Free Lunch to Meet the Gap: Intermediate Domain Reconstruction for Cross-Domain Few-Shot Learning
Cross-Domain Few-Shot Learning (CDFSL) endeavors to transfer generalized knowledge from the source domain to target domains using only a minimal amount of training data, which faces a triplet of learning challenges in the meantime, i.e., semantic disjoint, large domain discrepancy, and data scarcity. Different from predominant CDFSL works focused on generalized representations, we make novel attempts to construct Intermediate Domain Proxies (IDP) with source feature embeddings as the codebook and reconstruct the target domain feature with this learned codebook. We then conduct an empirical study to explore the intrinsic attributes from perspectives of visual styles and semantic contents in intermediate domain proxies. Reaping benefits from these attributes of intermediate domains, we develop a fast domain alignment method to use these proxies as learning guidance for target domain feature transformation. With the collaborative learning of intermediate domain reconstruction and target feature transformation, our proposed model is able to surpass the state-of-the-art models by a margin on 8 cross-domain few-shot learning benchmarks.
Code (0)
등록된 구현이 없습니다.
Tasks
cross-domain few-shot learningSimilar Papers 제목 키워드 기반
A Free Lunch in LLM Compression: Revisiting Retraining after Pruning
Post-training pruning can substantially reduce LLM inference costs, but it often degrades quality unless the remaining weights are adapted. Since global retraining is expensive at LLM scale, recent work has largely focus…
Free Lunch for Unified Multimodal Models: Enhancing Generation via Reflective Rectification with Inherent Understanding
Unified Multimodal Models (UMMs) aim to integrate visual understanding and generation within a single structure. However, these models exhibit a notable capability mismatch, where their understanding capability significa…
Visual ReasoningVisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters
Foundation models have emerged as a promising approach in time series forecasting (TSF). Existing approaches either repurpose large language models (LLMs) or build large-scale time series datasets to develop TSF foundati…
Image ReconstructionTime SeriesTime Series ForecastingFree Lunch for Optimisation under the Universal Distribution
Function optimisation is a major challenge in computer science. The No Free Lunch theorems state that if all functions with the same histogram are assumed to be equally probable then no algorithm outperforms any other in…
FreeInv: Free Lunch for Improving DDIM Inversion
Naive DDIM inversion process usually suffers from a trajectory deviation issue, i.e., the latent trajectory during reconstruction deviates from the one during inversion. To alleviate this issue, previous methods either l…
Video Editing