223 citations · 354 across the 31 of their papers we have counts for
22 papers · 1 filter
High-level Feature Guided Decoding for Semantic Segmentation
Ye Huang, Di Kang, Shenghua Gao +2
Existing pyramid-based upsamplers (e.g. SemanticFPN), although efficient, usually produce less accurate results compared to dilation-based models when using the same backbone. This…
CARD: Semantic Segmentation with Efficient Class-Aware Regularized Decoder
Ye Huang, Di Kang, Liang Chen +5
Semantic segmentation has recently achieved notable advances by exploiting "class-level" contextual information during learning. However, these approaches simply concatenate class-…
Minimizing Maximum Model Discrepancy for Transferable Black-box Targeted Attacks
Anqi Zhao, Tong Chu, Yahao Liu +3
In this work, we study the black-box targeted attack problem from the model discrepancy perspective. On the theoretical side, we present a generalization error bound for black-box…
Motion and Appearance Adaptation for Cross-Domain Motion Transfer
Borun Xu, Biao Wang, Jinhong Deng +5
Motion transfer aims to transfer the motion of a driving video to a source image. When there are considerable differences between object in the driving video and that in the source…
Motion Transformer for Unsupervised Image Animation
Jiale Tao, Biao Wang, Tiezheng Ge +3
Image animation aims to animate a source image by using motion learned from a driving video. Current state-of-the-art methods typically use convolutional neural networks (CNNs) to…
Cross-domain Detection Transformer based on Spatial-aware and Semantic-aware Token Alignment
Jinhong Deng, Xiaoyue Zhang, Wen Li +1
Detection transformers like DETR have recently shown promising performance on many object detection tasks, but the generalization ability of those methods is still quite challengin…
Undoing the Damage of Label Shift for Cross-domain Semantic Segmentation
Yahao Liu, Jinhong Deng, Jiale Tao +3
Existing works typically treat cross-domain semantic segmentation (CDSS) as a data distribution mismatch problem and focus on aligning the marginal distribution or conditional dist…
Structure-Aware Motion Transfer with Deformable Anchor Model
Jiale Tao, Biao Wang, Borun Xu +4
Given a source image and a driving video depicting the same object type, the motion transfer task aims to generate a video by learning the motion from the driving video while prese…
Region Comparison Network for Interpretable Few-shot Image Classification
Zhiyu Xue, Lixin Duan, Wen Li +2
While deep learning has been successfully applied to many real-world computer vision tasks, training robust classifiers usually requires a large amount of well-labeled data. Howeve…
Dynamic and Static Context-aware LSTM for Multi-agent Motion Prediction
Chaofan Tao, Qinhong Jiang, Lixin Duan +1
Multi-agent motion prediction is challenging because it aims to foresee the future trajectories of multiple agents (\textit{e.g.} pedestrians) simultaneously in a complicated scene…
Reconstruction Regularized Deep Metric Learning for Multi-label Image Classification
Changsheng Li, Chong Liu, Lixin Duan +2
In this paper, we present a novel deep metric learning method to tackle the multi-label image classification problem. In order to better learn the correlations among images feature…
Deeply Aligned Adaptation for Cross-domain Object Detection
Minghao Fu, Zhenshan Xie, Wen Li +1
Cross-domain object detection has recently attracted more and more attention for real-world applications, since it helps build robust detectors adapting well to new environments. I…
Learning Cross-domain Semantic-Visual Relationships for Transductive Zero-Shot Learning
Fengmao Lv, Jianyang Zhang, Guowu Yang +3
Zero-Shot Learning (ZSL) learns models for recognizing new classes. One of the main challenges in ZSL is the domain discrepancy caused by the category inconsistency between trainin…
Unbiased Mean Teacher for Cross-domain Object Detection
Jinhong Deng, Wen Li, Yuhua Chen +1
Cross-domain object detection is challenging, because object detection model is often vulnerable to data variance, especially to the considerable domain shift between two distincti…
Open-Ended Visual Question Answering by Multi-Modal Domain Adaptation
Yiming Xu, Lin Chen, Zhongwei Cheng +2
We study the problem of visual question answering (VQA) in images by exploiting supervised domain adaptation, where there is a large amount of labeled data in the source domain but…
Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach
Qing Lian, Fengmao Lv, Lixin Duan +1
We propose a new approach, called self-motivated pyramid curriculum domain adaptation (PyCDA), to facilitate the adaptation of semantic segmentation neural networks from synthetic…
Adversarial Multimodal Network for Movie Question Answering
Zhaoquan Yuan, Siyuan Sun, Lixin Duan +2
Visual question answering by using information from multiple modalities has attracted more and more attention in recent years. However, it is a very challenging task, as the visual…
Known-class Aware Self-ensemble for Open Set Domain Adaptation
Qing Lian, Wen Li, Lin Chen +1
Existing domain adaptation methods generally assume different domains have the identical label space, which is quite restrict for real-world applications. In this paper, we focus o…
MiniMax Entropy Network: Learning Category-Invariant Features for Domain Adaptation
Chaofan Tao, Fengmao Lv, Lixin Duan +1
How to effectively learn from unlabeled data from the target domain is crucial for domain adaptation, as it helps reduce the large performance gap due to domain shift or distributi…
Learning Transferable Self-attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision
Xiao-Yu Zhang, Haichao Shi, Changsheng Li +3
Action recognition in videos has attracted a lot of attention in the past decade. In order to learn robust models, previous methods usually assume videos are trimmed as short seque…
Exploiting Images for Video Recognition with Hierarchical Generative Adversarial Networks
Feiwu Yu, Xinxiao Wu, Yuchao Sun +1
Existing deep learning methods of video recognition usually require a large number of labeled videos for training. But for a new task, videos are often unlabeled and it is also tim…
Recurrent Image Captioner: Describing Images with Spatial-Invariant Transformation and Attention Filtering
Hao Liu, Yang Yang, Fumin Shen +2
Along with the prosperity of recurrent neural network in modelling sequential data and the power of attention mechanism in automatically identify salient information, image caption…