312 citations · 1k across the 25 of their papers we have counts for
26 papers
Masked Autoencoders are Efficient Class Incremental Learners
Jiang-Tian Zhai, Xialei Liu, Andrew D. Bagdanov +2
Class Incremental Learning (CIL) aims to sequentially learn new classes while avoiding catastrophic forgetting of previous knowledge. We propose to use Masked Autoencoders (MAEs) a…
Masked Cross-image Encoding for Few-shot Segmentation
Wenbo Xu, Huaxi Huang, Ming Cheng +3
Few-shot segmentation (FSS) is a dense prediction task that aims to infer the pixel-wise labels of unseen classes using only a limited number of annotated images. The key challenge…
YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection
Yuming Chen, Xinbin Yuan, Jiabao Wang +4
We aim at providing the object detection community with an efficient and performant object detector, termed YOLO-MS. The core design is based on a series of investigations on how m…
Delving Deeper into Data Scaling in Masked Image Modeling
Cheng-Ze Lu, Xiaojie Jin, Qibin Hou +3
Understanding whether self-supervised learning methods can scale with unlimited data is crucial for training large-scale models. In this work, we conduct an empirical study on the…
Co-Salient Object Detection with Co-Representation Purification
Ziyue Zhu, Zhao Zhang, Zheng Lin +2
Co-salient object detection (Co-SOD) aims at discovering the common objects in a group of relevant images. Mining a co-representation is essential for locating co-salient objects.…
MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer
Shanghua Gao, Pan Zhou, Ming-Ming Cheng +1
Despite its success in image synthesis, we observe that diffusion probabilistic models (DPMs) often lack contextual reasoning ability to learn the relations among object parts in a…
CMAE-V: Contrastive Masked Autoencoders for Video Action Recognition
Cheng-Ze Lu, Xiaojie Jin, Zhicheng Huang +3
Contrastive Masked Autoencoder (CMAE), as a new self-supervised framework, has shown its potential of learning expressive feature representations in visual image recognition. This…
Task-Adaptive Saliency Guidance for Exemplar-free Class Incremental Learning
Xialei Liu, Jiang-Tian Zhai, Andrew D. Bagdanov +2
Exemplar-free Class Incremental Learning (EFCIL) aims to sequentially learn tasks with access only to data from the current one. EFCIL is of interest because it mitigates concerns…
Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition
Qibin Hou, Cheng-Ze Lu, Ming-Ming Cheng +1
This paper does not attempt to design a state-of-the-art method for visual recognition but investigates a more efficient way to make use of convolutions to encode spatial features.…
Towards Sustainable Self-supervised Learning
Shanghua Gao, Pan Zhou, Ming-Ming Cheng +1
Although increasingly training-expensive, most self-supervised learning (SSL) models have repeatedly been trained from scratch but not fully utilized, since only a few SOTAs are em…
Long-Tailed Class Incremental Learning
Xialei Liu, Yu-Song Hu, Xu-Sheng Cao +3
In class incremental learning (CIL) a model must learn new classes in a sequential manner without forgetting old ones. However, conventional CIL methods consider a balanced distrib…
Class-Specific Semantic Reconstruction for Open Set Recognition
Hongzhi Huang, Yu Wang, Qinghua Hu +1
Open set recognition enables deep neural networks (DNNs) to identify samples of unknown classes, while maintaining high classification accuracy on samples of known classes. Existin…
Contrastive Masked Autoencoders are Stronger Vision Learners
Zhicheng Huang, Xiaojie Jin, Chengze Lu +5
Masked image modeling (MIM) has achieved promising results on various vision tasks. However, the limited discriminability of learned representation manifests there is still plenty…
Joint Super-Resolution and Inverse Tone-Mapping: A Feature Decomposition Aggregation Network and A New Benchmark
Gang Xu, Yu-chen Yang, Liang Wang +2
Joint Super-Resolution and Inverse Tone-Mapping (joint SR-ITM) aims to increase the resolution and dynamic range of low-resolution and standard dynamic range images. Recent network…
VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder
Yuchao Gu, Xintao Wang, Liangbin Xie +4
Although generative facial prior and geometric prior have recently demonstrated high-quality results for blind face restoration, producing fine-grained facial details faithful to i…
Towards An End-to-End Framework for Flow-Guided Video Inpainting
Zhen Li, Cheng-Ze Lu, Jianhua Qin +2
Optical flow, which captures motion information across frames, is exploited in recent video inpainting methods through propagating pixels along its trajectories. However, the hand-…
Representation Compensation Networks for Continual Semantic Segmentation
Chang-Bin Zhang, Jia-Wen Xiao, Xialei Liu +2
In this work, we study the continual semantic segmentation problem, where the deep neural networks are required to incorporate new classes continually without catastrophic forgetti…
Deeply Explain CNN via Hierarchical Decomposition
Ming-Ming Cheng, Peng-Tao Jiang, Ling-Hao Han +2
In computer vision, some attribution methods for explaining CNNs attempt to study how the intermediate features affect the network prediction. However, they usually ignore the feat…
Personalized Image Semantic Segmentation
Yu Zhang, Chang-Bin Zhang, Peng-Tao Jiang +2
Semantic segmentation models trained on public datasets have achieved great success in recent years. However, these models didn't consider the personalization issue of segmentation…
Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition
Qibin Hou, Zihang Jiang, Li Yuan +3
In this paper, we present Vision Permutator, a conceptually simple and data efficient MLP-like architecture for visual recognition. By realizing the importance of the positional in…
P2T: Pyramid Pooling Transformer for Scene Understanding
Yu-Huan Wu, Yun Liu, Xin Zhan +1
Recently, the vision transformer has achieved great success by pushing the state-of-the-art of various vision tasks. One of the most challenging problems in the vision transformer…
Large-scale Unsupervised Semantic Segmentation
Shanghua Gao, Zhong-Yu Li, Ming-Hsuan Yang +3
Empowered by large datasets, e.g., ImageNet, unsupervised learning on large-scale data has enabled significant advances for classification tasks. However, whether the large-scale u…
Salient Objects in Clutter
Deng-Ping Fan, Jing Zhang, Gang Xu +2
This paper identifies and addresses a serious design bias of existing salient object detection (SOD) datasets, which unrealistically assume that each image should contain at least…
Low-Light Image and Video Enhancement Using Deep Learning: A Survey
Chongyi Li, Chunle Guo, Linghao Han +4
Low-light image enhancement (LLIE) aims at improving the perception or interpretability of an image captured in an environment with poor illumination. Recent advances in this area…