Deep Domain Adaptation Hashing with Adversarial Learning

Long, Fuchen; Yao, Ting; Dai, Qi; Tian, Xinmei; Luo, Jiebo; Mei, Tao

doi:10.1145/3209978.3209999

Cited by 20 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The effectiveness of their proposed architecture was evaluated on cross domain question answering data. Long et al [45] also leveraged the adversarial learning framework by devising a domain discriminator to solve the problem of domain adaptation. They evaluated the effectiveness of their proposed method on three domain transfer tasks, including cross-domain digits retrieval, image to image and image to videos transfers, on several benchmarks.…”

Section: Ood Generalizabilitymentioning

confidence: 99%

Are Neural Ranking Models Robust?

Chen¹,

Zhang²,

Guo³

et al. 2021

Preprint

View full text Add to dashboard Cite

Recently, we have witnessed the bloom of neural ranking models in the information retrieval (IR) field. So far, much effort has been devoted to developing effective neural ranking models that can generalize well on new data. There has been less attention paid to the robustness perspective. Unlike the effectiveness which is about the average performance of a system under normal purpose, robustness cares more about the system performance in the worst case or under malicious operations instead. When a new technique enters into the real-world application, it is critical to know not only how it works in average, but also how would it behave in abnormal situations. So we raise the question in this work: Are neural ranking models robust? To answer this question, firstly, we need to clarify what we refer to when we talk about the robustness of ranking models in IR. We show that robustness is actually a multi-dimensional concept and there are three ways to define it in IR: 1) The performance variance under the independent and identically distributed (I.I.D.) setting; 2) The out-of-distribution (OOD) generalizability; and 3) The defensive ability against adversarial operations. The latter two definitions can be further specified into two different perspectives respectively, leading to 5 robustness tasks in total. Based on this taxonomy, we build corresponding benchmark datasets, design empirical experiments, and systematically analyze the robustness of several representative neural ranking models against traditional probabilistic ranking models and learning-to-rank (LTR) models. The empirical results show that there is no simple answer to our question. While neural ranking models are less robust against other IR models in most cases, some of them can still win 1 out of 5 tasks. This is the first comprehensive study on the robustness of neural ranking models. We believe the way we study the robustness as well as our findings would be beneficial to the IR community. We will also release all the data and codes to facilitate the future research in this direction.CCS Concepts: • Information systems → Retrieval models and ranking.

show abstract

Section: Ood Generalizabilitymentioning

confidence: 99%

Are Neural Ranking Models Robust?

Chen¹,

Zhang²,

Guo³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Another branch of unsupervised domain adaptation in DCNNs is to exploit the domain confusion by learning a domain discriminator [4,14,29,30,35]. Here the domain discriminator is designed to predict the domain (source/target) of each input sample and is trained in an adversarial fashion, similar to GANs [5], for learning domain invariant representation.…”

Section: Related Workmentioning

confidence: 99%

Transferrable Prototypical Networks for Unsupervised Domain Adaptation

Pan

Yao

Li³

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

347

211

View full text Add to dashboard Cite

In this paper, we introduce a new idea for unsupervised domain adaptation via a remold of Prototypical Networks, which learn an embedding space and perform classification via a remold of the distances to the prototype of each class. Specifically, we present Transferrable Prototypical Networks (TPN) for adaptation such that the prototypes for each class in source and target domains are close in the embedding space and the score distributions predicted by prototypes separately on source and target data are similar. Technically, TPN initially matches each target example to the nearest prototype in the source domain and assigns an example a "pseudo" label. The prototype of each class could then be computed on source-only, target-only and source-target data, respectively. The optimization of TPN is end-to-end trained by jointly minimizing the distance across the prototypes on three types of data and KLdivergence of score distributions output by each pair of the prototypes. Extensive experiments are conducted on the transfers across MNIST, USPS and SVHN datasets, and superior results are reported when comparing to state-of-theart approaches. More remarkably, we obtain an accuracy of 80.4% of single model on VisDA 2017 dataset.

show abstract

“…The main purpose of domain adaptation is to manipulate supervised information on the source domain to guide model training on the target domain without ground-truth labels. In the computer vision community, domain adaptation has been applied in segmentation [20] and image retrieval [21]. Unlike traditional training datasets that consist of single-domain data, domain-adaptive learning aims to train a unified model so that it can handle multiple domains (e.g., digits and handwritten numbers).…”

Section: Domain Adaptationmentioning

confidence: 99%

Unsupervised Domain-adaptive Hash for Networks

He¹,

Gao²,

Song³

et al. 2021

Preprint

View full text Add to dashboard Cite

Abundant real-world data can be naturally represented by large-scale networks, which demands efficient and effective learning algorithms. At the same time, labels may only be available for some networks, which demands these algorithms to be able to adapt to unlabeled networks. Domain-adaptive hash learning has enjoyed considerable success in the computer vision community in many practical tasks due to its lower cost in both retrieval time and storage footprint. However, it has not been applied to multiple-domain networks. In this work, we bridge this gap by developing an unsupervised domain-adaptive hash learning method for networks, dubbed UDAH. Specifically, we develop four task-specific yet correlated components: (1) network structure preservation via a hard groupwise contrastive loss, (2) relaxationfree supervised hashing, (3) cross-domain intersected discriminators, and (4) semantic center alignment. We conduct a wide range of experiments to eval-

show abstract

Deep Domain Adaptation Hashing with Adversarial Learning

Cited by 20 publications

References 20 publications

Are Neural Ranking Models Robust?

Are Neural Ranking Models Robust?

Transferrable Prototypical Networks for Unsupervised Domain Adaptation

Unsupervised Domain-adaptive Hash for Networks

Contact Info

Product

Resources

About