Learning the easy things first: Self-paced visual category discovery

By Yong Jae Lee, Kristen Grauman. 2011

229 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning, Optimization & Training

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 Representation & Self-Supervised Learning

In Optimization & Training

Citations in the corpus

Webly Supervised Learning of Convolutional Networks (2015, methodology): “After seventh layer, another fully connected layer is used to predict class labels.”
Learning to Execute (2014, methodology): “This approach can be implemented with curriculum learning (Bengio et al., 2009; Kumar et al., 2010; Lee & Grauman, 2011), which prescribes gradually increasing the “difﬁculty level” of the examples presented to the LSTM, and is partially motivated by fact that humans and animals learn much faster…”
Machine Teaching: An Inverse Problem to Machine Learning and an Approach Toward Optimal Education (2015, background): “…in machine teaching, such as the sequential teaching setting (Bengio et al. 2009; Khan, Zhu, and Mutlu 2011; McCandliss et al. 2002; Kumar, Packer, and Koller 2010; Lee and Grauman 2011; Cakmak and Lopes 2012; Pashler and Mozer 2013; Kobayashi and Shinohara 2009; Balbach and Zeugmann 2009).”
Unsupervised Discovery of Mid-Level Discriminative Patches (2012, background): “Since then, there has been a large body of work in the general area of unsupervised object discovery [25,26,27,28,29,30,31].”
Machine Teaching for Bayesian Learners in the Exponential Family (2013, background): “The third thread is the research on better ways to training machine learners such as curriculum learning or easy-to-hard ordering of training items [3, 15, 16], and optimal reward design in reinforcement learning [21].”
Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics (2020, background): “Similar intuitions have guided other work such as curriculum learning (Bengio et al., 2009) and self-paced learning (Kumar et al., 2010; Lee and Grauman, 2011) where all examples are prioritized based on their “difﬁculty”.”
Weakly Supervised Object Localization Using Things and Stuff Transfer (2017, unknown): “In this work we are interested in the task where we have the location annotations in the source and transfer them to help learn the classes in the target [18, 39, 21, 19, 23, 22].”
Prime Object Proposals with Randomized Prim's Algorithm (2013, background): “In a similar spirit, recent work has explored applications in object discovery [18], weakly supervised learning of object interaction with humans [19] or with other objects [5], as well as action recognition in still images [22] and content-aware media re-targeting [26].”
Learning to Teach (2018, background): “Curriculum learning (CL) (Bengio et al., 2009; Spitkovsky et al., 2010; Graves et al., 2017) and self-paced learning (SPL) (Kumar et al., 2010; Lee & Grauman, 2011; Jiang et al., 2014b) heuristically deﬁne the scheduling of training data in a from-easy-to-hard order.”
Learning object class detectors from weakly annotated video (2012, background): “Because manual annotation can be inflexible, expensive and tedious, recent work investigated methods that can learn from unlabeled or weakly annotated data [3, 6, 9, 23, 37].”
Expanding object detector's Horizon: Incremental learning framework for object detection in videos (2015, methodology): “In the original work of [21], self-paced learning was used to learn latent variables, and in [22], it was used to discover object categories from clustered image patches.”
Easy Questions First? A Case Study on Curriculum Learning for Question Answering (2016, methodology): “The techniques have been shown to be useful in some computer vision tasks (Lee and Grauman, 2011; Kumar et al., 2011; Tang et al., 2012; Supancic and Ramanan, 2013; Jiang et al., 2014a).”
Asymmetric multi-task learning based on task relatedness and loss (2016, background): “Lee & Grauman (2011) exploit a similar idea for unsupervised learning, where they iteratively discovered categories while using earlier learned categories as the context of later learned ones.”
How Do Humans Teach: On Curriculum Learning and Teaching Dimension (2011, background): “Computational teaching has been well studied in the machine learning community [9, 12, 10, 1, 2, 11, 13, 18, 4, 14, 15].”
What Objective Does Self-paced Learning Indeed Optimize? (2015, background): “where Ω1 = O([−7,−8], 4)∩{[x, y]|y < x},Ω2 = O([6, 8], 4)∩{[x, y]|y > x},Ω3 = {x, y|x, y ∈ [−180, 180]}, O(x0, r) represents a circle area with center x0 and radius r, N(μ, σ(2)) denotes the Gaussian distribution with mean μ and variance σ(2) and U(Ω) represents the uniform distribution on Ω.”