A codebook-free and annotation-free approach for fine-grained image categorization

By Bangpeng Yao, Gary R. Bradski, Li Fei-Fei. 2012

161 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, background): “Fine-grained classification has been extensively studied recently [21, 22, 11, 3, 5, 24, 27, 2, 4].”
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 [1,3,5,7,9,8,14,16,18,20,21,22,28,29,36,37,41,42,49,51,50,66,68,69,71,73,72,76,77,75,78].”
Taskonomy: Disentangling Task Transfer Learning (2018, background): “grained classification [44] and object recognition [23], multi-view reconstruction [36] and structure from motion [27], wide baseline matching [41], SLAM [35] and visual odometry[52].”
Continual Representation Learning for Biometric Identification (2020, background): “Second, biometric identification focuses on a more challenging setting which is similar to fine-grained classification [2,64,70,73].”
MatchNet: Unifying feature and metric learning for patch-based matching (2015, unknown): “, [36]), multi-view reconstruction (e.”
Improving Fine-Grained Visual Classification using Pairwise Confusion (2017, methodology): “[14] subsequently utilized template matching to avoid the need for a large number of annotations.”
Symbiotic Segmentation and Part Localization for Fine-Grained Categorization (2013, background): “Whether the parts arise from poselets [35] or are discovered from random initializations [33], there are benefits in comparing objects in finegrained visual categorization tasks at the part level where subtle discriminative features are more evident.”
Fine-Grained Crowdsourcing for Fine-Grained Recognition (2013, methodology): “Note that CFAF used 42000 random templates, a feature dimensionality of 882000, a customized SVM learning procedure, and 0.5 1 1.5 2 2.5 3 x 10 4 0.25 0.3 0.35 0.4 0.45 0.5 0.55 Number of bubbles mAP Figure 8.”
Destruction and Construction Learning for Fine-Grained Image Recognition (2019, background): “Due to the success of deep learning, fine-grained recognition methods have shifted from multistage frameworks based on hand-crafted features [39, 36, 23, 10] to multistage frameworks with CNN features [13, 31, 29].”
The Ignorant Led by the Blind: A Hybrid Human–Machine Vision System for Fine-Grained Categorization (2014, background): “The work of (Yao et al. 2011, 2012) and (Martınez-Munoz et al. 2009) relates to learning features that go beyond traditional codebook-based methods in object recognition.”
Ontological supervision for fine grained classification of Street View storefronts (2015, background): “Recently there has been renewed interest in Fine Grained classification [32, 33, 14] Yao et al.”
Which Looks Like Which: Exploring Inter-class Relationships in Fine-Grained Visual Categorization (2014, methodology): “We compare with the following published approaches: multiple kernel learning (MKL) [11], Birdlet [19], a random template method [41], and the KDES [10].”
Local Alignments for Fine-Grained Categorization (2014, methodology): “Surprisingly enough, the recent finegrained literature (Farrell et al. 2011; Yao et al. 2012) often focuses on more traditional color based descriptors as found in (Swain and Ballard 1991) rather than state-of-the-art solutions, see (van de Sande et al.”
Picking Deep Filter Responses for Fine-Grained Image Recognition (2016, unknown): “Most previous works employ some form of unsupervised clustering, such as k-means [23], [24], or template matching [30], to initialize a part model.”
Leveraging the Wisdom of the Crowd for Fine-Grained Recognition (2016, background): “Among all game rounds, 71 percent were successful (i.e. the player correctly identifies the category), 14 percent failed, and 15 percent were skipped by passing the image or switching categories.”
Nonparametric Part Transfer for Fine-Grained Recognition (2014, methodology): “Partbased approaches can be exploited to tackle this goal, since they allow for computing approximate pose invariant features [22, 39, 41].”
POOF: Part-Based One-vs.-One Features for Fine-Grained Categorization, Face Verification, and Attribute Estimation (2013, background): “[8, 32, 33, 35] in different ways attempt to find parts of the image that are discriminative without explicit part labels, but cannot achieve the accuracy of a supervised part-based approach.”
Learning a Discriminative Filter Bank Within a CNN for Fine-Grained Recognition (2016, background): “Fine-grained recognition Research in fine-grained recognition has shifted from multistage frameworks based on hand-crafted features [52, 3, 48, 6, 13] to multistage framework with CNN features [24, 44, 35, 53, 42], and then to end-to-end approaches.”