1.6k citations · 4.8k across the 90 of their papers we have counts for
20 papers · 1 filter
Slimmable Neural Networks
Jiahui Yu, Linjie Yang, Ning Xu +2
We present a simple and general method to train a single neural network executable at different widths (number of channels in a layer), permitting instant and adaptive accuracy-eff…
Weakly Supervised Scene Parsing with Point-based Distance Metric Learning
Rui Qian, Yunchao Wei, Honghui Shi +3
Semantic scene parsing is suffering from the fact that pixel-level annotations are hard to be collected. To tackle this issue, we propose a Point-based Distance Metric Learning (PD…
Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification
Yang Fu, Yunchao Wei, Guanshuo Wang +3
Domain adaptation in person re-identification (re-ID) has always been a challenging task. In this work, we explore how to harness the natural similar characteristics existing in th…
A Simple Non-i.i.d. Sampling Approach for Efficient Training and Better Generalization
Bowen Cheng, Yunchao Wei, Jiahui Yu +5
While training on samples drawn from independent and identical distribution has been a de facto paradigm for optimizing image classification networks, humans learn new concepts in…
Decoupled Classification Refinement: Hard False Positive Suppression for Object Detection
Bowen Cheng, Yunchao Wei, Rogerio Feris +4
In this paper, we analyze failure cases of state-of-the-art detectors and observe that most hard false positives result from classification instead of localization and they have a…
YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark
Ning Xu, Linjie Yang, Yuchen Fan +4
Learning long-term spatial-temporal features are critical for many video analysis tasks. However, existing video segmentation methods predominantly rely on static image segmentatio…