Hard-Aware Deeply Cascaded Embedding
arXiv:1611.05720
Abstract
Riding on the waves of deep neural networks, deep metric learning has also achieved promising results in various tasks using triplet network or Siamese network. Though the basic goal of making images from the same category closer than the ones from different categories is intuitive, it is hard to directly optimize due to the quadratic or cubic sample size. To solve the problem, hard example mining which only focuses on a subset of samples that are considered hard is widely used. However, hard is defined relative to a model, where complex models treat most samples as easy ones and vice versa for simple models, and both are not good for training. Samples are also with different hard levels, it is hard to define a model with the just right complexity and choose hard examples adequately. This motivates us to ensemble a set of models with different complexities in cascaded manner and mine hard examples adaptively, a sample is judged by a series of models with increasing complexities and only updates models that consider the sample as a hard case. We evaluate our method on CARS196, CUB-200-2011, Stanford Online Products, VehicleID and DeepFashion datasets. Our method outperforms state-of-the-art methods by a large margin.
accepted by ICCV 2017
References in corpus (8)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Residual Networks Behave Like Ensembles of Relatively Shallow Networks
- Learning Deep Embeddings with Histogram Loss
- Siamese Instance Search for Tracking
- Local Similarity-Aware Deep Feature Embedding
- Top-push Video-based Person Re-identification
- Learning a Metric Embedding for Face Recognition using the Multibatch Method
- Mining Discriminative Triplets of Patches for Fine-Grained Classification
Cited by in corpus (7)
- Leveraging Weakly Annotated Data for Fashion Image Retrieval and Label Prediction
- Sampling Matters in Deep Embedding Learning
- Classification is a Strong Baseline for Deep Metric Learning
- Incorporating Intra-Class Variance to Fine-Grained Visual Recognition
- Generalization in Metric Learning: Should the Embedding Layer be the Embedding Layer?
- AI Oriented Large-Scale Video Management for Smart City: Technologies, Standards and Beyond
- Attribute-Aware Attention Model for Fine-grained Representation Learning