Multimodal co-learning: Challenges, applications with datasets, recent advances and future directions
Multimodal deep learning systems that employ multiple modalities like text, image, audio,
video, etc., are showing better performance than individual modalities (ie, unimodal) …
video, etc., are showing better performance than individual modalities (ie, unimodal) …
A systematic review of robustness in deep learning for computer vision: Mind the gap?
Deep neural networks for computer vision are deployed in increasingly safety-critical and
socially-impactful applications, motivating the need to close the gap in model performance …
socially-impactful applications, motivating the need to close the gap in model performance …
Efficient test-time model adaptation without forgetting
Test-time adaptation provides an effective means of tackling the potential distribution shift
between model training and inference, by dynamically updating the model at test time. This …
between model training and inference, by dynamically updating the model at test time. This …
Tent: Fully test-time adaptation by entropy minimization
A model must adapt itself to generalize to new and different data during testing. In this
setting of fully test-time adaptation the model has only the test data and its own parameters …
setting of fully test-time adaptation the model has only the test data and its own parameters …
MedViT: a robust vision transformer for generalized medical image classification
Abstract Convolutional Neural Networks (CNNs) have advanced existing medical systems
for automatic disease diagnosis. However, there are still concerns about the reliability of …
for automatic disease diagnosis. However, there are still concerns about the reliability of …
Back to the source: Diffusion-driven adaptation to test-time corruption
Test-time adaptation harnesses test inputs to improve the accuracy of a model trained on
source data when tested on shifted target data. Most methods update the source model by …
source data when tested on shifted target data. Most methods update the source model by …
3d common corruptions and data augmentation
We introduce a set of image transformations that can be used as corruptions to evaluate the
robustness of models as well as data augmentation mechanisms for training neural …
robustness of models as well as data augmentation mechanisms for training neural …
Towards robust vision transformer
Abstract Recent advances on Vision Transformer (ViT) and its improved variants have
shown that self-attention-based networks surpass traditional Convolutional Neural Networks …
shown that self-attention-based networks surpass traditional Convolutional Neural Networks …
Augmax: Adversarial composition of random augmentations for robust training
Data augmentation is a simple yet effective way to improve the robustness of deep neural
networks (DNNs). Diversity and hardness are two complementary dimensions of data …
networks (DNNs). Diversity and hardness are two complementary dimensions of data …
Assaying out-of-distribution generalization in transfer learning
Since out-of-distribution generalization is a generally ill-posed problem, various proxy
targets (eg, calibration, adversarial robustness, algorithmic corruptions, invariance across …
targets (eg, calibration, adversarial robustness, algorithmic corruptions, invariance across …