Papers Read on AI

Few-shot learning, especially few-shot image classification, has received increasing attention and witnessed significant advances in recent years. Some recent studies implicitly show that many generic techniques or “tricks”, such as data augmentation, pre-training, knowledge distillation, and self-supervision, may greatly boost the performance of a few-shot learning method. Moreover, different works may employ different software platforms, different training schedules, different backbone architectures and even different input image sizes, making fair comparisons difficult and practitioners struggle with reproducibility. To address these situations, we propose a comprehensive library for few-shot learning (LibFewShot) by re-implementing seventeen state-of-the-art few-shot learning methods in a unified framework with the same single codebase in PyTorch. Furthermore, based on LibFewShot, we provide comprehensive evaluations on multiple benchmark datasets with multiple backbone architectures to evaluate common pitfalls and effects of different training tricks. In addition, given the recent doubts on the necessity of metaor episodic-training mechanism, our evaluation results show that such kind of mechanism is still necessary especially when combined with pre-training. We hope our work can not only lower the barriers for beginners to work on few-shot learning but also remove the effects of the nontrivial tricks to facilitate intrinsic research on few-shot learning. The source code is available from https://github.com/RL-VIG/LibFewShot.

2021: Wenbin Li, Chuanqi Dong, Pinzhuo Tian, Tiexin Qin, Xuesong Yang, Ziyi Wang, Jing Huo, Yinghuan Shi, Lei Wang, Yang Gao, Jiebo Luo

https://arxiv.org/pdf/2109.04898v1.pdf

Single-image super-resolution (SISR) is an important task in image processing, which aims to enhance the resolution of imaging systems. Recently, SISR has made a huge leap and has achieved promising results with the help of deep learning (DL). In this survey, we give an overview of DL-based SISR methods and group them according to their targets, such as reconstruction efficiency, reconstruction accuracy, and perceptual accuracy. Specifically, we first introduce the problem definition, research background, and the significance of SISR. Secondly, we introduce some related works, including benchmark datasets, upsampling methods, optimization objectives, and image quality assessment methods. Thirdly, we provide a detailed investigation of SISR and give some domain-specific applications of it. Fourthly, we present the reconstruction results of some classic SISR methods to intuitively know their performance. Finally, we discuss some issues that still exist in SISR and summarize some new trends and future directions. This is an exhaustive survey of SISR, which can help researchers better understand SISR and inspire more exciting research in this field. An investigation project for SISR is provided in https://github.com/CV-JunchengLi/SISR-Survey.

2021: Juncheng Li, Zehua Pei, Tieyong Zeng

https://arxiv.org/pdf/2109.14335v1.pdf

In this paper, we apply the self-attention from the state-of-art Transformer in Attention Is All You Need [69] the first time to a data-driven operator learning problem related to partial differential equations. We put together an effort to explain the heuristics of, and improve the efficacy of the self-attention by demonstrating that the softmax normalization in the scaled dot-product attention is sufficient but not necessary, and have proved the approximation capacity of a linear variant as a Petrov-Galerkin projection. A new layer normalization scheme is proposed to allow a scaling to propagate through attention layers, which helps the model achieve remarkable accuracy in operator learning tasks with unnormalized data. Finally, we present three operator learning experiments, including the viscid Burgers’ equation, an interface Darcy flow, and an inverse interface coefficient identification problem. All experiments validate the improvements of the newly proposed simple attention-based operator learner over their softmax-normalized counterparts.

2021: Shuhao Cao

https://arxiv.org/pdf/2105.14995v2.pdf

River is a machine learning library for dynamic data streams and continual learning. It provides multiple state-of-the-art learning methods, data generators/transformers, performance metrics and evaluators for different stream learning problems. It is the result from the merger of the two most popular packages for stream learning in Python: Creme and scikit-multiflow. River introduces a revamped architecture based on the lessons learnt from the seminal packages. River's ambition is to be the go-to library for doing machine learning on streaming data. Additionally, this open source package brings under the same umbrella a large community of practitioners and researchers. The source code is available at https://github.com/online-ml/river.

