UHNet: An Ultra-Lightweight and High-Speed Edge Detection Network

Edge detection is crucial in medical image processing, enabling precise extraction of structural information to support lesion identification and image analysis. Traditional edge detection models typically rely on complex Convolutional Neural Networks and Vision Transformer architectures. Due to their numerous parameters and high computational demands, these models are limited in their application on resource-constrained devices. This paper presents an ultra-lightweight edge detection model (UHNet), characterized by its minimal parameter count, rapid computation speed, negligible of pre-training costs, and commendable performance. UHNet boasts impressive performance metrics with 42.3k parameters, 166 FPS, and 0.79G FLOPs. By employing an innovative feature extraction module and optimized residual connection method, UHNet significantly reduces model complexity and computational requirements. Additionally, a lightweight feature fusion strategy is explored, enhancing detection accuracy. Experimental results on the BSDS500, NYUD, and BIPED datasets validate that UHNet achieves remarkable edge detection performance while maintaining high efficiency. This work not only provides new insights into the design of lightweight edge detection models but also demonstrates the potential and application prospects of the UHNet model in engineering applications such as medical image processing. The codes are available at https://github.com/stoneLi20cv/UHNet

Benchmarking General Purpose In-Context Learning

In-context learning (ICL) capabilities are becoming increasingly appealing for building general intelligence due to their sample efficiency and independence from artificial optimization skills. To enhance generalization, biological neural systems primarily inherit learning capabilities and subsequently refine their memory, acquiring diverse skills and knowledge through extensive lifelong experiences. This process gives rise to the concept of general-purpose in-context learning (GPICL). Compared to standard ICL, GPICL addresses a broader range of tasks, extends learning horizons, and starts at a lower zero-shot baseline. We introduce two lightweight but insightful benchmarks specifically crafted to train and evaluate GPICL functionalities. Each benchmark includes a vast number of tasks characterized by significant task variance and minimal transferable knowledge among tasks, facilitating lifelong in-context learning through continuous generation and interaction. These features pose significant challenges for models that rely on context or interactions to improve their proficiency, including language models, decision models, and world models. Our experiments reveal that parameter scale alone may not be crucial for ICL or GPICL, suggesting alternative approaches such as increasing the scale of contexts and memory states.

Semantic Gesticulator: Semantics-Aware Co-Speech Gesture Synthesis

In this work, we present Semantic Gesticulator, a novel framework designed to synthesize realistic gestures accompanying speech with strong semantic correspondence. Semantically meaningful gestures are crucial for effective non-verbal communication, but such gestures often fall within the long tail of the distribution of natural human motion. The sparsity of these movements makes it challenging for deep learning-based systems, trained on moderately sized datasets, to capture the relationship between the movements and the corresponding speech semantics. To address this challenge, we develop a generative retrieval framework based on a large language model. This framework efficiently retrieves suitable semantic gesture candidates from a motion library in response to the input speech. To construct this motion library, we summarize a comprehensive list of commonly used semantic gestures based on findings in linguistics, and we collect a high-quality motion dataset encompassing both body and hand movements. We also design a novel GPT-based model with strong generalization capabilities to audio, capable of generating high-quality gestures that match the rhythm of speech. Furthermore, we propose a semantic alignment mechanism to efficiently align the retrieved semantic gestures with the GPT's output, ensuring the naturalness of the final animation. Our system demonstrates robustness in generating gestures that are rhythmically coherent and semantically explicit, as evidenced by a comprehensive collection of examples. User studies confirm the quality and human-likeness of our results, and show that our system outperforms state-of-the-art systems in terms of semantic appropriateness by a clear margin.

Learning Crisp Boundaries Using Deep Refinement Network and Adaptive Weighting Loss

Significant progress has been made in boundary detection with the help of convolutional neural networks. Recent boundary detection models not only focus on real object boundary detection but also "crisp" boundaries (precisely localized along the object's contour). There are two methods to evaluate crisp boundary performance. One uses more strict tolerance to measure the distance between the ground truth and the detected contour. The other focuses on evaluating the contour map without any postprocessing. In this study, we analyze both methods and conclude that both methods are two aspects of crisp contour evaluation. Accordingly, we propose a novel network named deep refinement network (DRNet) that stacks multiple refinement modules to achieve richer feature representation and a novel loss function, which combines cross-entropy and dice loss through effective adaptive fusion. Experimental results demonstrated that we achieve state-of-the-art performance for several available datasets.