Test-Time Adaptation (TTA) allows to update pre-trained models to changing data distributions at deployment time.
2 code implementations • • Jessy Lauer, Mu Zhou, Shaokai Ye, William Menegas, Steffen Schneider, Tanmay Nath, Mohammed Mostafizur Rahman, Valentina Di Santo, Daniel Soberanes, Guoping Feng, Venkatesh N. Murthy, George Lauder, Catherine Dulac, Mackenzie Weygandt Mathis & Alexander Mathis
Estimating the pose of multiple animals is a challenging computer vision problem: frequent interactions cause occlusions and complicate the association of detected keypoints to the correct individuals, as well as having highly similar looking animals that interact more closely than in typical multi-human scenarios.
Ranked #4 on Animal Pose Estimation on TriMouse-161
We illustrate the utility of our models in behavioral classification in mice and gait analysis in horses.
Ranked #1 on Animal Pose Estimation on Animal-Pose Dataset (using extra training data)
1 code implementation • 13 Oct 2021 • Matthias Tangemann, Steffen Schneider, Julius von Kügelgen, Francesco Locatello, Peter Gehler, Thomas Brox, Matthias Kümmerer, Matthias Bethge, Bernhard Schölkopf
Learning generative object models from unlabelled videos is a long standing problem and required for causal scene modeling.
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)
We investigate the behavior of reinforcement learning (RL) agents under morphological distribution shifts.
Contrastive learning has recently seen tremendous success in self-supervised learning.
Ranked #1 on Disentanglement on KITTI-Masks
Extracting behavioral measurements non-invasively from video is stymied by the fact that it is a hard computational problem.
With the more robust DeepAugment+AugMix model, we improve the state of the art achieved by a ResNet50 model up to date from 53. 6% mCE to 45. 4% mCE.
Ranked #4 on Unsupervised Domain Adaptation on ImageNet-R
We propose vq-wav2vec to learn discrete representations of audio segments through a wav2vec-style self-supervised context prediction task.
Ranked #2 on Speech Recognition on TIMIT (using extra training data)
Neural networks are highly effective tools for pose estimation.
Ranked #1 on Animal Pose Estimation on Horse-10
Our experiments on WSJ reduce WER of a strong character-based log-mel filterbank baseline by up to 36% when only a few hours of transcribed data is available.
Ranked #5 on Speech Recognition on TIMIT (using extra training data)
While human observers are able to cope with variations in color and appearance of histological stains, digital pathology algorithms commonly require a well-normalized setting to achieve peak performance, especially when a limited amount of labeled data is available.