Search Results for author:
Found 22 papers, 12 papers with code
Block and Detail: Scaffolding Sketch-to-Image Generation
Our tool lets users sketch blocking strokes to coarsely represent the placement and form of objects and detail strokes to refine their shape and silhouettes.
Learning Subject-Aware Cropping by Outpainting Professional Photos
How to frame (or crop) a photo often depends on the image subject and its context; e. g., a human portrait.
Iterative Motion Editing with Natural Language
Text-to-motion diffusion models can generate realistic animations from text prompts, but do not support fine-grained motion editing controls.
Collage Diffusion
We seek to give users precise control over diffusion-based image generation by modeling complex scenes as sequences of layers, which define the desired spatial arrangement and visual attributes of objects in the scene.
Spotting Temporally Precise, Fine-Grained Events in Video
We introduce the task of spotting temporally precise, fine-grained events in video (detecting the precise moment in time events occur).
Ranked #6 on
Action Spotting
on SoccerNet-v2
Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learning
We first prove that adding a weighted class-conditional InfoNCE loss to SupCon controls the degree of spread.
Shoring Up the Foundations: Fusing Model Embeddings and Weak Supervision
Despite the black-box nature of foundation models, we prove results characterizing how our approach improves performance and show that lift scales with the smoothness of label distributions in embedding space.
The Details Matter: Preventing Class Collapse in Supervised Contrastive Learning
Supervised contrastive learning optimizes a loss that pushes together embeddings of points from the same class while pulling apart embeddings of points from different classes.
Low-Shot Validation: Active Importance Sampling for Estimating Classifier Performance on Rare Categories
For machine learning models trained with limited labeled training data, validation stands to become the main bottleneck to reducing overall annotation costs.
Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognition
This leads to poor accuracy when downstream tasks, such as action recognition, depend on pose.
Mandoline: Model Evaluation under Distribution Shift
If an unlabeled sample from the target distribution is available, along with a labeled sample from a possibly different source distribution, standard approaches such as importance weighting can be applied to estimate performance on the target.
Large Batch Simulation for Deep Reinforcement Learning
We accelerate deep reinforcement learning-based training in visually complex 3D environments by two orders of magnitude over prior work, realizing end-to-end training speeds of over 19, 000 frames of experience per second on a single GPU and up to 72, 000 frames per second on a single eight-GPU machine.
Learning Rare Category Classifiers on a Tight Labeling Budget
In this paper, we consider the scenario where we start with as-little-as five labeled positives of a rare category and a large amount of unlabeled data of which 99. 9% of it is negatives.
Iterative Text-based Editing of Talking-heads Using Neural Retargeting
We present a text-based tool for editing talking-head video that enables an iterative editing workflow.
Background Splitting: Finding Rare Classes in a Sea of Background
We focus on the real-world problem of training accurate deep models for image classification of a small number of rare categories.
Train and You'll Miss It: Interactive Model Iteration with Weak Supervision and Pre-Trained Embeddings
Our goal is to enable machine learning systems to be trained interactively.
Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods
In this work, we show that, for a class of latent variable models highly applicable to weak supervision, we can find a closed-form solution to model parameters, obviating the need for iterative solutions like stochastic gradient descent (SGD).
Multi-Resolution Weak Supervision for Sequential Data
Multi-resolution sources exacerbate this challenge due to complex correlations and sample complexity that scales in the length of the sequence.
Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels
Many real-world video analysis applications require the ability to identify domain-specific events in video, such as interviews and commercials in TV news broadcasts, or action sequences in film.
Online Model Distillation for Efficient Video Inference
Rather than learn a specialized student model on offline data from the video stream, we train the student in an online fashion on the live video, intermittently running the teacher to provide a target for learning.
HydraNets: Specialized Dynamic Architectures for Efficient Inference
On ImageNet, applying the HydraNet template improves accuracy up to 2. 5% when compared to an efficient baseline architecture with similar inference cost.
Scanner: Efficient Video Analysis at Scale
The challenge is that scaling applications to operate on these datasets requires efficient systems for pixel data access and parallel processing across large numbers of machines.
