Search Results for author:
Found 51 papers, 38 papers with code
ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization
Moreover, given the same computational resources, a ReNO-optimized one-step model outperforms widely-used open-source models such as SDXL and PixArt-$\alpha$, highlighting the efficiency and effectiveness of ReNO in enhancing T2I model performance at inference time.
Simple Open-Vocabulary Object Detection with Vision Transformers
Combining simple architectures with large-scale pre-training has led to massive improvements in image classification.
Ranked #1 on
One-Shot Object Detection
on MS COCO
Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations
In this work, we propose the Scene Representation Transformer (SRT), a method which processes posed or unposed RGB images of a new area, infers a "set-latent scene representation", and synthesises novel views, all in a single feed-forward pass.
Conditional Object-Centric Learning from Video
Object-centric representations are a promising path toward more systematic generalization by providing flexible abstractions upon which compositional world models can be built.
Do Vision Transformers See Like Convolutional Neural Networks?
Finally, we study the effect of (pretraining) dataset scale on intermediate features and transfer learning, and conclude with a discussion on connections to new architectures such as the MLP-Mixer.
MLP-Mixer: An all-MLP Architecture for Vision
Convolutional Neural Networks (CNNs) are the go-to model for computer vision.
Ranked #17 on
Image Classification
on OmniBenchmark
Differentiable Patch Selection for Image Recognition
Neural Networks require large amounts of memory and compute to process high resolution images, even when only a small part of the image is actually informative for the task at hand.
Learning Object-Centric Video Models by Contrasting Sets
We address this problem by introducing a global, set-based contrastive loss: instead of contrasting individual slot representations against one another, we aggregate the representations and contrast the joined sets against one another.
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited.
Ranked #1 on
Out-of-Distribution Generalization
on ImageNet-W
(Carton Gap metric)
NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections
We present a learning-based method for synthesizing novel views of complex scenes using only unstructured collections of in-the-wild photographs.
Object-Centric Learning with Slot Attention
Learning object-centric representations of complex scenes is a promising step towards enabling efficient abstract reasoning from low-level perceptual features.
You Only Train Once: Loss-Conditional Training of Deep Networks
At test time a model trained this way can be conditioned to generate outputs corresponding to any loss from the training distribution of losses.
Learning Depth With Very Sparse Supervision
Motivated by the astonishing capabilities of natural intelligent agents and inspired by theories from psychology, this paper explores the idea that perception gets coupled to 3D properties of the world via interaction with the environment.
A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark
And, how close are we to general visual representations?
Ranked #10 on
Image Classification
on VTAB-1k
(using extra training data)
Global-Local Network for Learning Depth with Very Sparse Supervision
Natural intelligent agents learn to perceive the three dimensional structure of the world without training on large datasets and are unlikely to have the precise equations of projective geometry hard-wired in the brain.
The Visual Task Adaptation Benchmark
Representation learning promises to unlock deep learning for the long tail of vision tasks without expansive labelled datasets.
Benchmarking Classic and Learned Navigation in Complex 3D Environments
However, this new line of work is largely disconnected from well-established classic navigation approaches.
Learning agile and dynamic motor skills for legged robots
In the present work, we introduce a method for training a neural network policy in simulation and transferring it to a state-of-the-art legged system, thereby leveraging fast, automated, and cost-effective data generation schemes.
Motion Perception in Reinforcement Learning with Dynamic Objects
In dynamic environments, learned controllers are supposed to take motion into account when selecting the action to be taken.
Unsupervised Learning of Shape and Pose with Differentiable Point Clouds
We address the problem of learning accurate 3D shape and camera pose from a collection of unlabeled category-specific images.
On Offline Evaluation of Vision-based Driving Models
We show that the correlation of offline evaluation with driving quality can be significantly improved by selecting an appropriate validation dataset and suitable offline metrics.
On Evaluation of Embodied Navigation Agents
Skillful mobile operation in three-dimensional environments is a primary topic of study in Artificial Intelligence.
TD or not TD: Analyzing the Role of Temporal Differencing in Deep Reinforcement Learning
Our understanding of reinforcement learning (RL) has been shaped by theoretical and empirical results that were obtained decades ago using tabular representations and linear function approximators.
Driving Policy Transfer via Modularity and Abstraction
Simulation can help end-to-end driving systems by providing a cheap, safe, and diverse training environment.
