Hierarchical Deep Click Feature Prediction for Fine-Grained Image Recognition

By Jun Yu, Min Tan, Hongyuan Zhang, Dacheng Tao, Yong Rui. 2019

447 citations recorded by the source corpus.

The click feature of an image, defined as the user click frequency vector of the image on a predefined word vocabulary, is known to effectively reduce the semantic gap for fine-grained image recognition. Unfortunately, user click frequency data are usually absent in practice. It remains challenging to predict the click feature from the visual feature, because the user click frequency vector of an image is always noisy and sparse. In this paper, we devise a Hierarchical Deep Word Embedding (HDWE) model by integrating sparse constraints and an improved RELU operator to address click feature prediction from visual features. HDWE is a coarse-to-fine click feature predictor that is learned with the help of an auxiliary image dataset containing click information. It can therefore discover the hierarchy of word semantics. We evaluate HDWE on three dog and one bird image datasets, in which Clickture-Dog and Clickture-Bird are utilized as auxiliary datasets to provide click data, respectively. Our empirical studies show that HDWE has 1) higher recognition accuracy, 2) a larger compression ratio, and 3) good one-shot learning ability and scalability to unseen categories.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Deng-Ping Fan
2. Ming-Ming Cheng
3. Ling Shao
4. Qibin Hou
5. Yun Liu
6. Jiaxing Zhao
7. Jianbing Shen
8. Huchuan Lu

Citations in the corpus

• SpatialFlow: Bridging All Tasks for Panoptic Segmentation (2019, background): “These methods have dramatically improved the state-of-the-art in many vision tasks, including image recognition[23], [25], [26], [27], [28], [29], [30], image retrieval [31], [32], metric learning [33], [34], [35], object detection [36], [37], [19], image segmentation [38], [39], [4], human pose est”
• Deep CNN for Brain Tumor Classification (2021, methodology): “These techniques used traditional machine learning [27–29] and recently exploited deep learning models [30–44].”
• Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks (2019, background): “, the weighted triplet loss [113], hierarchical deep features [114], visual question-driven saliency [115] into our D3Net to further boost the performance.”