Saved in:
Bibliographic Details
Main Authors: Yue, Kaiyu, Chen, Bor-Chun, Geiping, Jonas, Li, Hengduo, Goldstein, Tom, Lim, Ser-Nam
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2312.02142
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917626668646400
author Yue, Kaiyu
Chen, Bor-Chun
Geiping, Jonas
Li, Hengduo
Goldstein, Tom
Lim, Ser-Nam
author_facet Yue, Kaiyu
Chen, Bor-Chun
Geiping, Jonas
Li, Hengduo
Goldstein, Tom
Lim, Ser-Nam
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2312_02142
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Object Recognition as Next Token Prediction
Yue, Kaiyu
Chen, Bor-Chun
Geiping, Jonas
Li, Hengduo
Goldstein, Tom
Lim, Ser-Nam
Computer Vision and Pattern Recognition
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
title Object Recognition as Next Token Prediction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.02142