12 papers
DIFFCZSL: Compositional Zero-Shot Learning Regularized by Diffusion Representations
Hangyu Tian, Zhenqi He, Yanghao Wang +1
Compositional Zero-Shot Learning (CZSL) aims to recognize unseen attribute-object compositions by leveraging knowledge of primitive concepts learned from seen compositions. Althoug…
RIDGE: Re-Noising with Internal Dynamic Guidance for Image Editing
Ruiliang Gong, Zhen Wang, Yanghao Wang +1
Inversion-free flow-based image editing avoids latent inversion, but still requires a target-side state at every editing step. The widely used equal-displacement construction keeps…
ReBind: Multi-Reference Video Editing via Structured Instructions with Explicit Reference Relationships
Xinyu Liu, Shihao Li, Weihong Lin +10
Recent diffusion-based video generation models have made significant progress in multi-reference image-conditioned video editing. However, existing methods still struggle to coordi…
FlowCIR: Semantic Transport via Flow Matching for Zero-Shot Composed Image Retrieval
Zhenqi He, Ziqi Jiang, Yuanpei Liu +3
Zero-shot composed image retrieval (ZS-CIR) aims to retrieve a target image by editing a reference image with a natural-language instruction, without relying on domain-specific ann…
LISA: Likelihood Score Alignment for Visual-condition Controllable Generation
Yanghao Wang, Hongxu Chen, Jiazhen Liu +4
The prevalent dual-branch paradigm, i.e., training a side network to encode visual conditions and fusing its intermediate-layer features to a frozen pretrained main network, has sh…
Direct Product Flow Matching: Decoupling Radial and Angular Dynamics for Few-Shot Adaptation
Hongxu Chen, Yanghao Wang, Bowei Zhu +6
Recent flow matching (FM) methods improve the few-shot adaptation of vision-language models, by modeling cross-modal alignment as a continuous multi-step flow. In this paper, we ar…
Adaptive Weighted h-Transform Sampling for Coarse-Guided Visual Generation
Yanghao Wang, Ziqi Jiang, Zhen Wang +1
Coarse-guided visual generation, which synthesizes fine visual samples from degraded or low-fidelity coarse references, is essential for various real-world applications. While trai…
FlowDC: Flow-Based Decoupling-Decay for Complex Image Editing
Yilei Jiang, Zhen Wang, Yanghao Wang +4
With the surge of pre-trained text-to-image flow matching models, text-based image editing performance has gained remarkable improvement, especially for \underline{simple editing}…
Target-aware Image Editing via Cycle-consistent Constraints
Yanghao Wang, Zhen Wang, Long Chen
Recent pre-trained text-to-image flow models have enabled remarkable progress in text-based image editing. Mainstream approaches adopt a corruption-then-restoration paradigm, where…
Exploring Cross-Modal Flows for Few-Shot Learning
Ziqi Jiang, Yanghao Wang, Long Chen
Aligning features from different modalities, is one of the most fundamental challenges for cross-modal tasks. Although pre-trained vision-language models can achieve a general alig…
Noise Matters: Optimizing Matching Noise for Diffusion Classifiers
Yanghao Wang, Long Chen
Although today's pretrained discriminative vision-language models (e.g., CLIP) have demonstrated strong perception abilities, such as zero-shot image classification, they also suff…
Inversion Circle Interpolation: Diffusion-based Image Augmentation for Data-scarce Classification
Yanghao Wang, Long Chen
Data Augmentation (DA), i.e., synthesizing faithful and diverse samples to expand the original training set, is a prevalent and effective strategy to improve the performance of var…