Token Caching for Diffusion Transformer Acceleration

Diffusion transformers have gained substantial interest in diffusion generative modeling due to their outstanding performance. However, their high computational cost, arising from the quadratic computational complexity of attention mechanisms and multi-step inference, presents a significant bottleneck. To address this challenge, we propose TokenCache, a novel post-training acceleration method that leverages the token-based multi-block architecture of transformers to reduce redundant computations among tokens across inference steps. TokenCache specifically addresses three critical questions in the context of diffusion transformers: (1) which tokens should be pruned to eliminate redundancy, (2) which blocks should be targeted for efficient pruning, and (3) at which time steps caching should be applied to balance speed and quality. In response to these challenges, TokenCache introduces a Cache Predictor that assigns importance scores to tokens, enabling selective pruning without compromising model performance. Furthermore, we propose an adaptive block selection strategy to focus on blocks with minimal impact on the network's output, along with a Two-Phase Round-Robin (TPRR) scheduling policy to optimize caching intervals throughout the denoising process. Experimental results across various models demonstrate that TokenCache achieves an effective trade-off between generation quality and inference speed for diffusion transformers. Our code will be publicly available.

EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditions

The area of portrait image animation, propelled by audio input, has witnessed notable progress in the generation of lifelike and dynamic portraits. Conventional methods are limited to utilizing either audios or facial key points to drive images into videos, while they can yield satisfactory results, certain issues exist. For instance, methods driven solely by audios can be unstable at times due to the relatively weaker audio signal, while methods driven exclusively by facial key points, although more stable in driving, can result in unnatural outcomes due to the excessive control of key point information. In addressing the previously mentioned challenges, in this paper, we introduce a novel approach which we named EchoMimic. EchoMimic is concurrently trained using both audios and facial landmarks. Through the implementation of a novel training strategy, EchoMimic is capable of generating portrait videos not only by audios and facial landmarks individually, but also by a combination of both audios and selected facial landmarks. EchoMimic has been comprehensively compared with alternative algorithms across various public datasets and our collected dataset, showcasing superior performance in both quantitative and qualitative evaluations. Additional visualization and access to the source code can be located on the EchoMimic project page.

Learning to utilize gradient information for crisp edge detection

Edge detection is a fundamental task in computer vision and it has made great progress under the development of deep convolutional neural networks (DCNNs), some of them have achieved a beyond human-level performance. However, recent top-performing edge detection methods tend to generate thick and blurred edge lines. In this work, we propose an effective method to solve this problem. Our approach consists of a lightweight pre-trained backbone, multi-scale contextual enhancement module aggregating gradient information (MCGI), boundary correction module (BCM), and boundary refinement module (BRM). In addition to this, we construct a novel hybrid loss function based on the Tversky index for solving the issue of imbalanced pixel distribution. We test our method on three standard benchmarks and the experiment results illustrate that our method improves the visual effect of edge maps and achieves a top performance among several state-of-the-art methods on the BSDS500 dataset (ODS F-score in standard evaluation is 0.829, in crispness evaluation is 0.720), NYUD-V2 dataset (ODS F-score in standard evaluation is 0.768, in crispness evaluation is \textbf{0.546}), and BIPED dataset (ODS F-score in standard evaluation is 0.903).

A Novel DeBERTa-based Model for Financial Question Answering Task

As a rising star in the field of natural language processing, question answering systems (Q&A Systems) are widely used in all walks of life. Compared with other scenarios, the applicationin financial scenario has strong requirements in the traceability and interpretability of the Q&A systems. In addition, since the demand for artificial intelligence technology has gradually shifted from the initial computational intelligence to cognitive intelligence, this research mainly focuses on the financial numerical reasoning dataset - FinQA. In the shared task, the objective is to generate the reasoning program and the final answer according to the given financial report containing text and tables. We use the method based on DeBERTa pre-trained language model, with additional optimization methods including multi-model fusion, training set combination on this basis. We finally obtain an execution accuracy of 68.99 and a program accuracy of 64.53, ranking No. 4 in the 2022 FinQA Challenge.