Learning Deep Features For MSR-bing Information Retrieval Challenge

  title={Learning Deep Features For MSR-bing Information Retrieval Challenge},
  author={Qiang Song and Sixie Yu and Cong Leng and Jiaxiang Wu and Qinghao Hu and Jian Cheng},
  journal={Proceedings of the 23rd ACM international conference on Multimedia},
Two tasks have been put forward in the MSR-bing Grand Challenge 2015. To address the information retrieval task, we raise and integrate a series of methods with visual features obtained by convolution neural network (CNN) models. In our experiments, we discover that the ranking strategies of Hierarchical clustering and PageRank methods are mutually complementary. Another task is fine-grained classification. In contrast to basic-level recognition, fine-grained classification aims to distinguish… Expand
User-Click-Data-Based Fine-Grained Image Recognition via Weakly Supervised Metric Learning
This work presents a novel fine-grained image recognition framework using user click data, which can bridge the semantic gap in distinguishing categories that are similar in visual, and proposes a weakly-supervised metric and template leaning with smooth assumption and click prior method. Expand
Learning to recognition from Bing Clickture data
  • LI, Qiang Song, +4 authors Hanqing Lu
  • Computer Science
  • 2016 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)
  • 2016
This work presented a data cleaning method using faster-rcnn to learn a dog detector, and ensembeled a series of CNN models to enhance the robustness. Expand
Fine-grained image classification with factorized deep user click feature
The factorized deep click features to represent images are devised and it shows that: 1) the deep click feature learned on click tensor performs much better than traditional click frequency vectors; and 2) compared with many state-of-the-art textual representations, the proposedDeep click feature is more discriminative and with higher classification accuracies. Expand
Deep Neural Network Boosted Large Scale Image Recognition Using User Click Data
The experimental results for image recognition on Clickture-Dog dataset show that, compared to a common visual feature, the user click feature is more powerful to characterize the image contents and can beat the state-of-the-art CNN feature. Expand
DeepBE: Learning Deep Binary Encoding for Multi-label Classification
A framework of learning deep binary encoding (DeepBE) to deal with multi-label problems by transforming multi-labels to single labels is presented and an ensemble strategy is adopted to enhance the learning robustness. Expand


Cross-media relevance mining for evaluating text-based image search engine
This paper accumulates the experience from the one in 2013, and makes further investigation into different models to solve the relevance assessment problem at MSR-Bing Image Retrieval grand challenge, and combines the deep learning features with the wining solution of last year. Expand
An output aggregation system for large scale cross-modal retrieval
This paper presents the solution to MSR-Bing Image Retrieval Challenge to measure the relevance of web images and the query given in text form, and compares and integrates three typical methods to conduct the large-scale cross-modal retrieval task with concept-level visual features. Expand
Learning Deep Features for Scene Recognition using Places Database
A new scene-centric database called Places with over 7 million labeled pictures of scenes is introduced with new methods to compare the density and diversity of image datasets and it is shown that Places is as dense as other scene datasets and has more diversity. Expand
Very Deep Convolutional Networks for Large-Scale Image Recognition
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. Expand
Cross Modal Deep Model and Gaussian Process Based Model for MSR-Bing Challenge
A regression based cross modal deep learning model and a Gaussian Process scoring model are proposed that can score the query-image pairs based on the relevance between queries and images in the MSR-Bing Image Retrieval Challenge. Expand
ImageNet classification with deep convolutional neural networks
A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective. Expand
Visualizing and Understanding Convolutional Networks
A novel visualization technique is introduced that gives insight into the function of intermediate feature layers and the operation of the classifier in large Convolutional Network models, used in a diagnostic role to find model architectures that outperform Krizhevsky et al on the ImageNet classification benchmark. Expand
Search-based relevance association with auxiliary contextual cues
This work proposes a relevance association by investigating the effectiveness of different auxiliary contextual cues (i.e., face, click logs, visual similarity) and shows that the proposed method can have 16% relative improvement compared to the original ranking results. Expand
Caffe: Convolutional Architecture for Fast Feature Embedding
Caffe provides multimedia scientists and practitioners with a clean and modifiable framework for state-of-the-art deep learning algorithms and a collection of reference models for training and deploying general-purpose convolutional neural networks and other deep models efficiently on commodity architectures. Expand
Dog Breed Classification Using Part Localization
A novel approach to fine-grained image classification in which instances from different classes share common parts but have wide variation in shape and appearance is proposed, and results show that accurate part localization significantly increases classification performance compared to state-of-the-art approaches. Expand