Cuifeng Shen

Zilun Zhang, Cuifeng Shen, Yuan Shen et al.

Although CLIP-like Visual Language Models provide a functional joint feature space for image and text, due to the limitation of the CILP-like model's image input size (e.g., 224), subtle details are lost in the feature representation if we input high-resolution images (e.g., 2240). Our proposed framework addresses this issue by generating a single feature representation for a high-resolution image that retains image details from different scales while sharing the same semantic space as the original CLIP. An application scenario is remote sensing text-image retrieval, where targets (e.g., vehicles and ships) often appear at tiny scales. To achieve this, we develop a feature fusion model that relies on CLIP features extracted from a carefully designed image patch method, dubbed Complete Cover. This method ensures comprehensive coverage of objects across various scales and is weakly supervised by image-agnostic class prompted queries. We evaluate our framework's performance using real-world and synthetic datasets, demonstrating significant improvements in image retrieval tasks based on class prompted queries. To further showcase our framework's capability in detail retrieval, we introduce a CLEVR-like synthetic dataset, named CLVER-DS. This fully annotated dataset offers a controllable object scale, allowing for a more thorough examination of our approach's effectiveness.Our code is publicly available at https://github.com/zilunzhang/DetailCLIP

Chao Xu, Maohua Li, Qirui Li et al.

Diffusion Transformers (DiTs) have become a de facto backbone of modern visual generation, and nearly every major axis of their design -- tokenization, attention, conditioning, objectives, and latent autoencoders -- has been extensively revisited. The residual stream that governs how information accumulates across layers, however, has been directly inherited from the original Transformer. In this paper, we present a systematic empirical analysis of cross-layer information flow in DiTs, jointly along depth and denoising timestep, and identify three concrete symptoms of traditional residual addition, namely monotonic forward magnitude inflation, sharp backward gradient decay, and pronounced block-wise redundancy. Motivated by this diagnosis, we propose Diffusion-Adaptive Routing (\textsc{DAR}), a drop-in residual replacement that performs \emph{learnable, timestep-adaptive, and non-incremental} aggregation over the history of sublayer outputs. Moreover, the proposed \textsc{DAR} is compatible with many modern Transformer enhancement methods, such as REPA. On ImageNet $256\times256$, \textsc{DAR} improves SiT-XL/2 by $2.11$ FID ($7.56$ vs.\ $9.67$) and matches the baseline's converged quality with $8.75\times$ fewer training iterations. Stacked on top of REPA, it yields a $2\times$ training acceleration in the early stage, suggesting cross-layer information routing as an underexplored design axis in diffusion modeling, one that operates orthogonally to existing representation-alignment objectives. Beyond pretraining, \textsc{DAR} can also be applied during the fine-tuning stage of large-scale T2I models and preserves high-frequency details during Distribution Matching Distillation.

Zilun Zhang, Cuifeng Shen, Yuan Shen et al.

Although CLIP-like Visual Language Models provide a functional joint feature space for image and text, due to the limitation of the CILP-like model's image input size (e.g., 224), subtle details are lost in the feature representation if we input high-resolution images (e.g., 2240). In this work, we introduce an efficient framework that can produce a single feature representation for a high-resolution image that injects image details and shares the same semantic space as the original CLIP. In the framework, we train a feature fusing model based on CLIP features extracted from a carefully designed image patch method that can cover objects of any scale, weakly supervised by image-agnostic class prompted queries. We validate our framework by retrieving images from class prompted queries on the real world and synthetic datasets, showing significant performance improvement on these tasks. Furthermore, to fully demonstrate our framework's detail retrieval ability, we construct a CLEVR-like synthetic dataset called CLVER-DS, which is fully annotated and has a controllable object scale.

Cuifeng Shen, Yulu Gan, Chen Chen et al.

The goal of conditional image-to-video (cI2V) generation is to create a believable new video by beginning with the condition, i.e., one image and text.The previous cI2V generation methods conventionally perform in RGB pixel space, with limitations in modeling motion consistency and visual continuity. Additionally, the efficiency of generating videos in pixel space is quite low.In this paper, we propose a novel approach to address these challenges by disentangling the target RGB pixels into two distinct components: spatial content and temporal motions. Specifically, we predict temporal motions which include motion vector and residual based on a 3D-UNet diffusion model. By explicitly modeling temporal motions and warping them to the starting image, we improve the temporal consistency of generated videos. This results in a reduction of spatial redundancy, emphasizing temporal details. Our proposed method achieves performance improvements by disentangling content and motion, all without introducing new structural complexities to the model. Extensive experiments on various datasets confirm our approach's superior performance over the majority of state-of-the-art methods in both effectiveness and efficiency.