A key challenge in visible-infrared person re-identification (V-I ReID) is training a backbone model capable of effectively addressing the significant discrepancies across modalities. State-of-the-art methods that generate a single intermediate bridging domain are often less effective, as this generated domain may not adequately capture sufficient common discriminant information. This paper introduces the Bidirectional Multi-step Domain Generalization (BMDG), a novel approach for unifying feature representations across diverse modalities. BMDG creates multiple virtual intermediate domains by finding and aligning body part features extracted from both I and V modalities. Indeed, BMDG aims to reduce the modality gaps in two steps. First, it aligns modalities in feature space by learning shared and modality-invariant body part prototypes from V and I images. Then, it generalizes the feature representation by applying bidirectional multi-step learning, which progressively refines feature representations in each step and incorporates more prototypes from both modalities. In particular, our method minimizes the cross-modal gap by identifying and aligning shared prototypes that capture key discriminative features across modalities, then uses multiple bridging steps based on this information to enhance the feature representation. Experiments conducted on challenging V-I ReID datasets indicate that our BMDG approach outperforms state-of-the-art part-based models or methods that generate an intermediate domain from V-I person ReID.
Audiovisual emotion recognition (ER) in videos has immense potential over unimodal performance. It effectively leverages the inter- and intra-modal dependencies between visual and auditory modalities. This work proposes a novel audio-visual emotion recognition system utilizing a joint multimodal transformer architecture with key-based cross-attention. This framework aims to exploit the complementary nature of audio and visual cues (facial expressions and vocal patterns) in videos, leading to superior performance compared to solely relying on a single modality. The proposed model leverages separate backbones for capturing intra-modal temporal dependencies within each modality (audio and visual). Subsequently, a joint multimodal transformer architecture integrates the individual modality embeddings, enabling the model to effectively capture inter-modal (between audio and visual) and intra-modal (within each modality) relationships. Extensive evaluations on the challenging Affwild2 dataset demonstrate that the proposed model significantly outperforms baseline and state-of-the-art methods in ER tasks.
Domain adaptation methods for object detection (OD) strive to mitigate the impact of distribution shifts by promoting feature alignment across source and target domains. Multi-source domain adaptation (MSDA) allows leveraging multiple annotated source datasets, and unlabeled target data to improve the accuracy and robustness of the detection model. Most state-of-the-art MSDA methods for OD perform feature alignment in a class-agnostic manner. This is challenging since the objects have unique modal information due to variations in object appearance across domains. A recent prototype-based approach proposed a class-wise alignment, yet it suffers from error accumulation due to noisy pseudo-labels which can negatively affect adaptation with imbalanced data. To overcome these limitations, we propose an attention-based class-conditioned alignment scheme for MSDA that aligns instances of each object category across domains. In particular, an attention module coupled with an adversarial domain classifier allows learning domain-invariant and class-specific instance representations. Experimental results on multiple benchmarking MSDA datasets indicate that our method outperforms the state-of-the-art methods and is robust to class imbalance. Our code is available at https://github.com/imatif17/ACIA.
While state-of-the-art facial expression recognition (FER) classifiers achieve a high level of accuracy, they lack interpretability, an important aspect for end-users. To recognize basic facial expressions, experts resort to a codebook associating a set of spatial action units to a facial expression. In this paper, we follow the same expert footsteps, and propose a learning strategy that allows us to explicitly incorporate spatial action units (aus) cues into the classifier's training to build a deep interpretable model. In particular, using this aus codebook, input image expression label, and facial landmarks, a single action units heatmap is built to indicate the most discriminative regions of interest in the image w.r.t the facial expression. We leverage this valuable spatial cue to train a deep interpretable classifier for FER. This is achieved by constraining the spatial layer features of a classifier to be correlated with \aus map. Using a composite loss, the classifier is trained to correctly classify an image while yielding interpretable visual layer-wise attention correlated with aus maps, simulating the experts' decision process. This is achieved using only the image class expression as supervision and without any extra manual annotations. Moreover, our method is generic. It can be applied to any CNN- or transformer-based deep classifier without the need for architectural change or adding significant training time. Our extensive evaluation on two public benchmarks RAFDB, and AFFECTNET datasets shows that our proposed strategy can improve layer-wise interpretability without degrading classification performance. In addition, we explore a common type of interpretable classifiers that rely on Class-Activation Mapping methods (CAMs), and we show that our training technique improves the CAM interpretability.
Multimodal affect recognition models have reached remarkable performance in the lab environment due to their ability to model complementary and redundant semantic information. However, these models struggle in the wild, mainly because of the unavailability or quality of modalities used for training. In practice, only a subset of the training-time modalities may be available at test time. Learning with privileged information (PI) enables deep learning models (DL) to exploit data from additional modalities only available during training. State-of-the-art knowledge distillation (KD) methods have been proposed to distill multiple teacher models (each trained on a modality) to a common student model. These privileged KD methods typically utilize point-to-point matching and have no explicit mechanism to capture the structural information in the teacher representation space formed by introducing the privileged modality. We argue that encoding this same structure in the student space may lead to enhanced student performance. This paper introduces a new structural KD mechanism based on optimal transport (OT), where entropy-regularized OT distills the structural dark knowledge. Privileged KD with OT (PKDOT) method captures the local structures in the multimodal teacher representation by calculating a cosine similarity matrix and selects the top-k anchors to allow for sparse OT solutions, resulting in a more stable distillation process. Experiments were performed on two different problems: pain estimation on the Biovid dataset (ordinal classification) and arousal-valance prediction on the Affwild2 dataset (regression). Results show that the proposed method can outperform state-of-the-art privileged KD methods on these problems. The diversity of different modalities and fusion architectures indicates that the proposed PKDOT method is modality and model-agnostic.
