18 citations · 69 across the 19 of their papers we have counts for
22 papers
Generative Distribution Distillation
Jiequan Cui, Beier Zhu, Qingshan Xu +6
In this paper, we formulate the knowledge distillation (KD) as a conditional generative problem and propose the \textit{Generative Distribution Distillation (GenDD)} framework. A n…
Project-Probe-Aggregate: Efficient Fine-Tuning for Group Robustness
Beier Zhu, Jiequan Cui, Hanwang Zhang +1
While image-text foundation models have succeeded across diverse downstream tasks, they still face challenges in the presence of spurious correlations between the input and label.…
Generalized Kullback-Leibler Divergence Loss
Jiequan Cui, Beier Zhu, Qingshan Xu +5
In this paper, we delve deeper into the Kullback-Leibler (KL) Divergence loss and mathematically prove that it is equivalent to the Decoupled Kullback-Leibler (DKL) Divergence loss…
LoRA of Change: Learning to Generate LoRA for the Editing Instruction from A Single Before-After Image Pair
Xue Song, Jiequan Cui, Hanwang Zhang +4
In this paper, we propose the LoRA of Change (LoC) framework for image editing with visual instructions, i.e., before-after image pairs. Compared to the ambiguities, insufficient s…
Pushing Rendering Boundaries: Hard Gaussian Splatting
Qingshan Xu, Jiequan Cui, Xuanyu Yi +4
3D Gaussian Splatting (3DGS) has demonstrated impressive Novel View Synthesis (NVS) results in a real-time rendering manner. During training, it relies heavily on the average magni…
Robust Fine-tuning of Zero-shot Models via Variance Reduction
Beier Zhu, Jiequan Cui, Hanwang Zhang
When fine-tuning zero-shot models like CLIP, our desideratum is for the fine-tuned model to excel in both in-distribution (ID) and out-of-distribution (OOD). Recently, ensemble-bas…
Typicalness-Aware Learning for Failure Detection
Yijun Liu, Jiequan Cui, Zhuotao Tian +4
Deep neural networks (DNNs) often suffer from the overconfidence issue, where incorrect predictions are made with high confidence scores, hindering the applications in critical sys…
CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction
Yuan Zhou, Qingshan Xu, Jiequan Cui +4
Recently, large efforts have been made to design efficient linear-complexity visual Transformers. However, current linear attention models are generally unsuitable to be deployed i…
Instruction Tuning-free Visual Token Complement for Multimodal LLMs
Dongsheng Wang, Jiequan Cui, Miaoge Li +3
As the open community of large language models (LLMs) matures, multimodal LLMs (MLLMs) have promised an elegant bridge between vision and language. However, current research is inh…
Doubly Abductive Counterfactual Inference for Text-based Image Editing
Xue Song, Jiequan Cui, Hanwang Zhang +3
We study text-based image editing (TBIE) of a single image by counterfactual inference because it is an elegant formulation to precisely address the requirement: the edited image s…
Classes Are Not Equal: An Empirical Study on Image Recognition Fairness
Jiequan Cui, Beier Zhu, Xin Wen +3
In this paper, we present an empirical study on image recognition fairness, i.e., extreme class accuracy disparity on balanced data like ImageNet. We experimentally demonstrate tha…
Decoupled Kullback-Leibler Divergence Loss
Jiequan Cui, Zhuotao Tian, Zhisheng Zhong +3
In this paper, we delve deeper into the Kullback-Leibler (KL) Divergence loss and mathematically prove that it is equivalent to the Decoupled Kullback-Leibler (DKL) Divergence loss…
Learning Context-aware Classifier for Semantic Segmentation
Zhuotao Tian, Jiequan Cui, Li Jiang +5
Semantic segmentation is still a challenging task for parsing diverse contexts in different scenes, thus the fixed classifier might not be able to well address varying feature dist…
Understanding Imbalanced Semantic Segmentation Through Neural Collapse
Zhisheng Zhong, Jiequan Cui, Yibo Yang +4
A recent study has shown a phenomenon called neural collapse in that the within-class means of features and the classifier weight vectors converge to the vertices of a simplex equi…
Generalized Parametric Contrastive Learning
Jiequan Cui, Zhisheng Zhong, Zhuotao Tian +3
In this paper, we propose the Generalized Parametric Contrastive Learning (GPaCo/PaCo) which works well on both imbalanced and balanced data. Based on theoretical analysis, we obse…
Region Rebalance for Long-Tailed Semantic Segmentation
Jiequan Cui, Yuhui Yuan, Zhisheng Zhong +4
In this paper, we study the problem of class imbalance in semantic segmentation. We first investigate and identify the main challenges of addressing this issue through pixel rebala…
Rebalanced Siamese Contrastive Mining for Long-Tailed Recognition
Zhisheng Zhong, Jiequan Cui, Zeming Li +3
Deep neural networks perform poorly on heavily class-imbalanced datasets. Given the promising performance of contrastive learning, we propose Rebalanced Siamese Contrastive Mining…
Adversarial Attacks on ML Defense Models Competition
Yinpeng Dong, Qi-An Fu, Xiao Yang +25
Due to the vulnerability of deep neural networks (DNNs) to adversarial examples, a large number of defense techniques have been proposed to alleviate this problem in recent years.…
Parametric Contrastive Learning
Jiequan Cui, Zhisheng Zhong, Shu Liu +2
In this paper, we propose Parametric Contrastive Learning (PaCo) to tackle long-tailed recognition. Based on theoretical analysis, we observe supervised contrastive loss tends to b…
Improving Calibration for Long-Tailed Recognition
Zhisheng Zhong, Jiequan Cui, Shu Liu +1
Deep neural networks may perform poorly when training datasets are heavily class-imbalanced. Recently, two-stage methods decouple representation learning and classifier learning to…
ResLT: Residual Learning for Long-tailed Recognition
Jiequan Cui, Shu Liu, Zhuotao Tian +2
Deep learning algorithms face great challenges with long-tailed data distribution which, however, is quite a common case in real-world scenarios. Previous methods tackle the proble…
Learnable Boundary Guided Adversarial Training
Jiequan Cui, Shu Liu, Liwei Wang +1
Previous adversarial training raises model robustness under the compromise of accuracy on natural data. In this paper, we reduce natural accuracy degradation. We use the model logi…