2023-04-05 更新
2023-04-05 更新
Online Distillation with Continual Learning for Cyclic Domain Shifts
Authors:Joachim Houyon, Anthony Cioppa, Yasir Ghunaim, Motasem Alfarra, Anaïs Halin, Maxim Henry, Bernard Ghanem, Marc Van Droogenbroeck
In recent years, online distillation has emerged as a powerful technique for adapting real-time deep neural networks on the fly using a slow, but accurate teacher model. However, a major challenge in online distillation is catastrophic forgetting when the domain shifts, which occurs when the student model is updated with data from the new domain and forgets previously learned knowledge. In this paper, we propose a solution to this issue by leveraging the power of continual learning methods to reduce the impact of domain shifts. Specifically, we integrate several state-of-the-art continual learning methods in the context of online distillation and demonstrate their effectiveness in reducing catastrophic forgetting. Furthermore, we provide a detailed analysis of our proposed solution in the case of cyclic domain shifts. Our experimental results demonstrate the efficacy of our approach in improving the robustness and accuracy of online distillation, with potential applications in domains such as video surveillance or autonomous driving. Overall, our work represents an important step forward in the field of online distillation and continual learning, with the potential to significantly impact real-world applications.
PDF Accepted at the 4th Workshop on Continual Learning in Computer Vision (CVPR 2023)
点此查看论文截图
A Unified Contrastive Transfer Framework with Propagation Structure for Boosting Low-Resource Rumor Detection
Authors:Hongzhan Lin, Jing Ma, Ruichao Yang, Zhiwei Yang, Mingfei Cheng
The truth is significantly hampered by massive rumors that spread along with breaking news or popular topics. Since there is sufficient corpus gathered from the same domain for model training, existing rumor detection algorithms show promising performance on yesterday’s news. However, due to a lack of training data and prior expert knowledge, they are poor at spotting rumors concerning unforeseen events, especially those propagated in different languages (i.e., low-resource regimes). In this paper, we propose a unified contrastive transfer framework to detect rumors by adapting the features learned from well-resourced rumor data to that of the low-resourced. More specifically, we first represent rumor circulated on social media as an undirected topology, and then train a Multi-scale Graph Convolutional Network via a unified contrastive paradigm. Our model explicitly breaks the barriers of the domain and/or language issues, via language alignment and a novel domain-adaptive contrastive learning mechanism. To enhance the representation learning from a small set of target events, we reveal that rumor-indicative signal is closely correlated with the uniformity of the distribution of these events. We design a target-wise contrastive training mechanism with three data augmentation strategies, capable of unifying the representations by distinguishing target events. Extensive experiments conducted on four low-resource datasets collected from real-world microblog platforms demonstrate that our framework achieves much better performance than state-of-the-art methods and exhibits a superior capacity for detecting rumors at early stages.
PDF arXiv admin note: text overlap with arXiv:2204.08143
点此查看论文截图
Multimodal Neural Processes for Uncertainty Estimation
Authors:Myong Chol Jung, He Zhao, Joanna Dipnall, Belinda Gabbe, Lan Du
Neural processes (NPs) have brought the representation power of parametric deep neural networks and the reliable uncertainty estimation of non-parametric Gaussian processes together. Although recent development of NPs has shown success in both regression and classification, how to adapt NPs to multimodal data has not be carefully studied. For the first time, we propose a new model of NP family for multimodal uncertainty estimation, namely Multimodal Neural Processes. In a holistic and principled way, we develop a dynamic context memory updated by the classification error, a multimodal Bayesian aggregation mechanism to aggregate multimodal representations, and a new attention mechanism for calibrated predictions. In extensive empirical evaluation, our method achieves the state-of-the-art multimodal uncertainty estimation performance, showing its appealing ability of being robust against noisy samples and reliable in out-of-domain detection.
