Liang Bai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Liang Bai has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Tianyuan Yu
Laboratory for Big Data and Decision, National University of Defense Technology, Changsha, China
3 shared publications - Li Liu
National University of Defense Technology (NUDT)
2 shared publications - Yirun Ruan
Laboratory for Big Data and Decision, National University of Defense Technology, Changsha, China
2 shared publications - Aiming Zhang
Laboratory for Big Data and Decision, National University of Defense Technology, Changsha, China
1 shared publication - Changchong Sheng
National Key Laboratory of Electromagnetic Energy, Naval University of Engineering, Wuhan, China
1 shared publication - Chenping Hou
National University of Defense Technology, Changsha, Hunan, China
1 shared publication
Latest Publications
- 19 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 6002-6015
COLA: Context-Aware Language-Driven Test-Time Adaptation
Test-time adaptation (TTA) has gained increasing popularity due to its efficacy in addressing “distribution shift” issue while simultaneously protecting data privacy. However, most prior methods assume that a paired source domain model and target domain sharing the same label space coexist, heavily limiting their applicability. In this paper, we investigate a more general source model capable of adaptation to multiple target domains without needing shared labels. This is achieved by using a pre-trained vision-language model (VLM), e.g., CLIP, that can recognize images through matching with class descriptions. While the zero-shot performance of VLMs is impressive, they struggle to effectively capture the distinctive attributes of a target domain. To that end, we propose a novel method – Context-aware Language-driven TTA (COLA). The proposed method incorporates a lightweight context-aware module that consists of three key components: a task-aware adapter, a context-aware unit, and a residual connection unit for exploring task-specific knowledge, domain-specific knowledge from the VLM and prior knowledge of the VLM, respectively. It is worth noting that the context-aware module can be seamlessly integrated into a frozen VLM, ensuring both minimal effort and parameter efficiency. Additionally, we introduce a Class-Balanced Pseudo-labeling (CBPL) strategy to mitigate the adverse effects caused by class imbalance. We demonstrate the effectiveness of our method not only in TTA scenarios but also in class generalisation tasks. The source code is available at https://github.com/NUDT-Bai-Group/COLA-TTA.
- 19 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 6002-6015
COLA: Context-Aware Language-Driven Test-Time Adaptation
Test-time adaptation (TTA) has gained increasing popularity due to its efficacy in addressing “distribution shift” issue while simultaneously protecting data privacy. However, most prior methods assume that a paired source domain model and target domain sharing the same label space coexist, heavily limiting their applicability. In this paper, we investigate a more general source model capable of adaptation to multiple target domains without needing shared labels. This is achieved by using a pre-trained vision-language model (VLM), e.g., CLIP, that can recognize images through matching with class descriptions. While the zero-shot performance of VLMs is impressive, they struggle to effectively capture the distinctive attributes of a target domain. To that end, we propose a novel method – Context-aware Language-driven TTA (COLA). The proposed method incorporates a lightweight context-aware module that consists of three key components: a task-aware adapter, a context-aware unit, and a residual connection unit for exploring task-specific knowledge, domain-specific knowledge from the VLM and prior knowledge of the VLM, respectively. It is worth noting that the context-aware module can be seamlessly integrated into a frozen VLM, ensuring both minimal effort and parameter efficiency. Additionally, we introduce a Class-Balanced Pseudo-labeling (CBPL) strategy to mitigate the adverse effects caused by class imbalance. We demonstrate the effectiveness of our method not only in TTA scenarios but also in class generalisation tasks. The source code is available at https://github.com/NUDT-Bai-Group/COLA-TTA.
- 19 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-19
Heterogeneous Binary Pixel Difference Networks for Remote Sensing Object Detection
Recent research in remote-sensing object detection (RSOD) has significantly advanced the development of vision foundation models. However, deploying these models on resource-constrained edge devices is challenging due to their high computational demands. Binarized detectors utilize binary neural networks (BNNs) to achieve extreme compression by quantizing weights and activations to +1 or -1, which have been extensively studied for generic object detection tasks. In remote sensing images, the objects of interest typically exhibit weak responses, and the images often contain numerous unique local areas. Feature binarization in these images can lead to substantial loss of object contrast and scale prior information, which exacerbates performance issues, particularly for small objects, resulting in significant performance degradation. To address these challenges, we propose a novel binarized detector for RSOD named the heterogeneous binary pixel difference network (HBiPiDiNet). Initially, we developed a binary pixel difference convolution (BiPDC) that integrates local binary patterns (LBP) to capture local contrast information with traditional binary convolution, thereby enhancing the representation of small objects. Subsequently, we constructed heterogeneous kernel fusion convolution blocks (HKFCB) based on BiPDC and standard binary convolution. The HKFCB comprises multiple BiPDCs at different scales, effectively representing BiPDC under multiscale local binary patterns (LBP) and multiscale binary convolutions. Extensive experiments demonstrate that our proposed method significantly enhances the performance of state-of-the-art binary detection methods across three remote-sensing datasets: AI-TOD, VisDrone2019, and DIOR. We have released our code and models at https://github.com/yuhua666/HBiPiDiNet/tree/main.
