173 citations · 367 across the 39 of their papers we have counts for
39 papers
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…
Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognition
Xuanyu Yi, Jiajun Deng, Qianru Sun +3
We tackle the data scarcity challenge in few-shot point cloud recognition of 3D objects by using a joint prediction from a conventional 3D model and a well-trained 2D model. Surpri…
Random Boxes Are Open-world Object Detectors
Yanghao Wang, Zhongqi Yue, Xian-Sheng Hua +1
We show that classifiers trained with random region proposals achieve state-of-the-art Open-world Object Detection (OWOD): they can not only maintain the accuracy of the known obje…
DisCo: Disentangled Control for Realistic Human Dance Generation
Tan Wang, Linjie Li, Kevin Lin +6
Generative AI has made significant strides in computer vision, particularly in text-driven image/video synthesis (T2I/T2V). Despite the notable advancements, it remains challenging…
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…
Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection
Hui Lv, Zhongqi Yue, Qianru Sun +3
Weakly Supervised Video Anomaly Detection (WSVAD) is challenging because the binary anomaly label is only given on the video level, but the output requires snippet-level prediction…
Semantic Scene Completion with Cleaner Self
Fengyun Wang, Dong Zhang, Hanwang Zhang +2
Semantic Scene Completion (SSC) transforms an image of single-view depth and/or RGB 2D pixels into 3D voxels, each of whose semantic labels are predicted. SSC is a well-known ill-p…
Equivariant Similarity for Vision-Language Foundation Models
Tan Wang, Kevin Lin, Linjie Li +5
This study explores the concept of equivariance in vision-language foundation models (VLMs), focusing specifically on the multimodal similarity function that is not only the major…
Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection
Kaifeng Gao, Long Chen, Hanwang Zhang +2
Prompt tuning with large-scale pretrained vision-language models empowers open-vocabulary predictions trained on limited base categories, e.g., object classification and detection.…
Debiased Fine-Tuning for Vision-language Models by Prompt Regularization
Beier Zhu, Yulei Niu, Saeil Lee +2
We present a new paradigm for fine-tuning large-scale visionlanguage pre-trained models on downstream task, dubbed Prompt Regularization (ProReg). Different from traditional fine-t…
Attention-based Class Activation Diffusion for Weakly-Supervised Semantic Segmentation
Jianqiang Huang, Jian Wang, Qianru Sun +1
Extracting class activation maps (CAM) is a key step for weakly-supervised semantic segmentation (WSSS). The CAM of convolution neural networks fails to capture long-range feature…
Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foreground
Haoxin Li, Yuan Liu, Hanwang Zhang +1
In video action recognition, shortcut static features can interfere with the learning of motion features, resulting in poor out-of-distribution (OOD) generalization. The video back…
Respecting Transfer Gap in Knowledge Distillation
Yulei Niu, Long Chen, Chang Zhou +1
Knowledge distillation (KD) is essentially a process of transferring a teacher model's behavior, e.g., network response, to a student model. The network response serves as addition…
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…
NICEST: Noisy Label Correction and Training for Robust Scene Graph Generation
Lin Li, Jun Xiao, Hanrong Shi +4
Nearly all existing scene graph generation (SGG) models have overlooked the ground-truth annotation qualities of mainstream SGG datasets, i.e., they assume: 1) all the manually ann…
Equivariance and Invariance Inductive Bias for Learning from Insufficient Data
Tan Wang, Qianru Sun, Sugiri Pranata +2
We are interested in learning robust models from insufficient data, without the need for any externally pre-trained checkpoints. First, compared to sufficient data, we show why ins…
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…
On Non-Random Missing Labels in Semi-Supervised Learning
Xinting Hu, Yulei Niu, Chunyan Miao +2
Semi-Supervised Learning (SSL) is fundamentally a missing label problem, in which the label Missing Not At Random (MNAR) problem is more realistic and challenging, compared to the…
Prompt-aligned Gradient for Prompt Tuning
Beier Zhu, Yulei Niu, Yucheng Han +2
Thanks to the large pre-trained vision-language models (VLMs) like CLIP, we can craft a zero-shot classifier by "prompt", e.g., the confidence score of an image being "[CLASS]" can…
Certified Robustness Against Natural Language Attacks by Causal Intervention
Haiteng Zhao, Chang Ma, Xinshuai Dong +3
Deep learning models have achieved great success in many fields, yet they are vulnerable to adversarial examples. This paper follows a causal perspective to look into the adversari…
Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation
Zhaozheng Chen, Tan Wang, Xiongwei Wu +3
Extracting class activation maps (CAM) is arguably the most standard step of generating pseudo masks for weakly-supervised semantic segmentation (WSSS). Yet, we find that the crux…
Deconfounded Visual Grounding
Jianqiang Huang, Yu Qin, Jiaxin Qi +2
We focus on the confounding bias between language and location in the visual grounding pipeline, where we find that the bias is the major visual reasoning bottleneck. For example,…
Cross-Domain Empirical Risk Minimization for Unbiased Long-tailed Classification
Beier Zhu, Yulei Niu, Xian-Sheng Hua +1
We address the overlooked unbiasedness in existing long-tailed classification methods: we find that their overall improvement is mostly attributed to the biased preference of tail…