检索结果-内蒙古大学图书馆

Proposal Feature Learning Using Proposal Relations for Weakly Supervised Object Detection

学校读者我要写书评

暂无评论

Proposal Feature Learning Using Proposal Relations for Weakl...

IEEE International Conference on Multimedia and Expo (ICME)

作者： Zhaofei Wang Weijia Zhang Min-Ling Zhang School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China School of Information and Physical Sciences The University of Newcastle NSW Australia

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Weakly Supervised Object Detection (WSOD) trains detectors using only image-level annotations. Most existing WSOD models are based on pre-computed proposals and do not fully explore the relations of proposals. In this work, we address this limitation by proposing two approaches of Proposal Feature Learning for WSOD (PFL-WSOD), which effectively capture intra-proposal relations and inter-proposal relations respectively, thus improving proposal representation. To extract intra-proposal relations, we propose to utilize Self-Attention on Single Proposal for capturing relations inside each proposal. For inter-proposal relations, we propose Salient Region Banks by capturing a unique type of inter-proposal relation called deep inclusion, which significantly improves proposal representation when used in synergy with contrastive learning. Experimental results on benchmarks demonstrate the effectiveness of our methods.

关键词： Representation learning Annotations Object detection Contrastive learning Detectors Benchmark testing Feature extraction

Improving Scene Text Image Super-resolution via Dual Prior Modulation network

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhu, Shipeng Zhao, Zuoyan Fang, Pengfei Xue, Hui School of Computer Science and Engineering Southeast University Nanjing210096 China MOE Key Laboratory of Computer Network and Information Integration Southeast University China

Scene text image super-resolution (STISR) aims to simultaneously increase the resolution and legibility of the text images, and the resulting images will significantly affect the performance of downstream tasks. Although numerous progress has been made, existing approaches raise two crucial issues: (1) They neglect the global structure of the text, which bounds the semantic determinism of the scene text. (2) The priors, e.g., text prior or stroke prior, employed in existing works, are extracted from pre-trained text recognizers. That said, such priors suffer from the domain gap including low resolution and blurriness caused by poor imaging conditions, leading to incorrect guidance. Our work addresses these gaps and proposes a plug-and-play module dubbed Dual Prior Modulation network (DPMN), which leverages dual image-level priors to bring performance gain over existing approaches. Specifically, two types of prior-guided refinement modules, each using the text mask or graphic recognition result of the low-quality SR image from the preceding layer, are designed to improve the structural clarity and semantic accuracy of the text, respectively. The following attention mechanism hence modulates two quality-enhanced images to attain a superior SR result. Extensive experiments validate that our method improves the image quality and boosts the performance of downstream tasks over five typical approaches on the benchmark. Substantial visualizations and ablation studies demonstrate the advantages of the proposed DPMN. Code is available at: https://***/jdfxzzy/DPMN. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

Partial multi-label learning with probabilistic graphical disambiguation 23

学校读者我要写书评

暂无评论

Partial multi-label learning with probabilistic graphical di...

Proceedings of the 37th International Conference on Neural information Processing Systems

作者： Jun-Yi Hang Min-Ling Zhang School of Computer Science and Engineering Southeast University Nanjing China and Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education China

In partial multi-label learning (PML), each training example is associated with a set of candidate labels, among which only some labels are valid. As a common strategy to tackle PML problem, disambiguation aims to recover the ground-truth labeling information from such inaccurate annotations. However, existing approaches mainly rely on heuristics or ad-hoc rules to disambiguate candidate labels, which may not be universal enough in complicated real-world scenarios. To provide a principled way for disambiguation, we make a first attempt to explore the probabilistic graphical model for PML problem, where a directed graph is tailored to infer latent ground-truth labeling information from the generative process of partial multi-label data. Under the framework of stochastic gradient variational Bayes, a unified variational lower bound is derived for this graphical model, which is further relaxed probabilistically so that the desired prediction model can be induced with simultaneously identified ground-truth labeling information. Comprehensive experiments on multiple synthetic and real-world data sets show that our approach outperforms the state-of-the-art counterparts.

