35 citations · 82 across the 10 of their papers we have counts for
10 papers
Out-of-Distributed Semantic Pruning for Robust Semi-Supervised Learning
Yu Wang, Pengchong Qiao, Chang Liu +3
Recent advances in robust semi-supervised learning (SSL) typically filter out-of-distribution (OOD) information at the sample level. We argue that an overlooked problem of robust S…
Position Embedding Needs an Independent Layer Normalization
Runyi Yu, Zhennan Wang, Yinhuai Wang +5
The Position Embedding (PE) is critical for Vision Transformers (VTs) due to the permutation-invariance of self-attention operation. By analyzing the input and output of each encod…
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations
Peng Jin, Jinfa Huang, Fenglin Liu +5
Most video-and-language representation learning approaches employ contrastive learning, e.g., CLIP, to project the video and text features into a common latent space according to t…
Fuzzy Positive Learning for Semi-supervised Semantic Segmentation
Pengchong Qiao, Zhidan Wei, Yu Wang +6
Semi-supervised learning (SSL) essentially pursues class boundary exploration with less dependence on human annotations. Although typical attempts focus on ameliorating the inevita…
ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentation
Kehan Li, Zhennan Wang, Zesen Cheng +6
Recently, self-supervised large-scale visual pre-training models have shown great promise in representing pixel-level semantic relationships, significantly promoting the developmen…
Toward 3D Spatial Reasoning for Human-like Text-based Visual Question Answering
Hao Li, Jinfa Huang, Peng Jin +3
Text-based Visual Question Answering~(TextVQA) aims to produce correct answers for given questions about the images with multiple scene texts. In most cases, the texts naturally at…
Locality Guidance for Improving Vision Transformers on Tiny Datasets
Kehan Li, Runyi Yu, Zhennan Wang +3
While the Vision Transformer (VT) architecture is becoming trendy in computer vision, pure VT models perform poorly on tiny datasets. To address this issue, this paper proposes the…
BN: Enhancing Batch Normalization by Equalizing the Norms of Features
Zhennan Wang, Kehan Li, Runyi Yu +7
In this paper, we analyze batch normalization from the perspective of discriminability and find the disadvantages ignored by previous studies: the difference in norms of samp…
ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval
Mengjun Cheng, Yipeng Sun, Longchao Wang +8
Visual appearance is considered to be the most important cue to understand images for cross-modal retrieval, while sometimes the scene text appearing in images can provide valuable…
Harmonized Multimodal Learning with Gaussian Process Latent Variable Models
Guoli Song, Shuhui Wang, Qingming Huang +1
Multimodal learning aims to discover the relationship between multiple modalities. It has become an important research topic due to extensive multimodal applications such as cross-…