Author name cluster

Baodi Liu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

1 author row

EAAI Journal 2026 Journal Article

Uncertainty-aware adaptive feature completion networks for incomplete multi-view learning

Wenzheng Wang
Sichao Fu
Jun Wang
Baodi Liu
Chaofeng Tang
Weihua Ou

Incomplete multi-view learning (IMVL) has emerged as a prominent research focus, aiming to address the challenge of missing views by effectively utilizing available information while exploiting the inherent consistency and complementarity across different views. Among the major approaches in this field, feature reconstruction-based IMVL methods restore the structural integrity of the original feature through complex generation strategies. However, such methods tend to overlook the accuracy of reconstructed features for missing views, as they lack mechanisms to assess their reliability. This limitation often results in inaccurately reconstructed features being displaced within the multi-view fusion space, where they fail to align with their true semantic regions and ultimately lead to misclassification. To address these issues, we propose an uncertainty-aware adaptive feature completion network (UAFCN) for incomplete multi-view learning. UAFCN incorporates a multi-view evidence fusion module that explicitly quantifies the confidence of features for missing views, thereby reducing the influence of inaccurate reconstructions during the fusion process. Furthermore, an uncertainty constraint loss is introduced to limit the misleading effects of conflicting supervisory signals, which enhances the reliability of classifier decision boundaries. The framework also includes an adaptive pseudo-label generation module, which dynamically selects high-confidence pseudo-labels across all views via adaptive thresholding to further mitigate category misclassification. Extensive experiments conducted on four benchmark datasets across two multi-view learning tasks and seven different missing rates consistently demonstrate that our proposed UAFCN outperforms existing IMVL methods.

Details DOI

AAAI Conference 2025 Conference Paper

Excluding the Impossible for Open Vocabulary Semantic Segmentation

Shiyuan Zhao
Baodi Liu
Yu Bai
Weifeng Liu
Shuai Shao

Open vocabulary semantic segmentation is a hot topic in research, focusing on segmenting and recognizing a diverse array of categories in varied environments, including those previously unknown, thereby holding significant practical value. Mainstream studies utilize the CLIP model for direct semantic segmentation (denoted as “forward methods”), which often struggles to represent underrepresented categories effectively. To address this issue, this paper introduces a novel approach Excluding the ImpossibLe Semantic Segmentation Network (ELSE-Net) based on reverse thinking. By excluding improbable categories, ELSE-Net narrows the selection range for forward methods, significantly reducing the risk of misclassification. In implementation, we initially draw on leading research to design the General Processing Block (GP-Block), which generates inclusion probabilities (the likelihood of belonging to a category) by using the CLIP model cooperated with a Mask Proposal Network (MPN). We then present the EXcluding the ImPossible Block (EXP-Block), which computes exclusion probabilities (the likelihood of not belonging to a category) through the CLIPN model and a custom-designed Reverse Retrieval Adapter (R2-Adapter). These exclusion probabilities are subsequently used to refine the inclusion probabilities, which are ultimately employed to annotate class-agnostic masks. Moreover, the core component of our EXP-Block is model-agnostic, enabling it to enhance the capabilities of existing frameworks. Experimental results from four benchmark datasets validate the effectiveness of ELSE-Net and underscore the seamless model-agnostic functionality of the EXP-Block.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Collaborative Consortium of Foundation Models for Open-World Few-Shot Learning

Shuai Shao
Yu Bai
Yan Wang
Baodi Liu
Bin Liu

Open-World Few-Shot Learning (OFSL) is a crucial research field dedicated to accurately identifying target samples in scenarios where data is limited and labels are unreliable. This research holds significant practical implications and is highly relevant to real-world applications. Recently, the advancements in foundation models like CLIP and DINO have showcased their robust representation capabilities even in resource-constrained settings with scarce data. This realization has brought about a transformative shift in focus, moving away from “building models from scratch” towards “effectively harnessing the potential of foundation models to extract pertinent prior knowledge suitable for OFSL and utilizing it sensibly”. Motivated by this perspective, we introduce the Collaborative Consortium of Foundation Models (CO3), which leverages CLIP, DINO, GPT-3, and DALL-E to collectively address the OFSL problem. CO3 comprises four key blocks: (1) the Label Correction Block (LC-Block) corrects unreliable labels, (2) the Data Augmentation Block (DA-Block) enhances available data, (3) the Feature Extraction Block (FE-Block) extracts multi-modal features, and (4) the Text-guided Fusion Adapter (TeFu-Adapter) integrates multiple features while mitigating the impact of noisy labels through semantic constraints. Only the adapter's parameters are adjustable, while the others remain frozen. Through collaboration among these foundation models, CO3 effectively unlocks their potential and unifies their capabilities to achieve state-of-the-art performance on multiple benchmark datasets. https://github.com/The-Shuai/CO3.

