Local Alignments for Fine-Grained Categorization

By Efstratios Gavves, Basura Fernando, Cees G. M. Snoek, Arnold M. W. Smeulders, Tinne Tuytelaars. 2014

81 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition (2015, background): “The majority of research in fine-grained recognition has focused on developing improved models for classification [2, 5, 7, 15, 17, 18, 24, 30, 37, 44, 45, 58, 59, 60, 63, 64].”
Deep Image: Scaling up Image Recognition (2015, methodology): “ved accuracy of 85.6% by adding bounding box annotations only at test time. Table 2. Species categorization results on CUB-200-2011 Method Training Testing Accura BBox Part BBox Part cy(%) Alignments [17] 53.6 Attention [49] 77.9 B-CNN (D,M) [30] 80.9 Part discovery [44] 81.0 Ours 84.9 GMTL [38] √ √”
The Devil is in the Tails: Fine-grained Classification in the Wild (2017, background): “Most fine-grained research papers present a novel model for classification [4, 6, 7, 12, 15, 17, 25, 31, 40, 45, 46, 57, 58, 59, 61, 62].”
Rank Pooling for Action Recognition (2015, background): “What is more, simple but robust techniques such as temporal pyramids that are similar to spatially dividing images [33] and objects [16] are insufficient.”
Learning Deep Features for Discriminative Localization (2015, methodology): “This enables classification-trained CNNs to learn to perform object localization, without using any bounding box annotations.”
Fine-Grained Categorization and Dataset Bootstrapping Using Deep Metric Learning with Humans in the Loop (2015, unknown): “Alignments [15] 67.”
Fine-grained recognition without part annotations (2015, methodology): “[18, 19] segment images via GrabCut [37], and then roughly align objects by parameterizing them as an ellipse.”
Cross-Dimensional Weighting for Aggregated Deep Convolutional Features (2015, background): “It is worth noting that the highest performing competitors have very computationally heavy training and testing phases [30] or further require feature fusion [8].”
Adversarial Complementary Learning for Weakly Supervised Object Localization (2018, unknown): “4 Alignments [11] BBox 33.”
Coarse-to-Fine Description for Fine-Grained Visual Categorization (2016, background): “In [5], the authors simply define the distance measurement as the Euclidean distance of two pixels in the”
Diversified Visual Attention Networks for Fine-Grained Object Classification (2016, unknown): “Unsupervised grid alignments [51] √ 56.”
Towards Reversal-Invariant Image Representation (2017, background): “As observed in Berg and Belhumeur (2013), Chai et al. (2013),Gavves et al. (2014), the key tofine-grained recognition is the alignment of semantic object parts, such as the head or tail of a bird.”