ExchNet: A Unified Hashing Network for Large-Scale Fine-Grained Image Retrieval

Cui, Quan; Jiang, Qing; Wei, Xiu Shen; Li, Wu Jun; Yoshie, Osamu

doi:10.1007/978-3-030-58580-8_12

Cited by 32 publications

(40 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At present, CNN-based image hashing network has also achieved state-of-the-art results [16,25,53,58], but little attention to video hashing. The main categories of image retrieval are as follows: image-image [5,8,13,14,26,42,43], image-text-image [11,12,54] and hashing algorithms [53,58]. Most researchers focus on image retrieval, and less attention has been paid to video hashing.…”

Section: Related Workmentioning

confidence: 99%

Vision Transformer Based Video Hashing Retrieval for Tracing the Source of Fake Videos

Pei¹,

Zhao²,

Li³

et al. 2021

Preprint

View full text Add to dashboard Cite

Conventional fake video detection methods outputs a possibility value or a suspected mask of tampering images. However, such unexplainable results cannot be used as convincing evidence. So it is better to trace the sources of fake videos. The traditional hashing methods are used to retrieve semantic-similar images, which can't discriminate the nuances of the image. Specifically, the sources tracing compared with traditional video retrieval. It is a challenge to find the real one from similar source videos. We designed a novel loss Hash Triplet Loss to solve the problem that the videos of people are very similar: the same scene with different angles, similar scenes with the same person. We propose Vision Transformer based models named Video Tracing and Tampering Localization (VTL). In the first stage, we train the hash centers by ViTHash (VTL-T). Then, a fake video is inputted to ViTHash, which outputs a hash code. The hash code is used to retrieve the source video from hash centers. In the second stage, the source video and fake video are inputted to generator (VTL-L). Then, the suspect regions are masked to provide auxiliary information. Moreover, we constructed two datasets: DFTL and DAVIS2016-TL. Experiments on DFTL clearly show the superiority of our framework in sources tracing of similar videos. In particular, the VTL also achieved comparable performance with state-of-the-art methods on DAVIS2016-TL. Our source code and datasets have been released on GitHub: https://github.com/lajlksdf/vtl.

show abstract

Section: Related Workmentioning

confidence: 99%

Vision Transformer Based Video Hashing Retrieval for Tracing the Source of Fake Videos

Pei¹,

Zhao²,

Li³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Deep hash learning based image retrieval methods [1,2] have achieved a huge success recent year. [1] solves on the fine-grained hashing problem by a feature exchanging method.…”

Section: Introductionmentioning

confidence: 99%

“…Deep hash learning based image retrieval methods [1,2] have achieved a huge success recent year. [1] solves on the fine-grained hashing problem by a feature exchanging method. It aims to learn compact hash code for specific fine-grained object via an end-to-end architecture.…”

Section: Introductionmentioning

confidence: 99%

“…As for the fine-grained image retrieval, there are two basic components: query hash code, database hash code. To obtain these two hash codes, many efforts [3,4,1] have been done via symmetric hash learning methods or asymmetric hash learning methods. Deep Supervised Hashing [3] applies the negativepair and positive-pair to encourage the output hash code to approximate discrete values.…”

Section: Introductionmentioning

confidence: 99%

“…[4] proposes an asymmetric deep hashing method and obviously improves the training efficiency and retrieval accuracy by asymmetrically learning pairwise similarity. [1] researches on the fine-grained hashing problem, which aims to learn compact hash code for specific fine-grained object via an end-to-end architecture. By contrast to the symmetric hash learning methods, asymmetric hash learning methods show the outstanding retrieval performance and training efficiency.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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