Visual Recognition with Humans in the Loop

By Steve Branson, Catherine Wah, Florian Schroff, Boris Babenko, Peter Welinder, Pietro Perona, Serge J. Belongie. 2010

501 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

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 Representation & Self-Supervised Learning

Citations in the corpus

LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop (2015, methodology): “Clever methods have been proposed to improve the efﬁciency of human-in-the-loop annotation (e.g., [2, 5, 13, 20, 21]).”
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.”
Deep Networks with Internal Selective Attention through Feedback Connections (2014, background): “However, an expert ornithologist, asked to classify a bird belonging to one of two very similar species, may have to think for more than a few milliseconds before answering [16, 17], implying that several feedforward evaluations are performed, where each evaluation tries to elicit different informat”
Bird Species Categorization Using Pose Normalized Deep Convolutional Nets (2014, methodology): “Our architecture first computes an estimate of the object’s pose; this is used to compute local image features which are, in turn, used for classification.”
Label-Embedding for Image Classification (2015, neutral): “This might be viewed as a disadvantage of our approach as we might loose interpretability, an important property of attribute-based systems when, for instance, one wants to include a human in the loop [5], [69].”
Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning (2018, background): “Beyond pixels, we also leverage other information including parts [66, 7, 67], attributes [57, 18], human interactions [8, 13] and text descriptions [42, 22].”
A codebook-free and annotation-free approach for fine-grained image categorization (2012, background): “Fine-grained image classification [1] [13] [3] [31] [24] [10] [27] refers to the task of classifying objects that belong to the same basic-level category.”
Fine-Grained Categorization and Dataset Bootstrapping Using Deep Metric Learning with Humans in the Loop (2015, methodology): “This section presents a bootstrapping framework on how to grow a small scale, fine-grained dataset in an efficient manner.”
Fine-Grained Crowdsourcing for Fine-Grained Recognition (2013, methodology): “All images are cropped to the bounding boxes, as is standard for many published results [35, 5, 37, 36, 1].”
Attribute-Based Detection of Unfamiliar Classes with Humans in the Loop (2013, methodology): “We model the set of user attribute responses U in a similar fashion as [37] [6].”
Leafsnap: A Computer Vision System for Automatic Plant Species Identification (2012, background): “[2] describes a system that combines human input with computer vision results to assist in the identification of birds.”
Unsupervised Template Learning for Fine-Grained Object Recognition (2012, methodology): “Comparisons with the state-of-the-art algorithms: We compared our model with four recently published algorithms for fine-grained object recognition: multiple kernel learning [5], random forest [9], LLC [9], and multi-cue [6] in Table 3.”
Embracing Error to Enable Rapid Crowdsourcing (2016, methodology): “In an effort to reduce cost, many previous papers have studied the tradeoffs between speed (cost) and accuracy on a wide range of tasks [68, 6, 67, 49].”
A computer vision for animal ecology. (2018, methodology): “Known as “human in loop” approaches, this strategy can learn directly from human annotations to provide feedback and recommendation for future data labelling (Branson et al., 2010; Reda, Mateevitsi, & Offord, 2013).”
What are the Visual Features Underlying Human Versus Machine Vision? (2017, background): “Researchers have found that in cases like these human perceptual judgments can augment the performance of vision models [35], resulting in significant gains in face recognition and localization [24, 2, 14], action recognition [31], object detection and segmentation [20, 26, 32].”
How Do You Tell a Blackbird from a Crow? (2013, background): “Work on fine-grained visual categorization with “humans in the loop” [3, 25], proposes a model in which a person answers questions to assist a recognition system that makes a final identification.”