Search Results for author:
Found 19 papers, 5 papers with code
DreamWalk: Style Space Exploration using Diffusion Guidance
Text-conditioned diffusion models can generate impressive images, but fall short when it comes to fine-grained control.
MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection
Motivated by the success of SSMs, we present MambaMixer, a new architecture with data-dependent weights that uses a dual selection mechanism across tokens and channels, called Selective Token and Channel Mixer.
Stable Estimation of Survival Causal Effects
Our experiments on synthetic and semi-synthetic data demonstrate that our method has competitive bias and smaller variance than debiased machine learning approaches.
Test-Time Distribution Normalization for Contrastively Learned Vision-language Models
Advances in the field of vision-language contrastive learning have made it possible for many downstream applications to be carried out efficiently and accurately by simply taking the dot product between image and text representations.
Unsupervised Text Deidentification
We propose an unsupervised deidentification method that masks words that leak personally-identifying information.
Dimensions of Motion: Monocular Prediction through Flow Subspaces
We introduce a way to learn to estimate a scene representation from a single image by predicting a low-dimensional subspace of optical flow for each training example, which encompasses the variety of possible camera and object movement.
Pyramid Adversarial Training Improves ViT Performance
In this work, we present pyramid adversarial training (PyramidAT), a simple and effective technique to improve ViT's overall performance.
Ranked #9 on
Domain Generalization
on ImageNet-C
(using extra training data)
Deep survival analysis with longitudinal X-rays for COVID-19
Time-to-event analysis is an important statistical tool for allocating clinical resources such as ICU beds.
OCONet: Image Extrapolation by Object Completion
Existing methods struggle to extrapolate images with salient objects in the foreground or are limited to very specific objects such as humans, but tend to work well on indoor/outdoor scenes.
AutoFlow: Learning a Better Training Set for Optical Flow
Synthetic datasets play a critical role in pre-training CNN models for optical flow, but they are painstaking to generate and hard to adapt to new applications.
Object-centered image stitching
Image stitching is typically decomposed into three phases: registration, which aligns the source images with a common target image; seam finding, which determines for each target pixel the source image it should come from; and blending, which smooths transitions over the seams.
Robust image stitching with multiple registrations
Here, we observe that the use of a single registration often leads to errors, especially in scenes with significant depth variation or object motion.
Learning to Autofocus
Autofocus is an important task for digital cameras, yet current approaches often exhibit poor performance.
Channel selection using Gumbel Softmax
Important applications such as mobile computing require reducing the computational costs of neural network inference.
A discriminative view of MRF pre-processing algorithms
While Markov Random Fields (MRFs) are widely used in computer vision, they present a quite challenging inference problem.
Relaxation-Based Preprocessing Techniques for Markov Random Field Inference
Markov Random Fields (MRFs) are a widely used graphical model, but the inference problem is NP-hard.
Some medical applications of example-based super-resolution
Example-based super-resolution (EBSR) reconstructs a high-resolution image from a low-resolution image, given a training set of high-resolution images.
A Primal-Dual Algorithm for Higher-Order Multilabel Markov Random Fields
Graph cuts method such as a-expansion [4] and fusion moves [22] have been successful at solving many optimization problems in computer vision.
Structured learning of sum-of-submodular higher order energy functions
Rather than trying to formulate existing higher order priors as an SoS function, we take a discriminative learning approach, effectively searching the space of SoS functions for a higher order prior that performs well on our training set.
