Efficient and Versatile Robust Fine-Tuning of Zero-shot Models
원문 초록
Large-scale image-text pre-trained models enable zero-shot classification and provide consistent accuracy across various data distributions. Nonetheless, optimizing these models in downstream tasks typically requires fine-tuning, which reduces generalization to out-of-distribution (OOD) data and demands extensive computational resources. We introduce Robust Adapter (R-Adapter), a novel method for fine-tuning zero-shot models to downstream tasks while simultaneously addressing both these issues. Our method integrates lightweight modules into the pre-trained model and employs novel self-ensemble techniques to boost OOD robustness and reduce storage expenses substantially. Furthermore, we propose MPM-NCE loss designed for fine-tuning on vision-language downstream tasks. It ensures precise alignment of multiple image-text pairs and discriminative feature learning. By extending the benchmark for robust fine-tuning beyond classification to include diverse tasks such as cross-modal retrieval and open vocabulary segmentation, we demonstrate the broad applicability of R-Adapter. Our extensive experiments demonstrate that R-Adapter achieves state-of-the-art performance across a diverse set of tasks, tuning only 13% of the parameters of the CLIP encoders.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Promptable Concept Segmentation from Above: Evaluating Zero-Shot Textual and Visual Prompting of SAM 3 in Remote Sensing
입력 경로는 소형 트랜스포머의 퓨샷 바인딩을 형성하지만 제로샷은 아니다: 완전 열거 가능한 연구
Input Pathways Shape Few-Shot, Not Zero-Shot, Binding in Tiny Transformers: A Fully-Enumerable Study
멀티모달 컨셉 병목 모델
Multimodal Concept Bottleneck Models
원격 탐사 변화 탐지를 위한 시간 순서화된 영역 토큰 Mamba와 로짓 공간 확산 모델
Temporally Ordered Region-Token Mamba with Logit-Space Diffusion for Remote Sensing Change Detection
Undertone: Personalizing Frozen VLM Aesthetic Judges from Few Ratings
VIGOR: 모델 기반 강화학습에서 잠재 공간 일관성을 통한 제로샷 시각적 일반화
VIGOR: Zero-Shot Visual Generalization via Latent-Space Consistency in Model-Based Reinforcement Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.