相关论文: Intriguing properties of generative classifiers

Robust generalization to new concepts has long remained a distinctive feature of human intelligence. However, recent progress in deep generative models has now led to neural architectures capable of synthesizing novel instances of unknown…

The ultimate goal of generative models is to perfectly capture the data distribution. For image generation, common metrics of visual quality (e.g., FID) and the perceived truthfulness of generated images seem to suggest that we are nearing…

We demonstrate that a generative model for object shapes can achieve state of the art results on challenging scene text recognition tasks, and with orders of magnitude fewer training images than required for competing discriminative…

Discriminative approaches to classification often learn shortcuts that hold in-distribution but fail even under minor distribution shift. This failure mode stems from an overreliance on features that are spuriously correlated with the…

Humans rely on effective representations to learn from few examples and abstract useful information from sensory data. Inducing such representations in machine learning models has been shown to improve their performance on various…

The recent wave of large-scale text-to-image diffusion models has dramatically increased our text-based image generation abilities. These models can generate realistic images for a staggering variety of prompts and exhibit impressive…

Generative models have made immense progress in recent years, particularly in their ability to generate high quality images. However, that quality has been difficult to evaluate rigorously, with evaluation dominated by heuristic approaches…

A grand challenge in machine learning is the development of computational algorithms that match or outperform humans in perceptual inference tasks that are complicated by nuisance variation. For instance, visual object recognition involves…

The widespread adoption of generative AI models has raised growing concerns about representational harm and potential discriminatory outcomes. Yet, despite growing literature on this topic, the mechanisms by which bias emerges - especially…

Models that are learned from real-world data are often biased because the data used to train them is biased. This can propagate systemic human biases that exist and ultimately lead to inequitable treatment of people, especially minorities.…

The comparison between discriminative and generative classifiers has intrigued researchers since Efron's seminal analysis of logistic regression versus discriminant analysis. While early theoretical work established that generative…

Generative classifiers offer potential advantages over their discriminative counterparts, namely in the areas of data efficiency, robustness to data shift and adversarial examples, and zero-shot learning (Ng and Jordan,2002; Yogatama et…

This paper explores object detection in the small data regime, where only a limited number of annotated bounding boxes are available due to data rarity and annotation expense. This is a common challenge today with machine learning being…

We explore the question of whether the representations learned by classifiers can be used to enhance the quality of generative models. Our conjecture is that labels correspond to characteristics of natural data which are most salient to…

The excellent generative capabilities of text-to-image diffusion models suggest they learn informative representations of image-text data. However, what knowledge their representations capture is not fully understood, and they have not been…

Inspired by Geoffrey Hinton emphasis on generative modeling, To recognize shapes, first learn to generate them, we explore the use of 3D diffusion models for object classification. Leveraging the density estimates from these models, our…

Scientific expertise often requires recognizing subtle visual differences that remain challenging to articulate even for domain experts. We present a system that leverages generative models to automatically discover and visualize minimal…

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…

Human visual perception offers valuable insights for understanding computational principles of motion-based scene interpretation. Humans robustly detect and segment moving entities that constitute independently moveable chunks of matter,…

Semantic features have been playing a central role in investigating the nature of our conceptual representations. Yet the enormous time and effort required to empirically sample and norm features from human raters has restricted their use…