Dual Pose-invariant Embeddings: Learning Category And Object-specific Discriminative Representations For Recognition And Retrieval

Abstract

In the context of pose-invariant object recognition and retrieval, we demonstrate that it is possible to achieve significant improvements in performance if both the category-based and the object-identity-based embeddings are learned simultaneously during training. In hindsight, that sounds intuitive because learning about the categories is more fundamental than learning about the individual objects that correspond to those categories. However, to the best of what we know, no prior work in pose-invariant learning has demonstrated this effect. This paper presents an attention-based dual-encoder architecture with specially designed loss functions that optimize the inter- and intra-class distances simultaneously in two different embedding spaces, one for the category embeddings and the other for the object-level embeddings. The loss functions we have proposed are pose-invariant ranking losses that are designed to minimize the intra-class distances and maximize the inter-class distances in

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keysarkar2024dual

Related papers

• Category-level Pose Retrieval With Contrastive Features Learnt With Occlusion Augmentation (2022)1.91
• View-invariant, Occlusion-robust Probabilistic Embedding For Human Pose (2020)8.82
• A Pose-sensitive Embedding For Person Re-identification With Expanded Cross Neighborhood Re-ranking (2017)23.25
• DISP6D: Disentangled Implicit Shape And Pose Learning For Scalable 6D Pose Estimation (2021)9.03
• Pose Invariant Embedding For Deep Person Re-identification (2017)19.34
• Discriminate-and-rectify Encoders: Learning From Image Transformation Sets (2017)0.00
• Joint Representation Learning And Novel Category Discovery On Single- And Multi-modal Data (2021)13.11
• Cooperative Embeddings For Instance, Attribute And Category Retrieval (2019)0.00