paper-with-me

홈 › Papers

Distance Based Image Classification: A solution to generative classification's conundrum?

2022-10-04 · Wen-Yan Lin, Siying Liu, Bing Tian Dai, Hongdong Li

Most classifiers rely on discriminative boundaries that separate instances of each class from everything else. We argue that discriminative boundaries are counter-intuitive as they define semantics by what-they-are-not; and should be replaced by generative classifiers which define semantics by what-they-are. Unfortunately, generative classifiers are significantly less accurate. This may be caused by the tendency of generative models to focus on easy to model semantic generative factors and ignore non-semantic factors that are important but difficult to model. We propose a new generative model in which semantic factors are accommodated by shell theory's hierarchical generative process and non-semantic factors by an instance specific noise term. We use the model to develop a classification scheme which suppresses the impact of noise while preserving semantic cues. The result is a surprisingly accurate generative classifier, that takes the form of a modified nearest-neighbor algorithm; we term it distance classification. Unlike discriminative classifiers, a distance classifier: defines semantics by what-they-are; is amenable to incremental updates; and scales well with the number of classes.

📄 PDF Abstract BibTeX arXiv:2210.01349

Code (1)

wen-yan-lin/Image-Distance-Classification 공식 구현 tf

Tasks

image-classificationImage Classification

Similar Papers 제목 키워드 기반

Distance Guided Generative Adversarial Network for Explainable Binary Classifications

2023-12-29 · Xiangyu Xiong, Yue Sun, Xiaohong Liu, Wei Ke 외

Despite the potential benefits of data augmentation for mitigating the data insufficiency, traditional augmentation methods primarily rely on the prior intra-domain knowledge. On the other hand, advanced generative adver…

Binary ClassificationClassificationData AugmentationGenerative Adversarial Network+1

Rethinking Generative Image Pretraining: How Far Are We From Scaling Up Next-Pixel Prediction?

2025-11-11 · Xinchen Yan, Chen Liang, Lijun Yu, Adams Wei Yu 외 arxiv

This paper investigates the scaling properties of autoregressive next-pixel prediction, a simple, end-to-end yet under-explored framework for unified vision models. Starting with images at resolutions of 32x32, we train …

Image ClassificationImage Generation

Traditional Classification Neural Networks are Good Generators: They are Competitive with DDPMs and GANs

2022-11-27 · Guangrun Wang, Philip H. S. Torr

Classifiers and generators have long been separated. We break down this separation and showcase that conventional neural network classifiers can generate high-quality images of a large number of categories, being compara…

Image GenerationText to Image GenerationText-to-Image Generation

A sliced-Wasserstein distance-based approach for out-of-class-distribution detection

2023-02-02 · Mohammad Shifat E Rabbi, Abu Hasnat Mohammad Rubaiyat, Yan Zhuang, Gustavo K Rohde

There exist growing interests in intelligent systems for numerous medical imaging, image processing, and computer vision applications, such as face recognition, medical diagnosis, character recognition, and self-driving …

ClassificationFace RecognitionFeature EngineeringMedical Diagnosis+1

A Pragmatic Note on Evaluating Generative Models with Fréchet Inception Distance for Retinal Image Synthesis

2025-02-24 · Yuli Wu, Fucheng Liu, Rüveyda Yilmaz, Henning Konermann 외

Fr\'echet Inception Distance (FID), computed with an ImageNet pretrained Inception-v3 network, is widely used as a state-of-the-art evaluation metric for generative models. It assumes that feature vectors from Inception-…

Image Generation