Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone Ensembling
원문 초록
Contrastive Language-Image Pretraining (CLIP) stands out as a prominent method for image representation learning. Various architectures, from vision transformers (ViTs) to convolutional networks (ResNets) have been trained with CLIP to serve as general solutions to diverse vision tasks. This paper explores the differences across various CLIP-trained vision backbones. Despite using the same data and training objective, we find that these architectures have notably different representations, different classification performance across datasets, and different robustness properties to certain types of image perturbations. Our findings indicate a remarkable possible synergy across backbones by leveraging their respective strengths. In principle, classification accuracy could be improved by over 40 percentage with an informed selection of the optimal backbone per test example.Using this insight, we develop a straightforward yet powerful approach to adaptively ensemble multiple backbones. The approach uses as few as one labeled example per class to tune the adaptive combination of backbones. On a large collection of datasets, the method achieves a remarkable increase in accuracy of up to 39.1% over the best single backbone, well beyond traditional ensembles
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
UniPre3D: Unified Pre-training of 3D Point Cloud Models with Cross-Modal Gaussian Splatting
Efficient Skill Discovery via Regret-Aware Optimization
Step-wise Policy for Rare-tool Knowledge (SPaRK): Offline RL that Drives Diverse Tool Use in LLMs
Exploring Design of Multi-Agent LLM Dialogues for Research Ideation
Dual Dimensions Geometric Representation Learning Based Document Dewarping
MS-DPPs: Multi-Source Determinantal Point Processes for Contextual Diversity Refinement of Composite Attributes in Text to Image Retrieval
토론
이 논문과 연결된 포럼 글이 아직 없습니다.