1.9k citations · 6.4k across the 80 of their papers we have counts for
14 papers · 1 filter
Searching Parameterized AP Loss for Object Detection
Chenxin Tao, Zizhang Li, Xizhou Zhu +3
Loss functions play an important role in training deep-network-based object detectors. The most widely used evaluation metric for object detection is Average Precision (AP), which…
Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks
Xizhou Zhu, Jinguo Zhu, Hao Li +5
Biological intelligence systems of animals perceive the world by integrating information in different modalities and processing simultaneously for various tasks. In contrast, curre…
Exploring the Equivalence of Siamese Self-Supervised Learning via A Unified Gradient Framework
Chenxin Tao, Honghui Wang, Xizhou Zhu +4
Self-supervised learning has shown its great potential to extract powerful visual representations without human annotations. Various works are proposed to deal with self-supervised…
Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling
Renrui Zhang, Rongyao Fang, Wei Zhang +5
Contrastive Vision-Language Pre-training, known as CLIP, has provided a new paradigm for learning visual representations by using large-scale contrastive image-text pairs. It shows…
VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition
Changyao Tian, Wenhai Wang, Xizhou Zhu +2
Deep learning-based models encounter challenges when processing long-tailed data in the real world. Existing solutions usually employ some balancing strategies or transfer learning…
FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting
Rui Liu, Hanming Deng, Yangyi Huang +6
Transformer, as a strong and flexible architecture for modelling long-range relations, has been widely explored in vision tasks. However, when used in video inpainting that require…
Influence Selection for Active Learning
Zhuoming Liu, Hao Ding, Huaping Zhong +3
The existing active learning methods select the samples by evaluating the sample's uncertainty or its effect on the diversity of labeled datasets based on different task-specific o…
Fast Convergence of DETR with Spatially Modulated Co-Attention
Peng Gao, Minghang Zheng, Xiaogang Wang +2
The recently proposed Detection Transformer (DETR) model successfully applies Transformer to objects detection and achieves comparable performance with two-stage object detection f…
Collaborative Visual Navigation
Haiyang Wang, Wenguan Wang, Xizhou Zhu +2
As a fundamental problem for Artificial Intelligence, multi-agent system (MAS) is making rapid progress, mainly driven by multi-agent reinforcement learning (MARL) techniques. Howe…
Scalable Transformers for Neural Machine Translation
Peng Gao, Shijie Geng, Yu Qiao +3
Transformer has been widely adopted in Neural Machine Translation (NMT) because of its large capacity and parallel training of sequence generation. However, the deployment of Trans…
Decoupled Spatial-Temporal Transformer for Video Inpainting
Rui Liu, Hanming Deng, Yangyi Huang +6
Video inpainting aims to fill the given spatiotemporal holes with realistic appearance but is still a challenging task even with prosperous deep learning approaches. Recent works i…
AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks
Hao Li, Tianwen Fu, Jifeng Dai +3
Significant progress has been achieved in automating the design of various components in deep networks. However, the automatic design of loss functions for generic tasks with vario…
Fast Convergence of DETR with Spatially Modulated Co-Attention
Peng Gao, Minghang Zheng, Xiaogang Wang +2
The recently proposed Detection Transformer (DETR) model successfully applies Transformer to objects detection and achieves comparable performance with two-stage object detection f…
Exploring Cross-Image Pixel Contrast for Semantic Segmentation
Wenguan Wang, Tianfei Zhou, Fisher Yu +3
Current semantic segmentation methods focus only on mining "local" context, i.e., dependencies between pixels within individual images, by context-aggregation modules (e.g., dilate…