Feature Learning based Deep Supervised Hashing with Pairwise Labels

Li, Wu-Jun; Wang, Sheng; Kang, Wang-Cheng

doi:10.48550/arxiv.1511.03855

Cited by 114 publications

(80 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hashing is an encoding technique that maps high dimensional data into a set of binary codes, having low computational requirements and high storage efficiency. The proposed framework comprises three modules: features extraction based on MobileNet [134]; hash code learning, obtained using the last fully connected layer of MobileNet; and loss function, which is based on the likelihood [135], [136]. This work proposes a similar hierarchy method to distinguish similar images.…”

Section: ) Camera-based Networkmentioning

confidence: 99%

Place recognition survey: An update on deep learning approaches

Barros¹,

Pereira²,

Garrote³

et al. 2021

Preprint

View full text Add to dashboard Cite

Autonomous Vehicles (AV) are becoming more capable of navigating in complex environments with dynamic and changing conditions. A key component that enables these intelligent vehicles to overcome such conditions and become more autonomous is the sophistication of the perception and localization systems. As part of the localization system, place recognition has benefited from recent developments in other perception tasks such as place categorization or object recognition, namely with the emergence of deep learning (DL) frameworks. This paper surveys recent approaches and methods used in place recognition, particularly those based on deep learning. The contributions of this work are twofold: surveying recent sensors such as 3D LiDARs and RADARs, applied in place recognition; and categorizing the various DL-based place recognition works into supervised, unsupervised, semi-supervised, parallel, and hierarchical categories. First, this survey introduces key place recognition concepts to contextualize the reader. Then, sensor characteristics are addressed. This survey proceeds by elaborating on the various DL-based works, presenting summaries for each framework. Some lessons learned from this survey include: the importance of NetVLAD for supervised end-to-end learning; the advantages of unsupervised approaches in place recognition, namely for cross-domain applications; or the increasing tendency of recent works to seek, not only for higher performance but also for higher efficiency.

show abstract

Section: ) Camera-based Networkmentioning

confidence: 99%

Place recognition survey: An update on deep learning approaches

Barros¹,

Pereira²,

Garrote³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Though these handcrafted featurebased shallow methods achieved success to some extent, when applied to real data where dramatic appearance variation exists, they generally fail to capture the discriminative semantic information, leading to compromised performances. In light of this dilemma, a wealth of deep learning-based hash methods have been proposed [11][22] [23][24] [25]. [26] introduces a two-stage hashing scheme which first decomposes the similarity matrix S into a product of H and H T where each row of it is the hash code for a specific training image.…”

Section: A Hash For Content Retrievalmentioning

confidence: 99%

DVHN: A Deep Hashing Framework for Large-scale Vehicle Re-identification

Chen¹,

Zhang²,

Liu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Vehicle re-identification, which seeks to match query vehicle images with tremendous gallery images , has been gathering proliferating momentum. Conventional methods generally perform re-identification tasks by representing vehicle images as real-valued feature vectors and then ranking the gallery images by computing the corresponding Euclidean distances. Despite achieving remarkable retrieval accuracy, these methods require tremendous memory and computation when the gallery set is large, making them inapplicable in real-world scenarios.In light of this limitation, in this paper, we make the very first attempt to investigate the integration of deep hash learning with vehicle re-identification. We propose a deep hash-based vehicle re-identification framework, dubbed DVHN, which substantially reduces memory usage and promotes retrieval efficiency while reserving nearest neighbor search accuracy. Concretely, DVHN directly learns discrete compact binary hash codes for each image by jointly optimizing the feature learning network and the hash code generating module. Specifically, we directly constrain the output from the convolutional neural network to be discrete binary codes and ensure the learned binary codes are optimal for classification. To optimize the deep discrete hashing framework, we further propose an alternating minimization method for learning binary similarity-preserved hashing codes. Extensive experiments on two widely-studied vehicle re-identification datasets-VehicleID and VeRi-have demonstrated the superiority of our method against the state-of-the-art deep hash methods. DVHN of 2048 bits can achieve 13.94% and 10.21% accuracy improvement in terms of mAP and Rank@1 for VehicleID (800) dataset. For VeRi, we achieve 35.45% and 32.72% performance gains for Rank@1 and mAP, respectively.

show abstract

“…Ample experiments prove that LSH methods are inferior to learning to hash based methods, especially which integrates the deep learning method. Current hashing learning method based CNNs [29,30,3,31,32,4,1,2] mainly can be divided into supervised hashing learning and unsupervised hash learning respectively. [29] employs feature extractor network to gain feature vectors and then uses encoder network to obtain hash code.…”

Section: Related Workmentioning

confidence: 99%

“…[29] employs feature extractor network to gain feature vectors and then uses encoder network to obtain hash code. [30,3,32,4] devises the end-to-end network encoding the images to low dimensional hash code. Different from the symmetric hash method [30,3,31], [4] proposed an asymmetric method to accelerate training a model and achieve more promising performance than most symmetric hashing methods.…”

Section: Related Workmentioning

confidence: 99%

“…[30,3,32,4] devises the end-to-end network encoding the images to low dimensional hash code. Different from the symmetric hash method [30,3,31], [4] proposed an asymmetric method to accelerate training a model and achieve more promising performance than most symmetric hashing methods. [2] first combines the deep hashing with salient detection method to mine salient regions, which contains much semantic information.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Feature Consistency Driven Attention Erasing Network for Fine-Grained Image Retrieval

Zhao¹,

Wang²,

Lyu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Large-scale fine-grained image retrieval has two main problems. First, low dimensional feature embedding can fasten the retrieval process but bring accuracy reduce due to overlooking the feature of significant attention regions of images in fine-grained datasets. Second, fine-grained images lead to the same category query hash codes mapping into the different cluster in database hash latent space. To handle these two issues, we propose a feature consistency driven attention erasing network (FCAENet) for fine-grained image retrieval.For the first issue, we propose an adaptive augmentation module in FCAENet, which is selective region erasing module (SREM). SREM makes the network more robust on subtle differences of fine-grained task by adaptively covering some regions of raw images. The feature extractor and hash layer can learn more representative hash code for fine-grained images by SREM. With regard to the second issue, we fully exploit the pair-wise similarity information and add the enhancing space relation loss (ESRL) in FCAENet to make the vulnerable relation stabler between the query hash code and database hash code. We conduct extensive experiments on five fine-grained benchmark datasets (CUB2011, Aircraft, NABirds, VegFru, Food101) for 12bits, 24bits, 32bits, 48bits hash code. The results show that FCAENet achieves the state-of-the-art (SOTA) fine-grained retrieval performance compared with other methods.

show abstract

Feature Learning based Deep Supervised Hashing with Pairwise Labels

Cited by 114 publications

References 24 publications

Place recognition survey: An update on deep learning approaches

Place recognition survey: An update on deep learning approaches

DVHN: A Deep Hashing Framework for Large-scale Vehicle Re-identification

A Feature Consistency Driven Attention Erasing Network for Fine-Grained Image Retrieval

Contact Info

Product

Resources

About