Object Recognition as Next Token Prediction
Abstract
We present an approach to pose object recognition as next token prediction. The idea is to apply a language decoder that auto-regressively predicts the text tokens from image embeddings to form labels. To ground this prediction process in auto-regression, we customize a non-causal attention mask for the decoder, incorporating two key features: modeling tokens from different labels to be independent, and treating image tokens as a prefix. This masking mechanism inspires an efficient method - one-shot sampling - to simultaneously sample tokens of multiple labels in parallel and rank generated labels by their probabilities during inference. To further enhance the efficiency, we propose a simple strategy to construct a compact decoder by simply discarding the intermediate blocks of a pretrained language model. This approach yields a decoder that matches the full model's performance while being notably more efficient. The code is available at https://github.com/kaiyuyue/nxtp
- Publication:
-
arXiv e-prints
- Pub Date:
- December 2023
- DOI:
- 10.48550/arXiv.2312.02142
- arXiv:
- arXiv:2312.02142
- Bibcode:
- 2023arXiv231202142Y
- Keywords:
-
- Computer Science - Computer Vision and Pattern Recognition
- E-Print:
- CVPR 2024