相关论文: Transfer Hashing with Privileged Information

In this work, we propose a coding strategy designed to enhance the throughput of hybrid ARQ (HARQ) transmissions over i.i.d. block-fading channels with the channel state information (CSI) unknown at the transmitter. We use a joint packet…

Generalising deep networks to novel domains without manual labels is challenging to deep learning. This problem is intrinsically difficult due to unpredictable changing nature of imagery data distributions in novel domains. Pre-learned…

Deep neural models have hitherto achieved significant performances on numerous classification tasks, but meanwhile require sufficient manually annotated data. Since it is extremely time-consuming and expensive to annotate adequate data for…

Unsupervised binary representation allows fast data retrieval without any annotations, enabling practical application like fast person re-identification and multimedia retrieval. It is argued that conflicts in binary space are one of the…

Multi-source transfer learning has been proven effective when within-target labeled data is scarce. Previous work focuses primarily on exploiting domain similarities and assumes that source domains are richly or at least comparably labeled.…

We propose an incremental strategy for learning hash functions with kernels for large-scale image search. Our method is based on a two-stage classification framework that treats binary codes as intermediate variables between the feature…

Maintaining the pair similarity relationship among originally high-dimensional data into a low-dimensional binary space is a popular strategy to learn binary codes. One simiple and intutive method is to utilize two identical code matrices…

Encrypted traffic classification (TC) methods must adapt to new protocols and extensions as well as to advancements in other machine learning fields. In this paper, we adopt a transfer learning setup best known from computer vision. We…

Learning using privileged information (LUPI) paradigm, which pioneered teacher-student interaction mechanism, makes the learning models use additional information in training stage. This paper is the first to propose an incremental learning…

Post-training quantization (PTQ) reduces the memory footprint of LLMs by quantizing weights to low-precision datatypes. Since LLM inference is usually memory-bound, PTQ methods can improve inference throughput. Recent state-of-the-art PTQ…

Aided target recognition (AiTR), the problem of classifying objects from sensor data, is an important problem with applications across industry and defense. While classification algorithms continue to improve, they often require more…

Deep hashing has shown promising performance in large-scale image retrieval. However, latent codes extracted by Deep Neural Networks (DNNs) will inevitably lose semantic information during the binarization process, which damages the…

Training a good deep learning model requires substantial data and computing resources, which makes the resulting neural model a valuable intellectual property. To prevent the neural network from being undesirably exploited, non-transferable…

Neural network quantization enables the deployment of models on edge devices. An essential requirement for their hardware efficiency is that the quantizers are hardware-friendly: uniform, symmetric, and with power-of-two thresholds. To the…

In order to learn quickly with few samples, meta-learning utilizes prior knowledge learned from previous tasks. However, a critical challenge in meta-learning is task uncertainty and heterogeneity, which can not be handled via globally…

Unlike ReLU, newer activation functions (like Swish, H-swish, Mish) that are frequently employed in popular efficient architectures can also result in negative activation values, with skewed positive and negative ranges. Typical learnable…

TalkBank is an online database that facilitates the sharing of linguistics research data. However, the existing TalkBank's API has limited data filtering and batch processing capabilities. To overcome these limitations, this paper…

In this paper, we propose feature-based federated transfer learning as a novel approach to improve communication efficiency by reducing the uplink payload by multiple orders of magnitude compared to that of existing approaches in federated…

Fast and accurate load parameters identification has great impact on the power systems operation and stability analysis. This paper proposes a novel transfer reinforcement learning based method to identify composite ZIP and induction motor…

Post-training quantization (PTQ) has evolved as a prominent solution for compressing complex models, which advocates a small calibration dataset and avoids end-to-end retraining. However, most existing PTQ methods employ block-wise…