Multi-label Image Classification using Adaptive Graph Convolutional Networks: from a Single Domain to Multiple Domains
- URL: http://arxiv.org/abs/2301.04494v5
- Date: Mon, 22 Jul 2024 08:16:26 GMT
- Title: Multi-label Image Classification using Adaptive Graph Convolutional Networks: from a Single Domain to Multiple Domains
- Authors: Indel Pal Singh, Enjie Ghorbel, Oyebade Oyedotun, Djamila Aouada,
- Abstract summary: This paper proposes an adaptive graph-based approach for multi-label image classification.
It is done by integrating an attention-based mechanism and a similarity-preserving strategy.
The proposed framework is then extended to multiple domains using an adversarial training scheme.
- Score: 8.02139126500224
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: This paper proposes an adaptive graph-based approach for multi-label image classification. Graph-based methods have been largely exploited in the field of multi-label classification, given their ability to model label correlations. Specifically, their effectiveness has been proven not only when considering a single domain but also when taking into account multiple domains. However, the topology of the used graph is not optimal as it is pre-defined heuristically. In addition, consecutive Graph Convolutional Network (GCN) aggregations tend to destroy the feature similarity. To overcome these issues, an architecture for learning the graph connectivity in an end-to-end fashion is introduced. This is done by integrating an attention-based mechanism and a similarity-preserving strategy. The proposed framework is then extended to multiple domains using an adversarial training scheme. Numerous experiments are reported on well-known single-domain and multi-domain benchmarks. The results demonstrate that our approach achieves competitive results in terms of mean Average Precision (mAP) and model size as compared to the state-of-the-art. The code will be made publicly available.
Related papers
- CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive
Graph Classification [32.479834854094214]
We propose Coupled Contrastive Graph Representation Learning (CoCo), which extracts the topological information from coupled learning branches.
CoCo outperforms competing baselines in different settings generally.
arXiv Detail & Related papers (2023-06-08T07:10:35Z) - 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) - Similarity-aware Positive Instance Sampling for Graph Contrastive
Pre-training [82.68805025636165]
We propose to select positive graph instances directly from existing graphs in the training set.
Our selection is based on certain domain-specific pair-wise similarity measurements.
Besides, we develop an adaptive node-level pre-training method to dynamically mask nodes to distribute them evenly in the graph.
arXiv Detail & Related papers (2022-06-23T20:12:51Z) - SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object
Detection [26.0630601028093]
Domain Adaptive Object Detection (DAOD) leverages a labeled domain to learn an object detector generalizing to a novel domain free of annotations.
Recent advances align class-conditional distributions by narrowing down cross-domain prototypes (class centers)
We propose a novel SemantIc-complete Graph MAtching framework for hallucinationD, which completes mismatched semantics and reformulates the adaptation with graph matching.
arXiv Detail & Related papers (2022-03-12T10:14:17Z) - Graph Attention Transformer Network for Multi-Label Image Classification [50.0297353509294]
We propose a general framework for multi-label image classification that can effectively mine complex inter-label relationships.
Our proposed methods can achieve state-of-the-art performance on three datasets.
arXiv Detail & Related papers (2022-03-08T12:39:05Z) - Graph-Relational Domain Adaptation [21.47087742618527]
Existing domain adaptation methods treat every domain equally and align them all perfectly.
In this work, we relax such uniform alignment by using a domain graph to encode domain adjacency.
We generalize the existing adversarial learning framework with a novel graph discriminator.
arXiv Detail & Related papers (2022-02-08T03:53:32Z) - Efficient Hierarchical Domain Adaptation for Pretrained Language Models [77.02962815423658]
Generative language models are trained on diverse, general domain corpora.
We introduce a method to scale domain adaptation to many diverse domains using a computationally efficient adapter approach.
arXiv Detail & Related papers (2021-12-16T11:09:29Z) - Source Free Unsupervised Graph Domain Adaptation [60.901775859601685]
Unsupervised Graph Domain Adaptation (UGDA) shows its practical value of reducing the labeling cost for node classification.
Most existing UGDA methods heavily rely on the labeled graph in the source domain.
In some real-world scenarios, the source graph is inaccessible because of privacy issues.
We propose a novel scenario named Source Free Unsupervised Graph Domain Adaptation (SFUGDA)
arXiv Detail & Related papers (2021-12-02T03:18:18Z) - Efficient Variational Graph Autoencoders for Unsupervised Cross-domain
Prerequisite Chains [3.358838755118655]
We introduce Domain-versaational Variational Graph Autoencoders (DAVGAE) to solve this cross-domain prerequisite chain learning task efficiently.
Our novel model consists of a variational graph autoencoder (VGAE) and a domain discriminator.
Results show that our model outperforms recent graph-based computation using only 1/10 graph scale and 1/3 time.
arXiv Detail & Related papers (2021-09-17T19:07:27Z) - Semantic Distribution-aware Contrastive Adaptation for Semantic
Segmentation [50.621269117524925]
Domain adaptive semantic segmentation refers to making predictions on a certain target domain with only annotations of a specific source domain.
We present a semantic distribution-aware contrastive adaptation algorithm that enables pixel-wise representation alignment.
We evaluate SDCA on multiple benchmarks, achieving considerable improvements over existing algorithms.
arXiv Detail & Related papers (2021-05-11T13:21:25Z)
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.