Litcius/Paper detail

Deep Pyramidal Pooling With Attention for Person Re-Identification

Niki Martinel, Gian Luca Foresti, Christian Micheloni

2020IEEE Transactions on Image Processing51 citationsDOI

Abstract

Learning discriminative, view-invariant and multi-scale representations of object appearance with different semantic levels is of paramount importance for person Re-Identification (ReID). Recently, the community has focused on learning deep Re-ID models to capture a single holistic representation. To improve the achieved results, additional visual attributes and object part-driven models have been considered, inevitably introducing additional human annotation labor or computational efforts. In this paper, we argue that pyramid-inspired methods capturing multi-scale information may overcome such requirements. Precisely, multi-scale pooled regions representing visual information of an object are integrated within a novel deep architecture factorizing them into discriminative features at multiple semantic levels. These are exploited through an attention mechanism later considered in an identification-similarity multi-task loss, trained by means of a curriculum learning strategy. Extensive results on three person ReID benchmarks demonstrate that better performance than existing methods are achieved. Code is available at https://github.com/iN1k1.

Topics & Concepts

Discriminative modelComputer scienceArtificial intelligencePoolingDeep learningPyramid (geometry)Cognitive neuroscience of visual object recognitionMachine learningFeature learningIdentification (biology)Object (grammar)Representation (politics)VisualizationSimilarity (geometry)Source codePattern recognition (psychology)Image (mathematics)Political scienceBotanyPoliticsOperating systemPhysicsBiologyOpticsLawVideo Surveillance and Tracking MethodsHuman Pose and Action RecognitionFace recognition and analysis
Deep Pyramidal Pooling With Attention for Person Re-Identification | Litcius