presented in this paper will help in further research progress in image retrieval using deep learning.

A Decade Survey of Content Based Image Retrieval using Deep Learning

Recent developments of content-based image retrieval (CBIR)

Nearest neighbor search is to find the data points in the database such that the distances from them to the query are the smallest, which is a fundamental problem in various domains, such as computer vision, recommendation systems and machine learning. Hashing is one of the most widely used methods for its computational and storage efficiency. With the development of deep learning, deep hashing methods show more advantages than traditional methods. In this paper, we present a comprehensive survey of the deep hashing algorithms. Specifically, we categorize deep supervised hashing methods into pairwise similarity preserving, multiwise similarity preserving, implicit similarity preserving, classification-oriented preserving as well as quantization according to the manners of preserving the similarities. In addition, we also introduce some other topics such as deep unsupervised hashing and multi-modal deep hashing methods. Meanwhile, we also present some commonly used public datasets and the scheme to measure the performance of deep hashing algorithms. Finally, we discussed some potential research directions in conclusion.

A Survey on Deep Hashing Methods

The content based image retrieval aims to find the similar images from a large scale dataset against a query image. Generally, the similarity between the representative features of the query image and dataset images is used to rank the images for retrieval. In early days, various hand designed feature descriptors have been investigated based on the visual cues such as color, texture, shape, etc. that represent the images. However, the deep learning has emerged as a dominating alternative of hand-designed feature engineering from a decade. It learns the features automatically from the data. This paper presents a comprehensive survey of deep learning based developments in the past decade for content based image retrieval. The categorization of existing state-of-the-art methods from different perspectives is also performed for greater understanding of the progress. The taxonomy used in this survey covers different supervision, different networks, different descriptor type and different retrieval type. A performance analysis is also performed using the state-of-the-art methods. The insights are also presented for the benefit of the researchers to observe the progress and to make the best choices. The survey presented in this paper will help in further research progress in image retrieval using deep learning. 

/pdf/a-decade-survey-of-content-based-image-retrieval-using-deep-2t6n1pnd.pdf

A Decade Survey of Content Based Image Retrieval Using Deep Learning

Rate control (RC) plays a critical role in the transmission of high-quality video data under certain bandwidth restrictions in High Efficiency Video Coding (HEVC). Most current HEVC RC algorithms based on spatio-temporal information for rate-distortion (R-D) model parameters cannot effectively handle the cases with dynamic video sequences that contain fast moving objects, significant object occlusion or scene changes. In this paper, we propose an RC method based on deep reinforcement learning (DRL) for dynamic video sequences in HEVC to improve the coding efficiency. First, the rate control problem is formulated as a Markov decision process (MDP) problem. Second, with the MDP model, we develop a DRL-based algorithm to find the optimal quantization parameters (QPs) by training a deep neural network. The resulting intelligent agent selects the optimal RC strategy to reduce distortion, buffer and quality fluctuations by observing the current state of the encoder. The asynchronous advantage actor-critic (A3C) method is used to solve the MDP problem. Finally, the proposed DRL-based RC method is implemented in the newest video coding standard. Experimental results show that the proposed method offers substantially enhanced RC accuracy and consistently outperforms HEVC reference software and other state-of-the-art algorithms.

Rate Control Method Based on Deep Reinforcement Learning for Dynamic Video Sequences in HEVC

In this paper, we propose a coding tree unit (CTU)-level rate control scheme from the perspective of SSIM-based rate-distortion optimization to improve the coding efficiency. First, we establish the SSIM-based rate-distortion model based on the divisive normalization scheme, which characterizes the relationship between the local visual quality and the coding bits. Then, the established model is applied to the CTU-level rate control and transformed into a global optimization problem solved by convex optimization. Finally, a new model parameter updating strategy for the CTU-level rate control is presented that is robust to scene variations. Our algorithm can achieve optimal CTU-level bit allocation given the bit-rate budget. The experimental results show that our algorithm substantially enhances the coding performance and consistently outperforms both the rate control scheme in the HEVC reference software and existing algorithms in terms of rate-perceptual distortion performance using different test configurations.

