How Do You Tell a Blackbird from a Crow?

By Thomas Berg, Peter N. Belhumeur. 2013

40 citations recorded by the source corpus.

Subfields: Developmental Biology, Ecological Modeling, Global and Planetary Change

How researchers see this paper

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

In Developmental Biology

In Ecological Modeling

In Global and Planetary Change

Citations in the corpus

Multimodal Explanations: Justifying Decisions and Pointing to the Evidence (2018, methodology): “Some methods find discriminative visual patches [7, 11] whereas others aim to understand what specific neurons represent [12, 38, 39].”
Attentive Explanations: Justifying Decisions and Pointing to the Evidence (2016, methodology): “Some methods ﬁnd discriminative visual patches [12, 7] whereas others aim to understand intermediate features which are important for end decisions [40, 14, 41] e.g. what does a certain neuron represent.”
Generating Visual Explanations (2016, background): “Many vision methods focus on discovering visual features which can help “explain” an image classification decision [3,16,6].”
Becoming the expert - interactive multi-class machine teaching (2015, background): “Visualizations such as pair-wise comparisons [22], and highlighting local regions [11] or parts [6], may prove more effective at conveying discriminative details and characteristics of different categories.”
Teaching Categories to Human Learners with Visual Explanations (2018, methodology): “Attempts have been made to automate the creation of these guides using highlighted part annotations [3], automatic generation of image specific text descriptions [15], or through gamification [8].”
Learning a Discriminative Filter Bank Within a CNN for Fine-Grained Recognition (2016, background): “ response map. vantages of both categories of previous approaches. 2. Related Work Fine-grained recognition Research in ﬁne-grained recognition has shifted to deep learning from multistage frameworks [48,38,13,30,34,29,8,53,4,3,49,6, 35,10,54,14] based on hand-crafted features such as utilizing DPM ”
Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering (2016, methodology): “Closest to our counter-example explanation work is the work by [7] for fine-grained bird classification.”
Which Looks Like Which: Exploring Inter-class Relationships in Fine-Grained Visual Categorization (2014, methodology): “The idea of using the class relationships was also exploited very recently in [8,9], where the authors proposed to use one-vs-most SVMs to find significant features that distinguish different species by omitting some similar classes, which is fundamentally different from our proposed solution.”