Direct optimization, by gradient descent, of an evaluation metric, is not possible when it is non-differentiable, which is the case for recall in retrieval.
Ranked #1 on Vehicle Re-Identification on VehicleID Medium
1 code implementation • 17 Jun 2021 • Matthijs Douze, Giorgos Tolias, Ed Pizzi, Zoë Papakipos, Lowik Chanussot, Filip Radenovic, Tomas Jenicek, Maxim Maximov, Laura Leal-Taixé, Ismail Elezi, Ondřej Chum, Cristian Canton Ferrer
The goal is to determine whether a query image is a modified copy of any image in a reference corpus of size 1~million.
Ranked #1 on Image Similarity Detection on DISC21 dev
At inference, the local descriptors are provided by the activations of internal components of the network.
In this work we consider the problem of learning a classifier from noisy labels when a few clean labeled examples are given.
We show successful attacks to partially unknown systems, by designing various loss functions for the adversarial image construction.
In this work, we employ a transductive label propagation method that is based on the manifold assumption to make predictions on the entire dataset and use these predictions to generate pseudo-labels for the unlabeled data and train a deep neural network.
State of the art image retrieval performance is achieved with CNN features and manifold ranking using a k-NN similarity graph that is pre-computed off-line.
In particular, annotation errors, the size of the dataset, and the level of challenge are addressed: new annotation for both datasets is created with an extra attention to the reliability of the ground truth.
Positive examples are distant points on a single manifold, while negative examples are nearby points on different manifolds.
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.
Eliminating the impact of the clutter on the image descriptor increases the chance of retrieving relevant images and prevents topic drift due to actually retrieving the clutter in the case of query expansion.
To demonstrate the advantages of the AFM method, we derive a short vector image representation that, due to asymmetric feature maps, supports efficient scale and translation invariant sketch-based image retrieval.
The diffusion is carried out on descriptors of overlapping image regions rather than on a global image descriptor like in previous approaches.
Convolutional Neural Networks (CNNs) achieve state-of-the-art performance in many computer vision tasks.
Ranked #5 on Image Retrieval on Par6k
Recently, image representation built upon Convolutional Neural Network (CNN) has been shown to provide effective descriptors for image search, outperforming pre-CNN features as short-vector representations.
Ranked #4 on Image Retrieval on Par6k
Our results show that the regular dense detector is outperformed by other methods in most situations, leading us to improve the state of the art in comparable setups on standard retrieval and fined-grain benchmarks.
Our geometric-aware aggregation strategy is effective for image search, as shown by experiments performed on standard benchmarks for image and particular object retrieval, namely Holidays and Oxford buildings.