Sort by
Enhancing and Adapting in the Clinic: Source-Free Unsupervised Domain Adaptation for Medical Image Enhancement.

Medical imaging provides many valuable clues involving anatomical structure and pathological characteristics. However, image degradation is a common issue in clinical practice, which can adversely impact the observation and diagnosis by physicians and algorithms. Although extensive enhancement models have been developed, these models require a well pre-training before deployment, while failing to take advantage of the potential value of inference data after deployment. In this paper, we raise an algorithm for source-free unsupervised domain adaptive medical image enhancement (SAME), which adapts and optimizes enhancement models using test data in the inference phase. A structure-preserving enhancement network is first constructed to learn a robust source model from synthesized training data. Then a teacher-student model is initialized with the source model and conducts source-free unsupervised domain adaptation (SFUDA) by knowledge distillation with the test data. Additionally, a pseudo-label picker is developed to boost the knowledge distillation of enhancement tasks. Experiments were implemented on ten datasets from three medical image modalities to validate the advantage of the proposed algorithm, and setting analysis and ablation studies were also carried out to interpret the effectiveness of SAME. The remarkable enhancement performance and benefits for downstream tasks demonstrate the potential and generalizability of SAME. The code is available at https://github.com/liamheng/Annotation-free-Medical-Image-Enhancement.

Open Access
Relevant
Learning in Sinusoidal Spaces With Physics-Informed Neural Networks

A physics-informed neural network (PINN) uses physics-augmented loss functions, e.g., incorporating the residual term from governing partial differential equations (PDEs), to ensure its output is consistent with fundamental physics laws. However, it turns out to be difficult to train an accurate PINN model for many problems in practice. In this paper, we present a novel perspective of the merits of learning in sinusoidal spaces with PINNs. By analyzing behavior at model initialization, we first show that a PINN of increasing expressiveness induces an initial bias around flat output functions. Notably, this initial solution can be very close to satisfying many physics PDEs, i.e., falling into a local minimum of the PINN loss that only minimizes PDE residuals, while still being far from the true solution that jointly minimizes PDE residuals and the initial and/or boundary conditions. It is difficult for gradient descent optimization to escape from such a local minimum trap, often causing the training to stall. We then prove that the sinusoidal mapping of inputs, in an architecture we label as sf-PINN, is effective to increase input gradient variability, thus avoiding being trapped in such deceptive local minimum. The level of variability can be effectively modulated to match high-frequency patterns in the problem at hand. A key facet of this paper is the comprehensive empirical study that demonstrates the efficacy of learning in sinusoidal spaces with PINNs for a wide range of forward and inverse modelling problems spanning multiple physics domains.

Open Access
Relevant
RCT: Resource Constrained Training for Edge AI.

Efficient neural network training is essential for in situ training of edge artificial intelligence (AI) and carbon footprint reduction in general. Train neural network on the edge is challenging because there is a large gap between limited resources on edge and the resource requirement of current training methods. Existing training methods are based on the assumption that the underlying computing infrastructure has sufficient memory and energy supplies. These methods involve two copies of the model parameters, which is usually beyond the capacity of on-chip memory in processors. The data movement between off-chip and on-chip memory incurs large amounts of energy. We propose resource constrained training (RCT) to realize resource-efficient training for edge devices and servers. RCT only keeps a quantized model throughout the training so that the memory requirement for model parameters in training is reduced. It adjusts per-layer bitwidth dynamically to save energy when a model can learn effectively with lower precision. We carry out experiments with representative models and tasks in image classification, natural language processing, and crowd counting applications. Experiments show that on average, 8-15-bit weight update is sufficient for achieving SOTA performance in these applications. RCT saves 63.5%-80% memory for model parameters and saves more energy for communications. Through experiments, we observe that the common practice on the first/last layer in model compression does not apply to efficient training. Also, interestingly, the more challenging a dataset is, the lower bitwidth is required for efficient training.

Open Access
Relevant
Who Wants to Shop With You: Joint Product-Participant Recommendation for Group-Buying Service.

Recent years have witnessed the great success of group buying (GB) in social e-commerce, opening up a new way of online shopping. In this business model, a user can launch a GB as an initiator to share her interested product with social friends. The GB is clinched once enough friends join in as participants to copurchase the shared product. As such, a successful GB depends on not only whether the initiator can find her interested product but also whether the friends are willing to join in as participants. Most existing recommenders are incompetent in such complex scenario, as they merely seek to help users find their preferred products and cannot help identify potential participants to join in a GB. To this end, we propose a novel joint product-participant recommendation (J2PRec) framework, which recommends both candidate products and participants for maximizing the success rate of a GB. Specifically, J2PRec first designs a relational graph embedding module, which effectively encodes the various relations in GB for learning enhanced user and product embeddings. It then jointly learns the product and participant recommendation tasks under a probabilistic framework to maximize the GB likelihood, i.e., boost the success rate of a GB. Extensive experiments on three real-world datasets demonstrate the superiority of J2PRec for GB recommendation.

Relevant