A Backbone Benchmarking Study on Self-supervised Learning as a Auxiliary Task with Texture-based Local Descriptors for Face Analysis

• URL: http://arxiv.org/abs/2603.22190v1
• Date: Mon, 23 Mar 2026 16:49:50 GMT
• Title: A Backbone Benchmarking Study on Self-supervised Learning as a Auxiliary Task with Texture-based Local Descriptors for Face Analysis
• Abstract summary: We benchmark different backbones and study their impact for self-supervised learning (SSL) as an auxiliary task.<n>We employ different shallow to deep backbones for the SSL task of Masked Auto-Encoder (MAE) as an auxiliary objective.<n>For consistency of feature representation quality and generalisation capability across various face analysis paradigms, there is no unified backbone.
• Score: 1.9269756235105742
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this work, we benchmark with different backbones and study their impact for self-supervised learning (SSL) as an auxiliary task to blend texture-based local descriptors into feature modelling for efficient face analysis. It is established in previous work that combining a primary task and a self-supervised auxiliary task enables more robust and discriminative representation learning. We employed different shallow to deep backbones for the SSL task of Masked Auto-Encoder (MAE) as an auxiliary objective to reconstruct texture features such as local patterns alongside the primary task in local pattern SSAT (L-SSAT), ensuring robust and unbiased face analysis. To expand the benchmark, we conducted a comprehensive comparative analysis across multiple model configurations within the proposed framework. To this end, we address the three research questions: "What is the role of the backbone in performance L-SSAT?", "What type of backbone is effective for different face analysis tasks?", and "Is there any generalized backbone for effective face analysis with L-SSAT?". Towards answering these questions, we provide a detailed study and experiments. The performance evaluation demonstrates that the backbone for the proposed method is highly dependent on the downstream task, achieving average accuracies of 0.94 on FaceForensics++, 0.87 on CelebA, and 0.88 on AffectNet. For consistency of feature representation quality and generalisation capability across various face analysis paradigms, including face attribute prediction, emotion classification, and deepfake detection, there is no unified backbone.

Related papers

• Self-supervised Auxiliary Learning for Texture and Model-based Hybrid Robust and Fair Featuring in Face Analysis [7.479920049311377]
  We explore Self-supervised Learning (SSL) as an auxiliary task to blend the texture-based local descriptors into feature modelling for efficient face analysis. We used the SSL task of mask auto-encoder (MAE) as an auxiliary task to reconstruct texture features such as local patterns along with the primary task for robust and unbiased face analysis.
  arXiv  Detail & Related papers  (2024-09-29T07:03:05Z)
• Deep Content Understanding Toward Entity and Aspect Target Sentiment Analysis on Foundation Models [0.8602553195689513]
  Entity-Aspect Sentiment Triplet Extraction (EASTE) is a novel Aspect-Based Sentiment Analysis task. Our research aims to achieve high performance on the EASTE task and investigates the impact of model size, type, and adaptation techniques on task performance. Ultimately, we provide detailed insights and achieving state-of-the-art results in complex sentiment analysis.
  arXiv  Detail & Related papers  (2024-07-04T16:48:14Z)
• Task-adaptive Q-Face [75.15668556061772]
  We propose a novel task-adaptive multi-task face analysis method named as Q-Face. Q-Face simultaneously performs multiple face analysis tasks with a unified model. Our method achieves state-of-the-art performance on face expression recognition, action unit detection, face attribute analysis, age estimation, and face pose estimation.
  arXiv  Detail & Related papers  (2024-05-15T03:13:11Z)
• FaceXFormer: A Unified Transformer for Facial Analysis [59.94066615853198]
  FaceXFormer is an end-to-end unified transformer model capable of performing ten facial analysis tasks.<n>Tasks include face parsing, landmark detection, head pose estimation, attribute prediction, age, gender, and race estimation.<n>We train FaceXFormer on ten diverse face perception datasets and evaluate it against both specialized and multi-task models.
  arXiv  Detail & Related papers  (2024-03-19T17:58:04Z)
• Faceptor: A Generalist Model for Face Perception [52.8066001012464]
  Faceptor is proposed to adopt a well-designed single-encoder dual-decoder architecture. Layer-Attention into Faceptor enables the model to adaptively select features from optimal layers to perform the desired tasks. Our training framework can also be applied to auxiliary supervised learning, significantly improving performance in data-sparse tasks such as age estimation and expression recognition.
  arXiv  Detail & Related papers  (2024-03-14T15:42:31Z)
• SHIELD : An Evaluation Benchmark for Face Spoofing and Forgery Detection with Multimodal Large Language Models [61.8876114116716]
  Multimodal large language models (MLLMs) have demonstrated strong capabilities in vision-related tasks.<n>However, their ability to detect subtle visual spoofing and forgery clues in face attack detection tasks remains underexplored.<n>We introduce a benchmark, SHIELD, to evaluate MLLMs for face spoofing and forgery detection.
  arXiv  Detail & Related papers  (2024-02-06T17:31:36Z)
• Masked Momentum Contrastive Learning for Zero-shot Semantic Understanding [39.424931953675994]
  Self-supervised pretraining (SSP) has emerged as a popular technique in machine learning, enabling the extraction of meaningful feature representations without labelled data. This study endeavours to evaluate the effectiveness of pure self-supervised learning (SSL) techniques in computer vision tasks.
  arXiv  Detail & Related papers  (2023-08-22T13:55:57Z)
• Revisiting the Evaluation of Image Synthesis with GANs [55.72247435112475]
  This study presents an empirical investigation into the evaluation of synthesis performance, with generative adversarial networks (GANs) as a representative of generative models. In particular, we make in-depth analyses of various factors, including how to represent a data point in the representation space, how to calculate a fair distance using selected samples, and how many instances to use from each set.
  arXiv  Detail & Related papers  (2023-04-04T17:54:32Z)
• ENInst: Enhancing Weakly-supervised Low-shot Instance Segmentation [23.621454800084724]
  We address a weakly-supervised low-shot instance segmentation, an annotation-efficient training method to deal with novel classes effectively. Our ENInst is 7.5 times more efficient in achieving comparable performance to the existing fully-supervised few-shot models and even outperforms them at times.
  arXiv  Detail & Related papers  (2023-02-20T05:15:23Z)
• A Practical Contrastive Learning Framework for Single-Image Super-Resolution [51.422185656787285]
  We investigate contrastive learning-based single image super-resolution from two perspectives. We propose a practical contrastive learning framework for SISR, named PCL-SR. Compared with existing benchmark methods, we re-train them by our proposed PCL-SR framework and achieve superior performance.
  arXiv  Detail & Related papers  (2021-11-27T15:42:12Z)
• Hierarchical Deep CNN Feature Set-Based Representation Learning for Robust Cross-Resolution Face Recognition [59.29808528182607]
  Cross-resolution face recognition (CRFR) is important in intelligent surveillance and biometric forensics. Existing shallow learning-based and deep learning-based methods focus on mapping the HR-LR face pairs into a joint feature space. In this study, we desire to fully exploit the multi-level deep convolutional neural network (CNN) feature set for robust CRFR.
  arXiv  Detail & Related papers  (2021-03-25T14:03:42Z)
• Dynamic Feature Integration for Simultaneous Detection of Salient Object, Edge and Skeleton [108.01007935498104]
  In this paper, we solve three low-level pixel-wise vision problems, including salient object segmentation, edge detection, and skeleton extraction. We first show some similarities shared by these tasks and then demonstrate how they can be leveraged for developing a unified framework.
  arXiv  Detail & Related papers  (2020-04-18T11:10:11Z)

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.