Visualizing Data using t-SNE

By L. V. D. van der Maaten, Geoffrey E. Hinton. 2008

50,192 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Dissecting Contextual Word Embeddings: Architecture and Representation (2018, methodology): “Figure 2 shows a t-SNE (Maaten and Hinton, 2008) visualization of span representations of 3,000 labeled chunks and 500 spans not labeled as chunks from the CoNLL 2000 chunking dataset (Sang and Buchholz, 2000), from the first layer of the 4-layer LSTM.”
Graph Attention Networks (2017, methodology): “…effectiveness of the learned feature representations may also be investigated qualitatively—and for this purpose we provide a visualization of the t-SNE (Maaten & Hinton, 2008)-transformed feature representations extracted by the ﬁrst layer of a GAT model pre-trained on the Cora dataset (Figure 2).”
A Simple Framework for Contrastive Learning of Visual Representations (2020, positive): “(Maaten & Hinton, 2008) visualizations of h and z = g ( h ) for randomly selected 10 classes by our best ResNet-50 (top-1 linear evaluation 69.3%).”
SummAE: Zero-Shot Abstractive Text Summarization using Length-Agnostic Auto-Encoders (2019, methodology): “D using t-SNE (Maaten and Hinton, 2008), with and without the critic.”
Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them (2019, methodology): “shows the tSNE (Maaten and Hinton, 2008) projection of the vectors before and after debiasing, for both models.”
Do Better ImageNet Models Transfer Better? (2018, methodology): “Low dimensional embeddings of Oxford 102 Flowers using t-SNE [46] on features from the penultimate layer of Inception v4, for 10 classes from the test set.”
Growing a Brain: Fine-Tuning by Increasing Model Capacity (2017, methodology): “Feature visualization: To roughly understand the topology of the feature spaces, we visualize the features using the standard t-SNE algorithm [46].”
Measuring and Improving BERT’s Mathematical Abilities by Predicting the Order of Reasoning. (2021, methodology): “For our analysis, we sample 2500 questions with a single operator in rationales, and next we visualise them with T-SNE (Van der Maaten and Hinton, 2008).”
Robust Neural Machine Translation with Joint Textual and Phonetic Embedding (2018, methodology): “We projects the whole pinyin embedding space into a 2 -dimensional space using t-SNE technique (Maaten and Hinton, 2008 that pinyins with similar pronunciations are close to each other, such as ZHEN and ZHENG, JI and QI, MU and HU.”
Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval (2020, methodology): “An example t-SNE [17] representation used in DR is shown in Fig.”
Contrastive Learning of Medical Visual Representations from Paired Images and Text (2020, methodology): “To understand how well ConVIRT pretraining helps separate images from different abnormality categories in its encoding space, in Figure 3 we present t-SNE plots (Maaten and Hinton, 2008) of candidate images in the CheXpert 8x200 dataset for five selected categories, from the ImageNet pretrained CNN ”
Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks (2020, methodology): “ OscarB OscarB ! Test-dev 60.00 !! !61.19 61.58 Test-std 60 .33 60 83 60 65 63 17 6123 62 Table 12: Evaluation results on GQA. Method Test-dev Test-std LXMERT [39] 60.00 60.33 MMN [4] ! 60.83 12-in-1 [24] ! 60.65 NSM [12] ! 63.17 OscarB 61.19 61.23 OscarB ! 61.58 61.62 20 X. Li, X. Yin, C. Li et al.”
FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age (2019, methodology): “We ﬁrst visualize randomly sampled faces in 2D space using t-SNE [38] as shown in Figure 4.”
Representation Learning with Contrastive Predictive Coding (2018, background): “Additionally, Figure 2 shows a t-SNE visualization [33] of how discriminative the embeddings are for speaker voice-characteristics.”
Learning Visual Features from Large Weakly Supervised Data (2015, methodology): “To obtain more insight into the features learned by the models, we applied t-SNE [51, 52] to features extracted from the penultimate layer of an AlexNet trained on 1 , 000 words.”
Language Understanding for Text-based Games using Deep Reinforcement Learning (2015, methodology): “Figure 5 shows a visualization 12The parameters for the Action Scorer (θA) are initialized randomly. of learnt word embeddings, reduced to two dimensions using t-SNE (Van der Maaten and Hinton, 2008).”
Zero-Shot Learning Through Cross-Modal Transfer (2013, methodology): “In the case where V = s , i.e. the point is considered to be of a known class, we can use any clas-siﬁer for obtaining P ( y | V = s, x, X s ) .”