alignedReID: surpassing human-level performance in person re-identification (paper reading)
2017-12-08 11:37
387 查看
关键点:
1)对齐 (8%)
2)mutual learning (3%)
3)classification loss, hard triplet同时
4)re-ranking (5~6%)
关于对齐:
作者在resnet pool5 7*7那里,分两路,pool成7*1,1*1。对于7*1,进一步pairs对齐,(用动态规划),形成N*N距离矩阵。两个矩阵矩阵,其中对于动态规划,用最短路径来描述。
这两个矩阵只用于hard triplet
关于测试:
由于训练时利用了“pairs”的relationship,而不是absolute,这在测试时将会非常麻烦;所以,测试时直接忽略到pairs,只提取global特征。值得思考原因!
1)对齐 (8%)
2)mutual learning (3%)
3)classification loss, hard triplet同时
4)re-ranking (5~6%)
关于对齐:
作者在resnet pool5 7*7那里,分两路,pool成7*1,1*1。对于7*1,进一步pairs对齐,(用动态规划),形成N*N距离矩阵。两个矩阵矩阵,其中对于动态规划,用最短路径来描述。
这两个矩阵只用于hard triplet
关于测试:
由于训练时利用了“pairs”的relationship,而不是absolute,这在测试时将会非常麻烦;所以,测试时直接忽略到pairs,只提取global特征。值得思考原因!
相关文章推荐
- Re-ID:AlignedReID: Surpassing Human-Level Performance in Person Re-Identification 论文解析
- 【Person Re-ID】AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
- 【Person Re-ID】AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
- part-aligned系列论文:1711.AlignedReID- Surpassing Human-Level Performance in Person Re-Id 论文阅读
- Paper Reading: In Defense of the Triplet Loss for Person Re-Identification
- [paper note] Human-In-The-Loop Person Re-Identification
- paper reading——《Improving Person Re-identification by Attribute and Identity Learning》
- part-aligned系列论文:1707.Deeply-Learned Part-Aligned Representations for Person Re-Identification 论文笔记
- 【Person Re-ID】In Defense of the Triplet Loss for Person Re-Identification
- [Paper note] MARS: A Video Benchmark for Large-Scale Person Re-identification
- 【论文笔记】In Defense of the Triplet Loss for Person Re-Identification
- 1703.In Defense of the Triplet Loss for Person Re-Identification 论文阅读笔记
- [Paper note] Embedding Deep Metric for Person Re-identification: A Study Against Large Variation
- part-aligned系列论文:1707.ICCV.Pedestrian Alignment Network for Large-scale Person Re-identification 论文
- [Paper note] Video-based Person Re-identification with Accumulative Motion Context
- [paper note] Deep Attributes Driven Person Re-identification
- 论文提要“DeepFace: Closing the Gap to Human-Level Performance in Face Verification”
- Paper Reading - In Search of an Understandable Consensus Algorithm(Raft)
- 【翻译+原创】DeepFace: Closing the Gap to Human-Level Performance in Face Verification 论文笔记
- 学习笔记: Top-push Video-based Person Re-identification