- 19 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-19
Heterogeneous Binary Pixel Difference Networks for Remote Sensing Object Detection
Recent research in remote-sensing object detection (RSOD) has significantly advanced the development of vision foundation models. However, deploying these models on resource-constrained edge devices is challenging due to their high computational demands. Binarized detectors utilize binary neural networks (BNNs) to achieve extreme compression by quantizing weights and activations to +1 or -1, which have been extensively studied for generic object detection tasks. In remote sensing images, the objects of interest typically exhibit weak responses, and the images often contain numerous unique local areas. Feature binarization in these images can lead to substantial loss of object contrast and scale prior information, which exacerbates performance issues, particularly for small objects, resulting in significant performance degradation. To address these challenges, we propose a novel binarized detector for RSOD named the heterogeneous binary pixel difference network (HBiPiDiNet). Initially, we developed a binary pixel difference convolution (BiPDC) that integrates local binary patterns (LBP) to capture local contrast information with traditional binary convolution, thereby enhancing the representation of small objects. Subsequently, we constructed heterogeneous kernel fusion convolution blocks (HKFCB) based on BiPDC and standard binary convolution. The HKFCB comprises multiple BiPDCs at different scales, effectively representing BiPDC under multiscale local binary patterns (LBP) and multiscale binary convolutions. Extensive experiments demonstrate that our proposed method significantly enhances the performance of state-of-the-art binary detection methods across three remote-sensing datasets: AI-TOD, VisDrone2019, and DIOR. We have released our code and models at https://github.com/yuhua666/HBiPiDiNet/tree/main.
- Open Access
- 14 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 167834-167844
Consistent Augmentation Learning for Generalizing CLIP to Unseen Domains
Domain generalization (DG) is a challenging transfer learning task focused on learning invariant knowledge from limited source domains, thereby enhancing generalization to the out-of-distribution data in unseen domains. Recent advancements in vision-language models (VLMs) have notably boosted the capability of deep models to generalize across unseen target domains. Models like CLIP have recently demonstrated promising zero-shot transferability by image-text matching, making it a robust tool for domain generalization. In this work, we explore generic methods to leverage CLIP for DG tasks in image classification. Specifically, we propose Consistent Augmentation Learning (CAL), a simple and effective extension of CLIP within the domain generalization framework. In the training phase, CAL introduces a new fine-tuning method called Consistent Augmentation Fine-Tuning (CAFT), which leverages feature consistency across different augmented views of the same sample. In the inference phase, CAL introduces a new Test-Time Augmentation strategy called Entropy-guided Test-time Augmentation (ETTA), which enhances the prediction confidence and robustness of the fine-tuned CLIP model by leveraging information extracted from test images. Extensive experiments have shown that CAL is successful in extracting domain-invariant features, thereby greatly enhancing the generalization capability of CLIP and achieving the state-of-the-art performance across three challenging benchmarks: Domainbed generalization, ImageNet classification, and Base-to-New generalization.
- 14 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 167834-167844
Open AccessConsistent Augmentation Learning for Generalizing CLIP to Unseen Domains
Domain generalization (DG) is a challenging transfer learning task focused on learning invariant knowledge from limited source domains, thereby enhancing generalization to the out-of-distribution data in unseen domains. Recent advancements in vision-language models (VLMs) have notably boosted the capability of deep models to generalize across unseen target domains. Models like CLIP have recently demonstrated promising zero-shot transferability by image-text matching, making it a robust tool for domain generalization. In this work, we explore generic methods to leverage CLIP for DG tasks in image classification. Specifically, we propose Consistent Augmentation Learning (CAL), a simple and effective extension of CLIP within the domain generalization framework. In the training phase, CAL introduces a new fine-tuning method called Consistent Augmentation Fine-Tuning (CAFT), which leverages feature consistency across different augmented views of the same sample. In the inference phase, CAL introduces a new Test-Time Augmentation strategy called Entropy-guided Test-time Augmentation (ETTA), which enhances the prediction confidence and robustness of the fine-tuned CLIP model by leveraging information extracted from test images. Extensive experiments have shown that CAL is successful in extracting domain-invariant features, thereby greatly enhancing the generalization capability of CLIP and achieving the state-of-the-art performance across three challenging benchmarks: Domainbed generalization, ImageNet classification, and Base-to-New generalization.
- Top Cited Papers
- 13 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (9) , 6001-6022
Deep Learning for Visual Speech Analysis: A Survey
Visual speech, referring to the visual domain of speech, has attracted increasing attention due to its wide applications, such as public security, medical treatment, military defense, and film entertainment. As a powerful AI strategy, deep learning techniques have extensively promoted the development of visual speech learning. Over the past five years, numerous deep learning based methods have been proposed to address various problems in this area, especially automatic visual speech recognition and generation. To push forward future research on visual speech, this paper will present a comprehensive review of recent progress in deep learning methods on visual speech analysis. We cover different aspects of visual speech, including fundamental problems, challenges, benchmark datasets, a taxonomy of existing methods, and state-of-the-art performance. Besides, we also identify gaps in current research and discuss inspiring future research directions.
- 13 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (9) , 6001-6022
Top Cited PapersDeep Learning for Visual Speech Analysis: A Survey
Visual speech, referring to the visual domain of speech, has attracted increasing attention due to its wide applications, such as public security, medical treatment, military defense, and film entertainment. As a powerful AI strategy, deep learning techniques have extensively promoted the development of visual speech learning. Over the past five years, numerous deep learning based methods have been proposed to address various problems in this area, especially automatic visual speech recognition and generation. To push forward future research on visual speech, this paper will present a comprehensive review of recent progress in deep learning methods on visual speech analysis. We cover different aspects of visual speech, including fundamental problems, challenges, benchmark datasets, a taxonomy of existing methods, and state-of-the-art performance. Besides, we also identify gaps in current research and discuss inspiring future research directions.
- 20 April 2023
- Published by Springer Nature in Neural Processing Letters
- Vol. 55 (6) , 7649-7666
Generalized Few-Shot Classification with Knowledge Graph
- 20 April 2023
- Published by Springer Nature in Neural Processing Letters
- Vol. 55 (6) , 7649-7666
Generalized Few-Shot Classification with Knowledge Graph