PDF Details DOI

EAAI Journal 2024 Journal Article

Ensembling Multi-View Discriminative Semantic Feature for Few-Shot Classification

Rui Xu
Shuai Shao
Lei Xing
Yanjiang Wang
Baodi Liu
Weifeng Liu

Few-Shot Classification (FSC) is an innovative application in machine learning. FSC consists of two main components: (1) Pre-training, where a feature extraction model (FEM) is trained using base data, and (2) Meta-testing, where the FEM is utilized to extract features from novel data (with categories different from the base data) for classification. Implementing FSC presents several challenges. For example, due to the cross-domain limitation (base data → novel data), the FEM may generate inappropriate features for new classes, leading to a Sample-Feature-Mismatch problem, and the corresponding feature is dubbed as Original-Shift-Feature (OSF). This paper proposes a generative method to construct Multi-View Discriminative Semantic Feature (MVDSF) to address the fundamental problem from the perspective of improving the discriminability of OSF. Typically, a linear projection is designed to transform OSF into a semantic space, generating Discriminative-Semantic-Features (DSF). By incorporating a reconstructive representation that is not solely reliant on the FEM, the influence of the Sample-Feature-Mismatch problem is reduced. Furthermore, considering that descriptions based on a single DSF tend to be one-sided, an attention mechanism is devised to fuse multi-view DSF, thereby improving the robustness of the proposed method. The effectiveness of MVDSF is evaluated on five benchmark few-shot learning datasets, where it achieves outstanding performance. This evaluation demonstrates the efficiency and performance of the proposed approach.

Details DOI

EAAI Journal 2024 Journal Article

Feedback-Irrelevant Mapping: An evaluation method for decoupled few-shot classification

Rui Xu
Shuai Shao
Lei Xing
Yanjiang Wang
Baodi Liu
Weifeng Liu

Few-shot classification (FSC) has become a significant area of research in recent years. A prevalent method in this field is the separation of feature representations from classifiers, involving two key steps: pre-training a feature extractor on a large base dataset and then applying it to novel, category-diverse data with limited samples. The ability of the pre-trained extractor to adapt to new data is vital for effective feature discrimination and classification performance. Traditional evaluation techniques, such as Class Activation Mapping (CAM), encounter challenges due to the lack of back-propagation when extracting features from novel classes. To address this, we present Feedback-Irrelevant Mapping (FIM), an approach based on dictionary learning theory. FIM utilizes channel weights in feature maps for both visualization and performance evaluation of the extractor on new data. We also introduce two quantitative metrics, Visual Localization Accuracy (VLA) and Visual Intersection Accuracy (VIA), to enable consistent assessments. Our experiments demonstrate that FIM not only preserves the model’s performance but can also improve it by approximately 0. 5%. When applied to various decoupled FSC frameworks, FIM effectively evaluates their capabilities. An important finding is that larger pre-trained models do not always equate to superior FSC results. For instance, models with a ResNet-12 backbone have shown to surpass others by at least 1. 7%.

Details DOI

IJCAI Conference 2023 Conference Paper

Annealing Genetic-based Preposition Substitution for Text Rubbish Example Generation

Chen Li
Xinghao Yang
Baodi Liu
Weifeng Liu
Honglong Chen

Modern Natural Language Processing (NLP) models expose under-sensitivity towards text rubbish examples. The text rubbish example is the heavily modified input text which is nonsensical to humans but does not change the model’s prediction. Prior work crafts rubbish examples by iteratively deleting words and determining the deletion order with beam search. However, the produced rubbish examples usually cause a reduction in model confidence and sometimes deliver human-readable text. To address these problems, we propose an Annealing Genetic based Preposition Substitution (AGPS) algorithm for text rubbish sample generation with two major merits. Firstly, the AGPS crafts rubbish text examples by substituting input words with meaningless prepositions instead of directly removing them, which brings less degradation to the model’s confidence. Secondly, we design an Annealing Genetic algorithm to optimize the word replacement priority, which allows the Genetic Algorithm (GA) to jump out the local optima with probabilities. This is significant in achieving better objectives, i. e. , a high word modification rate and a high model confidence. Experimental results on five popular datasets manifest the superiority of AGPS compared with the baseline and expose the fact: the NLP models can not really understand the semantics of sentences, as they give the same prediction with even higher confidence for the nonsensical preposition sequences.

PDF Details DOI

EAAI Journal 2023 Journal Article

CSN: Component supervised network for few-shot classification

Rui Xu
Shuai Shao
Lei Xing
Yujun Wei
Weifeng Liu
Baodi Liu
Yanjiang Wang

The few-shot classification (FSC) task aims to classify data with limited labeled examples across different categories. Typically, researchers pre-train a feature extractor using base data and use it to extract features from novel data for classification Notably, the novel set only has a few annotated samples and has non-overlapped categories from the base set, which leads to the fact that the pre-trained feature extractor cannot adapt to the novel data flawlessly. We dub this problem as Feature-Extractor-Maladaptive (FEM) problem. Starting from the root cause of this problem, this paper presents a new scheme called Component Supervised Network (CSN), to improve the performance of FSC. We believe that even though the categories in the base and novel sets are different, their sample components share similarities. For example, both cats and dogs contain leg and head components. These entity components are intra-class stable and have cross-category versatility, making them useful for generalization to new categories. However, finding common information among different categories is difficult in real-world scenarios, hindering the possibility of modeling based on this assumption. To overcome this, we first design a Dictionary-based Implicit-Component Generator (DICG) to mine common information of different sets; then construct an implicit-component-based auxiliary task to improve the adaptability of the feature extractor. We evaluated our CSN on three benchmark datasets (mini-ImageNet, tiered-ImageNet, and FC100) and achieved improvements of at least 0. 9% compared to classical methods, demonstrating the efficiency of our approach.

Details DOI