关键词：

Multi-Instance Partial-Label Learning with Margin Adjustment

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Tang, Wei Yang, Yin-Fang Wang, Zhaofei Zhang, Weijia Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China School of Information and Physical Sciences The University of Newcastle CallaghanNSW2308 Australia

Multi-instance partial-label learning (MIPL) is an emerging learning framework where each training sample is represented as a multi-instance bag associated with a candidate label set. Existing MIPL algorithms often overlook the margins for attention scores and predicted probabilities, leading to suboptimal generalization performance. A critical issue with these algorithms is that the highest prediction probability of the classifier may appear on a non-candidate label. In this paper, we propose an algorithm named MIPLMA, i.e., Multi-Instance Partial-Label learning with Margin Adjustment, which adjusts the margins for attention scores and predicted probabilities. We introduce a margin-aware attention mechanism to dynamically adjust the margins for attention scores and propose a margin distribution loss to constrain the margins between the predicted probabilities on candidate and non-candidate label sets. Experimental results demonstrate the superior performance of MIPLMA over existing MIPL algorithms, as well as other well-established multi-instance learning algorithms and partial-label learning algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

学校读者我要写书评

暂无评论

2021 IEEE International Conference on Artificial Intelligence and Industrial Design, AIID 2021

作者： Changhu, Cheng Peng, Yang School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Southeast University Nanjing China

ISBN: (纸本)9780738110837

Few-shot learning aims to build a classification model by training a small amount of labeled sample data, which can be well adapted to new domains. The key point of few-shot learning is that a small amount of sample data cannot reflect the true data distribution. Training on a small amount of sample data will lead to over-fitting of the deep neural network model. The differences between different categories are ignored when using similarity measures for classification. This paper proposes a novel few-shot learning method based on similarity-difference relation network, which uses shallow wide residual network to extract the features of the training dataset and fuses them into a category prototype. Meanwhile, SDRN pays attention to the characterization of similarities and differences between positive and negative samples. This paper verifies the effectiveness of the similarity-difference relational network on the Mini-ImageNet and Tiered-ImageNet datasets. The experimental results show that the similarity-difference two-way relational network further improves image classification accuracy in the few-shot learning task. © 2021 IEEE.

关键词： Deep neural networks

Learning label shift correction for test-agnostic long-tailed recognition 24

学校读者我要写书评

暂无评论

Learning label shift correction for test-agnostic long-taile...

Proceedings of the 41st International Conference on Machine Learning

作者： Tong Wei Zhen Mao Zi-Hao Zhou Yuanyu Wan Min-Ling Zhang School of Computer Science and Engineering Southeast University Nanjing China and Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education China School of Software Technology Zhejiang University Ningbo China

Long-tail learning primarily focuses on mitigating the label distribution shift between longtailed training data and uniformly distributed test data. However, in real-world applications, we often encounter a more intricate challenge where the test label distribution is agnostic. To address this problem, we first theoretically establish the substantial potential for reducing the generalization error if we can precisely estimate the test label distribution. Motivated by the theoretical insight, we introduce a simple yet effective solution called label shift correction (LSC). LSC estimates the test label distribution within the proposed framework of generalized black box shift estimation, and adjusts the predictions from a pre-trained model to align with the test distribution. Theoretical analyses confirm that accurate estimation of test label distribution can effectively reduce the generalization error. Extensive experimental results demonstrate that our method significantly outperforms previous state-of-the-art approaches, especially when confronted with non-uniform test label distribution. Notably, the proposed method is general and complements existing longtail learning approaches, consistently improving their performance. The source code is available at https://***/Stomach-ache/label-shift-correction.

