Related papers: Attribute Based Interpretable Evaluation Metrics f…
Existing attribute editing methods treat semantic attributes as binary, resulting in a single edit per attribute. However, attributes such as eyeglasses, smiles, or hairstyles exhibit a vast range of diversity. In this work, we formulate…
Autonomous driving requires an understanding of the static environment from sensor data. Learned Bird's-Eye View (BEV) encoders are commonly used to fuse multiple inputs, and a vector decoder predicts a vectorized map representation from…
Diffusion models, while trained for image generation, have emerged as powerful foundational feature extractors for downstream tasks. We find that off-the-shelf diffusion models, trained exclusively to generate natural RGB images, can…
Generative models have been applied in the medical imaging domain for various image recognition and synthesis tasks. However, a more controllable and interpretable image synthesis model is still lacking yet necessary for important…
Learning visual similarity requires to learn relations, typically between triplets of images. Albeit triplet approaches being powerful, their computational complexity mostly limits training to only a subset of all possible training…
Learning the distribution of images in order to generate new samples is a challenging task due to the high dimensionality of the data and the highly non-linear relations that are involved. Nevertheless, some promising results have been…
We performed a billion locality sensitive hash comparisons between artificially generated data samples to answer the critical question - can we reproduce the results of generative AI models? Reproducibility is one of the pillars of…
Text-to-image diffusion models achieve impressive generation quality but inherit and amplify training-data biases, skewing coverage of semantic attributes. Prior work addresses this in two ways. Closed-set approaches mitigate biases in…
Recent advancements in GANs and diffusion models have enabled the creation of high-resolution, hyper-realistic images. However, these models may misrepresent certain social groups and present bias. Understanding bias in these models remains…
3D object generation from a single image involves estimating the full 3D geometry and texture of unseen views from an unposed RGB image captured in the wild. Accurately reconstructing an object's complete 3D structure and texture has…
In this paper, we investigate when and how visual representations learned by two different generative models diverge. Given two text-to-image models, our goal is to discover visual attributes that appear in images generated by one model but…
With the success of image generation, generative diffusion models are increasingly adopted for discriminative tasks, as pixel generation provides a unified perception interface. However, directly repurposing the generative denoising process…
Text-to-image diffusion models have shown impressive capabilities in generating realistic visuals from natural-language prompts, yet they often struggle with accurately binding attributes to corresponding objects, especially in prompts…
Variable selection for high-dimensional, highly correlated data has long been a challenging problem, often yielding unstable and unreliable models. We propose a resample-aggregate framework that exploits diffusion models' ability to…
Diffusion models have recently become the dominant paradigm for image generation, yet existing systems struggle to interpret and follow numeric instructions for adjusting semantic attributes. In real-world creative scenarios, especially…
Evaluating text-to-image generative models remains a challenge, despite the remarkable progress being made in their overall performances. While existing metrics like CLIPScore work for coarse evaluations, they lack the sensitivity to…
Recent breakthroughs in diffusion models, multimodal pretraining, and efficient finetuning have led to an explosion of text-to-image generative models. Given human evaluation is expensive and difficult to scale, automated methods are…
In this paper, we propose an improved quantitative evaluation framework for Generative Adversarial Networks (GANs) on generating domain-specific images, where we improve conventional evaluation methods on two levels: the feature…
While many unsupervised learning models focus on one family of tasks, either generative or discriminative, we explore the possibility of a unified representation learner: a model which addresses both families of tasks simultaneously. We…
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…