USB: A Unified Semi-supervised Learning Benchmark

• URL: http://arxiv.org/abs/2208.07204v1
• Date: Fri, 12 Aug 2022 15:45:48 GMT
• Title: USB: A Unified Semi-supervised Learning Benchmark
• Authors: Yidong Wang, Hao Chen, Yue Fan, Wang Sun, Ran Tao, Wenxin Hou, Renjie Wang, Linyi Yang, Zhi Zhou, Lan-Zhe Guo, Heli Qi, Zhen Wu, Yu-Feng Li, Satoshi Nakamura, Wei Ye, Marios Savvides, Bhiksha Raj, Takahiro Shinozaki, Bernt Schiele, Jindong Wang, Xing Xie, Yue Zhang
• Abstract summary: Semi-supervised learning (SSL) improves model generalization by leveraging massive unlabeled data to augment limited labeled samples. Previous work typically trains deep neural networks from scratch, which is time-consuming and environmentally unfriendly. We construct a Unified SSL Benchmark (USB) by selecting 15 diverse, challenging, and comprehensive tasks.
• Score: 125.25384569880525
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Semi-supervised learning (SSL) improves model generalization by leveraging massive unlabeled data to augment limited labeled samples. However, currently, popular SSL evaluation protocols are often constrained to computer vision (CV) tasks. In addition, previous work typically trains deep neural networks from scratch, which is time-consuming and environmentally unfriendly. To address the above issues, we construct a Unified SSL Benchmark (USB) by selecting 15 diverse, challenging, and comprehensive tasks from CV, natural language processing (NLP), and audio processing (Audio), on which we systematically evaluate dominant SSL methods, and also open-source a modular and extensible codebase for fair evaluation on these SSL methods. We further provide pre-trained versions of the state-of-the-art neural models for CV tasks to make the cost affordable for further tuning. USB enables the evaluation of a single SSL algorithm on more tasks from multiple domains but with less cost. Specifically, on a single NVIDIA V100, only 37 GPU days are required to evaluate FixMatch on 15 tasks in USB while 335 GPU days (279 GPU days on 4 CV datasets except for ImageNet) are needed on 5 CV tasks with the typical protocol.

Related papers

• Exploring Green AI for Audio Deepfake Detection [21.17957700009653]
  State-of-the-art audio deepfake detectors leveraging deep neural networks exhibit impressive recognition performance. Deep NLP models produce around 626k lbs of COtextsubscript2 which is equivalent to five times of average US car emission at its lifetime. This study presents a novel framework for audio deepfake detection that can be seamlessly trained using standard CPU resources.
  arXiv  Detail & Related papers  (2024-03-21T10:54:21Z)
• Visual Self-supervised Learning Scheme for Dense Prediction Tasks on X-ray Images [3.782392436834913]
  Self-supervised learning (SSL) has led to considerable progress in natural language processing (NLP) However, the incorporation of contrastive learning into existing visual SSL models has led to considerable progress, often surpassing supervised counterparts. Here, we focus on dense prediction tasks using security inspection x-ray images to evaluate our proposed model, Segment localization (SegLoc) Based upon the Instance localization (InsLoc) model, SegLoc addresses one of the key challenges of contrastive learning, i.e., false negative pairs of query embeddings.
  arXiv  Detail & Related papers  (2023-10-12T15:42:17Z)
• Joint Prediction and Denoising for Large-scale Multilingual Self-supervised Learning [69.77973092264338]
  We show that more powerful techniques can lead to more efficient pre-training, opening SSL to more research groups. We propose WavLabLM, which extends WavLM's joint prediction and denoising to 40k hours of data across 136 languages. We show that further efficiency can be achieved with a vanilla HuBERT Base model, which can maintain 94% of XLS-R's performance with only 3% of the data.
  arXiv  Detail & Related papers  (2023-09-26T23:55:57Z)
• Match to Win: Analysing Sequences Lengths for Efficient Self-supervised Learning in Speech and Audio [19.865050806327147]
  Self-supervised learning has proven vital in speech and audio-related applications. This paper provides the first empirical study of SSL pre-training for different specified sequence lengths. We find that training on short sequences can dramatically reduce resource costs while retaining a satisfactory performance for all tasks.
  arXiv  Detail & Related papers  (2022-09-30T16:35:42Z)
• Learning Rate Curriculum [75.98230528486401]
  We propose a novel curriculum learning approach termed Learning Rate Curriculum (LeRaC) LeRaC uses a different learning rate for each layer of a neural network to create a data-agnostic curriculum during the initial training epochs. We compare our approach with Curriculum by Smoothing (CBS), a state-of-the-art data-agnostic curriculum learning approach.
  arXiv  Detail & Related papers  (2022-05-18T18:57:36Z)
• DATA: Domain-Aware and Task-Aware Pre-training [94.62676913928831]
  We present DATA, a simple yet effective NAS approach specialized for self-supervised learning (SSL) Our method achieves promising results across a wide range of computation costs on downstream tasks, including image classification, object detection and semantic segmentation.
  arXiv  Detail & Related papers  (2022-03-17T02:38:49Z)
• Sound and Visual Representation Learning with Multiple Pretraining Tasks [104.11800812671953]
  Self-supervised tasks (SSL) reveal different features from the data. This work aims to combine Multiple SSL tasks (Multi-SSL) that generalizes well for all downstream tasks. Experiments on sound representations demonstrate that Multi-SSL via incremental learning (IL) of SSL tasks outperforms single SSL task models.
  arXiv  Detail & Related papers  (2022-01-04T09:09:38Z)
• Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Cloud [79.99653758293277]
  We present the first generative approach for both Zero-Shot Learning (ZSL) and Generalized ZSL (GZSL) on 3D data. We show that it reaches or outperforms the state of the art on ModelNet40 classification for both inductive ZSL and inductive GZSL. Our experiments show that our method outperforms strong baselines, which we additionally propose for this task.
  arXiv  Detail & Related papers  (2021-08-13T13:29:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.