Learning and aggregating deep local descriptors for instance-level
recognition
- URL: http://arxiv.org/abs/2007.13172v1
- Date: Sun, 26 Jul 2020 16:30:56 GMT
- Title: Learning and aggregating deep local descriptors for instance-level
recognition
- Authors: Giorgos Tolias, Tomas Jenicek, Ond\v{r}ej Chum
- Abstract summary: Training only requires examples of positive and negative image pairs.
At inference, the local descriptors are provided by the activations of internal components of the network.
We achieve state-of-the-art performance, in some cases even with a backbone network as small as ResNet18.
- Score: 11.692327697598175
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We propose an efficient method to learn deep local descriptors for
instance-level recognition. The training only requires examples of positive and
negative image pairs and is performed as metric learning of sum-pooled global
image descriptors. At inference, the local descriptors are provided by the
activations of internal components of the network. We demonstrate why such an
approach learns local descriptors that work well for image similarity
estimation with classical efficient match kernel methods. The experimental
validation studies the trade-off between performance and memory requirements of
the state-of-the-art image search approach based on match kernels. Compared to
existing local descriptors, the proposed ones perform better in two
instance-level recognition tasks and keep memory requirements lower. We
experimentally show that global descriptors are not effective enough at large
scale and that local descriptors are essential. We achieve state-of-the-art
performance, in some cases even with a backbone network as small as ResNet18.
Related papers
- Residual Learning for Image Point Descriptors [56.917951170421894]
We propose a very simple and effective approach to learning local image descriptors by using a hand-crafted detector and descriptor.
We optimize the final descriptor by leveraging the knowledge already present in the handcrafted descriptor.
Our approach has potential applications in ensemble learning and learning with non-differentiable functions.
arXiv Detail & Related papers (2023-12-24T12:51:30Z) - TALDS-Net: Task-Aware Adaptive Local Descriptors Selection for Few-shot
Image Classification [6.777813518399343]
Few-shot image classification aims to classify images from unseen novel classes with few samples.
Recent works demonstrate that deep local descriptors exhibit enhanced representational capabilities compared to image-level features.
We propose a novel Task-Aware Adaptive Local Descriptors Selection Network (TALDS-Net)
arXiv Detail & Related papers (2023-12-09T03:33:14Z) - Learning-Based Dimensionality Reduction for Computing Compact and
Effective Local Feature Descriptors [101.62384271200169]
A distinctive representation of image patches in form of features is a key component of many computer vision and robotics tasks.
We investigate multi-layer perceptrons (MLPs) to extract low-dimensional but high-quality descriptors.
We consider different applications, including visual localization, patch verification, image matching and retrieval.
arXiv Detail & Related papers (2022-09-27T17:59:04Z) - ZippyPoint: Fast Interest Point Detection, Description, and Matching
through Mixed Precision Discretization [71.91942002659795]
We investigate and adapt network quantization techniques to accelerate inference and enable its use on compute limited platforms.
ZippyPoint, our efficient quantized network with binary descriptors, improves the network runtime speed, the descriptor matching speed, and the 3D model size.
These improvements come at a minor performance degradation as evaluated on the tasks of homography estimation, visual localization, and map-free visual relocalization.
arXiv Detail & Related papers (2022-03-07T18:59:03Z) - Visualization of Supervised and Self-Supervised Neural Networks via
Attribution Guided Factorization [87.96102461221415]
We develop an algorithm that provides per-class explainability.
In an extensive battery of experiments, we demonstrate the ability of our methods to class-specific visualization.
arXiv Detail & Related papers (2020-12-03T18:48:39Z) - Region Comparison Network for Interpretable Few-shot Image
Classification [97.97902360117368]
Few-shot image classification has been proposed to effectively use only a limited number of labeled examples to train models for new classes.
We propose a metric learning based method named Region Comparison Network (RCN), which is able to reveal how few-shot learning works.
We also present a new way to generalize the interpretability from the level of tasks to categories.
arXiv Detail & Related papers (2020-09-08T07:29:05Z) - ReMarNet: Conjoint Relation and Margin Learning for Small-Sample Image
Classification [49.87503122462432]
We introduce a novel neural network termed Relation-and-Margin learning Network (ReMarNet)
Our method assembles two networks of different backbones so as to learn the features that can perform excellently in both of the aforementioned two classification mechanisms.
Experiments on four image datasets demonstrate that our approach is effective in learning discriminative features from a small set of labeled samples.
arXiv Detail & Related papers (2020-06-27T13:50:20Z) - Weakly-supervised Object Localization for Few-shot Learning and
Fine-grained Few-shot Learning [0.5156484100374058]
Few-shot learning aims to learn novel visual categories from very few samples.
We propose a Self-Attention Based Complementary Module (SAC Module) to fulfill the weakly-supervised object localization.
We also produce the activated masks for selecting discriminative deep descriptors for few-shot classification.
arXiv Detail & Related papers (2020-03-02T14:07:05Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.