2018 Turing Award, 2021 Communications of the ACM — The Turing Award is often referred to as the computer science equivalent of the Nobel Prize. Yoshua Bengio, Yann LeCun, and Geoffrey Hinton are recipients of the 2018 ACM A.M. Turing Award for breakthroughs that have made deep neural networks a critical component of computing. This time, I would like…

Use Image-Level Labels to Help Biomedical Image Segmentation — Learning to Segment Images with Classification Labels Ciga JMEDIA’21, by University of Toronto, and Sunnybrook Research Institute 2021 JMEDIA (Sik-Ho Tsang @ Medium) Image Classification, Medical Image Segmentation, Weakly Supervised Learning An architecture is proposed that can alleviate the requirements for segmentation- level ground truth by making use of image-level…

MoE, By Hinton in 1991. Hinton Extended to NLP in 2017 — Adaptive Mixtures of Local Experts MoE, by MIT, and University of Toronto, 1991 JNEUCOM, Over 5000 Citations (Sik-Ho Tsang @ Medium) Mixture of Experts, MoE, Sequence Model, Vowel Recognition By using gating network, different experts are on/off based on the input signal. This is a paper by Prof. Hinton’s research…

Back Translation+Sampling, Good at Low Resource Languages — Understanding Back-Translation at Scale Back-Translation+Sampling, by Facebook AI Research, and Google Brain 2018 EMNLP, Over 700 Citations (Sik-Ho Tsang @ Medium) Natural Language Processing, NLP, Neural Machine Translation, NMT Back Translation of target language sentences, is an effective method to generate synthetic source sentences.

My Study on Graph & Normalized Laplacian Matrix — When I read Self-supervised Semi-supervised Learning for Data Labeling and Quality Evaluation (2021 NeurIPSW), I come across some equations related to graph. To know more about it, I tried two simple cases, one is graph with all edge strengths=1, one is graph with different edge strengths. Indeed, it is more…

BEiT-Pretrained ViT, Self-Supervised Learning by BYOL, Semi-Supervised Learning by Label Propagation (LP) — Self-supervised Semi-supervised Learning for Data Labeling and Quality Evaluation, BYOL+LP, by Apple 2021 NeurIPS DCAI Workshop (Sik-Ho Tsang @ Medium) Self-Supervised Learning, Semi-Supervised Learning, BEiT, BYOL, ViT This paper showcases that self-supervised learning helps reducing annotation cost and increasing annotation quality.

ICMLM, Pretraining Using Images & Captions for Image Classification — Learning Visual Representations with Caption Annotations ICMLM, by NAVER LABS Europe 2020 ECCV, Over 50 Citations (Sik-Ho Tsang @ Medium) Image Captioning, Image Classification, Weakly Supervised, Object Detection Image-Conditioned Masked Language Modeling (ICMLM) is proposed to learn visual representations over image-caption pairs, which is a kind of weakly supervised learning.

Pure MLP With Axial Shift, Comparable With Swin Transformer — AS-MLP: An Axial Shifted MLP Architecture for Vision AS-MLP, by ShanghaiTech University, Tencent, Shanghai Engineering Research Center of Intelligent Vision and Imaging & Shanghai Engineering Research Center of Energy Efficient and Custom AI IC 2022 ICLR, Over 40 Citations (Sik-Ho Tsang @ Medium) Image Classification, MLP Pure MLP architecture is…

Adversarial Training with Cross-Domain Similarity Local Scaling (CSLS) for NMT model — Word Translation Without Parallel Data CSLS, by Facebook AI Research, and Sorbonne Universités 2018 ICLR, Over 1300 Citations (Sik-Ho Tsang @ Medium) Natural Language Processing, NLP, Neural Machine Translation, NMT A bilingual dictionary is built between two languages without using any parallel corpora, by aligning monolingual word embedding spaces in…