Search Results for author:
Found 10 papers, 8 papers with code
Video Diffusion Alignment via Reward Gradients
We show that backpropagating gradients from these reward models to a video diffusion model can allow for compute and sample efficient alignment of the video diffusion model.
Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback
Our method, Diffusion-TTA, adapts pre-trained discriminative models such as image classifiers, segmenters and depth predictors, to each unlabelled example in the test set using generative feedback from a diffusion model.
Aligning Text-to-Image Diffusion Models with Reward Backpropagation
Due to their unsupervised training, controlling their behavior in downstream tasks, such as maximizing human-perceived image quality, image-text alignment, or ethical image generation, is difficult.
Your Diffusion Model is Secretly a Zero-Shot Classifier
Our generative approach to classification, which we call Diffusion Classifier, attains strong results on a variety of benchmarks and outperforms alternative methods of extracting knowledge from diffusion models.
Ranked #1 on
Image Classification
on ObjectNet (ImageNet classes)
Test-time Adaptation with Slot-Centric Models
In our work, we find evidence that these losses are insufficient for the task of scene decomposition, without also considering architectural inductive biases.
CoCoNets: Continuous Contrastive 3D Scene Representations
This paper explores self-supervised learning of amodal 3D feature representations from RGB and RGB-D posed images and videos, agnostic to object and scene semantic content, and evaluates the resulting scene representations in the downstream tasks of visual correspondence, object tracking, and object detection.
3D-OES: Viewpoint-Invariant Object-Factorized Environment Simulators
Object motion predictions are computed by a graph neural network that operates over the object features extracted from the 3D neural scene representation.
Disentangling 3D Prototypical Networks For Few-Shot Concept Learning
We present neural architectures that disentangle RGB-D images into objects' shapes and styles and a map of the background scene, and explore their applications for few-shot 3D object detection and few-shot concept classification.
3D Object Recognition By Corresponding and Quantizing Neural 3D Scene Representations
We can compare the 3D feature maps of two objects by searching alignment across scales and 3D rotations, and, as a result of the operation, we can estimate pose and scale changes without the need for 3D pose annotations.
Embodied Language Grounding with 3D Visual Feature Representations
We propose associating language utterances to 3D visual abstractions of the scene they describe.
