Learning the distribution of errors in stereo matching for joint disparity and uncertainty estimation
We present a new loss function for joint disparity and uncertainty estimation in deep stereo
matching. Our work is motivated by the need for precise uncertainty estimates and the …
matching. Our work is motivated by the need for precise uncertainty estimates and the …
AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge Distillation
Due to privacy or patent concerns, a growing number of large models are released without
granting access to their training data, making transferring their knowledge inefficient and …
granting access to their training data, making transferring their knowledge inefficient and …
Learning confidence measure with transformer in stereo matching
J Yang, M Yoo, J Cho, S Kim - Pattern Recognition, 2024 - Elsevier
We introduce a novel approach for stereo confidence estimation, called ConFormer,
leveraging the Transformer architecture. Recent confidence estimation methods commonly …
leveraging the Transformer architecture. Recent confidence estimation methods commonly …
AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge Distillation
Due to privacy or patent concerns, a growing number of large models are released without
granting access to their training data, making transferring their knowledge inefficient and …
granting access to their training data, making transferring their knowledge inefficient and …