中文
相关论文

相关论文: Don't freeze: Finetune encoders for better Self-Su…

200 篇论文

To improve performance in visual feature representation from photos or videos for practical applications, we generally require large-scale human-annotated labeled data while training deep neural networks. However, the cost of gathering and…

计算机视觉与模式识别 · 计算机科学 2022-10-10 Zhenyuan Lu

Self-supervised representation learning solves auxiliary prediction tasks (known as pretext tasks) without requiring labeled data to learn useful semantic representations. These pretext tasks are created solely using the input features,…

机器学习 · 计算机科学 2021-11-16 Jason D. Lee , Qi Lei , Nikunj Saunshi , Jiacheng Zhuo

We study how to transfer representations pretrained on source tasks to target tasks in visual percept based RL. We analyze two popular approaches: freezing or finetuning the pretrained representations. Empirical studies on a set of popular…

机器学习 · 计算机科学 2023-02-14 Sébastien M. R. Arnold , Fei Sha

Self-supervised learning, which benefits from automatically constructing labels through pre-designed pretext task, has recently been applied for strengthen supervised learning. Since previous self-supervised pretext tasks are based on…

计算机视觉与模式识别 · 计算机科学 2021-06-10 Zilin Ding , Yuhang Yang , Xuan Cheng , Xiaomin Wang , Ming Liu

Labeling a large set of data is expensive. Active learning aims to tackle this problem by asking to annotate only the most informative data from the unlabeled set. We propose a novel active learning approach that utilizes self-supervised…

计算机视觉与模式识别 · 计算机科学 2022-07-27 John Seon Keun Yi , Minseok Seo , Jongchan Park , Dong-Geol Choi

Self-supervised learning is popular method because of its ability to learn features in images without using its labels and is able to overcome limited labeled datasets used in supervised learning. Self-supervised learning works by using a…

计算机视觉与模式识别 · 计算机科学 2023-07-28 Aristo Renaldo Ruslim , Novanto Yudistira , Budi Darma Setiawan

Deep learning perception models require a massive amount of labeled training data to achieve good performance. While unlabeled data is easy to acquire, the cost of labeling is prohibitive and could create a tremendous burden on companies or…

计算机视觉与模式识别 · 计算机科学 2021-11-19 Xinnan Du , William Zhang , Jose M. Alvarez

Pretext-based self-supervised learning learns the semantic representation via a handcrafted pretext task over unlabeled data and then uses the learned representation for downstream tasks, which effectively reduces the sample complexity of…

机器学习 · 计算机科学 2022-02-24 Jiaye Teng , Weiran Huang , Haowei He

Self-supervised learning has emerged as a powerful way to pre-train generalizable machine learning models on large amounts of unlabeled data. It is particularly compelling in the music domain, where obtaining labeled data is time-consuming,…

声音 · 计算机科学 2024-04-16 Gabriel Meseguer-Brocal , Dorian Desblancs , Romain Hennequin

Data labeling in supervised learning is considered an expensive and infeasible tool in some conditions. The self-supervised learning method is proposed to tackle the learning effectiveness with fewer labeled data, however, there is a lack…

机器学习 · 计算机科学 2021-08-18 Hilal AlQuabeh , Ameera Bawazeer , Abdulateef Alhashmi

Self-training is a simple semi-supervised learning approach: Unlabelled examples that attract high-confidence predictions are labelled with their predictions and added to the training set, with this process being repeated multiple times.…

计算机视觉与模式识别 · 计算机科学 2021-09-13 Attaullah Sahito , Eibe Frank , Bernhard Pfahringer

Self-supervised learning is an effective way for label-free model pre-training, especially in the video domain where labeling is expensive. Existing self-supervised works in the video domain use varying experimental setups to demonstrate…

计算机视觉与模式识别 · 计算机科学 2023-11-22 Akash Kumar , Ashlesha Kumar , Vibhav Vineet , Yogesh Singh Rawat

Self-supervised learning has gained popularity because of its ability to avoid the cost of annotating large-scale datasets. It is capable of adopting self-defined pseudo labels as supervision and use the learned representations for several…

计算机视觉与模式识别 · 计算机科学 2021-02-09 Ashish Jaiswal , Ashwin Ramesh Babu , Mohammad Zaki Zadeh , Debapriya Banerjee , Fillia Makedon

In self-supervised learning, one trains a model to solve a so-called pretext task on a dataset without the need for human annotation. The main objective, however, is to transfer this model to a target domain and task. Currently, the most…

计算机视觉与模式识别 · 计算机科学 2018-05-02 Mehdi Noroozi , Ananth Vinjimoor , Paolo Favaro , Hamed Pirsiavash

Traditional self-supervised learning requires CNNs using external pretext tasks (i.e., image- or video-based tasks) to encode high-level semantic visual representations. In this paper, we show that feature transformations within CNNs can…

计算机视觉与模式识别 · 计算机科学 2021-06-10 Yuhang Yang , Zilin Ding , Xuan Cheng , Xiaomin Wang , Ming Liu

Pre-trained speech Transformers have facilitated great success across various speech processing tasks. However, fine-tuning these encoders for downstream tasks require sufficiently large training data to converge or to achieve…

计算与语言 · 计算机科学 2022-10-25 Hao Yang , Jinming Zhao , Gholamreza Haffari , Ehsan Shareghi

Self-supervised tasks have been utilized to build useful representations that can be used in downstream tasks when the annotation is unavailable. In this paper, we introduce a self-supervised video representation learning method based on…

计算机视觉与模式识别 · 计算机科学 2021-02-23 Duc Quang Vu , Ngan T. H. Le , Jia-Ching Wang

We present a technique to improve the transferability of deep representations learned on small labeled datasets by introducing self-supervised tasks as auxiliary loss functions. While recent approaches for self-supervised learning have…

计算机视觉与模式识别 · 计算机科学 2019-06-18 Jong-Chyi Su , Subhransu Maji , Bharath Hariharan

Recent advances have spurred incredible progress in self-supervised pretraining for vision. We investigate what factors may play a role in the utility of these pretraining methods for practitioners. To do this, we evaluate various…

计算机视觉与模式识别 · 计算机科学 2020-04-01 Alejandro Newell , Jia Deng

Self-supervised pre-training of transformer models has revolutionized NLP applications. Such pre-training with language modeling objectives provides a useful initial point for parameters that generalize well to new tasks with fine-tuning.…

计算与语言 · 计算机科学 2020-11-17 Trapit Bansal , Rishikesh Jha , Tsendsuren Munkhdalai , Andrew McCallum
‹ 上一页 1 2 3 10 下一页 ›