One-Shot Fine-Grained Instance Retrieval

@article{Yao2017OneShotFI,
  title={One-Shot Fine-Grained Instance Retrieval},
  author={Hantao Yao and Shiliang Zhang and Yongdong Zhang and Jintao Li and Qi Tian},
  journal={Proceedings of the 25th ACM international conference on Multimedia},
  year={2017}
}
Fine-Grained Visual Categorization (FGVC) has achieved significant progress recently. However, the number of fine-grained species could be huge and dynamically increasing in real scenarios, making it difficult to recognize unseen objects under the current FGVC framework. This raises an open issue to perform large-scale fine-grained identification without a complete training set. Aiming to conquer this issue, we propose a retrieval task named One-Shot Fine-Grained Instance Retrieval (OSFGIR… 
View on ACM
arxiv.org
16 Citations
Highly Influential Citations
2
Background Citations
8
Methods Citations
6
Results Citations
2

16 Citations

Citation Type

Citation Type

Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classification
TLDR
This paper addresses the Few-Shot Fine-Grained (FSFG) classification problem, which focuses on tackling the fine-grained classification under the challenging few-shot learning setting, and proposes a novel low-rank pairwise bilinear pooling operation to capture the nuanced differences between the support and query images for learning an effective distance metric.
Compare More Nuanced: Pairwise Alignment Bilinear Network for Few-Shot Fine-Grained Learning
TLDR
This work proposes a simple yet effective model for the Few-Shot Fine-Grained recognition, which tries to tackle the challenging fine-grained recognition task using meta-learning, and uses a novel pairwise bilinear pooling to compare the nuanced differences between base images and query images for learning a deep distance metric.
Adversarial Learning for Fine-Grained Image Search
TLDR
This work proposes an end-to-end network, called FGGAN, that learns discriminative representations by implicitly learning a geometric transformation from multi-view images for fine-grained rigid object retrieval and integrates a generative adversarial network (GAN) that can automatically handle complex view and pose variations by converting them to a canonical view without any predefined transformations.
Fine-Grained Grocery Product Recognition by One-Shot Learning
TLDR
A novel hybrid classification approach that combines feature-based matching and one-shot deep learning with a coarse-to-fine strategy to improve the accuracy of fine-grained grocery products recognition effectively is presented.
Fine-Grained Visual-Textual Representation Learning
TLDR
A fine-grained visual-textual representation learning (VTRL) approach, which achieves the best categorization accuracy compared with the state-of-the-art methods.
Weighted Multi-feature Fusion Algorithm for Fine-Grained Image Retrieval
TLDR
A new constraint to select discriminative patches is designed, which makes use of the irregular but more accurate object region to select the discriminate patches, and the Deep Belief Network is introduced to effectively fuse multi-level features.
Alaskan Dog Husky Dog BMW 1 Series BMW 3 Series Cat Dog Bird Car Easy to Recognise A Little Hard to Classify
TLDR
A simple yet effective model for the Few-Shot Fine-Grained recognition, which tries to tackle the challenging fine-grained recognition task using meta-learning, using a novel pairwise bilinear pooling to compare the nuanced differences between base images and query images for learning a deep distance metric.
Fine-grained Recognition of 3D Shapes Based on Multi-view Recurrent Neural Network
TLDR
A recurrent neural network was adopted to fuse multi-view features instead of max-pooling operation, which is named as MVRNN, and a loss function taking the discrimination of fused features into consideration was defined to train the MVCNN.
Self-aligned Spatial Feature Extraction Network for UAV Vehicle Re-identification
TLDR
An unsupervised self-aligned network consisting of three branches is developed to extract efficient fine-grained features and avoid tedious annotating work, and achieves the best performance compared with recent ReID works.
VP-ReID: Vehicle and Person Re-Identification System
TLDR
A robust and efficient person and video ReID system named as VP-ReID is developed, build based on recent works including Deep Convolutional Neural Network design for discriminative feature extraction, efficient off-line indexing, as well as distance metric optimization for deep feature learning.
...
...

References

SHOWING 1-10 OF 68 REFERENCES
Part-Based R-CNNs for Fine-Grained Category Detection
TLDR
This work proposes a model for fine-grained categorization that overcomes limitations by leveraging deep convolutional features computed on bottom-up region proposals, and learns whole-object and part detectors, enforces learned geometric constraints between them, and predicts a fine- grained category from a pose-normalized representation.
Coarse-to-Fine Description for Fine-Grained Visual Categorization
TLDR
A multi-level coarse-to-fine object description that only requires the original image as input, but could automatically generate visual descriptions discriminative enough for fine-grained visual categorization.
Part-Stacked CNN for Fine-Grained Visual Categorization
TLDR
A novel Part-Stacked CNN architecture that explicitly explains the finegrained recognition process by modeling subtle differences from object parts is proposed, from multiple perspectives of classification accuracy, model interpretability, and efficiency.
The application of two-level attention models in deep convolutional neural network for fine-grained image classification
TLDR
This paper proposes to apply visual attention to fine-grained classification task using deep neural network and achieves the best accuracy under the weakest supervision condition, and is competitive against other methods that rely on additional annotations.
Mask-CNN: Localizing Parts and Selecting Descriptors for Fine-Grained Image Recognition
TLDR
The proposed Mask-CNN model has the smallest number of parameters, lowest feature dimensionality and highest recognition accuracy when compared with state-of-the-arts fine-grained approaches.
Fine-Grained Categorization by Alignments
TLDR
It is argued that in the distinction of fine grained sub-categories, classification-oriented encodings like Fisher vectors are better suited for describing localized information than popular matching oriented features like HOG.
Fine-grained recognition without part annotations
TLDR
This work proposes a method for fine-grained recognition that uses no part annotations, based on generating parts using co-segmentation and alignment, which is combined in a discriminative mixture.
Fine-Grained Image Search
TLDR
It is suggested that instance search should return not only near-duplicate images, but also fine-grained results, which is usually the actual intention of a user, in order to find semantically matched search results.
Subset feature learning for fine-grained category classification
TLDR
A learning system which first clusters visually similar classes and then learns deep convolutional neural network features specific to each subset of bird classes, yielding improvements in accuracy.
Local Alignments for Fine-Grained Categorization
TLDR
By using object detectors as voters to generate object confidence saliency maps, the proposed local alignments set a new state-of-the-art on both the fine-grained birds and dogs datasets, even without any human intervention.
...
...