Active Learning with Contrastive Pre-training for Facial Expression Recognition

Deep learning has played a significant role in the success of facial expression recognition (FER), thanks to large models and vast amounts of labelled data. However, obtaining labelled data requires a tremendous amount of human effort, time, and financial resources. Even though some prior works have focused on reducing the need for large amounts of labelled data using different unsupervised methods, another promising approach called active learning is barely explored in the context of FER. This approach involves selecting and labelling the most representative samples from an unlabelled set to make the best use of a limited 'labelling budget'. In this paper, we implement and study 8 recent active learning methods on three public FER datasets, FER13, RAF-DB, and KDEF. Our findings show that existing active learning methods do not perform well in the context of FER, likely suffering from a phenomenon called 'Cold Start', which occurs when the initial set of labelled samples is not well representative of the entire dataset. To address this issue, we propose contrastive self-supervised pre-training, which first learns the underlying representations based on the entire unlabelled dataset. We then follow this with the active learning methods and observe that our 2-step approach shows up to 9.2% improvement over random sampling and up to 6.7% improvement over the best existing active learning baseline without the pre-training. We will make the code for this study public upon publication at: github.com/ShuvenduRoy/ActiveFER.

Continual Learning for Out-of-Distribution Pedestrian Detection

A continual learning solution is proposed to address the out-of-distribution generalization problem for pedestrian detection. While recent pedestrian detection models have achieved impressive performance on various datasets, they remain sensitive to shifts in the distribution of the inference data. Our method adopts and modifies Elastic Weight Consolidation to a backbone object detection network, in order to penalize the changes in the model weights based on their importance towards the initially learned task. We show that when trained with one dataset and fine-tuned on another, our solution learns the new distribution and maintains its performance on the previous one, avoiding catastrophic forgetting. We use two popular datasets, CrowdHuman and CityPersons for our cross-dataset experiments, and show considerable improvements over standard fine-tuning, with a 9% and 18% miss rate percent reduction improvement in the CrowdHuman and CityPersons datasets, respectively.

Can Continual Learning Improve Long-Tailed Recognition? Toward a Unified Framework

The Long-Tailed Recognition (LTR) problem emerges in the context of learning from highly imbalanced datasets, in which the number of samples among different classes is heavily skewed. LTR methods aim to accurately learn a dataset comprising both a larger Head set and a smaller Tail set. We propose a theorem where under the assumption of strong convexity of the loss function, the weights of a learner trained on the full dataset are within an upper bound of the weights of the same learner trained strictly on the Head. Next, we assert that by treating the learning of the Head and Tail as two separate and sequential steps, Continual Learning (CL) methods can effectively update the weights of the learner to learn the Tail without forgetting the Head. First, we validate our theoretical findings with various experiments on the toy MNIST-LT dataset. We then evaluate the efficacy of several CL strategies on multiple imbalanced variations of two standard LTR benchmarks (CIFAR100-LT and CIFAR10-LT), and show that standard CL methods achieve strong performance gains in comparison to baselines and approach solutions that have been tailor-made for LTR. We also assess the applicability of CL techniques on real-world data by exploring CL on the naturally imbalanced Caltech256 dataset and demonstrate its superiority over state-of-the-art classifiers. Our work not only unifies LTR and CL but also paves the way for leveraging advances in CL methods to tackle the LTR challenge more effectively.

