IIR-VLM: In-Context Instance-level Recognition for Large Vision-Language Models

TL;DR

This paper introduces IIR-VLM, a novel vision-language model that enhances instance-level recognition by integrating specialized encoders, enabling effective one-shot learning and improved recognition of diverse instances across various categories.

Contribution

The paper proposes IIR-VLM, which incorporates ILR expert models into VLMs for in-context learning, addressing limitations in existing models for fine-grained, instance-level recognition.

Findings

Outperforms existing ILR models on personalization benchmarks.

Effective one-shot learning of new instances in diverse categories.

Demonstrates superior performance on a new challenging benchmark.

Abstract

Instance-level recognition (ILR) concerns distinguishing individual instances from one another, with person re-identification as a prominent example. Despite the impressive visual perception capabilities of modern VLMs, we find their performance on ILR unsatisfactory, often dramatically underperforming domain-specific ILR models. This limitation hinders many practical application of VLMs, e.g. where recognizing familiar people and objects is crucial for effective visual understanding. Existing solutions typically learn to recognize instances one at a time using instance-specific datasets, which not only incur substantial data collection and training costs but also struggle with fine-grained discrimination. In this work, we propose IIR-VLM, a VLM enhanced for In-context Instance-level Recognition. We integrate pre-trained ILR expert models as auxiliary visual encoders to provide specialized features for learning diverse instances, which enables VLMs to learn new instances in-context in a one-shot manner. Further, IIR-VLM leverages this knowledge for instance-aware visual understanding. We validate IIR-VLM's efficacy on existing instance personalization benchmarks. Finally, we demonstrate its superior ILR performance on a challenging new benchmark, which assesses ILR capabilities across varying difficulty and diverse categories, with person, face, pet and general objects as the instances at task.