SSIM-Based Global Optimization for CTU-Level Rate Control in HEVC

Deep convolutional neural networks (CNNs) have been successfully applied on no-reference image quality assessment (NR-IQA) with respect to human perception. Most of these methods deal with small image patches and use the average score of the test patches for predicting the whole image quality. We discovered that image patches from homogenous regions are unreliable for both neural network training and final image quality score estimation. In addition, image patches with complex structures have much higher chances of achieving better image quality prediction. Based on these findings, we enhanced the conventional CNN-based NR-IQA algorithm to avoid homogenous patches for the network training and quality score estimation. Moreover, we also use a variance-based weighting average to bias the final image quality score to the patches with complex structure. The experimental results show that this simple approach can achieve state-of-the-art performance compared with well-known NR-IQA algorithms.

A Novel Patch Variance Biased Convolutional Neural Network for No-Reference Image Quality Assessment

Different from the conventional calculative methods, a learning-based initial quantization parameter (LIQP) method is proposed in this paper to improve rate control of high efficiency video coding (H265) First, the framework for initial quantization parameter (QP) learning is proposed, where a novel equivalent approach to build the benchmark labels is proposed using the single rate-distortion (R-D) pair in each initial QP testing With the criterion of maximizing the prediction accuracy of initial QPs, features and parameters of the learning model are refined Instead of the traditionally used target bits per pixel (bpp) for intraframe, the target bpp for all remaining frames is proposed to avoid the empirical setting on intracoding bits, and thus the related inaccuracy can be prevented We clearly present the motivations of the proposed LIQP method, as well as the reasons for the extracted features and model parameters The proposed LIQP method outperforms the latest HM-1614 by achieving significant gains on R-D performance (−1548% BD-BR and 0782 dB BD-PSNR gains), quality smoothness (1581 dB versus 2598 dB), and more stable buffer occupancy control, with similar high bit rate accuracy (9984% versus 9987%), and can also work well for scene change cases

Data-Driven Rate Control for Rate-Distortion Optimization in HEVC Based on Simplified Effective Initial QP Learning

High dynamic range (HDR) video compression technology, which is capable of delivering a wider range of luminance and a larger colour gamut than standard dynamic range (SDR) technology, has been widely used in recent years in many fields, including industrial image processing, digital entertainment, and machine vision. Rate control (RC) is of paramount importance to HDR compression and transmission; accordingly, an RC scheme for HDR in High Efficiency Video Coding (HEVC) is proposed in this paper. First, considering the HDR characteristics, we propose an HDR-Visual Difference Predictor (VDP)-2-based rate-distortion (R-D) model to improve the coding performance. Second, we directly utilize $\lambda $ rather than the bit rate in the optimization process to obtain the optimal solution. Finally, we propose a new model parameter estimation method to further reduce the RC errors. According to our experimental results, significant bit rate reductions in terms of HDR-VDP-2, the Video Quality Metric (VQM) and the mean peak-signal-to-noise ratio (mPSNR) can be achieved on average compared with the state-of-the-art algorithm used in HM16.19.

Global Rate-Distortion Optimization-Based Rate Control for HEVC HDR Coding

Deep learning based image hashing methods learn hash codes by using powerful feature extractors and nonlinear transformations to achieve highly efficient image retrieval. For most end-to-end deep hashing methods, the supervised learning process relies on pair-wise or triplet-wise information to provide an internal relationship of similarity data. However, the use of pair-wise and triplet loss function is limited not only by expensive training costs but also by quantization errors. In this paper, we propose a novel semantic learning based hashing method for image retrieval to optimize the deep features structure in the hash space from a perspective of angular view. Specifically, we proposed an angular hashing loss function that explicitly improve intra-class compactness and inter-class separability between features in hash space. Geometrically, angular hashing loss can be regarded as imposing hash constraints on hypersphere manifold. In order to solve the training problem on the multi-label case, we further designed a dynamic Softmax training strategy that can directly train the network using gradient descent method. Extensive experiments on two well-known datasets of CIFAR-10 and NUS-WIDE demonstrate that the proposed Angular Deep Supervised Hashing (ADSH) method can generate high-quality and compact binary codes, which can achieve state-of-the-art performance as compared with conventional image hashing and deep learning-based hashing methods.

/pdf/angular-deep-supervised-hashing-for-image-retrieval-50egb3dmil.pdf

Wilson Y. F. Yuen

Papers

SSIM-Based Global Optimization for CTU-Level Rate Control in HEVC

A Novel Patch Variance Biased Convolutional Neural Network for No-Reference Image Quality Assessment

Data-Driven Rate Control for Rate-Distortion Optimization in HEVC Based on Simplified Effective Initial QP Learning

Global Rate-Distortion Optimization-Based Rate Control for HEVC HDR Coding

Angular Deep Supervised Hashing for Image Retrieval