Bin Liu
Research Subjects
Bin Liu has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Han Zhu
Taobao & Tmall Group of Alibaba, Beijing, China
4 shared publications Jianmin Wang
Tsinghua University & Beijing National Research Center for Information Science and Technology, Beijing, China
4 shared publicationsYue Cao
Tsinghua University & Beijing National Research Center for Information Science and Technology, Beijing, China
4 shared publications- Ziru Xu
Taobao & Tmall Group of Alibaba, Beijing, China
4 shared publications - Jian Xu
Alibaba Group, Hangzhou, China
3 shared publications Mingsheng Long
Tsinghua University & Beijing National Research Center for Information Science and Technology, Beijing, China
3 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5886-5897
ClusterRec: Cluster-Aware Recommendation with Large Language Models for Efficient and Scalable Inference
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5886-5897
Open AccessClusterRec: Cluster-Aware Recommendation with Large Language Models for Efficient and Scalable Inference
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8377-8385
Bidding-Aware Retrieval for Multi-Stage Consistency in Online Advertising
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8377-8385
Open AccessBidding-Aware Retrieval for Multi-Stage Consistency in Online Advertising
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8319-8327
Large Language Model as Universal Retriever in Industrial-Scale Recommender System
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8319-8327
Open AccessLarge Language Model as Universal Retriever in Industrial-Scale Recommender System
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8784-8792
TransRetrieval: Scaling Up Transformer-Based Retrieval for Industrial Recommendation
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8784-8792
Open AccessTransRetrieval: Scaling Up Transformer-Based Retrieval for Industrial Recommendation
- 1 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1317-1326
Deep Metric Transfer for Label Propagation with Limited Annotated Data
We study object recognition under the constraint that each object class is only represented by very few observations. Semi-supervised learning, transfer learning, and few-shot recognition all concern with achieving fast generalization with few labeled data. In this paper, we propose a generic framework that utilize unlabeled data to aid generalization for all three tasks. Our approach is to create much more training data through label propagation from the few labeled examples to a vast collection of unannotated images. The main contribution of the paper is that we show such a label propagation scheme can be highly effective when the similarity metric used for propagation is transferred from other related domains. We test various combinations of supervised and unsupervised metric learning methods with various label propagation algorithms. We find that our framework is very generic without being sensitive to any specific techniques. By taking advantage of unlabeled data in this way, we achieve significant improvements on all three tasks. Code is availble at http://github.com/Microsoft/metric-transfer.pytorch.
- 1 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1317-1326
Deep Metric Transfer for Label Propagation with Limited Annotated Data
We study object recognition under the constraint that each object class is only represented by very few observations. Semi-supervised learning, transfer learning, and few-shot recognition all concern with achieving fast generalization with few labeled data. In this paper, we propose a generic framework that utilize unlabeled data to aid generalization for all three tasks. Our approach is to create much more training data through label propagation from the few labeled examples to a vast collection of unannotated images. The main contribution of the paper is that we show such a label propagation scheme can be highly effective when the similarity metric used for propagation is transferred from other related domains. We test various combinations of supervised and unsupervised metric learning methods with various label propagation algorithms. We find that our framework is very generic without being sensitive to any specific techniques. By taking advantage of unlabeled data in this way, we achieve significant improvements on all three tasks. Code is availble at http://github.com/Microsoft/metric-transfer.pytorch.
- Open Access
- 15 October 2018
- Published by Association for Computing Machinery (ACM)
- p. 755-763
Deep Triplet Quantization
Deep hashing establishes efficient and effective image retrieval by end-to-end learning of deep representations and hash codes from similarity data. We present a compact coding solution, focusing on deep learning to quantization approach that has shown superior performance over hashing solutions for similarity retrieval. We propose Deep Triplet Quantization (DTQ), a novel approach to learning deep quantization models from the similarity triplets. To enable more effective triplet training, we design a new triplet selection approach, Group Hard, that randomly selects hard triplets in each image group. To generate compact binary codes, we further apply a triplet quantization with weak orthogonality during triplet training. The quantization loss reduces the codebook redundancy and enhances the quantizability of deep representations through back-propagation. Extensive experiments demonstrate that DTQ can generate high-quality and compact binary codes, which yields state-of-the-art image retrieval performance on three benchmark datasets, NUS-WIDE, CIFAR-10, and MS-COCO.
