paper-with-me

Papers

WAVECLIP: Wavelet Tokenization for Adaptive-Resolution CLIP

2025-09-25 · Moshe Kimhi, Erez Koifman, Ehud Rivlin, Eli Schwartz, Chaim Baskin arxiv

We introduce WAVECLIP, a single unified model for adaptive resolution inference in CLIP, enabled by wavelet-based tokenization. WAVECLIP replaces standard patch embeddings with a multi-level wavelet decomposition, enabling the model to process images coarse to fine while naturally supporting multiple resolutions within the same model. At inference time, the model begins with low resolution tokens and refines only when needed, using key-value caching and causal cross-level attention to reuse computation, effectively introducing to the model only new information when needed. We evaluate WAVECLIP in zero-shot classification, demonstrating that a simple confidence-based gating mechanism enables adaptive early exits. This allows users to dynamically choose a compute-accuracy trade-off using a single deployed model. Our approach requires only lightweight distillation from a frozen CLIP teacher and achieves competitive accuracy with significant computational savings.

📄 PDF Abstract BibTeX arXiv:2509.21153

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Diffusion Transformer meets Multi-level Wavelet Spectrum for Single Image Super-Resolution

2025-11-03 · Peng Du, Hui Li, Han Xu, Paul Barom Jeon 외 arxiv

Discrete Wavelet Transform (DWT) has been widely explored to enhance the performance of image superresolution (SR). Despite some DWT-based methods improving SR by capturing fine-grained frequency signals, most existing a…

Image Super-ResolutionImage Generation

Speaking Numbers to LLMs: Multi-Wavelet Number Embeddings for Time Series Forecasting

2026-06-25 · Defu Cao, Zijie Lei, Muyan Weng, Jiao Sun 외 arxiv

Large language models (LLMs) are attractive for context-aware time series forecasting because they can integrate heterogeneous textual signals, yet their discrete, language-oriented tokenization and embedding interfaces …

Time Series Forecasting

Wavelet-Aware Anomaly Detection in Multi-Channel User Logs via Deviation Modulation and Resolution-Adaptive Attention

2026-01-18 · Kaichuan Kong, Dongjie Liu, Xiaobo Jin, Shijie Xu 외 arxiv

Insider threat detection is a key challenge in enterprise security, relying on user activity logs that capture rich and complex behavioral patterns. These logs are often multi-channel, non-stationary, and anomalies are r…

Anomaly Detection

Wavelet-based Frame Selection by Detecting Semantic Boundary for Long Video Understanding

2026-02-28 · Wang Chen, Yuhui Zeng, Yongdong Luo, Tianyu Xie 외 arxiv

Frame selection is crucial due to high frame redundancy and limited context windows when applying Large Vision-Language Models (LVLMs) to long videos. Current methods typically select frames with high relevance to a give…

Efficient Long Video Tokenization via Coordinate-based Patch Reconstruction

2024-11-22 · CVPR 2025 1 · Huiwon Jang, Sihyun Yu, Jinwoo Shin, Pieter Abbeel 외

Efficient tokenization of videos remains a challenge in training vision models that can process long videos. One promising direction is to develop a tokenizer that can encode long video clips, as it would enable the toke…