175 citations · 1.3k across the 83 of their papers we have counts for
84 papers
VTOS: Learning to Orchestrate Vision Tools by Co-Searching Solutions and Observers
Jinchao Ge, Lingqiao Liu, Shuwen Zhao +1
Vision foundation tools such as open-vocabulary detectors, segmentation models, and post-processing operators are powerful building blocks for computer vision, but their effectiven…
Domain Generalization via Rationale Invariance
Liang Chen, Yong Zhang, Yibing Song +2
This paper offers a new perspective to ease the challenge of domain generalization, which involves maintaining robust results even in unseen environments. Our design focuses on the…
Learning Conditional Attributes for Compositional Zero-Shot Learning
Qingsheng Wang, Lingqiao Liu, Chenchen Jing +4
Compositional Zero-Shot Learning (CZSL) aims to train models to recognize novel compositional concepts based on learned concepts such as attribute-object combinations. One of the c…
You Can Generate It Again: Data-to-Text Generation with Verification and Correction Prompting
Xuan Ren, Zeyu Zhang, Lingqiao Liu
Small language models like T5 excel in generating high-quality text for data-to-text tasks, offering adaptability and cost-efficiency compared to Large Language Models (LLMs). Howe…
Out-of-Distribution Generalization in Text Classification: Past, Present, and Future
Linyi Yang, Yaoxiao Song, Xuan Ren +6
Machine learning (ML) systems in natural language processing (NLP) face significant challenges in generalizing to out-of-distribution (OOD) data, where the test distribution differ…
Semantic Role Labeling Guided Out-of-distribution Detection
Jinan Zou, Maihao Guo, Yu Tian +5
Identifying unexpected domain-shifted instances in natural language processing is crucial in real-world applications. Previous works identify the out-of-distribution (OOD) instance…
The CLIP Model is Secretly an Image-to-Prompt Converter
Yuxuan Ding, Chunna Tian, Haoxuan Ding +1
The Stable Diffusion model is a prominent text-to-image generation model that relies on a text prompt as its input, which is encoded using the Contrastive Language-Image Pre-Traini…
Improved Test-Time Adaptation for Domain Generalization
Liang Chen, Yong Zhang, Yibing Song +2
The main challenge in domain generalization (DG) is to handle the distribution shift problem that lies between the training and test data. Recent studies suggest that test-time tra…
METransformer: Radiology Report Generation by Transformer with Multiple Learnable Expert Tokens
Zhanyu Wang, Lingqiao Liu, Lei Wang +1
In clinical scenarios, multi-specialist consultation could significantly benefit the diagnosis, especially for intricate cases. This inspires us to explore a "multi-expert joint di…
Revisiting Image Reconstruction for Semi-supervised Semantic Segmentation
Yuhao Lin, Haiming Xu, Lingqiao Liu +2
Autoencoding, which aims to reconstruct the input images through a bottleneck latent representation, is one of the classic feature representation learning strategies. It has been s…
Learning Common Rationale to Improve Self-Supervised Representation for Fine-Grained Visual Recognition Problems
Yangyang Shu, Anton van den Hengel, Lingqiao Liu
Self-supervised learning (SSL) strategies have demonstrated remarkable performance in various recognition tasks. However, both our preliminary investigation and recent studies sugg…
Generalizable Person Re-Identification via Viewpoint Alignment and Fusion
Bingliang Jiao, Lingqiao Liu, Liying Gao +5
In the current person Re-identification (ReID) methods, most domain generalization works focus on dealing with style differences between domains while largely ignoring unpredictabl…
Stock Market Prediction via Deep Learning Techniques: A Survey
Jinan Zou, Qingying Zhao, Yang Jiao +6
Existing surveys on stock market prediction often focus on traditional machine learning methods instead of deep learning methods. This motivates us to provide a structured and comp…
ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation
Ziqin Zhou, Bowen Zhang, Yinjie Lei +2
Recently, CLIP has been applied to pixel-level zero-shot learning tasks via a two-stage scheme. The general idea is to first generate class-agnostic region proposals and then feed…
Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization
Hai-Ming Xu, Lingqiao Liu, Qiuchen Bian +1
Semi-supervised semantic segmentation requires the model to effectively propagate the label information from limited annotated images to unlabeled ones. A challenge for such a per-…
Regularizing Neural Network Training via Identity-wise Discriminative Feature Suppression
Avraham Chapman, Lingqiao Liu
It is well-known that a deep neural network has a strong fitting capability and can easily achieve a low training error even with randomly assigned class labels. When the number of…
Pretrained Language Encoders are Natural Tagging Frameworks for Aspect Sentiment Triplet Extraction
Yanjie Gou, Yinjie Lei, Lingqiao Liu +3
Aspect Sentiment Triplet Extraction (ASTE) aims to extract the spans of aspect, opinion, and their sentiment relations as sentiment triplets. Existing works usually formulate the s…
Dual Decision Improves Open-Set Panoptic Segmentation
Hai-Ming Xu, Hao Chen, Lingqiao Liu +1
Open-set panoptic segmentation (OPS) problem is a new research direction aiming to perform segmentation for both \known classes and \unknown classes, i.e., the objects ("things") t…
Single-Stage Open-world Instance Segmentation with Cross-task Consistency Regularization
Xizhe Xue, Dongdong Yu, Lingqiao Liu +6
Open-World Instance Segmentation (OWIS) is an emerging research topic that aims to segment class-agnostic object instances from images. The mainstream approaches use a two-stage se…
Improving Fine-Grained Visual Recognition in Low Data Regimes via Self-Boosting Attention Mechanism
Yangyang Shu, Baosheng Yu, Haiming Xu +1
The challenge of fine-grained visual recognition often lies in discovering the key discriminative regions. While such regions can be automatically identified from a large-scale lab…
Don't Stop Learning: Towards Continual Learning for the CLIP Model
Yuxuan Ding, Lingqiao Liu, Chunna Tian +2
The Contrastive Language-Image Pre-training (CLIP) Model is a recently proposed large-scale pre-train model which attracts increasing attention in the computer vision community. Be…
Learning Resolution-Adaptive Representations for Cross-Resolution Person Re-Identification
Lin Wu, Lingqiao Liu, Yang Wang +3
The cross-resolution person re-identification (CRReID) problem aims to match low-resolution (LR) query identity images against high resolution (HR) gallery images. It is a challeng…
Astock: A New Dataset and Automated Stock Trading based on Stock-specific News Analyzing Model
Jinan Zou, Haiyao Cao, Lingqiao Liu +3
Natural Language Processing(NLP) demonstrates a great potential to support financial decision-making by analyzing the text from social media or news outlets. In this work, we build…
Progressive Class Semantic Matching for Semi-supervised Text Classification
Hai-Ming Xu, Lingqiao Liu, Ehsan Abbasnejad
Semi-supervised learning is a promising way to reduce the annotation cost for text-classification. Combining with pre-trained language models (PLMs), e.g., BERT, recent semi-superv…