Domain Generalization

623 papers with code • 19 benchmarks • 25 datasets

The idea of Domain Generalization is to learn from one or multiple training domains, to extract a domain-agnostic model which can be applied to an unseen domain

Source: Diagram Image Retrieval using Sketch-Based Deep Learning and Transfer Learning

Generative Medical Segmentation

king-haw/gms 27 Mar 2024

Concretely, GMS employs a robust pre-trained Variational Autoencoder (VAE) to derive latent representations of both images and masks, followed by a mapping model that learns the transition from image to mask in the latent space.

3
27 Mar 2024

MatchSeg: Towards Better Segmentation via Reference Image Matching

keeplearning-again/matchseg 23 Mar 2024

Few-shot learning aims to overcome the need for annotated data by using a small labeled dataset, known as a support set, to guide predicting labels for new, unlabeled images, known as the query set.

7
23 Mar 2024

DomainLab: A modular Python package for domain generalization in deep learning

marrlab/domainlab 21 Mar 2024

DomainLab is a modular Python package for training user specified neural networks with composable regularization loss terms.

31
21 Mar 2024

M-HOF-Opt: Multi-Objective Hierarchical Output Feedback Optimization via Multiplier Induced Loss Landscape Scheduling

marrlab/domainlab 20 Mar 2024

When a neural network parameterized loss function consists of many terms, the combinatorial choice of weight multipliers during the optimization process forms a challenging problem.

31
20 Mar 2024

Negative Yields Positive: Unified Dual-Path Adapter for Vision-Language Models

zhangce01/dualadapter 19 Mar 2024

Recently, large-scale pre-trained Vision-Language Models (VLMs) have demonstrated great potential in learning open-world visual representations, and exhibit remarkable performance across a wide range of downstream tasks through efficient fine-tuning.

10
19 Mar 2024

Towards Generalizing to Unseen Domains with Few Labels

chumsy0725/fbc-sa 18 Mar 2024

Existing domain generalization (DG) methods which are unable to exploit unlabeled data perform poorly compared to semi-supervised learning (SSL) methods under SSDG setting.

4
18 Mar 2024

Neural Markov Random Field for Stereo Matching

aeolusguan/NMRF 17 Mar 2024

Stereo matching is a core task for many computer vision and robotics applications.

28
17 Mar 2024

A Dual-Augmentor Framework for Domain Generalization in 3D Human Pose Estimation

davidpengucf/daf-dg 17 Mar 2024

Furthermore, the pose estimator's optimization is not exposed to domain shifts, limiting its overall generalization ability.

3
17 Mar 2024

Single Domain Generalization for Crowd Counting

shimmer93/mpcount 14 Mar 2024

We propose MPCount, a novel SDG approach effective even for narrow source distribution.

4
14 Mar 2024

Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts

szc12153/sparse_meta_tuning 13 Mar 2024

Conventional wisdom suggests parameter-efficient fine-tuning of foundation models as the state-of-the-art method for transfer learning in vision, replacing the rich literature of alternatives such as meta-learning.

2
13 Mar 2024