Adding register tokens to Vision Transformers eliminates high-norm background artifacts and raises state-of-the-art performance on dense visual prediction tasks.
preprint arXiv:2010.10504 , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
Pretrained audio models show large performance gaps between standard MIR tasks and music recommendation in both hot and cold-start settings.
ViP-VL achieves claimed state-of-the-art results on Vietnamese ASR, emotion recognition, dialect classification, and speaker verification via vector-quantization self-supervised pretraining on 17k hours with 8x subsampling modifications.
Evaluation of open-source and commercial ASR models on narrow-band Hindi and Indian English shows poor zero-shot results and inconsistent fine-tuning benefits tied to pretraining exposure.
citing papers explorer
-
Vision Transformers Need Registers
Adding register tokens to Vision Transformers eliminates high-norm background artifacts and raises state-of-the-art performance on dense visual prediction tasks.