Unmasking Deepfakes: Masked Autoencoding Spatiotemporal Transformers for Enhanced Video Forgery Detection

We present a novel approach for the detection of deepfake videos using a pair of vision transformers pre-trained by a self-supervised masked autoencoding setup. Our method consists of two distinct components, one of which focuses on learning spatial information from individual RGB frames of the video, while the other learns temporal consistency information from optical flow fields generated from consecutive frames. Unlike most approaches where pre-training is performed on a generic large corpus of images, we show that by pre-training on smaller face-related datasets, namely Celeb-A (for the spatial learning component) and YouTube Faces (for the temporal learning component), strong results can be obtained. We perform various experiments to evaluate the performance of our method on commonly used datasets namely FaceForensics++ (Low Quality and High Quality, along with a new highly compressed version named Very Low Quality) and Celeb-DFv2 datasets. Our experiments show that our method sets a new state-of-the-art on FaceForensics++ (LQ, HQ, and VLQ), and obtains competitive results on Celeb-DFv2. Moreover, our method outperforms other methods in the area in a cross-dataset setup where we fine-tune our model on FaceForensics++ and test on CelebDFv2, pointing to its strong cross-dataset generalization ability.

Toward Fair Facial Expression Recognition with Improved Distribution Alignment

We present a novel approach to mitigate bias in facial expression recognition (FER) models. Our method aims to reduce sensitive attribute information such as gender, age, or race, in the embeddings produced by FER models. We employ a kernel mean shrinkage estimator to estimate the kernel mean of the distributions of the embeddings associated with different sensitive attribute groups, such as young and old, in the Hilbert space. Using this estimation, we calculate the maximum mean discrepancy (MMD) distance between the distributions and incorporate it in the classifier loss along with an adversarial loss, which is then minimized through the learning process to improve the distribution alignment. Our method makes sensitive attributes less recognizable for the model, which in turn promotes fairness. Additionally, for the first time, we analyze the notion of attractiveness as an important sensitive attribute in FER models and demonstrate that FER models can indeed exhibit biases towards more attractive faces. To prove the efficacy of our model in reducing bias regarding different sensitive attributes (including the newly proposed attractiveness attribute), we perform several experiments on two widely used datasets, CelebA and RAF-DB. The results in terms of both accuracy and fairness measures outperform the state-of-the-art in most cases, demonstrating the effectiveness of the proposed method.

Uncovering the Hidden Dynamics of Video Self-supervised Learning under Distribution Shifts

Video self-supervised learning (VSSL) has made significant progress in recent years. However, the exact behavior and dynamics of these models under different forms of distribution shift are not yet known. In this paper, we comprehensively study the behavior of six popular self-supervised methods (v-SimCLR, v-MOCO, v-BYOL, v-SimSiam, v-DINO, v-MAE) in response to various forms of natural distribution shift, i.e., (i) context shift, (ii) viewpoint shift, (iii) actor shift, (iv) source shift, (v) generalizability to unknown classes (zero-shot), and (vi) open-set recognition. To perform this extensive study, we carefully craft a test bed consisting of $17$ in-distribution and out-of-distribution benchmark pairs using available public datasets and a series of evaluation protocols to stress-test the different methods under the intended shifts. Our study uncovers a series of intriguing findings and interesting behaviors of VSSL methods. For instance, we observe that while video models generally struggle with context shifts, v-MAE and supervised learning exhibit more robustness. Moreover, our study shows that v-MAE is a strong temporal learner, whereas contrastive methods, v-SimCLR and v-MOCO, exhibit strong performances against viewpoint shifts. When studying the notion of open-set recognition, we notice a trade-off between closed-set and open-set recognition performance, particularly if the pretrained VSSL encoders are used without finetuning. We hope that our work will contribute to the development of robust video representation learning frameworks for various real-world scenarios.

Exploring the Boundaries of Semi-Supervised Facial Expression Recognition: Learning from In-Distribution, Out-of-Distribution, and Unconstrained Data

