Fine-tuning CNN Image Retrieval with No Human Annotation

Code

• github.com/filipradenovic/cnnimageretrieval-pytorch
  Officialpytorch★ 0
• github.com/layumi/University1652-Baseline
  pytorch★ 617
• github.com/nikosefth/freedom
  pytorch★ 47
• github.com/raojay7/cnnimageretrieval-pytorch
  pytorch★ 0
• github.com/jandaldrop/landmark-recognition-challenge
  tf★ 0
• github.com/naver/deep-image-retrieval
  pytorch★ 0
• github.com/HuangXiaoquan127/Google-Landmarks-Retrieval-and-Recognition-2019-19h-Place-Solution
  pytorch★ 0
• github.com/tuananh1007/CNN-Image-Retrieval-in-PyTorch
  pytorch★ 0
• github.com/osimeoni/DSM
  none★ 0
• github.com/layer6ai-labs/GSS
  tf★ 0

Abstract

Image descriptors based on activations of Convolutional Neural Networks (CNNs) have become dominant in image retrieval due to their discriminative power, compactness of representation, and search efficiency. Training of CNNs, either from scratch or fine-tuning, requires a large amount of annotated data, where a high quality of annotation is often crucial. In this work, we propose to fine-tune CNNs for image retrieval on a large collection of unordered images in a fully automated manner. Reconstructed 3D models obtained by the state-of-the-art retrieval and structure-from-motion methods guide the selection of the training data. We show that both hard-positive and hard-negative examples, selected by exploiting the geometry and the camera positions available from the 3D models, enhance the performance of particular-object retrieval. CNN descriptor whitening discriminatively learned from the same training data outperforms commonly used PCA whitening. We propose a novel trainable Generalized-Mean (GeM) pooling layer that generalizes max and average pooling and show that it boosts retrieval performance. Applying the proposed method to the VGG network achieves state-of-the-art performance on the standard benchmarks: Oxford Buildings, Paris, and Holidays datasets.

Tasks

Benchmark Results

Reproductions