关键词：

EAT: Towards Long-Tailed Out-of-Distribution Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wei, Tong Wang, Bo-Lin Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China

Despite recent advancements in out-of-distribution (OOD) detection, most current studies assume a class-balanced in-distribution training dataset, which is rarely the case in real-world scenarios. This paper addresses the challenging task of long-tailed OOD detection, where the in-distribution data follows a long-tailed class distribution. The main difficulty lies in distinguishing OOD data from samples belonging to the tail classes, as the ability of a classifier to detect OOD instances is not strongly correlated with its accuracy on the in-distribution classes. To overcome this issue, we propose two simple ideas: (1) Expanding the in-distribution class space by introducing multiple abstention classes. This approach allows us to build a detector with clear decision boundaries by training on OOD data using virtual labels. (2) Augmenting the context-limited tail classes by overlaying images onto the context-rich OOD data. This technique encourages the model to pay more attention to the discriminative features of the tail classes. We provide a clue for separating in-distribution and OOD data by analyzing gradient noise. Through extensive experiments, we demonstrate that our method outperforms the current state-of-the-art on various benchmark datasets. Moreover, our method can be used as an add-on for existing long-tail learning approaches, significantly enhancing their OOD detection performance. Code is available at: https://***/Stomachache/Long-Tailed-OOD-Detection. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

Fine-grainedly Synthesize Streaming Data Based On Large Language Models With Graph Structure Understanding For Data Sparsity

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Xin Zhang, Linhai Zhou, Deyu Xu, Guoqiang School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China SANY Group Co. Ltd China

Due to the sparsity of user data, sentiment analysis on user reviews in e-commerce platforms often suffers from poor performance, especially when faced with extremely sparse user data or long-tail labels. Recently, the emergence of LLMs has introduced new solutions to such problems by leveraging graph structures to generate supplementary user profiles. However, previous approaches have not fully utilized the graph understanding capabilities of LLMs and have struggled to adapt to complex streaming data environments. In this work, we propose a fine-grained streaming data synthesis framework that categorizes sparse users into three categories: Mid-tail, Long-tail, and Extreme. Specifically, we design LLMs to comprehensively understand three key graph elements in streaming data, including Local-global Graph Understanding, Second-Order Relationship Extraction, and Product Attribute Understanding, which enables the generation of high-quality synthetic data to effectively address sparsity across different categories. Experimental results on three real datasets demonstrate significant performance improvements, with synthesized data contributing to MSE reductions of 45.85%, 3.16%, and 62.21%, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Sentiment analysis

PE: A Poincare Explanation Method for Fast Text Hierarchy Generation

学校读者我要写书评

暂无评论

PE: A Poincare Explanation Method for Fast Text Hierarchy Ge...

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Chen, Qian Li, Dongyang He, Xiaofeng Li, Hongzhao Yi, Hongyu School of Computer Science and Technology East China Normal University Shanghai China NPPA Key Laboratory of Publishing Integration Development ECNUP Shanghai China Sichuan Caizi Software Information Network Co. Ltd. China

ISBN: (纸本)9798891761681

The black-box nature of deep learning models in NLP hinders their widespread *** research focus has shifted to Hierarchical Attribution (HA) for its ability to model feature *** works model non-contiguous combinations with a time-costly greedy search in Euclidean spaces, neglecting underlying linguistic information in feature *** this work, we introduce a novel method, namely Poincare Explanation (PE), for modeling feature interactions with hyperbolic spaces in a time efficient ***, we take building text hierarchies as finding spanning trees in hyperbolic *** we project the embeddings into hyperbolic spaces to elicit inherit semantic and syntax hierarchical *** we propose a simple yet effective strategy to calculate Shapley *** we build the the hierarchy with proving the constructing process in the projected space could be viewed as building a minimum spanning tree and introduce a time efficient building *** results demonstrate the effectiveness of our approach. © 2024 Association for Computational Linguistics.

关键词： Semantics