349 citations · 900 across the 26 of their papers we have counts for
15 papers · 1 filter
Loong: Generating Minute-level Long Videos with Autoregressive Language Models
Yuqing Wang, Tianwei Xiong, Daquan Zhou +5
It is desirable but challenging to generate content-rich long videos in the scale of minutes. Autoregressive large language models (LLMs) have achieved great success in generating…
Harnessing Diffusion Models for Visual Perception with Meta Prompts
Qiang Wan, Zilong Huang, Bingyi Kang +2
The issue of generative pretraining for vision models has persisted as a long-standing conundrum. At present, the text-to-image (T2I) diffusion model demonstrates remarkable profic…
BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs
Yang Zhao, Zhijie Lin, Daquan Zhou +3
LLMs have demonstrated remarkable abilities at interacting with humans through language, especially with the usage of instruction-following data. Recent advancements in LLMs, such…
Deep Long-Tailed Learning: A Survey
Yifan Zhang, Bingyi Kang, Bryan Hooi +2
Deep long-tailed learning, one of the most challenging problems in visual recognition, aims to train well-performing deep models from a large number of images that follow a long-ta…
Refiner: Refining Self-attention for Vision Transformers
Daquan Zhou, Yujun Shi, Bingyi Kang +6
Vision Transformers (ViTs) have shown competitive accuracy in image classification tasks compared with CNNs. Yet, they generally require much more data for model pre-training. Most…
DeepViT: Towards Deeper Vision Transformer
Daquan Zhou, Bingyi Kang, Xiaojie Jin +5
Vision transformers (ViTs) have been successfully applied in image classification tasks recently. In this paper, we show that, unlike convolution neural networks (CNNs)that can be…
Few-shot Classification via Adaptive Attention
Zihang Jiang, Bingyi Kang, Kuangqi Zhou +1
Training a neural network model that can quickly adapt to a new task is highly desirable yet challenging for few-shot learning problems. Recent few-shot learning methods mostly con…
The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation
Tao Wang, Yu Li, Bingyi Kang +5
Most existing object instance detection and segmentation models only work well on fairly balanced benchmarks where per-category training sample numbers are comparable, such as COCO…
Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax
Yu Li, Tao Wang, Bingyi Kang +4
Solving long-tail large vocabulary object detection with deep learning based models is a challenging and demanding task, which is however under-explored.In this work, we provide th…
Classification Calibration for Long-tail Instance Segmentation
Tao Wang, Yu Li, Bingyi Kang +5
Remarkable progress has been made in object instance detection and segmentation in recent years. However, existing state-of-the-art methods are mostly evaluated with fairly balance…
Decoupling Representation and Classifier for Long-Tailed Recognition
Bingyi Kang, Saining Xie, Marcus Rohrbach +4
The long-tail distribution of the visual world poses great challenges for deep learning based classification models on how to handle the class imbalance problem. Existing solutions…
Exploring Simple and Transferable Recognition-Aware Image Processing
Zhuang Liu, Hung-Ju Wang, Tinghui Zhou +4
Recent progress in image recognition has stimulated the deployment of vision systems at an unprecedented scale. As a result, visual data are now often consumed not only by humans b…
Similarity R-C3D for Few-shot Temporal Activity Detection
Huijuan Xu, Bingyi Kang, Ximeng Sun +3
Many activities of interest are rare events, with only a few labeled examples available. Therefore models for temporal activity detection which are able to learn from a few example…
Few-shot Object Detection via Feature Reweighting
Bingyi Kang, Zhuang Liu, Xin Wang +3
Conventional training of a deep CNN based object detector demands a large number of bounding box annotations, which may be unavailable for rare categories. In this work we develop…
Sharing Residual Units Through Collective Tensor Factorization in Deep Neural Networks
Chen Yunpeng, Jin Xiaojie, Kang Bingyi +2
Residual units are wildly used for alleviating optimization difficulties when building deep neural networks. However, the performance gain does not well compensate the model size i…