Search Results for author:
Found 21 papers, 9 papers with code
Edit One for All: Interactive Batch Image Editing
With increased human control, it is now possible to edit an image in a plethora of ways; from specifying in text what we want to change, to straight up dragging the contents of the image in an interactive point-based manner.
Probing clustering in neural network representations
Neural network representations contain structure beyond what was present in the training labels.
Language-Conditioned Observation Models for Visual Object Search
In this work, we bridge the gap in realistic object search by posing the search problem as a partially observable Markov decision process (POMDP) where the object detector and visual sensor noise in the observation model is determined by a single Deep Neural Network conditioned on complex language descriptions.
Guiding Image Captioning Models Toward More Specific Captions
We further explore the use of language models to guide the decoding process, obtaining small improvements over the Pareto frontier of reference-free vs. reference-based captioning metrics that arises from classifier-free guidance, and substantially improving the quality of captions generated from a model trained only on minimally curated web data.
Visual Instruction Inversion: Image Editing via Visual Prompting
Given pairs of example that represent the "before" and "after" images of an edit, our goal is to learn a text-based editing direction that can be used to perform the same edit on new images.
DataComp: In search of the next generation of multimodal datasets
Multimodal datasets are a critical component in recent breakthroughs such as Stable Diffusion and GPT-4, yet their design does not receive the same research attention as model architectures or training algorithms.
From Plate to Prevention: A Dietary Nutrient-aided Platform for Health Promotion in Singapore
In this paper, we share our experience in addressing this issue and attaining medical-grade nutrient intake information to benefit Singaporeans in different aspects.
Quality Not Quantity: On the Interaction between Dataset Design and Robustness of CLIP
Web-crawled datasets have enabled remarkable generalization capabilities in recent image-text models such as CLIP (Contrastive Language-Image pre-training) or Flamingo, but little is known about the dataset creation processes.
Detecting COVID-19 from digitized ECG printouts using 1D convolutional neural networks
Experiments on the COVID-19 ECG images dataset demonstrate that the proposed digitization method is able to capture correctly the original signals, with a mean absolute error of 28. 11 ms. Our proposed 1D-CNN model, which is trained on the digitized ECG signals, allows identifying individuals with COVID-19 and other subjects accurately, with classification accuracies of 98. 42%, 95. 63%, and 98. 50% for classifying COVID-19 vs. Normal, COVID-19 vs. Abnormal Heartbeats, and COVID-19 vs. other classes, respectively.
A novel deep learning-based approach for sleep apnea detection using single-lead ECG signals
In this study, a novel method of feature extraction based on the detection of S peaks is proposed to enhance the detection of adjacent SA segments using a single-lead ECG.
On the Origins of the Block Structure Phenomenon in Neural Network Representations
Recent work has uncovered a striking phenomenon in large-capacity neural networks: they contain blocks of contiguous hidden layers with highly similar representations.
Dominant Datapoints and the Block Structure Phenomenon in Neural Network Hidden Representations
Recent work has uncovered a striking phenomenon in large-capacity neural networks: they contain blocks of contiguous hidden layers with highly similar representations.
Lipstick ain't enough: Beyond Color Matching for In-the-Wild Makeup Transfer
However, existing works overlooked the latter components and confined makeup transfer to color manipulation, focusing only on light makeup styles.
Ranked #1 on
Facial Makeup Transfer
on CPM-Synt-2
FineNet: Frame Interpolation and Enhancement for Face Video Deblurring
The objective of this work is to deblur face videos.
Robust and Private Learning of Halfspaces
In this work, we study the trade-off between differential privacy and adversarial robustness under L2-perturbations in the context of learning halfspaces.
Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth
We begin by investigating how varying depth and width affects model hidden representations, finding a characteristic block structure in the hidden representations of larger capacity (wider or deeper) models.
Concept Bottleneck Models
We seek to learn models that we can interact with using high-level concepts: if the model did not think there was a bone spur in the x-ray, would it still predict severe arthritis?
Robot Object Retrieval with Contextual Natural Language Queries
The model takes in a language command containing a verb, for example "Hand me something to cut," and RGB images of candidate objects and selects the object that best satisfies the task specified by the verb.
Grounding Language Attributes to Objects using Bayesian Eigenobjects
Our system is able to disambiguate between novel objects, observed via depth images, based on natural language descriptions.
Planning with State Abstractions for Non-Markovian Task Specifications
Often times, we specify tasks for a robot using temporal language that can also span different levels of abstraction.
Predicting Inpatient Discharge Prioritization With Electronic Health Records
Identifying patients who will be discharged within 24 hours can improve hospital resource management and quality of care.