The dot product self-attention (DPSA) is a fundamental component of transformers. However, scaling them to long sequences, like documents or high-resolution images, becomes prohibitively expensive due to quadratic time and memory complexities arising from the softmax operation. Kernel methods are employed to simplify computations by approximating softmax but often lead to performance drops compared to softmax attention. We propose SeTformer, a novel transformer, where DPSA is purely replaced by Self-optimal Transport (SeT) for achieving better performance and computational efficiency. SeT is based on two essential softmax properties: maintaining a non-negative attention matrix and using a nonlinear reweighting mechanism to emphasize important tokens in input sequences. By introducing a kernel cost function for optimal transport, SeTformer effectively satisfies these properties. In particular, with small and basesized models, SeTformer achieves impressive top-1 accuracies of 84.7% and 86.2% on ImageNet-1K. In object detection, SeTformer-base outperforms the FocalNet counterpart by +2.2 mAP, using 38% fewer parameters and 29% fewer FLOPs. In semantic segmentation, our base-size model surpasses NAT by +3.5 mIoU with 33% fewer parameters. SeTformer also achieves state-of-the-art results in language modeling on the GLUE benchmark. These findings highlight SeTformer's applicability in vision and language tasks.
Automatic pain intensity estimation plays a pivotal role in healthcare and medical fields. While many methods have been developed to gauge human pain using behavioral or physiological indicators, facial expressions have emerged as a prominent tool for this purpose. Nevertheless, the dependence on labeled data for these techniques often renders them expensive and time-consuming. To tackle this, we introduce the Adaptive Hierarchical Spatio-temporal Dynamic Image (AHDI) technique. AHDI encodes spatiotemporal changes in facial videos into a singular RGB image, permitting the application of simpler 2D deep models for video representation. Within this framework, we employ a residual network to derive generalized facial representations. These representations are optimized for two tasks: estimating pain intensity and differentiating between genuine and simulated pain expressions. For the former, a regression model is trained using the extracted representations, while for the latter, a binary classifier identifies genuine versus feigned pain displays. Testing our method on two widely-used pain datasets, we observed encouraging results for both tasks. On the UNBC database, we achieved an MSE of 0.27 outperforming the SOTA which had an MSE of 0.40. On the BioVid dataset, our model achieved an accuracy of 89.76%, which is an improvement of 5.37% over the SOTA accuracy. Most notably, for distinguishing genuine from simulated pain, our accuracy stands at 94.03%, marking a substantial improvement of 8.98%. Our methodology not only minimizes the need for extensive labeled data but also augments the precision of pain evaluations, facilitating superior pain management.
Adapting a deep learning (DL) model to a specific target individual is a challenging task in facial expression recognition (FER) that may be achieved using unsupervised domain adaptation (UDA) methods. Although several UDA methods have been proposed to adapt deep FER models across source and target data sets, multiple subject-specific source domains are needed to accurately represent the intra- and inter-person variability in subject-based adaption. In this paper, we consider the setting where domains correspond to individuals, not entire datasets. Unlike UDA, multi-source domain adaptation (MSDA) methods can leverage multiple source datasets to improve the accuracy and robustness of the target model. However, previous methods for MSDA adapt image classification models across datasets and do not scale well to a larger number of source domains. In this paper, a new MSDA method is introduced for subject-based domain adaptation in FER. It efficiently leverages information from multiple source subjects (labeled source domain data) to adapt a deep FER model to a single target individual (unlabeled target domain data). During adaptation, our Subject-based MSDA first computes a between-source discrepancy loss to mitigate the domain shift among data from several source subjects. Then, a new strategy is employed to generate augmented confident pseudo-labels for the target subject, allowing a reduction in the domain shift between source and target subjects. Experiments\footnote{\textcolor{red}{\textbf{Supplementary material} contains our code, which will be made public, and additional experimental results.}} on the challenging BioVid heat and pain dataset (PartA) with 87 subjects shows that our Subject-based MSDA can outperform state-of-the-art methods yet scale well to multiple subject-based source domains.
Object detection models are commonly used for people counting (and localization) in many applications but require a dataset with costly bounding box annotations for training. Given the importance of privacy in people counting, these models rely more and more on infrared images, making the task even harder. In this paper, we explore how weaker levels of supervision can affect the performance of deep person counting architectures for image classification and point-level localization. Our experiments indicate that counting people using a CNN Image-Level model achieves competitive results with YOLO detectors and point-level models, yet provides a higher frame rate and a similar amount of model parameters.