Adaptive Hierarchical Graph Cut for Multi-granularity Out-of-distribution Detection
- URL: http://arxiv.org/abs/2412.15668v1
- Date: Fri, 20 Dec 2024 08:32:02 GMT
- Title: Adaptive Hierarchical Graph Cut for Multi-granularity Out-of-distribution Detection
- Authors: Xiang Fang, Arvind Easwaran, Blaise Genest, Ponnuthurai Nagaratnam Suganthan,
- Abstract summary: This paper focuses on a significant yet challenging task: out-of-distribution detection (OOD detection)
Previous works have made decent success, but they are ineffective for real-world challenging applications.
We propose a novel Adaptive Hierarchical Graph Cut network (AHGC) to explore the semantic relationship between different images.
- Score: 10.200872243175183
- License:
- Abstract: This paper focuses on a significant yet challenging task: out-of-distribution detection (OOD detection), which aims to distinguish and reject test samples with semantic shifts, so as to prevent models trained on in-distribution (ID) data from producing unreliable predictions. Although previous works have made decent success, they are ineffective for real-world challenging applications since these methods simply regard all unlabeled data as OOD data and ignore the case that different datasets have different label granularity. For example, "cat" on CIFAR-10 and "tabby cat" on Tiny-ImageNet share the same semantics but have different labels due to various label granularity. To this end, in this paper, we propose a novel Adaptive Hierarchical Graph Cut network (AHGC) to deeply explore the semantic relationship between different images. Specifically, we construct a hierarchical KNN graph to evaluate the similarities between different images based on the cosine similarity. Based on the linkage and density information of the graph, we cut the graph into multiple subgraphs to integrate these semantics-similar samples. If the labeled percentage in a subgraph is larger than a threshold, we will assign the label with the highest percentage to unlabeled images. To further improve the model generalization, we augment each image into two augmentation versions, and maximize the similarity between the two versions. Finally, we leverage the similarity score for OOD detection. Extensive experiments on two challenging benchmarks (CIFAR- 10 and CIFAR-100) illustrate that in representative cases, AHGC outperforms state-of-the-art OOD detection methods by 81.24% on CIFAR-100 and by 40.47% on CIFAR-10 in terms of "FPR95", which shows the effectiveness of our AHGC.
Related papers
- Adaptive Anchor Label Propagation for Transductive Few-Shot Learning [18.29463308334406]
Few-shot learning addresses the issue of classifying images using limited labeled data.
We propose a novel algorithm that adapts the feature embeddings of the labeled data by minimizing a differentiable loss function.
Our algorithm outperforms the standard label propagation algorithm by as much as 7% and 2% in the 1-shot and 5-shot settings respectively.
arXiv Detail & Related papers (2023-10-30T20:29:31Z) - Fine-grained Recognition with Learnable Semantic Data Augmentation [68.48892326854494]
Fine-grained image recognition is a longstanding computer vision challenge.
We propose diversifying the training data at the feature-level to alleviate the discriminative region loss problem.
Our method significantly improves the generalization performance on several popular classification networks.
arXiv Detail & Related papers (2023-09-01T11:15:50Z) - Learning Hierarchical Graph Representation for Image Manipulation
Detection [50.04902159383709]
The objective of image manipulation detection is to identify and locate the manipulated regions in the images.
Recent approaches mostly adopt the sophisticated Convolutional Neural Networks (CNNs) to capture the tampering artifacts left in the images.
We propose a hierarchical Graph Convolutional Network (HGCN-Net), which consists of two parallel branches.
arXiv Detail & Related papers (2022-01-15T01:54:25Z) - Weakly-supervised Generative Adversarial Networks for medical image
classification [1.479639149658596]
We propose a novel medical image classification algorithm called Weakly-Supervised Generative Adversarial Networks (WSGAN)
WSGAN only uses a small number of real images without labels to generate fake images or mask images to enlarge the sample size of the training set.
We show that WSGAN can obtain relatively high learning performance by using few labeled and unlabeled data.
arXiv Detail & Related papers (2021-11-29T15:38:48Z) - SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised
Classification [24.386165255835063]
A common classification task situation is where one has a large amount of data available for training, but only a small portion is with class labels.
The goal of semi-supervised training, in this context, is to improve classification accuracy by leverage information from a large amount of unlabeled data.
We propose a novel unsupervised objective that focuses on the less studied relationship between the high confidence unlabeled data that are similar to each other.
Our proposed SimPLE algorithm shows significant performance gains over previous algorithms on CIFAR-100 and Mini-ImageNet, and is on par with the state-of-the-art methods
arXiv Detail & Related papers (2021-03-30T23:48:06Z) - Attention-Driven Dynamic Graph Convolutional Network for Multi-Label
Image Recognition [53.17837649440601]
We propose an Attention-Driven Dynamic Graph Convolutional Network (ADD-GCN) to dynamically generate a specific graph for each image.
Experiments on public multi-label benchmarks demonstrate the effectiveness of our method.
arXiv Detail & Related papers (2020-12-05T10:10:12Z) - G-SimCLR : Self-Supervised Contrastive Learning with Guided Projection
via Pseudo Labelling [0.8164433158925593]
In computer vision, it is evident that deep neural networks perform better in a supervised setting with a large amount of labeled data.
In this work, we propose that, with the normalized temperature-scaled cross-entropy (NT-Xent) loss function, it is beneficial to not have images of the same category in the same batch.
We use the latent space representation of a denoising autoencoder trained on the unlabeled dataset and cluster them with k-means to obtain pseudo labels.
arXiv Detail & Related papers (2020-09-25T02:25:37Z) - Instance-Aware Graph Convolutional Network for Multi-Label
Classification [55.131166957803345]
Graph convolutional neural network (GCN) has effectively boosted the multi-label image recognition task.
We propose an instance-aware graph convolutional neural network (IA-GCN) framework for multi-label classification.
arXiv Detail & Related papers (2020-08-19T12:49:28Z) - Sequential Graph Convolutional Network for Active Learning [53.99104862192055]
We propose a novel pool-based Active Learning framework constructed on a sequential Graph Convolution Network (GCN)
With a small number of randomly sampled images as seed labelled examples, we learn the parameters of the graph to distinguish labelled vs unlabelled nodes.
We exploit these characteristics of GCN to select the unlabelled examples which are sufficiently different from labelled ones.
arXiv Detail & Related papers (2020-06-18T00:55:10Z) - High-Order Information Matters: Learning Relation and Topology for
Occluded Person Re-Identification [84.43394420267794]
We propose a novel framework by learning high-order relation and topology information for discriminative features and robust alignment.
Our framework significantly outperforms state-of-the-art by6.5%mAP scores on Occluded-Duke dataset.
arXiv Detail & Related papers (2020-03-18T12:18:35Z)
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.