Discriminate-and-rectify Encoders: Learning From Image Transformation Sets

Abstract

The complexity of a learning task is increased by transformations in the input space that preserve class identity. Visual object recognition for example is affected by changes in viewpoint, scale, illumination or planar transformations. While drastically altering the visual appearance, these changes are orthogonal to recognition and should not be reflected in the representation or feature encoding used for learning. We introduce a framework for weakly supervised learning of image embeddings that are robust to transformations and selective to the class distribution, using sets of transforming examples (orbit sets), deep parametrizations and a novel orbit-based loss. The proposed loss combines a discriminative, contrastive part for orbits with a reconstruction error that learns to rectify orbit transformations. The learned embeddings are evaluated in distance metric-based tasks, such as one-shot classification under geometric transformations, as well as face verification and retrieval un

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keytacchetti2017discriminate

Related papers

• Dual Pose-invariant Embeddings: Learning Category And Object-specific Discriminative Representations For Recognition And Retrieval (2024)4.52
• Regressing Transformers For Data-efficient Visual Place Recognition (2024)3.58
• Backward-compatible Aligned Representations Via An Orthogonal Transformation Layer (2024)0.00
• Adversarial Training For Adverse Conditions: Robust Metric Localisation Using Appearance Transfer (2018)14.43
• From Measurement To Mitigation: Quantifying And Reducing Identity Leakage In Image Representation Encoders With Linear Subspace Removal (2026)0.00
• Training Vision Transformers For Image Retrieval (2021)0.00
• Steerable Equivariant Representation Learning (2023)0.00
• With A Little Help From My Friends: Nearest-neighbor Contrastive Learning Of Visual Representations (2021)18.76