Fine-Grained Crowdsourcing for Fine-Grained Recognition

By Jia Deng, Jonathan Krause, Li Fei-Fei. 2013

313 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Evaluation & Benchmarks

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

In Evaluation & Benchmarks

Citations in the corpus

Shaping Visual Representations with Language for Few-Shot Classification (2019, background): “In this framework, learning with attributes and other domain-specific rationales has been tackled extensively [8, 9, 29], but language remains relatively unexplored.”
ReferItGame: Referring to Objects in Photographs of Natural Scenes (2014, background): “These games can be released publicly on the web or used on Mechanical Turk to enhance and encourage turker participation (Deng et al., 2013).”
Part-Based R-CNNs for Fine-Grained Category Detection (2014, background): “Human-in-the-loop methods [9, 13, 15] ask a human to name attributes of the object, click on certain parts or mark the most discriminative regions to improve classification accuracy.”
Learning Deep Representations of Fine-Grained Visual Descriptions (2016, background): “In particular for the finegrained regime [46, 10, 7, 51], where images of differThe beak is yellow and pointed Accumulate matching score +8.”
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].”
Evaluation of output embeddings for fine-grained image classification (2014, background): “describe well-known common characteristics of objects, are an appealing source of information, and they can be easily obtained through crowd-sourcing techniques [8, 41].”
Latent Embeddings for Zero-Shot Classification (2016, background): “Caltech-UCSD Birds (CUB), Stanford Dogs (Dogs) are standard benchmarks of fine-grained recognition [7, 5, 37, 18] and Animals With Attributes (AWA) is another popular and challenging benchmark dataset [20].”
Co-teaching: Robust training of deep neural networks with extremely noisy labels (2018, background): “, 45% of noisy labels occur in the fine-grained classification with multiple classes [8]).”
Discovering Attribute Shades of Meaning with the Crowd (2015, background): “Furthermore, recent work using crowds to isolate informative spatial regions (Donahue and Grauman 2011; Deng et al. 2013) has a different purpose (fine-grained image classification) and takes an entirely different approach (explicitly asking labelers to outline the regions needed to make their label”
Building a bird recognition app and large scale dataset with citizen scientists: The fine print in fine-grained dataset collection (2015, background): “Notable examples include the ESP Game [33], reCAPTCHA [34], and BubbleBank [7].”
Integrating Scene Text and Visual Appearance for Fine-Grained Image Classification (2017, background): “In [11] and [19], the authors proposed to include humans in loop to select discriminative features.”
Learning Features and Parts for Fine-Grained Recognition (2014, background): “ELLF beats the previous state of the art, LLC [22], as well as BB [34] and BB-3D-G [13], two works designed for fine-grained recognition.”
Embedding Human Knowledge into Deep Neural Network via Attention Map (2019, methodology): “In the CUB-200-2010 dataset (Welinder et al., 2010), we embed human knowledge into an attention map by using bubble information (Deng et al., 2013).”
Deep LAC: Deep localization, alignment and classification for fine-grained recognition (2015, unknown): “[6] 32.”
Understanding Objects in Detail with Fine-Grained Attributes (2014, methodology): “[6] [27] use a comparison principle to corwdsource attributes from image collections.”
Leveraging the Wisdom of the Crowd for Fine-Grained Recognition (2016, background): “accuracy of 32:8 percent, which was the best result on CUB200-2010 when it was first published in [1].”
Y Qualification Main task Y Return N N Y User qualified ? N Feedback Pass ? Pass ? Annotator training Annotating images (2017, background): “Note that the scheme we propose does not require a human-in-the-loop setup [12, 46, 47, 72, 24]: clicks can be acquired separately, independently of the detector training framework used.”
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]).”