Xing Zhang

Jiaxi Gu, Shicong Wang, Haoyu Zhao et al.

Inspired by the remarkable success of Latent Diffusion Models (LDMs) for image synthesis, we study LDM for text-to-video generation, which is a formidable challenge due to the computational and memory constraints during both model training and inference. A single LDM is usually only capable of generating a very limited number of video frames. Some existing works focus on separate prediction models for generating more video frames, which suffer from additional training cost and frame-level jittering, however. In this paper, we propose a framework called "Reuse and Diffuse" dubbed $\textit{VidRD}$ to produce more frames following the frames already generated by an LDM. Conditioned on an initial video clip with a small number of frames, additional frames are iteratively generated by reusing the original latent features and following the previous diffusion process. Besides, for the autoencoder used for translation between pixel space and latent space, we inject temporal layers into its decoder and fine-tune these layers for higher temporal consistency. We also propose a set of strategies for composing video-text data that involve diverse content from multiple existing datasets including video datasets for action recognition and image-text datasets. Extensive experiments show that our method achieves good results in both quantitative and qualitative evaluations. Our project page is available $\href{https://anonymous0x233.github.io/ReuseAndDiffuse/}{here}$.

Haoyu Zhao, Tianyi Lu, Jiaxi Gu et al.

The diffusion model is widely leveraged for either video generation or video editing. As each field has its task-specific problems, it is difficult to merely develop a single diffusion for completing both tasks simultaneously. Video diffusion sorely relying on the text prompt can be adapted to unify the two tasks. However, it lacks a high capability of aligning heterogeneous modalities between text and image, leading to various misalignment problems. In this work, we are the first to propose a unified Multi-alignment Diffusion, dubbed as MagDiff, for both tasks of high-fidelity video generation and editing. The proposed MagDiff introduces three types of alignments, including subject-driven alignment, adaptive prompts alignment, and high-fidelity alignment. Particularly, the subject-driven alignment is put forward to trade off the image and text prompts, serving as a unified foundation generative model for both tasks. The adaptive prompts alignment is introduced to emphasize different strengths of homogeneous and heterogeneous alignments by assigning different values of weights to the image and the text prompts. The high-fidelity alignment is developed to further enhance the fidelity of both video generation and editing by taking the subject image as an additional model input. Experimental results on four benchmarks suggest that our method outperforms the previous method on each task.

Geon Park, Jaehong Yoon, Haiyang Zhang et al.

Neural network quantization aims to transform high-precision weights and activations of a given neural network into low-precision weights/activations for reduced memory usage and computation, while preserving the performance of the original model. However, extreme quantization (1-bit weight/1-bit activations) of compactly-designed backbone architectures (e.g., MobileNets) often used for edge-device deployments results in severe performance degeneration. This paper proposes a novel Quantization-Aware Training (QAT) method that can effectively alleviate performance degeneration even with extreme quantization by focusing on the inter-weight dependencies, between the weights within each layer and across consecutive layers. To minimize the quantization impact of each weight on others, we perform an orthonormal transformation of the weights at each layer by training an input-dependent correlation matrix and importance vector, such that each weight is disentangled from the others. Then, we quantize the weights based on their importance to minimize the loss of the information from the original weights/activations. We further perform progressive layer-wise quantization from the bottom layer to the top, so that quantization at each layer reflects the quantized distributions of weights and activations at previous layers. We validate the effectiveness of our method on various benchmark datasets against strong neural quantization baselines, demonstrating that it alleviates the performance degeneration on ImageNet and successfully preserves the full-precision model performance on CIFAR-100 with compact backbone networks.

Guilin Li, Xing Zhang, Zitong Wang et al.

Recently, the efficiency of automatic neural architecture design has been significantly improved by gradient-based search methods such as DARTS. However, recent literature has brought doubt to the generalization ability of DARTS, arguing that DARTS performs poorly when the search space is changed, i.e, when different set of candidate operators are used. Regularization techniques such as early stopping have been proposed to partially solve this problem. In this paper, we tackle this problem from a different perspective by identifying two contributing factors to the collapse of DARTS when the search space changes: (1) the correlation of similar operators incurs unfavorable competition among them and makes their relative importance score unreliable and (2) the optimization complexity gap between the proxy search stage and the final training. Based on these findings, we propose a new hierarchical search algorithm. With its operator clustering and optimization complexity match, the algorithm can consistently find high-performance architecture across various search spaces. For all the five variants of the popular cell-based search spaces, the proposed algorithm always obtains state-of-the-art architecture with best accuracy on the CIFAR-10, CIFAR-100 and ImageNet over other well-established DARTS-alike algorithms. Code is available at https://github.com/susan0199/StacNAS.