PDF
点此查看论文截图
Summary of ChatGPT/GPT-4 Research and Perspective Towards the Future of Large Language Models
Authors:Yiheng Liu, Tianle Han, Siyuan Ma, Jiayue Zhang, Yuanyuan Yang, Jiaming Tian, Hao He, Antong Li, Mengshen He, Zhengliang Liu, Zihao Wu, Dajiang Zhu, Xiang Li, Ning Qiang, Dingang Shen, Tianming Liu, Bao Ge
This paper presents a comprehensive survey of ChatGPT and GPT-4, state-of-the-art large language models (LLM) from the GPT series, and their prospective applications across diverse domains. Indeed, key innovations such as large-scale pre-training that captures knowledge across the entire world wide web, instruction fine-tuning and Reinforcement Learning from Human Feedback (RLHF) have played significant roles in enhancing LLMs’ adaptability and performance. We performed an in-depth analysis of 194 relevant papers on arXiv, encompassing trend analysis, word cloud representation, and distribution analysis across various application domains. The findings reveal a significant and increasing interest in ChatGPT/GPT-4 research, predominantly centered on direct natural language processing applications, while also demonstrating considerable potential in areas ranging from education and history to mathematics, medicine, and physics. This study endeavors to furnish insights into ChatGPT’s capabilities, potential implications, ethical concerns, and offer direction for future advancements in this field.
PDF
点此查看论文截图
PODIA-3D: Domain Adaptation of 3D Generative Model Across Large Domain Gap Using Pose-Preserved Text-to-Image Diffusion
Authors:Gwanghyun Kim, Ji Ha Jang, Se Young Chun
Recently, significant advancements have been made in 3D generative models, however training these models across diverse domains is challenging and requires an huge amount of training data and knowledge of pose distribution. Text-guided domain adaptation methods have allowed the generator to be adapted to the target domains using text prompts, thereby obviating the need for assembling numerous data. Recently, DATID-3D presents impressive quality of samples in text-guided domain, preserving diversity in text by leveraging text-to-image diffusion. However, adapting 3D generators to domains with significant domain gaps from the source domain still remains challenging due to issues in current text-to-image diffusion models as following: 1) shape-pose trade-off in diffusion-based translation, 2) pose bias, and 3) instance bias in the target domain, resulting in inferior 3D shapes, low text-image correspondence, and low intra-domain diversity in the generated samples. To address these issues, we propose a novel pipeline called PODIA-3D, which uses pose-preserved text-to-image diffusion-based domain adaptation for 3D generative models. We construct a pose-preserved text-to-image diffusion model that allows the use of extremely high-level noise for significant domain changes. We also propose specialized-to-general sampling strategies to improve the details of the generated samples. Moreover, to overcome the instance bias, we introduce a text-guided debiasing method that improves intra-domain diversity. Consequently, our method successfully adapts 3D generators across significant domain gaps. Our qualitative results and user study demonstrates that our approach outperforms existing 3D text-guided domain adaptation methods in terms of text-image correspondence, realism, diversity of rendered images, and sense of depth of 3D shapes in the generated samples
PDF Project page: https://gwang-kim.github.io/podia_3d/
点此查看论文截图
Strong Baselines for Parameter Efficient Few-Shot Fine-tuning
Authors:Samyadeep Basu, Daniela Massiceti, Shell Xu Hu, Soheil Feizi
Few-shot classification (FSC) entails learning novel classes given only a few examples per class after a pre-training (or meta-training) phase on a set of base classes. Recent works have shown that simply fine-tuning a pre-trained Vision Transformer (ViT) on new test classes is a strong approach for FSC. Fine-tuning ViTs, however, is expensive in time, compute and storage. This has motivated the design of parameter efficient fine-tuning (PEFT) methods which fine-tune only a fraction of the Transformer’s parameters. While these methods have shown promise, inconsistencies in experimental conditions make it difficult to disentangle their advantage from other experimental factors including the feature extractor architecture, pre-trained initialization and fine-tuning algorithm, amongst others. In our paper, we conduct a large-scale, experimentally consistent, empirical analysis to study PEFTs for few-shot image classification. Through a battery of over 1.8k controlled experiments on large-scale few-shot benchmarks including Meta-Dataset (MD) and ORBIT, we uncover novel insights on PEFTs that cast light on their efficacy in fine-tuning ViTs for few-shot classification. Through our controlled empirical study, we have two main findings: (i) Fine-tuning just the LayerNorm parameters (which we call LN-Tune) during few-shot adaptation is an extremely strong baseline across ViTs pre-trained with both self-supervised and supervised objectives, (ii) For self-supervised ViTs, we find that simply learning a set of scaling parameters for each attention matrix (which we call AttnScale) along with a domain-residual adapter (DRA) module leads to state-of-the-art performance (while being $\sim!$ 9$\times$ more parameter-efficient) on MD. Our extensive empirical findings set strong baselines and call for rethinking the current design of PEFT methods for FSC.
PDF
点此查看论文截图