Related papers: Extending and Analyzing Self-Supervised Learning Across Domains

Extending and Analyzing Self-Supervised Learning Across Domains

URL: http://arxiv.org/abs/2004.11992v2
Date: Mon, 17 Aug 2020 16:13:46 GMT
Title: Extending and Analyzing Self-Supervised Learning Across Domains
Authors: Bram Wallace, Bharath Hariharan
Abstract summary: Self-supervised representation learning has achieved impressive results in recent years. Experiments primarily come on ImageNet or other similarly large internet imagery datasets. We experiment with several popular methods on an unprecedented variety of domains.
Score: 50.13326427158233
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Self-supervised representation learning has achieved impressive results in recent years, with experiments primarily coming on ImageNet or other similarly large internet imagery datasets. There has been little to no work with these methods on other smaller domains, such as satellite, textural, or biological imagery. We experiment with several popular methods on an unprecedented variety of domains. We discover, among other findings, that Rotation is by far the most semantically meaningful task, with much of the performance of Jigsaw and Instance Discrimination being attributable to the nature of their induced distribution rather than semantic understanding. Additionally, there are several areas, such as fine-grain classification, where all tasks underperform. We quantitatively and qualitatively diagnose the reasons for these failures and successes via novel experiments studying pretext generalization, random labelings, and implicit dimensionality. Code and models are available at https://github.com/BramSW/Extending_SSRL_Across_Domains/.

Related papers

Multi-Domain Long-Tailed Learning by Augmenting Disentangled Representations [80.76164484820818]
There is an inescapable long-tailed class-imbalance issue in many real-world classification problems. We study this multi-domain long-tailed learning problem and aim to produce a model that generalizes well across all classes and domains. Built upon a proposed selective balanced sampling strategy, TALLY achieves this by mixing the semantic representation of one example with the domain-associated nuisances of another.
arXiv Detail & Related papers (2022-10-25T21:54:26Z)
Fuse and Attend: Generalized Embedding Learning for Art and Sketches [6.375982344506753]
We propose a novel Embedding Learning approach with the goal of generalizing across different domains. We show the prowess of our method using the Domain framework, on the popular PACS (Photo, Art painting, Cartoon, and Sketch) dataset.
arXiv Detail & Related papers (2022-08-20T14:44:11Z)
Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations [78.12377360145078]
Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. In this paper, we first study how biases in the dataset affect existing methods. We show that current contrastive approaches work surprisingly well across: (i) object- versus scene-centric, (ii) uniform versus long-tailed and (iii) general versus domain-specific datasets.
arXiv Detail & Related papers (2021-06-10T17:59:13Z)
Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization [112.68171734288237]
We propose a novel framework for discriminative pixel-level tasks using a generative model of both images and labels. We learn a generative adversarial network that captures the joint image-label distribution and is trained efficiently using a large set of unlabeled images. We demonstrate strong in-domain performance compared to several baselines, and are the first to showcase extreme out-of-domain generalization.
arXiv Detail & Related papers (2021-04-12T21:41:25Z)
Streaming Self-Training via Domain-Agnostic Unlabeled Images [62.57647373581592]
We present streaming self-training (SST) that aims to democratize the process of learning visual recognition models. Key to SST are two crucial observations: (1) domain-agnostic unlabeled images enable us to learn better models with a few labeled examples without any additional knowledge or supervision; and (2) learning is a continuous process and can be done by constructing a schedule of learning updates.
arXiv Detail & Related papers (2021-04-07T17:58:39Z)
Domain Adapting Ability of Self-Supervised Learning for Face Recognition [0.0]
Deep convolutional networks have achieved great performance in face recognition tasks. The challenge of domain discrepancy still exists in real world applications. In this paper, self-supervised learning is adopted to learn a better embedding space.
arXiv Detail & Related papers (2021-02-26T06:23:14Z)
A Review of Single-Source Deep Unsupervised Visual Domain Adaptation [81.07994783143533]
Large-scale labeled training datasets have enabled deep neural networks to excel across a wide range of benchmark vision tasks. In many applications, it is prohibitively expensive and time-consuming to obtain large quantities of labeled data. To cope with limited labeled training data, many have attempted to directly apply models trained on a large-scale labeled source domain to another sparsely labeled or unlabeled target domain.
arXiv Detail & Related papers (2020-09-01T00:06:50Z)
Learning Cross-domain Generalizable Features by Representation Disentanglement [11.74643883335152]
Deep learning models exhibit limited generalizability across different domains. We propose Mutual-Information-based Disentangled Neural Networks (MIDNet) to extract generalizable features that enable transferring knowledge to unseen categorical features in target domains. We demonstrate our method on handwritten digits datasets and a fetal ultrasound dataset for image classification tasks.
arXiv Detail & Related papers (2020-02-29T17:53:16Z)

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