Related papers: What and Where: Learn to Plug Adapters via NAS for…
Network security is a critical concern in the digital landscape of today, with users demanding secure browsing experiences and protection of their personal data. This study explores the dynamic integration of Machine Learning (ML)…
Design exploration is an important step in the engineering design process. This involves the search for design/s that meet the specified design criteria and accomplishes the predefined objective/s. In recent years, machine learning-based…
Domain adaptation for semantic image segmentation is very necessary since manually labeling large datasets with pixel-level labels is expensive and time consuming. Existing domain adaptation techniques either work on limited datasets, or…
Information Retrieval (IR) practitioners often train separate ranking models for different domains (geographic regions, languages, stores, websites,...) as it is believed that exclusively training on in-domain data yields the best…
Deep Metric Learning (DML) plays an important role in modern computer vision research, where we learn a distance metric for a set of image representations. Recent DML techniques utilize the proxy to interact with the corresponding image…
Binary Neural Networks (BNNs) have gained extensive attention for their superior inferencing efficiency and compression ratio compared to traditional full-precision networks. However, due to the unique characteristics of BNNs, designing a…
We propose two methods to make unsupervised domain adaptation (UDA) more parameter efficient using adapters, small bottleneck layers interspersed with every layer of the large-scale pre-trained language model (PLM). The first method…
Neural architecture search (NAS) has recently reshaped our understanding on various vision tasks. Similar to the success of NAS in high-level vision tasks, it is possible to find a memory and computationally efficient solution via NAS with…
Due to the remarkable capabilities of powerful Large Language Models (LLMs) in effectively following instructions, there has been a growing number of assistants in the community to assist humans. Recently, significant progress has been made…
Cross-domain few-shot segmentation (CD-FSS) is proposed to pre-train the model on a source-domain dataset with sufficient samples, and then transfer the model to target-domain datasets where only a few samples are available for efficient…
Multimodal large language models (MLLMs) have shown remarkable capabilities in multimodal perception and understanding tasks. However, their effectiveness in specialized domains, such as remote sensing and medical imaging, remains limited.…
Neural Architecture Search (NAS) aims to automate the discovery of high-performing deep neural network architectures. Traditional objective-based NAS approaches typically optimize a certain performance metric (e.g., prediction accuracy),…
In astronomy, neural networks are often trained on simulation data with the prospect of being used on telescope observations. Unfortunately, training a model on simulation data and then applying it to instrument data leads to a substantial…
The traditional method for designing branch-line couplers involves a trial-and-error optimization process that requires multiple design iterations through electromagnetic (EM) simulations. Thus, it is extremely time consuming and labor…
Large language models fine-tuned via a two-stage pipeline (domain adaptation followed by instruction alignment) can exhibit non-trivial interference after adapter merging, including the re-emergence of explicit reasoning traces under strict…
Few-Shot Learning (FSL) is a topic of rapidly growing interest. Typically, in FSL a model is trained on a dataset consisting of many small tasks (meta-tasks) and learns to adapt to novel tasks that it will encounter during test time. This…
Neural architecture search (NAS) has become increasingly popular in the deep learning community recently, mainly because it can provide an opportunity to allow interested users without rich expertise to benefit from the success of deep…
Data association is a key step within the multi-object tracking pipeline that is notoriously challenging due to its combinatorial nature. A popular and general way to formulate data association is as the NP-hard multidimensional assignment…
We focus on bridging domain discrepancy in lane detection among different scenarios to greatly reduce extra annotation and re-training costs for autonomous driving. Critical factors hinder the performance improvement of cross-domain lane…
Parameter-efficient tuning (PET) methods such as LoRA, Adapter, and Visual Prompt Tuning (VPT) have found success in enabling adaptation to new domains by tuning small modules within a transformer model. However, the number of domains…