Fine-Grained Categorization by Alignments

By Efstratios Gavves, Basura Fernando, Cees G. M. Snoek, Arnold M. W. Smeulders, Tinne Tuytelaars. 2013

200 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 application of two-level attention models in deep convolutional neural network for fine-grained image classification (2014, neutral): “[5] 61.0 Alignment [9] 62.7 DeCAF 6 [7] 58.8 CNNaug-SVM [15] 61.8 Part RCNN [24] 73.5 Pose Normalized CNN [4] 75.7 POOF [2] 56.8 Part RCNN [24] 76.7 POOF [2] 73.3”
Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks (2015, background): “The work of [17] and [18] demonstrated nonparametric part detection for fine-grained recognition.”
From generic to specific deep representations for visual recognition (2014, neutral): “non-ConvNet [35] [22] [40] [26] [38] [45] [25] [12] [18] [24] [42] [30] [37] [46] [37] [37] [4] 71.”
Bird Species Categorization Using Pose Normalized Deep Convolutional Nets (2014, methodology): “ained categorization over the past 5 years has been extensive. Areas explored include feature representations that better preserve ﬁne-grained information [35,46,47,48], segmentation-based approaches [1,13,14,15,21,37] that facilitate extraction of purer features, and part/pose normalized feature sp”
Birdsnap: Large-Scale Fine-Grained Visual Categorization of Birds (2014, background): “Much recent work in fine-grained visual categorization has focused on species identification, with work on leaves [14] [25], flowers [19] [25], butterflies [8] [29], insects [17], cats and dogs (e.g., [16] [21]), and birds (e.g., [4] [6] [7] [8] [12] [30] [32] [33]).”
Local Alignments for Fine-Grained Categorization (2014, background): “Where user input is often required both during training and testing, either in providing the object location (Gavves et al. 2013; Chai et al. 2013; Zhang et al. 2013), its parts (Bran-son et al. 2011) or its attributes (Duan et al. 2012; Branson et al. 2014), we present a system that does not rely…”
Fine-grained recognition without part annotations (2015, methodology): “Of the methods developed that do not use part annotations, there have been a few works philosophically similar to ours in the goal of finding localized parts or regions in an unsupervised fashion [15, 18, 10], with [18] and [10] more relevant.”
Picking Deep Filter Responses for Fine-Grained Image Recognition (2016, methodology): “[10] propose a supervised alignment method which retrieves nearest neighbor training images for a test image, and regresses part locations from these neighboring training images to the test image.”
Weakly Supervised Fine-Grained Image Categorization (2015, methodology): “Some works [10, 13] transfer the part annotations from objects in training images to those sharing similar shapes in testing images instead of applying object / part detectors.”
The Ignorant Led by the Blind: A Hybrid Human–Machine Vision System for Fine-Grained Categorization (2014, methodology): “A number of papers (Berg and Belhumeur 2013; Zhang et al. 2013; Chai et al. 2013; Gavves et al. 2013) have recently come out in CVPR and ICCV 2013 that significantly outperform earlier methods on CUB200-2011.”
Part-Based R-CNNs for Fine-Grained Category Detection (2014, methodology): “Bounding Box Given DPD [48] 50.98% DPD+DeCAF feature [14] 64.96% POOF [7] 56.78% Symbiotic Segmentation [10] 59.40% Alignment [20] 62 shows, in this setting our part-based method works much better than the base-line DPD model.”
Dynamic Computational Time for Visual Attention (2017, background): “The second group attempts to localize discriminative parts to effectively deal with large intra-class variation as well as subtle inter-class variation [55, 56, 57, 47, 9].”
Factors of Transferability for a Generic ConvNet Representation (2014, unknown): “ectionFine-grained RecognitionCompositionalInstance Retrieval VOC07 MIT SUN SunAtt UIUC H3D Pet CUB Flower VOCa. Act40 Phrase Holid. UKB Oxf. Paris Scul. nonConvNet [38] [25] [44] [30] [42] [50] [29] [12] [20] [28] [46] [34] [40] [51] [40] [40] [4] 71.1 68.5 37.5 87.5 90.2 69.1 59.2 62.7 90.2 69.6 4”
Fully Convolutional Attention Networks for Fine-Grained Recognition (2016, unknown): “[37] and Chai et al .”
Fine-Grained Image Classification by Exploring Bipartite-Graph Labels (2015, background): “Various pose-normalization pooling strategies combined with 2D or 3D geometry have been proposed for recognizing birds [7, 17, 20, 62, 63, 64], dogs [37] and cars [28, 30].”