50 citations · 201 across the 17 of their papers we have counts for
19 papers
KUPAS MASTER: Distilling the Tacit Expertise of Master Practitioners into Agent-Ready Experience Corpora
Changmian Wang, Yuchao Ma, Xuchao Lu +13
Experienced professionals know more than just facts and conclusions. They know which cues matter, why a judgment is reasonable, and which action to take. Routine work records often…
RealCAD: Towards Real-World Image-to-CAD Reconstruction under Domain Shift and Parameter Bias
Yihe Sun, Ziyu Lu, Kaihua Tang +1
Reconstructing editable Computer-Aided Design (CAD) models from images is essential for downstream modification, manufacturing, and design reuse. However, existing image-to-CAD met…
AffordAny: Open-World 3D Affordance Grounding from Monocular RGB Images via Vision-Language-Guided Geometric Reasoning
Junqi Wu, Kaihua Tang, Xuanwen Chen +3
Open-world 3D affordance grounding requires localizing functional object parts in 3D given free-form language queries. Existing methods typically assume pre-built object-centric 3D…
Breaking the Horizontal Prior: From Long-Tailed Orientation Bias to Roll-Robust Monocular Depth Estimation
Kaihua Tang, Ziqing Xia, Xiaoxu Zheng +4
Despite recent advances in Monocular Depth Estimation, state-of-the-art depth foundation models remain vulnerable to robustness issues. Particularly, even slight camera rolls can r…
A Reconstruction-Based Framework for Caption Evaluation Beyond Reference Captions
Zhijiang Tang, Jiaxin Qi, Kaihua Tang +2
Image captioning is a primary task in vision--language research, yet assessing how faithfully a caption preserves image semantics without relying on reference captions remains unse…
RIRF: Reasoning Image Restoration Framework
Wending Yan, Rongkai Zhang, Kaihua Tang +2
Universal image restoration (UIR) aims to recover clean images from diverse and unknown degradations using a unified model. Existing UIR methods primarily focus on pixel reconstruc…
Scaling Test-Time Robustness of Vision-Language Models via Self-Critical Inference Framework
Kaihua Tang, Jiaxin Qi, Jinli Ou +2
The emergence of Large Language Models (LLMs) has driven rapid progress in multi-modal learning, particularly in the development of Large Vision-Language Models (LVLMs). However, e…
Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models
Beier Zhu, Kaihua Tang, Qianru Sun +1
Foundation models like CLIP allow zero-shot transfer on various tasks without additional training data. Yet, the zero-shot performance is less competitive than a fully supervised o…
Class Is Invariant to Context and Vice Versa: On Learning Invariance for Out-Of-Distribution Generalization
Jiaxin Qi, Kaihua Tang, Qianru Sun +2
Out-Of-Distribution generalization (OOD) is all about learning invariance against environmental changes. If the context in every class is evenly distributed, OOD would be trivial b…
Identifying Hard Noise in Long-Tailed Sample Distribution
Xuanyu Yi, Kaihua Tang, Xian-Sheng Hua +2
Conventional de-noising methods rely on the assumption that all samples are independent and identically distributed, so the resultant classifier, though disturbed by noise, can sti…
Invariant Feature Learning for Generalized Long-Tailed Classification
Kaihua Tang, Mingyuan Tao, Jiaxin Qi +2
Existing long-tailed classification (LT) methods only focus on tackling the class-wise imbalance that head classes have more samples than tail classes, but overlook the attribute-w…
Adversarial Visual Robustness by Causal Intervention
Kaihua Tang, Mingyuan Tao, Hanwang Zhang
Adversarial training is the de facto most promising defense against adversarial examples. Yet, its passive nature inevitably prevents it from being immune to unknown attackers. To…
Distilling Causal Effect of Data in Class-Incremental Learning
Xinting Hu, Kaihua Tang, Chunyan Miao +2
We propose a causal framework to explain the catastrophic forgetting in Class-Incremental Learning (CIL) and then derive a novel distillation method that is orthogonal to the exist…
Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect
Kaihua Tang, Jianqiang Huang, Hanwang Zhang
As the class size grows, maintaining a balanced dataset across many classes is challenging because the data are long-tailed in nature; it is even impossible when the sample-of-inte…
Counterfactual VQA: A Cause-Effect Look at Language Bias
Yulei Niu, Kaihua Tang, Hanwang Zhang +3
VQA models may tend to rely on language bias as a shortcut and thus fail to sufficiently learn the multi-modal knowledge from both vision and language. Recent debiasing methods pro…
Learning to Segment the Tail
Xinting Hu, Yi Jiang, Kaihua Tang +3
Real-world visual recognition requires handling the extreme sample imbalance in large-scale long-tailed data. We propose a "divide&conquer" strategy for the challenging LVIS task:…
Unbiased Scene Graph Generation from Biased Training
Kaihua Tang, Yulei Niu, Jianqiang Huang +2
Today's scene graph generation (SGG) task is still far from practical, mainly due to the severe training bias, e.g., collapsing diverse "human walk on / sit on / lay on beach" into…
Auto-Encoding Scene Graphs for Image Captioning
Xu Yang, Kaihua Tang, Hanwang Zhang +1
We propose Scene Graph Auto-Encoder (SGAE) that incorporates the language inductive bias into the encoder-decoder image captioning framework for more human-like captions. Intuitive…
Learning to Compose Dynamic Tree Structures for Visual Contexts
Kaihua Tang, Hanwang Zhang, Baoyuan Wu +2
We propose to compose dynamic tree structures that place the objects in an image into a visual context, helping visual reasoning tasks such as scene graph generation and visual Q&A…