2020: Jacob Montiel, Max Halford, S. M. Mastelini, Geoffrey Bolmier, Raphael Sourty, Robin Vaysse, A. Zouitine, Heitor Murilo Gomes, Jesse Read, T. Abdessalem, A. Bifet

https://arxiv.org/pdf/2012.04740v1.pdf

In this paper, we show theoretical and empirical evidence that the potential capacity of self-supervised monocular depth estimation can be excavated without increasing this cost. In particular, we propose (1) a novel data augmentation approach called data grafting, which forces the model to explore more cues to infer depth besides the vertical image position, (2) an exploratory self-distillation loss, which is supervised by the self-distillation label generated by our new post-processing method selective post-processing, and (3) the full-scale network, designed to endow the encoder with the specialization of depth estimation task and enhance the representational power of the model. Extensive experiments show that our contributions can bring significant performance improvement to the baseline with even less computational overhead, and our model, named EPCDepth, surpasses the previous state-of-the-art methods even those supervised by additional constraints. Code is available at https://github.com/prstrive/EPCDepth.

2021: Rui Peng, Ronggang Wang, Yawen Lai, Luyang Tang, Yangang Cai

https://arxiv.org/pdf/2109.12484v1.pdf

Many datasets have been created for training reading comprehension models, and a natural question is whether we can combine them to build models that (1) perform better on all of the training datasets and (2) generalize and transfer better to new datasets. Our approach is to model multi-dataset question answering with a collection of single-dataset experts, by training a collection of lightweight, dataset-specific adapter modules (Houlsby et al., 2019) that share an underlying Transformer model. We find that these Multi-Adapter Dataset Experts (MADE) outperform all our baselines in terms of in-distribution accuracy, and simple methods based on parameter-averaging lead to better zero-shot generalization and few-shot transfer performance, offering a strong and versatile starting point for building new reading comprehension systems.

2021: Dan Friedman, Ben Dodge, Danqi Chen

https://arxiv.org/pdf/2109.13880v1.pdf

We propose using self-supervised discrete representations for the task of speech resynthesis. To generate disentangled representation, we separately extract low-bitrate representations for speech content, prosodic information, and speaker identity. This allows to synthesize speech in a controllable manner. We analyze various state-of-the-art, self-supervised representation learning methods and shed light on the advantages of each method while considering reconstruction quality and disentanglement properties.

2021: A. Polyak, Yossi Adi, Jade Copet, E. Kharitonov, Kushal Lakhotia, Wei-Ning Hsu, Abdelrahman Mohamed, Emmanuel Dupoux

https://arxiv.org/pdf/2104.00355v3.pdf

We introduce Merlion1, an open-source machine learning library for time series. It features a unified interface for many commonly used models and datasets for anomaly detection and forecasting on both univariate and multivariate time series, along with standard pre/postprocessing layers. It has several modules to improve ease-of-use, including visualization, anomaly score calibration to improve interpetability, AutoML for hyperparameter tuning and model selection, and model ensembling. Merlion also provides a unique evaluation framework that simulates the live deployment and re-training of a model in production. This library aims to provide engineers and researchers a one-stop solution to rapidly develop models for their specific time series needs and benchmark them across multiple time series datasets. In this technical report, we highlight Merlion’s architecture and major functionalities, and we report benchmark numbers across different baseline models and ensembles.

2021: Aadyot Bhatnagar, Paul Kassianik, Chenghao Liu, Tian Lan, Wenzhuo Yang, Rowan Cassius, Doyen Sahoo, Devansh Arpit, Sri Subramanian, Gerald Woo, Amrita Saha, A. Jagota, Gokulakrishnan Gopalakrishnan, Manpreet Singh, K. C. Krithika, Sukumar Maddineni, Daeki Cho, Bo Zong, Yingbo Zhou, Caiming Xiong, S. Savarese, S. Hoi, Huan Wang

https://arxiv.org/pdf/2109.09265v1.pdf

Classic: The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.

2017: Ashish Vaswani, Noam M. Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin

BLEU, Transformer, Machine translation, Encoder, Convolution, Transduction (machine learning), Recurrent neural network, Image, Network architecture, Input/output, TensorFlow, Network Abstraction Layer, Artificial neural network

https://arxiv.org/pdf/1706.03762.pdf

News recommendation is critical for personalized news access. Existing news recommendation methods usually infer users’ personal interest based on their historical clicked news, and train the news recommendation models by predicting future news clicks. A core assumption behind these methods is that news click behaviors can indicate user interest. However, in practical scenarios, beyond the relevance between user interest and news content, the news click behaviors may also be affected by other factors, such as the bias of news presentation in the online platform. For example, news with higher positions and larger sizes are usually more likely to be clicked. Experiments on two real-world datasets show that our method can effectively improve the performance of news recommendation.

2021: Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang

Ranked #1 on News Recommendation on MIND

https://arxiv.org/pdf/2108.09084v6.pdf