In summary, we present the TSST task, a new benchmark for style transfer and emphasizing human-oriented evaluation, exploring and advancing the performance of current LLMs.
Large Language Models (LLMs) have demonstrated remarkable performance across various natural language tasks, marking significant strides towards general artificial intelligence.
In this study, we assess the effectiveness of utilizing OpenAI's ChatGPT to repair software specifications written in the Alloy declarative language.
Contrary to prior understanding of multi-armed bandits, our work reveals a surprising fact that the attackability of a specific CMAB instance also depends on whether the bandit instance is known or unknown to the adversary.
However, the presence of intrinsic noise and unmatched image-text pairs in web data can potentially affect the performance of representation learning.
Predicting stock prices presents a challenging research problem due to the inherent volatility and non-linear nature of the stock market.
This paper proposes DiffFit, a parameter-efficient strategy to fine-tune large pre-trained diffusion models that enable fast adaptation to new domains.
By adjusting the perturbation strength in the direction of the paths, our proposed augmentation is controllable and auditable.
In this work, the VQVAE focus on feature extraction and reconstruction of images, and the transformers fit the manifold and locate anomalies in the latent space.
To tackle this problem, we propose a multimodal relevance estimation network to capture the relevant semantics among modalities in multimodal emotions.
Unsupervised surface anomaly detection aims at discovering and localizing anomalous patterns using only anomaly-free training samples.
Specifically, MSFDPM consists of a side information feature extractor, a multi-scale feature domain patch matching module, and a multi-scale feature fusion network.
To make a step forward, this paper outlines an automatic annotation system called SsaA, working in a self-supervised learning manner, for continuously making the online visual inspection in the manufacturing automation scenarios.
Few-shot abstractive summarization has become a challenging task in natural language generation.
Specifically, we carefully design an end-to-end QG module on the basis of a classical QA module, which could help the model understand the context by asking inherently logical sub-questions, thus inheriting interpretability from the QD-based method and showing superior performance.
We found that our newly identified code smells are prevalent and impactful on the maintenance of DL systems from the developer's perspective.
To tackle this problem, we propose a method for dynamic texture recognition using PDV hashing and dictionary learning on multi-scale volume local binary pattern (PHD-MVLBP).
First, we theoretically show the transferability of robustness from an adversarially trained teacher model to a student model with the help of mixup augmentation.
In this paper, we study the Salient Object Ranking (SOR) task, which manages to assign a ranking order of each detected object according to its visual saliency.
Since the existing naive model parameter averaging method is contradictory to the learning paradigm of neural networks, we simulate the process of human cognition and communication, and analogy multi-party learning as a many-to-one knowledge sharing problem.
no code implementations • 19 Feb 2021 • Ruibin Bai, Xinan Chen, Zhi-Long Chen, Tianxiang Cui, Shuhui Gong, Wentao He, Xiaoping Jiang, Huan Jin, Jiahuan Jin, Graham Kendall, Jiawei Li, Zheng Lu, Jianfeng Ren, Paul Weng, Ning Xue, Huayan Zhang
The Vehicle Routing Problem (VRP) is one of the most intensively studied combinatorial optimisation problems for which numerous models and algorithms have been proposed.
Alongside the prevalence of mobile videos, the general public leans towards consuming vertical videos on hand-held devices.
Automated data augmentation has shown superior performance in image recognition.
In this way, features corresponding to background and occlusion can be suppressed for amodal mask estimation.
1 code implementation • 3 Nov 2020 • Bochao Wang, Hang Xu, Jiajin Zhang, Chen Chen, Xiaozhi Fang, Yixing Xu, Ning Kang, Lanqing Hong, Chenhan Jiang, Xinyue Cai, Jiawei Li, Fengwei Zhou, Yong Li, Zhicheng Liu, Xinghao Chen, Kai Han, Han Shu, Dehua Song, Yunhe Wang, Wei zhang, Chunjing Xu, Zhenguo Li, Wenzhi Liu, Tong Zhang
Automated Machine Learning (AutoML) is an important industrial solution for automatic discovery and deployment of the machine learning models.
To address this issue, we propose a novel regression tree, named James-Stein Regression Tree (JSRT) by considering global information from different nodes.
Interpretability and effectiveness are two essential and indispensable requirements for adopting machine learning methods in reality.
We combine the idea of ACAI and GANs, and propose a novel idea of alternative supervision method by applying supervised and unsupervised training alternatively to raise the accuracy of human organ structures in CT while keeping high quality.
How to obtain a model with good interpretability and performance has always been an important research topic.
Despite the impressive performance of random forests (RF), its theoretical properties have not been thoroughly understood.
Label estimation is an important component in an unsupervised person re-identification (re-ID) system.
Ranked #8 on Person Re-Identification on PRID2011