Unified Negative Pair Generation toward Well-discriminative Feature Space for Face Recognition

• URL: http://arxiv.org/abs/2203.11593v2
• Date: Fri, 19 Apr 2024 00:35:35 GMT
• Title: Unified Negative Pair Generation toward Well-discriminative Feature Space for Face Recognition
• Authors: Junuk Jung, Seonhoon Lee, Heung-Seon Oh, Yongjun Park, Joochan Park, Sungbin Son,
• Abstract summary: Face recognition models form a well-discriminative feature space (WDFS) that satisfies $infmathcalSp > supmathcalSn$. This paper proposes a unified negative pair generation (UNPG) by combining two PG strategies.
• Score: 2.816374336026564
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The goal of face recognition (FR) can be viewed as a pair similarity optimization problem, maximizing a similarity set $\mathcal{S}^p$ over positive pairs, while minimizing similarity set $\mathcal{S}^n$ over negative pairs. Ideally, it is expected that FR models form a well-discriminative feature space (WDFS) that satisfies $\inf{\mathcal{S}^p} > \sup{\mathcal{S}^n}$. With regard to WDFS, the existing deep feature learning paradigms (i.e., metric and classification losses) can be expressed as a unified perspective on different pair generation (PG) strategies. Unfortunately, in the metric loss (ML), it is infeasible to generate negative pairs taking all classes into account in each iteration because of the limited mini-batch size. In contrast, in classification loss (CL), it is difficult to generate extremely hard negative pairs owing to the convergence of the class weight vectors to their center. This leads to a mismatch between the two similarity distributions of the sampled pairs and all negative pairs. Thus, this paper proposes a unified negative pair generation (UNPG) by combining two PG strategies (i.e., MLPG and CLPG) from a unified perspective to alleviate the mismatch. UNPG introduces useful information about negative pairs using MLPG to overcome the CLPG deficiency. Moreover, it includes filtering the similarities of noisy negative pairs to guarantee reliable convergence and improved performance. Exhaustive experiments show the superiority of UNPG by achieving state-of-the-art performance across recent loss functions on public benchmark datasets. Our code and pretrained models are publicly available.

Related papers

• Statistical-Computational Trade-offs for Greedy Recursive Partitioning Estimators [23.056208049082134]
  We show that greedy algorithms for high-dimensional regression get stuck at local optima. We show that greedy training requires $exp(Omega(d))$ to achieve low estimation error. We also show that greedy training can attain small estimation error with only $O(log d)$ samples.
  arXiv  Detail & Related papers  (2024-11-07T03:11:53Z)
• Negative-Free Self-Supervised Gaussian Embedding of Graphs [29.26519601854811]
  Graph Contrastive Learning (GCL) has emerged as a promising graph self-supervised learning framework. We propose a negative-free objective to achieve uniformity, inspired by the fact that points distributed according to a normalized isotropic Gaussian are uniformly spread across the unit hypersphere. Our proposal achieves competitive performance with fewer parameters, shorter training times, and lower memory consumption compared to existing GCL methods.
  arXiv  Detail & Related papers  (2024-11-02T07:04:40Z)
• Addressing GAN Training Instabilities via Tunable Classification Losses [8.151943266391493]
  Generative adversarial networks (GANs) allow generating synthetic data with formal guarantees. We show that all symmetric $f$-divergences are equivalent in convergence. We also highlight the value of tuning $(alpha_D,alpha_G)$ in alleviating training instabilities for the synthetic 2D Gaussian mixture ring.
  arXiv  Detail & Related papers  (2023-10-27T17:29:07Z)
• Learning by Sorting: Self-supervised Learning with Group Ordering Constraints [75.89238437237445]
  This paper proposes a new variation of the contrastive learning objective, Group Ordering Constraints (GroCo) It exploits the idea of sorting the distances of positive and negative pairs and computing the respective loss based on how many positive pairs have a larger distance than the negative pairs, and thus are not ordered correctly. We evaluate the proposed formulation on various self-supervised learning benchmarks and show that it not only leads to improved results compared to vanilla contrastive learning but also shows competitive performance to comparable methods in linear probing and outperforms current methods in k-NN performance.
  arXiv  Detail & Related papers  (2023-01-05T11:17:55Z)
• Positive-Negative Equal Contrastive Loss for Semantic Segmentation [8.664491798389662]
  Previous works commonly design plug-and-play modules and structural losses to effectively extract and aggregate the global context. We propose Positive-Negative Equal contrastive loss (PNE loss), which increases the latent impact of positive embedding on the anchor and treats the positive as well as negative sample pairs equally. We conduct comprehensive experiments and achieve state-of-the-art performance on two benchmark datasets.
  arXiv  Detail & Related papers  (2022-07-04T13:51:29Z)
• Rebalanced Siamese Contrastive Mining for Long-Tailed Recognition [120.80038161330623]
  We show that supervised contrastive learning suffers a dual class-imbalance problem at both the original batch and Siamese batch levels. We propose supervised hard positive and negative pairs mining to pick up informative pairs for contrastive computation and improve representation learning.
  arXiv  Detail & Related papers  (2022-03-22T07:30:38Z)
• Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm Performance [53.49803579981569]
  We consider a global objective for contrastive learning, which contrasts each positive pair with all negative pairs for an anchor point. Existing methods such as SimCLR requires a large batch size in order to achieve a satisfactory result. We propose a memory-efficient optimization algorithm for solving the Global Contrastive Learning of Representations, named SogCLR.
  arXiv  Detail & Related papers  (2022-02-24T22:16:53Z)
• Prototypical Graph Contrastive Learning [141.30842113683775]
  We propose a Prototypical Graph Contrastive Learning (PGCL) approach to mitigate the critical sampling bias issue. Specifically, PGCL models the underlying semantic structure of the graph data via clustering semantically similar graphs into the same group, and simultaneously encourages the clustering consistency for different augmentations of the same graph. For a query, PGCL further reweights its negative samples based on the distance between their prototypes (cluster centroids) and the query prototype.
  arXiv  Detail & Related papers  (2021-06-17T16:45:31Z)
• Multi-group Agnostic PAC Learnability [7.9649015115693444]
  We study "multi-group agnostic PAC learnability" We provide a characterization of the loss functions for which such a predictor is guaranteed to exist. Our results unify and extend previous positive and negative results from the multi-group fairness literature.
  arXiv  Detail & Related papers  (2021-05-20T18:43:36Z)
• Scalable Personalised Item Ranking through Parametric Density Estimation [53.44830012414444]
  Learning from implicit feedback is challenging because of the difficult nature of the one-class problem. Most conventional methods use a pairwise ranking approach and negative samplers to cope with the one-class problem. We propose a learning-to-rank approach, which achieves convergence speed comparable to the pointwise counterpart.
  arXiv  Detail & Related papers  (2021-05-11T03:38:16Z)
• Non-Convex SGD Learns Halfspaces with Adversarial Label Noise [50.659479930171585]
  We show the solution to the problem of learning surrogate learning homogeneous halfspaces in the distribution-specific model. In any convex distributions, we show that the misclassification error inherently leads to misclassification error of halfspace.
  arXiv  Detail & Related papers  (2020-06-11T18:55:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.