The Ignorant Led by the Blind: A Hybrid Human–Machine Vision System for Fine-Grained Categorization

By Steve Branson, Grant Van Horn, Catherine Wah, Pietro Perona, Serge J. Belongie. 2014

83 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Developmental Biology, Molecular Biology

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Developmental Biology

In Molecular Biology

Citations in the corpus

The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition (2015, background): “The crowdsourcing literature has studied how to increase accuracy of noisy labelers via rater modeling [11, 56] or clever construction of easier tasks based on attributes, parts, or visual similarity [55, 6, 36].”
Visual Causal Feature Learning (2014, background): “…very encouraging results in image classification (Krizhevsky et al., 2012), object detection (Dollar et al., 2012) and fine-grained classification (Branson et al., 2014; Zhang et al., 2014), some researchers have found that visual neural networks can be easily fooled using adversarial examples…”
Bird Species Categorization Using Pose Normalized Deep Convolutional Nets (2014, background): “Each of these domains individually is of particular importance to its constituent enthusiasts; moreover, it has been shown that the mistakes of state-of-the-art recognition algorithms on the ImageNet Challenge usually pertain to distinguishing related subcategories [41].”
Guide Me: Interacting with Deep Networks (2018, background): “In [9] the user and an algorithm work together to solve fine grained recognition tasks, leveraging analytic strengths of the system and visual recognition power of the human.”
Local Alignments for Fine-Grained Categorization (2014, methodology): “…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 on any user input, not even during training, without sacriﬁcing the ﬁne-grained…”
A scalable active framework for region annotation in 3D shape collections (2016, background): “Their main advantage is that they acquire training data incrementally, enabling a classifier to predict which samples need to be labeled next to improve their performance [Vijayanarasimhan and Grauman 2008; Branson et al. 2011; Vezhnevets et al. 2012; Branson et al. 2014].”
Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition (2018, background): “[26] and [27] incorporate human knowledge and various types of computer vision algorithms into a human-in-the-loop framework for the complementary strengths of both ends.”
Fine-Grained Image Classification by Exploring Bipartite-Graph Labels (2015, methodology): “Fine-grained image classification concerns the task of distinguishing sub-ordinate categories of some base classes such as dogs [26, 43], birds [5, 8], flowers [1, 40], plants [32, 45], cars [30, 36, 48], food [3, 6, 38, 59], clothes [14], fonts [10] and furniture [4].”
Fine-grained recognition without part annotations (2015, background): “Expert human performance on CUB-2011 is roughly 93% [7].”
Part-Stacked CNN for Fine-Grained Visual Categorization (2015, unknown): “Existing fine-grained recognition methods that aim to provide a visual field guide mostly follow the routine of “part-based one-vs-one features” (POOFs) [3, 2, 4] or employ human-in-the-loop methods [20, 7, 38].”
Learning Concept Embeddings with Combined Human-Machine Expertise (2015, background): “Many researchers use similar embeddings to enhance the performance of classifiers [27, 9, 34], build retrieval sysFigure 1.”