SSDA: Bridging Spectral and Structural Gaps via Dual Adaptation for Vision-Based Time Series Forecasting

Mingrui Zhang, Hanchen Yang, Wengen Li, Xudong Jiang, Yichao Zhang, Jihong Guan, Shuigeng Zhou

arXiv:2605.12550 · 2026-05-14 공개 · arXiv · PDF

few-shot-learning vision-models attention-mechanism low-rank-adaptation time-series-forecasting spectral-gap structural-gap fft

Abstract

Large vision models (LVMs) have recently proven to be surprisingly effective time series forecasters, simply by rendering temporal data as images. This success, how ever, rests on a largely unexamined premise: the rendered time series images are sufficiently close to natural images for knowledge in pre-trained models to transfer effectively. We argue that two gaps still remain, i.e., spectral and structural gaps, fundamentally limiting the potential of LVMs for time series forecasting. Spectrally, we systematically reveal that rendered time series images exhibit a markedly shallower power spectrum than the natural images LVMs are pre-trained to recognize. Structurally, reshaping 1D temporal sequences into 2D grids fabricates spurious spatial adjacencies while severing genuine temporal continuities, misleading the spatial inductive biases of pre-trained LVMs. To bridge these gaps, we propose SSDA, a dual-branch network that spectrally and structurally adapts to unlock the full potential of LVMs for time series forecasting. At the data level, a Spectral Magnitude Aligner (SMA) applies 2D FFT to selectively enhance the magnitude spectrum toward natural-image statistics while preserving phase. At the model level, a Structural-Guided Low-Rank Adaptation (SG-LoRA) injects position-aware temporal encodings into patch embeddings and adapts at tention via low-rank updates. The two branches are further adaptively fused to produce the final forecast. Extensive experiments on seven real-world benchmarks demonstrate that SSDA consistently outperforms strong LVM- and LLM-based baselines under both full-shot and few-shot settings. Code is publicly available at https://anonymous.4open.science/r/SSDA-8C5B.

한국어 요약

📋 한 줄 요약

**[시계열 예측 / 비전 파운데이션 모델]** 대형 비전 모델로 시계열을 이미지로 렌더해 예측할 때 발생하는 스펙트럼·구조적 격차를 진단하고, 양 격차를 동시에 좁히는 이중 분기 적응 프레임워크 SSDA 제안.

🎯 핵심 기여도

💡 핵심 아이디어

"렌더된 시계열 이미지 ≈ 자연 이미지"라는 암묵적 전제는 깨져 있다. 스펙트럼 통계를 자연 이미지에 가깝게 정렬하고 구조적 사전 지식을 시간적 인코딩으로 주입하면, 비전 모델의 사전 학습 표현을 시계열 예측에 효과적으로 전이할 수 있다.

🔬 기술적 접근법

📊 주요 결과

💭 의의 및 한계

**의의**: "이미지로 그리면 비전 파운데이션 모델이 시계열을 잘 푼다"는 최근 흐름의 전제를 비판적으로 검증하고, 실용적 해결책을 함께 제시. **한계**: 이미지 렌더링 자체에 의존하는 패러다임 안에서의 보정으로, 비-이미지 표현 기반 접근과의 근본 비교는 본문 범위 밖.

🚀 실용적 활용