- 15 October 2018
- Published by Association for Computing Machinery (ACM)
- p. 755-763
Open AccessDeep Triplet Quantization
Deep hashing establishes efficient and effective image retrieval by end-to-end learning of deep representations and hash codes from similarity data. We present a compact coding solution, focusing on deep learning to quantization approach that has shown superior performance over hashing solutions for similarity retrieval. We propose Deep Triplet Quantization (DTQ), a novel approach to learning deep quantization models from the similarity triplets. To enable more effective triplet training, we design a new triplet selection approach, Group Hard, that randomly selects hard triplets in each image group. To generate compact binary codes, we further apply a triplet quantization with weak orthogonality during triplet training. The quantization loss reduces the codebook redundancy and enhances the quantizability of deep representations through back-propagation. Extensive experiments demonstrate that DTQ can generate high-quality and compact binary codes, which yields state-of-the-art image retrieval performance on three benchmark datasets, NUS-WIDE, CIFAR-10, and MS-COCO.
- 1 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1287-1296
HashGAN: Deep Learning to Hash with Pair Conditional Wasserstein GAN
Deep learning to hash improves image retrieval performance by end-to-end representation learning and hash coding from training data with pairwise similarity information. Subject to the scarcity of similarity information that is often expensive to collect for many application domains, existing deep learning to hash methods may overfit the training data and result in substantial loss of retrieval quality. This paper presents HashGAN, a novel architecture for deep learning to hash, which learns compact binary hash codes from both real images and diverse images synthesized by generative models. The main idea is to augment the training data with nearly real images synthesized from a new Pair Conditional Wasserstein GAN (PC-WGAN) conditioned on the pairwise similarity information. Extensive experiments demonstrate that HashGAN can generate high-quality binary hash codes and yield state-of-the-art image retrieval performance on three benchmarks, NUS-WIDE, CIFAR-10, and MS-COCO.
- 1 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1287-1296
HashGAN: Deep Learning to Hash with Pair Conditional Wasserstein GAN
Deep learning to hash improves image retrieval performance by end-to-end representation learning and hash coding from training data with pairwise similarity information. Subject to the scarcity of similarity information that is often expensive to collect for many application domains, existing deep learning to hash methods may overfit the training data and result in substantial loss of retrieval quality. This paper presents HashGAN, a novel architecture for deep learning to hash, which learns compact binary hash codes from both real images and diverse images synthesized by generative models. The main idea is to augment the training data with nearly real images synthesized from a new Pair Conditional Wasserstein GAN (PC-WGAN) conditioned on the pairwise similarity information. Extensive experiments demonstrate that HashGAN can generate high-quality binary hash codes and yield state-of-the-art image retrieval performance on three benchmarks, NUS-WIDE, CIFAR-10, and MS-COCO.
- 1 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1229-1237
Deep Cauchy Hashing for Hamming Space Retrieval
Due to its computation efficiency and retrieval quality, hashing has been widely applied to approximate nearest neighbor search for large-scale image retrieval, while deep hashing further improves the retrieval quality by end-to-end representation learning and hash coding. With compact hash codes, Hamming space retrieval enables the most efficient constant-time search that returns data points within a given Hamming radius to each query, by hash table lookups instead of linear scan. However, subject to the weak capability of concentrating relevant images to be within a small Hamming ball due to mis-specified loss functions, existing deep hashing methods may underperform for Hamming space retrieval. This work presents Deep Cauchy Hashing (DCH), a novel deep hashing model that generates compact and concentrated binary hash codes to enable efficient and effective Hamming space retrieval. The main idea is to design a pairwise cross-entropy loss based on Cauchy distribution, which penalizes significantly on similar image pairs with Hamming distance larger than the given Hamming radius threshold. Comprehensive experiments demonstrate that DCH can generate highly concentrated hash codes and yield state-of-the-art Hamming space retrieval performance on three datasets, NUS-WIDE, CIFAR-10, and MS-COCO.
- 1 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1229-1237
Deep Cauchy Hashing for Hamming Space Retrieval
Due to its computation efficiency and retrieval quality, hashing has been widely applied to approximate nearest neighbor search for large-scale image retrieval, while deep hashing further improves the retrieval quality by end-to-end representation learning and hash coding. With compact hash codes, Hamming space retrieval enables the most efficient constant-time search that returns data points within a given Hamming radius to each query, by hash table lookups instead of linear scan. However, subject to the weak capability of concentrating relevant images to be within a small Hamming ball due to mis-specified loss functions, existing deep hashing methods may underperform for Hamming space retrieval. This work presents Deep Cauchy Hashing (DCH), a novel deep hashing model that generates compact and concentrated binary hash codes to enable efficient and effective Hamming space retrieval. The main idea is to design a pairwise cross-entropy loss based on Cauchy distribution, which penalizes significantly on similar image pairs with Hamming distance larger than the given Hamming radius threshold. Comprehensive experiments demonstrate that DCH can generate highly concentrated hash codes and yield state-of-the-art Hamming space retrieval performance on three datasets, NUS-WIDE, CIFAR-10, and MS-COCO.