Learning Classification with Unlabeled Data

By Virginia de Sa. 1993

Subfields: 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 Representation & Self-Supervised Learning

Citations in the corpus

Self-Supervised Learning of Video-Induced Visual Invariances (2019, background): “Multi-modal learning methods that combine vision and audio [42, 9, 46, 3], and vision and text [57] achieve better performance than unimodal baselines.”
Learning Features by Watching Objects Move (2016, background): “The assumption in these works is that to perform these tasks, the network will need to recognize high-level concepts, such as objects, in order to succeed.”
A critical analysis of self-supervision, or what we can learn from a single image (2019, neutral): “…al., 2017), optical-ﬂow (Gan et al., 2018; Mahendran et al., 2018), future-frame synthesis (Srivastava et al., 2015), audio prediction from video (de Sa, 1994; Owens et al., 2016), audio-video alignment (Arandjelovi´c & Zisserman, 2017), ego-motion estimation (Ja-yaraman & Grauman, 2015), slow…”
Scaling and Benchmarking Self-Supervised Visual Representation Learning (2019, background): “A large portion of such approaches are grouped under the term ‘selfsupervised’ learning [9] in which the key principle is to automatically generate ‘labels’ from the data.”
Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction (2016, methodology): “Our method is especially related to [4, 5, 41], which use bidirectional data prediction to learn representations from two sensory modalities.”
Learning Hierarchical Discrete Linguistic Units from Visually-Grounded Speech (2019, background): “Visual grounding of speech is a form of self-supervised learning (Virginia de Sa, 1994), which is powerful in part because it offers a way of training models with a discriminative objective that does not depend on traditional transcriptions or annotations.”
Deep Clustering for Unsupervised Learning of Visual Features (2018, background): “A popular form of unsupervised learning, called “self-supervised learning” [52], uses pretext tasks to replace the labels annotated by humans by “pseudo-labels” directly computed from the raw input data.”
Self-labelling via simultaneous clustering and representation learning (2019, neutral): “…al., 2017), optical-ﬂow (Gan et al., 2018; Mahendran et al., 2018), future-frame synthesis (Srivastava et al., 2015), audio prediction from video (de Sa, 1994; Owens et al., 2016), audio-video alignment (Arandjelovi´c & Zisserman, 2017), ego-motion estimation (Jayaraman & Grauman, 2015), slow…”
The Challenges of Continuous Self-Supervised Learning (2022, background): “…, 54 , 55 ], inpainting [ 59 ] and colorization [ 18 , 34 , 86 ], to methods that learn representations predictive of spatial context [ 19 , 22 , 53 ], temporal context [ 21 , 47 , 58 , 60 , 78 , 79 ], or concurrent modalities like audio [ 4 , 52 , 57 , 69 ], text [17, 23, 61] or speech [43, 44].”
Audio-Visual Scene Analysis with Self-Supervised Multisensory Features (2018, background): “Starting with the early work of de Sa [3], there have been many self-supervised methods that learn to find correlations between sight and sound [13,14,15,16].”
Self-Supervised Learning: Generative or Contrastive (2020, neutral): “Repainted from [32].”
Cross Pixel Optical Flow Similarity for Self-Supervised Learning (2018, neutral): “Some methods exploit audio channels by prediction audio from video frames [16,17].”
Audio-Visual Instance Discrimination with Cross-Modal Agreement (2020, background): “Self-supervised learning is a well studied problem [13, 47, 52, 55, 60, 72].”
The Sound of Pixels (2018, background): “In this paper, however, we leverage joint audio-visual learning to discover objects that produce sound in the world without manual supervision [13,14,15].”
Learning Distributed Representations of Symbolic Structure Using Binding and Unbinding Operations (2018, background): “Recent advances in deep learning benefit largely from neural networks’ ability to learn distributed representations of inputs from various domains [8]; even samples from different modalities can be easily compared in a common representation space [16, 42].”
Multi-view clustering: A survey (2018, unknown): “[45] constructed a custom kernel combination method based on the minimizing-disagreement algorithm[46, 47].”