Search Results for author:
Found 20 papers, 8 papers with code
TeST: Test-time Self-Training under Distribution Shift
We find that TeST sets the new state-of-the art for test-time domain adaptation algorithms.
Unsupervised Object Learning via Common Fate
Learning generative object models from unlabelled videos is a long standing problem and required for causal scene modeling.
Dynamic Inference with Neural Interpreters
Modern neural network architectures can leverage large amounts of data to generalize well within the training distribution.
You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction
Applying this procedure to state-of-the-art trajectory prediction methods on standard benchmark datasets shows that they are, in fact, unable to reason about interactions.
CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations
Contrastive learning allows us to flexibly define powerful losses by contrasting positive pairs from sets of negative samples.
Visual Representation Learning Does Not Generalize Strongly Within the Same Domain
An important component for generalization in machine learning is to uncover underlying latent factors of variation as well as the mechanism through which each factor acts in the world.
The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agents
By training 240 representations and over 10, 000 reinforcement learning (RL) policies on a simulated robotic setup, we evaluate to what extent different properties of pretrained VAE-based representations affect the OOD generalization of downstream agents.
Backward-Compatible Prediction Updates: A Probabilistic Approach
; and (ii) if the new predictions differ from the current ones, should we update?
Towards Total Recall in Industrial Anomaly Detection
Being able to spot defective parts is a critical component in large-scale industrial manufacturing.
Ranked #1 on
Anomaly Segmentation
on GoodsAD
If your data distribution shifts, use self-learning
We demonstrate that self-learning techniques like entropy minimization and pseudo-labeling are simple and effective at improving performance of a deployed computer vision model under systematic domain shifts.
Ranked #1 on
Unsupervised Domain Adaptation
on ImageNet-A
(using extra training data)
Towards causal generative scene models via competition of experts
Learning how to model complex scenes in a modular way with recombinable components is a pre-requisite for higher-order reasoning and acting in the physical world.
Rehabilitating the ColorChecker Dataset for Illuminant Estimation
In a previous work, it was shown that there is a curious problem with the benchmark ColorChecker dataset for illuminant estimation.
Deep Directional Statistics: Pose Estimation with Uncertainty Quantification
However, in challenging imaging conditions such as on low-resolution images or when the image is corrupted by imaging artifacts, current systems degrade considerably in accuracy.
Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image
We then fit (top-down) a recently published statistical body shape model, called SMPL, to the 2D joints.
Ranked #31 on
3D Human Pose Estimation
on HumanEva-I
DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation
This paper considers the task of articulated human pose estimation of multiple people in real world images.
Ranked #2 on
Multi-Person Pose Estimation
on WAF
3D Object Class Detection in the Wild
Object class detection has been a synonym for 2D bounding box localization for the longest time, fueled by the success of powerful statistical learning techniques, combined with robust image representations.
2D Human Pose Estimation: New Benchmark and State of the Art Analysis
Human pose estimation has made significant progress during the last years.
Multi-View Priors for Learning Detectors from Sparse Viewpoint Data
While the majority of today's object class models provide only 2D bounding boxes, far richer output hypotheses are desirable including viewpoint, fine-grained category, and 3D geometry estimate.
Poselet Conditioned Pictorial Structures
In this paper we consider the challenging problem of articulated human pose estimation in still images.
Occlusion Patterns for Object Class Detection
Despite the success of recent object class recognition systems, the long-standing problem of partial occlusion remains a major challenge, and a principled solution is yet to be found.
