471 citations · 3.1k across the 59 of their papers we have counts for
11 papers · 1 filter
Loss re-scaling VQA: Revisiting the LanguagePrior Problem from a Class-imbalance View
Yangyang Guo, Liqiang Nie, Zhiyong Cheng +2
Recent studies have pointed out that many well-developed Visual Question Answering (VQA) models are heavily affected by the language prior problem, which refers to making predictio…
Label Decoupling Framework for Salient Object Detection
Jun Wei, Shuhui Wang, Zhe Wu +3
To get more accurate saliency maps, recent methods mainly focus on aggregating multi-level features from fully convolutional network (FCN) and introducing edge information as auxil…
Learning Task-oriented Disentangled Representations for Unsupervised Domain Adaptation
Pingyang Dai, Peixian Chen, Qiong Wu +4
Unsupervised domain adaptation (UDA) aims to address the domain-shift problem between a labeled source domain and an unlabeled target domain. Many efforts have been made to address…
Dual Distribution Alignment Network for Generalizable Person Re-Identification
Peixian Chen, Pingyang Dai, Jianzhuang Liu +3
Domain generalization (DG) serves as a promising solution to handle person Re-Identification (Re-ID), which trains the model using labels from the source domain alone, and then dir…
Cascaded Regression Tracking: Towards Online Hard Distractor Discrimination
Ning Wang, Wengang Zhou, Qi Tian +1
Visual tracking can be easily disturbed by similar surrounding objects. Such objects as hard distractors, even though being the minority among negative samples, increase the risk o…
Rethinking Performance Estimation in Neural Architecture Search
Xiawu Zheng, Rongrong Ji, Qiang Wang +4
Neural architecture search (NAS) remains a challenging problem, which is attributed to the indispensable and time-consuming component of performance estimation (PE). In this paper,…
Projection & Probability-Driven Black-Box Attack
Jie Li, Rongrong Ji, Hong Liu +4
Generating adversarial examples in a black-box setting retains a significant challenge with vast practical application prospects. In particular, existing black-box attacks suffer f…
Learning to Select Base Classes for Few-shot Classification
Linjun Zhou, Peng Cui, Xu Jia +2
Few-shot learning has attracted intensive research attention in recent years. Many methods have been proposed to generalize a model learned from provided base classes to novel clas…
Gradually Vanishing Bridge for Adversarial Domain Adaptation
Shuhao Cui, Shuhui Wang, Junbao Zhuo +3
In unsupervised domain adaptation, rich domain-specific characteristics bring great challenge to learn domain-invariant representations. However, domain discrepancy is considered t…
Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situations
Shuhao Cui, Shuhui Wang, Junbao Zhuo +3
The learning of the deep networks largely relies on the data with human-annotated labels. In some label insufficient situations, the performance degrades on the decision boundary w…
Filter Sketch for Network Pruning
Mingbao Lin, Liujuan Cao, Shaojie Li +5
We propose a novel network pruning approach by information preserving of pre-trained network weights (filters). Network pruning with the information preserving is formulated as a m…