相关论文: Decorrelating Structure via Adapters Makes Ensembl…

Decentralized and lifelong-adaptive multi-agent collaborative learning aims to enhance collaboration among multiple agents without a central server, with each agent solving varied tasks over time. To achieve efficient collaboration, agents…

Most few-shot learning works rely on the same domain assumption between the base and the target tasks, hindering their practical applications. This paper proposes an adaptive transformer network (ADAPTER), a simple but effective solution…

In many real-world scenarios, data to train machine learning models become available over time. However, neural network models struggle to continually learn new concepts without forgetting what has been learnt in the past. This phenomenon…

Infrared-visible object detection has shown great potential in real-world applications, enabling robust all-day perception by leveraging the complementary information of infrared and visible images. However, existing methods typically…

Accurate image segmentation remains challenging, particularly in generating sharp, confident boundaries. While modern architectures have advanced the field, many of them still rely on standard loss functions like Cross-Entropy and Dice,…

The proposed method in this paper proposes an end-to-end unsupervised semantic segmentation architecture DMSA based on four loss functions. The framework uses Atrous Spatial Pyramid Pooling (ASPP) module to enhance feature extraction. At…

Despite recent advancements in deep learning, deep neural networks continue to suffer from performance degradation when applied to new data that differs from training data. Test-time adaptation (TTA) aims to address this challenge by…

Despite the fact real-world video deinterlacing and demosaicing are well-suited to supervised learning from synthetically degraded data because the degradation models are known and fixed, learned video deinterlacing and demosaicing have…

This paper presents an unsupervised multi-modal learning system that learns associative representation from two input modalities, or channels, such that input on one channel will correctly generate the associated response at the other and…

In this paper, we introduce an Adaptive Graph Signal Processing with Dynamic Semantic Alignment (AGSP DSA) framework to perform robust multimodal data fusion over heterogeneous sources, including text, audio, and images. The requested…

CNNs and Self attention have achieved great success in multimedia applications for dynamic association learning of self-attention and convolution in image restoration. However, CNNs have at least two shortcomings: 1) limited receptive…

Semi-supervised domain adaptation (SSDA) adapts a learner to a new domain by effectively utilizing source domain data and a few labeled target samples. It is a practical yet under-investigated research topic. In this paper, we analyze the…

While supervised learning has achieved remarkable success, obtaining large-scale labeled datasets in biomedical imaging is often impractical due to high costs and the time-consuming annotations required from radiologists. Semi-supervised…

Deep learning has become the state of the art approach in many machine learning problems such as classification. It has recently been shown that deep learning is highly vulnerable to adversarial perturbations. Taking the camera systems of…

In this paper, we propose a new adapter network for adapting a pre-trained deep neural network to a target domain with minimal computation. The proposed model, unidirectional thin adapter (UDTA), helps the classifier adapt to new data by…

This paper introduces DNCASR, a novel end-to-end trainable system designed for joint neural speaker clustering and automatic speech recognition (ASR), enabling speaker-attributed transcription of long multi-party meetings. DNCASR uses two…

Model ensembles have long been a cornerstone for improving generalization and robustness in deep learning. However, their effectiveness often comes at the cost of substantial computational overhead. To address this issue, state-of-the-art…

Adapters have become a widely adopted strategy for efficient fine-tuning of large pretrained models, particularly in resource-constrained settings. However, their performance under extreme data scarcity, common in medical imaging due to…

Object recognition is a key enabler across industry and defense. As technology changes, algorithms must keep pace with new requirements and data. New modalities and higher resolution sensors should allow for increased algorithm robustness.…

Improper or erroneous labelling can pose a hindrance to reliable generalization for supervised learning. This can have negative consequences, especially for critical fields such as healthcare. We propose an effective new approach for…