Zobrazeno 1 - 10
of 51
pro vyhledávání: '"Kozinski, Mateusz"'
We propose a novel approach to video anomaly detection: we treat feature vectors extracted from videos as realizations of a random variable with a fixed distribution and model this distribution with a neural network. This lets us estimate the likelih
Externí odkaz:
http://arxiv.org/abs/2403.14497
Autor:
Mirza, M. Jehanzeb, Karlinsky, Leonid, Lin, Wei, Doveh, Sivan, Micorek, Jakub, Kozinski, Mateusz, Kuehne, Hilde, Possegger, Horst
Prompt ensembling of Large Language Model (LLM) generated category-specific prompts has emerged as an effective method to enhance zero-shot recognition ability of Vision-Language Models (VLMs). To obtain these category-specific prompts, the present m
Externí odkaz:
http://arxiv.org/abs/2403.11755
Autor:
Leitner, Stefan, Mirza, M. Jehanzeb, Lin, Wei, Micorek, Jakub, Masana, Marc, Kozinski, Mateusz, Possegger, Horst, Bischof, Horst
In autonomous driving scenarios, current object detection models show strong performance when tested in clear weather. However, their performance deteriorates significantly when tested in degrading weather conditions. In addition, even when adapted t
Externí odkaz:
http://arxiv.org/abs/2305.18953
Autor:
Mirza, M. Jehanzeb, Karlinsky, Leonid, Lin, Wei, Kozinski, Mateusz, Possegger, Horst, Feris, Rogerio, Bischof, Horst
Recently, large-scale pre-trained Vision and Language (VL) models have set a new state-of-the-art (SOTA) in zero-shot visual classification enabling open-vocabulary recognition of potentially unlimited set of categories defined as simple language pro
Externí odkaz:
http://arxiv.org/abs/2305.18287
Autor:
Lin, Wei, Karlinsky, Leonid, Shvetsova, Nina, Possegger, Horst, Kozinski, Mateusz, Panda, Rameswar, Feris, Rogerio, Kuehne, Hilde, Bischof, Horst
Large scale Vision-Language (VL) models have shown tremendous success in aligning representations between visual and text modalities. This enables remarkable progress in zero-shot recognition, image generation & editing, and many other exciting tasks
Externí odkaz:
http://arxiv.org/abs/2303.08914
Autor:
Lin, Wei, Mirza, Muhammad Jehanzeb, Kozinski, Mateusz, Possegger, Horst, Kuehne, Hilde, Bischof, Horst
Although action recognition systems can achieve top performance when evaluated on in-distribution test points, they are vulnerable to unanticipated distribution shifts in test data. However, test-time adaptation of video action recognition models aga
Externí odkaz:
http://arxiv.org/abs/2211.15393
Autor:
Mirza, Muhammad Jehanzeb, Soneira, Pol Jané, Lin, Wei, Kozinski, Mateusz, Possegger, Horst, Bischof, Horst
Test-Time-Training (TTT) is an approach to cope with out-of-distribution (OOD) data by adapting a trained model to distribution shifts occurring at test-time. We propose to perform this adaptation via Activation Matching (ActMAD): We analyze activati
Externí odkaz:
http://arxiv.org/abs/2211.12870
Autor:
Mirza, M. Jehanzeb, Shin, Inkyu, Lin, Wei, Schriebl, Andreas, Sun, Kunyang, Choe, Jaesung, Possegger, Horst, Kozinski, Mateusz, Kweon, In So, Yoon, Kun-Jin, Bischof, Horst
Our MATE is the first Test-Time-Training (TTT) method designed for 3D data, which makes deep networks trained for point cloud classification robust to distribution shifts occurring in test data. Like existing TTT methods from the 2D image domain, MAT
Externí odkaz:
http://arxiv.org/abs/2211.11432
Many biological and medical tasks require the delineation of 3D curvilinear structures such as blood vessels and neurites from image volumes. This is typically done using neural networks trained by minimizing voxel-wise loss functions that do not cap
Externí odkaz:
http://arxiv.org/abs/2207.06832
Publikováno v:
IEEE Transactions on Medical Imaging ( Volume: 41, Issue: 12, December 2022)
Deep learning-based approaches to delineating 3D structure depend on accurate annotations to train the networks. Yet, in practice, people, no matter how conscientious, have trouble precisely delineating in 3D and on a large scale, in part because the
Externí odkaz:
http://arxiv.org/abs/2112.02781