Semi-parametric Topological Memory for Navigation
We introduce a new memory architecture for navigation in previously unseen environments, inspired by landmark-based navigation in animals.
What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?
The finding that very large networks can be trained efficiently and reliably has led to a paradigm shift in computer vision from engineered solutions to learning formulations.
MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments
We present MINOS, a simulator designed to support the development of multisensory models for goal-directed navigation in complex indoor environments.
CARLA: An Open Urban Driving Simulator
We introduce CARLA, an open-source simulator for autonomous driving research.
End-to-end Driving via Conditional Imitation Learning
However, driving policies trained via imitation learning cannot be controlled at test time.
Artistic style transfer for videos and spherical images
We propose a deep network architecture and training procedures that allow us to stylize arbitrary-length videos in a consistent and stable way, and nearly in real time.
Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs
We present a deep convolutional decoder architecture that can generate volumetric 3D outputs in a compute- and memory-efficient manner by using an octree representation.
Ranked #3 on
3D Reconstruction
on Data3D−R2N2
DeMoN: Depth and Motion Network for Learning Monocular Stereo
In this paper we formulate structure from motion as a learning problem.
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Particularly on small displacements and real-world data, FlowNet cannot compete with variational methods.
Dense Pixel Correspondence Estimation
Optical Flow Estimation
+1
Protein contact prediction from amino acid co-evolution using convolutional networks for graph-valued images
A contact map is a compact representation of the three-dimensional structure of a protein via the pairwise contacts between the amino acid constituting the protein.
Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space
PPGNs are composed of 1) a generator network G that is capable of drawing a wide range of image types and 2) a replaceable "condition" network C that tells the generator what to draw.
Learning to Act by Predicting the Future
A model trained using the presented approach won the Full Deathmatch track of the Visual Doom AI Competition, which was held in previously unseen environments.
Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
Understanding the inner workings of such computational brains is both fascinating basic science that is interesting in its own right - similar to why we study the human brain - and will enable researchers to further improve DNNs.
Artistic style transfer for videos
We present an approach that transfers the style from one image (for example, a painting) to a whole video sequence.
Generating Images with Perceptual Similarity Metrics based on Deep Networks
This metric better reflects perceptually similarity of images and thus leads to better results.
A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation
By combining a flow and disparity estimation network and training it jointly, we demonstrate the first scene flow estimation with a convolutional network.
Multi-view 3D Models from Single Images with a Convolutional Network
We present a convolutional network capable of inferring a 3D representation of a previously unseen object given a single image of this object.
Inverting Visual Representations with Convolutional Networks
Inverting a deep network trained on ImageNet provides several insights into the properties of the feature representation learned by the network.
Learning to Generate Chairs With Convolutional Neural Networks
We train a generative convolutional neural network which is able to generate images of objects given object type, viewpoint, and color.
FlowNet: Learning Optical Flow with Convolutional Networks
Optical flow estimation has not been among the tasks where CNNs were successful.
Striving for Simplicity: The All Convolutional Net
Most modern convolutional neural networks (CNNs) used for object recognition are built using the same principles: Alternating convolution and max-pooling layers followed by a small number of fully connected layers.
Ranked #125 on
Image Classification
on CIFAR-10
Discriminative Unsupervised Feature Learning with Convolutional Neural Networks
Current methods for training convolutional neural networks depend on large amounts of labeled samples for supervised training.
Ranked #84 on
Image Classification
on STL-10
Learning to Generate Chairs, Tables and Cars with Convolutional Networks
We train generative 'up-convolutional' neural networks which are able to generate images of objects given object style, viewpoint, and color.
Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks
While such generic features cannot compete with class specific features from supervised training on a classification task, we show that they are advantageous on geometric matching problems, where they also outperform the SIFT descriptor.
Descriptor Matching with Convolutional Neural Networks: a Comparison to SIFT
Surprisingly, convolutional neural networks clearly outperform SIFT on descriptor matching.
Unsupervised feature learning by augmenting single images
We then extend these trivial one-element classes by applying a variety of transformations to the initial 'seed' patches.
An Iterated L1 Algorithm for Non-smooth Non-convex Optimization in Computer Vision
Here we extend the problem class to linearly constrained optimization of a Lipschitz continuous function, which is the sum of a convex function and a function being concave and increasing on the non-negative orthant (possibly non-convex and nonconcave on the whole space).