Deep learning-based methods have been the key driving force behind much of the recent success of facial expression recognition (FER) systems. However, the need for large amounts of labelled data remains a challenge. Semi-supervised learning offers a way to overcome this limitation, allowing models to learn from a small amount of labelled data along with a large unlabelled dataset. While semi-supervised learning has shown promise in FER, most current methods from general computer vision literature have not been explored in the context of FER. In this work, we present a comprehensive study on 11 of the most recent semi-supervised methods, in the context of FER, namely Pi-model, Pseudo-label, Mean Teacher, VAT, UDA, MixMatch, ReMixMatch, FlexMatch, CoMatch, and CCSSL. Our investigation covers semi-supervised learning from in-distribution, out-of-distribution, unconstrained, and very small unlabelled data. Our evaluation includes five FER datasets plus one large face dataset for unconstrained learning. Our results demonstrate that FixMatch consistently achieves better performance on in-distribution unlabelled data, while ReMixMatch stands out among all methods for out-of-distribution, unconstrained, and scarce unlabelled data scenarios. Another significant observation is that semi-supervised learning produces a reasonable improvement over supervised learning, regardless of whether in-distribution, out-of-distribution, or unconstrained data is utilized as the unlabelled set. We also conduct sensitivity analyses on critical hyper-parameters for the two best methods of each setting.

Scaling Up Semi-supervised Learning with Unconstrained Unlabelled Data

We propose UnMixMatch, a semi-supervised learning framework which can learn effective representations from unconstrained unlabelled data in order to scale up performance. Most existing semi-supervised methods rely on the assumption that labelled and unlabelled samples are drawn from the same distribution, which limits the potential for improvement through the use of free-living unlabeled data. Consequently, the generalizability and scalability of semi-supervised learning are often hindered by this assumption. Our method aims to overcome these constraints and effectively utilize unconstrained unlabelled data in semi-supervised learning. UnMixMatch consists of three main components: a supervised learner with hard augmentations that provides strong regularization, a contrastive consistency regularizer to learn underlying representations from the unlabelled data, and a self-supervised loss to enhance the representations that are learnt from the unlabelled data. We perform extensive experiments on 4 commonly used datasets and demonstrate superior performance over existing semi-supervised methods with a performance boost of 4.79%. Extensive ablation and sensitivity studies show the effectiveness and impact of each of the proposed components of our method.

Consistency-guided Prompt Learning for Vision-Language Models

We propose Consistency-guided Prompt learning (CoPrompt), a new fine-tuning method for vision-language models that addresses the challenge of improving the generalization capability of large foundation models while fine-tuning them on downstream tasks in a few-shot setting. The basic idea of CoPrompt is to enforce a consistency constraint in the prediction of the trainable and pre-trained models to prevent overfitting on the downstream task. Additionally, we introduce the following two components into our consistency constraint to further boost the performance: enforcing consistency on two perturbed inputs and combining two dominant paradigms of tuning, prompting and adapter. Enforcing consistency on perturbed input further regularizes the consistency constraint, effectively improving generalization, while tuning additional parameters with prompting and adapters improves the performance on downstream tasks. Extensive experiments show that CoPrompt outperforms existing methods on a range of evaluation suites, including base-to-novel generalization, domain generalization, and cross-dataset evaluation tasks. On the generalization task, CoPrompt improves the state-of-the-art by 2.09% on the zero-shot task and 1.93% on the harmonic mean over 11 recognition datasets. Detailed ablation studies show the effectiveness of each of the components in CoPrompt.

Privacy-Preserving Remote Heart Rate Estimation from Facial Videos

Remote Photoplethysmography (rPPG) is the process of estimating PPG from facial videos. While this approach benefits from contactless interaction, it is reliant on videos of faces, which often constitutes an important privacy concern. Recent research has revealed that deep learning techniques are vulnerable to attacks, which can result in significant data breaches making deep rPPG estimation even more sensitive. To address this issue, we propose a data perturbation method that involves extraction of certain areas of the face with less identity-related information, followed by pixel shuffling and blurring. Our experiments on two rPPG datasets (PURE and UBFC) show that our approach reduces the accuracy of facial recognition algorithms by over 60%, with minimal impact on rPPG extraction. We also test our method on three facial recognition datasets (LFW, CALFW, and AgeDB), where our approach reduced performance by nearly 50%. Our findings demonstrate the potential of our approach as an effective privacy-preserving solution for rPPG estimation.