Zheng Li, Xiang Li, Xinyi Fu et al.

Prompt learning has emerged as a valuable technique in enhancing vision-language models (VLMs) such as CLIP for downstream tasks in specific domains. Existing work mainly focuses on designing various learning forms of prompts, neglecting the potential of prompts as effective distillers for learning from larger teacher models. In this paper, we introduce an unsupervised domain prompt distillation framework, which aims to transfer the knowledge of a larger teacher model to a lightweight target model through prompt-driven imitation using unlabeled domain images. Specifically, our framework consists of two distinct stages. In the initial stage, we pre-train a large CLIP teacher model using domain (few-shot) labels. After pre-training, we leverage the unique decoupled-modality characteristics of CLIP by pre-computing and storing the text features as class vectors only once through the teacher text encoder. In the subsequent stage, the stored class vectors are shared across teacher and student image encoders for calculating the predicted logits. Further, we align the logits of both the teacher and student models via KL divergence, encouraging the student image encoder to generate similar probability distributions to the teacher through the learnable prompts. The proposed prompt distillation process eliminates the reliance on labeled data, enabling the algorithm to leverage a vast amount of unlabeled images within the domain. Finally, the well-trained student image encoders and pre-stored text features (class vectors) are utilized for inference. To our best knowledge, we are the first to (1) perform unsupervised domain-specific prompt-driven knowledge distillation for CLIP, and (2) establish a practical pre-storing mechanism of text features as shared class vectors between teacher and student. Extensive experiments on 11 datasets demonstrate the effectiveness of our method.

Steven McDonagh, Sarah Parisot, Fengwei Zhou et al.

Digital camera pipelines employ color constancy methods to estimate an unknown scene illuminant, in order to re-illuminate images as if they were acquired under an achromatic light source. Fully-supervised learning approaches exhibit state-of-the-art estimation accuracy with camera-specific labelled training imagery. Resulting models typically suffer from domain gaps and fail to generalise across imaging devices. In this work, we propose a new approach that affords fast adaptation to previously unseen cameras, and robustness to changes in capture device by leveraging annotated samples across different cameras and datasets. We present a general approach that utilizes the concept of color temperature to frame color constancy as a set of distinct, homogeneous few-shot regression tasks, each associated with an intuitive physical meaning. We integrate this novel formulation within a meta-learning framework, enabling fast generalisation to previously unseen cameras using only handfuls of camera specific training samples. Consequently, the time spent for data collection and annotation substantially diminishes in practice whenever a new sensor is used. To quantify this gain, we evaluate our pipeline on three publicly available datasets comprising 12 different cameras and diverse scene content. Our approach delivers competitive results both qualitatively and quantitatively while requiring a small fraction of the camera-specific samples compared to standard approaches.

Yongyi Tang, Xing Zhang, Jingwen Wang et al.

This paper describes our solution for the 2$^\text{nd}$ YouTube-8M video understanding challenge organized by Google AI. Unlike the video recognition benchmarks, such as Kinetics and Moments, the YouTube-8M challenge provides pre-extracted visual and audio features instead of raw videos. In this challenge, the submitted model is restricted to 1GB, which encourages participants focus on constructing one powerful single model rather than incorporating of the results from a bunch of models. Our system fuses six different sub-models into one single computational graph, which are categorized into three families. More specifically, the most effective family is the model with non-local operations following the NetVLAD encoding. The other two family models are Soft-BoF and GRU, respectively. In order to further boost single models performance, the model parameters of different checkpoints are averaged. Experimental results demonstrate that our proposed system can effectively perform the video classification task, achieving 0.88763 on the public test set and 0.88704 on the private set in terms of GAP@20, respectively. We finally ranked at the fourth place in the YouTube-8M video understanding challenge.