Search Results for author:
Found 23 papers, 12 papers with code
Language models scale reliably with over-training and on downstream tasks
We fit scaling laws that extrapolate in both the number of model parameters and the ratio of training tokens to parameters.
pix2gestalt: Amodal Segmentation by Synthesizing Wholes
We introduce pix2gestalt, a framework for zero-shot amodal segmentation, which learns to estimate the shape and appearance of whole objects that are only partially visible behind occlusions.
Understanding Video Transformers via Universal Concept Discovery
Concretely, we seek to explain the decision-making process of video transformers based on high-level, spatiotemporal concepts that are automatically discovered.
TAO-Amodal: A Benchmark for Tracking Any Object Amodally
Amodal perception, the ability to comprehend complete object structures from partial visibility, is a fundamental skill, even for infants.
Zero-Shot Open-Vocabulary Tracking with Large Pre-Trained Models
This begs the question: can we re-purpose these large-scale pre-trained static image models for open-vocabulary video tracking?
Shape of You: Precise 3D shape estimations for diverse body types
This paper presents Shape of You (SoY), an approach to improve the accuracy of 3D body shape estimation for vision-based clothing recommendation systems.
Ranked #4 on
3D Human Shape Estimation
on SSP-3D
HandsOff: Labeled Dataset Generation With No Additional Human Annotations
Recent work leverages the expressive power of generative adversarial networks (GANs) to generate labeled synthetic datasets.
Towards Long-Tailed 3D Detection
Moreover, semantic classes are often organized within a hierarchy, e. g., tail classes such as child and construction-worker are arguably subclasses of pedestrian.
Differentiable Raycasting for Self-supervised Occupancy Forecasting
Self-supervised representations proposed for large-scale planning, such as ego-centric freespace, confound these two motions, making the representation difficult to use for downstream motion planners.
BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video
Multiple existing benchmarks involve tracking and segmenting objects in video e. g., Video Object Segmentation (VOS) and Multi-Object Tracking and Segmentation (MOTS), but there is little interaction between them due to the use of disparate benchmark datasets and metrics (e. g. J&F, mAP, sMOTSA).
Ranked #4 on
Long-tail Video Object Segmentation
on BURST-val
(using extra training data)
Long-tail Video Object Segmentation
Multi-Object Tracking
+6
Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)
Contrastively trained language-image models such as CLIP, ALIGN, and BASIC have demonstrated unprecedented robustness to multiple challenging natural distribution shifts.
Ranked #94 on
Image Classification
on ObjectNet
(using extra training data)
Opening Up Open World Tracking
A benchmark that would allow us to perform an apple-to-apple comparison of existing efforts is a crucial first step towards advancing this important research field.
Ranked #3 on
Open-World Video Segmentation
on BURST-val
(using extra training data)
Opening up Open-World Tracking
We hope to open a new front in multi-object tracking research that will hopefully bring us a step closer to intelligent systems that can operate safely in the real world.
Evaluating Large-Vocabulary Object Detectors: The Devil is in the Details
On one hand, this is desirable as it treats all classes equally.
Detecting Invisible People
We demonstrate that current detection and tracking systems perform dramatically worse on this task.
Measuring Robustness to Natural Distribution Shifts in Image Classification
We study how robust current ImageNet models are to distribution shifts arising from natural variations in datasets.
Ranked #41 on
Domain Generalization
on VizWiz-Classification
TAO: A Large-Scale Benchmark for Tracking Any Object
To this end, we ask annotators to label objects that move at any point in the video, and give names to them post factum.
Learning to Track Any Object
Moreover, at test time the same network can be applied to detection and tracking, resulting in a unified approach for the two tasks.
When Robustness Doesn’t Promote Robustness: Synthetic vs. Natural Distribution Shifts on ImageNet
We conduct a large experimental comparison of various robustness metrics for image classification.
Do Image Classifiers Generalize Across Time?
Additionally, we evaluate three detection models and show that natural perturbations induce both classification as well as localization errors, leading to a median drop in detection mAP of 14 points.
A Systematic Framework for Natural Perturbations from Videos
We introduce a systematic framework for quantifying the robustness of classifiers to naturally occurring perturbations of images found in videos.
Towards Segmenting Anything That Moves
To address this concern, we propose two new benchmarks for generic, moving object detection, and show that our model matches top-down methods on common categories, while significantly out-performing both top-down and bottom-up methods on never-before-seen categories.
Predictive-Corrective Networks for Action Detection
While deep feature learning has revolutionized techniques for static-image understanding, the same does not quite hold for video processing.
