Hierarchical Part Matching for Fine-Grained Visual Categorization

By Lingxi Xie, Qi Tian, Richang Hong, Shuicheng Yan. 2013

149 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

Fine-Grained Image Classification via Combining Vision and Language (2017, methodology): “And even part annotations are used in these methods [14, 15].”
Part-Based R-CNNs for Fine-Grained Category Detection (2014, methodology): “The Poselet [8] and DPM [17] methods have previously been utilized to obtain part localizations with a modest degree of success; methods generally report adequate part localization only when given a known bounding box at test time [11, 20, 35, 36, 42].”
Which Looks Like Which: Exploring Inter-class Relationships in Fine-Grained Visual Categorization (2014, methodology): “Segmentation based approaches were also explored in [1,14,39].”
Coarse-to-Fine Description for Fine-Grained Visual Categorization (2016, methodology): “Once the bounding box is given or generated, GrabCut [27] is widely used for foreground segmentation, i.e., Gavves et al. [16] and Xie et al. [10] both simply apply the GrabCut for foreground segmentation with the ground truth bounding box.”
Learning to Navigate for Fine-grained Classification (2018, background): “Some previous works [45,8,3,46,13,2,29] take advantage of fine-grained human annotations, like annotations for bird parts in bird classification.”
Deep LAC: Deep localization, alignment and classification for fine-grained recognition (2015, background): “In [5, 1, 24], segmentation and part localization were unified in one framework to alleviate the distracting effect of background.”
Towards Reversal-Invariant Image Representation (2017, unknown): “Recently, researchers design complicated part-based recognition algorithms, including Chai et al. (2013), Gavves et al. (2014), Xie et al. (2013), Zhang et al. (2013), Zhang et al. (2014b),Zhanget al. (2014a),Li et al. (2015), andZhanget al. (2016)).”
Geometric Neural Phrase Pooling: Modeling the Spatial Co-occurrence of Neurons (2016, methodology): “It can be used to filter out the false matches in object retrieval [24,27], or improve the descriptive ability of visual features for image classification [26,28].”
Audio Visual Attribute Discovery for Fine-Grained Object Recognition (2018, methodology): “…are the visual fine-grained annotations, e.g. the visual part label, (Branson et al. 2014; Huang et al. 2016; Krause et al. 2015; Liu et al. 2012; Xie et al. 2013; Zhang et al. 2016a; 2014; 2016b) and the text descriptions e.g. attributes (Berg and ∗corresponding author Copyright c© 2018,…”
Object-Part Attention Model for Fine-Grained Image Classification (2017, background): “Early works [38], [43], [44] choose SIFT [16] as features, and the performances are limited and much lower than our OPAM approach no mater whether using the object and part annotations or not.”
Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches (2020, background): “Early work mostly finds discriminative regions with the assistance of manual annotations [2,21,34,37,16].”
Image Classification and Retrieval are ONE (2015, background): “Descriptors are thereafter quantized onto the codebook as compact feature vectors [63][51][37][55], and summarized as an image-level representation [26][17][57][59].”
The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification (2020, methodology): “Some of the earlier works [2], [5], [30], [45] take advantages of bounding-box/part annotations, as an additional information for both training and testing.”
Picking Deep Filter Responses for Fine-Grained Image Recognition (2016, background): “In order to achieve accurate object and part locations, most existing works explicitly require object level or even part level annotations at both training and testing stages [3], [28], [33].”