MIMIC: Mask Image Pre-training with Mix Contrastive Fine-tuning for Facial Expression Recognition

Cutting-edge research in facial expression recognition (FER) currently favors the utilization of convolutional neural networks (CNNs) backbone which is supervisedly pre-trained on face recognition datasets for feature extraction. However, due to the vast scale of face recognition datasets and the high cost associated with collecting facial labels, this pre-training paradigm incurs significant expenses. Towards this end, we propose to pre-train vision Transformers (ViTs) through a self-supervised approach on a mid-scale general image dataset. In addition, when compared with the domain disparity existing between face datasets and FER datasets, the divergence between general datasets and FER datasets is more pronounced. Therefore, we propose a contrastive fine-tuning approach to effectively mitigate this domain disparity. Specifically, we introduce a novel FER training paradigm named Mask Image pre-training with MIx Contrastive fine-tuning (MIMIC). In the initial phase, we pre-train the ViT via masked image reconstruction on general images. Subsequently, in the fine-tuning stage, we introduce a mix-supervised contrastive learning process, which enhances the model with a more extensive range of positive samples by the mixing strategy. Through extensive experiments conducted on three benchmark datasets, we demonstrate that our MIMIC outperforms the previous training paradigm, showing its capability to learn better representations. Remarkably, the results indicate that the vanilla ViT can achieve impressive performance without the need for intricate, auxiliary-designed modules. Moreover, when scaling up the model size, MIMIC exhibits no performance saturation and is superior to the current state-of-the-art methods.

Retrieving Multimodal Information for Augmented Generation: A Survey

In this survey, we review methods that retrieve multimodal knowledge to assist and augment generative models. This group of works focuses on retrieving grounding contexts from external sources, including images, codes, tables, graphs, and audio. As multimodal learning and generative AI have become more and more impactful, such retrieval augmentation offers a promising solution to important concerns such as factuality, reasoning, interpretability, and robustness. We provide an in-depth review of retrieval-augmented generation in different modalities and discuss potential future directions. As this is an emerging field, we continue to add new papers and methods.

Adapter Incremental Continual Learning of Efficient Audio Spectrogram Transformers

Continual learning involves training neural networks incrementally for new tasks while retaining the knowledge of previous tasks. However, efficiently fine-tuning the model for sequential tasks with minimal computational resources remains a challenge. In this paper, we propose Task Incremental Continual Learning (TI-CL) of audio classifiers with both parameter-efficient and compute-efficient Audio Spectrogram Transformers (AST). To reduce the trainable parameters without performance degradation for TI-CL, we compare several Parameter Efficient Transfer (PET) methods and propose AST with Convolutional Adapters for TI-CL, which has less than 5% of trainable parameters of the fully fine-tuned counterparts. To reduce the computational complexity, we introduce a novel Frequency-Time factorized Attention (FTA) method that replaces the traditional self-attention in transformers for audio spectrograms. FTA achieves competitive performance with only a factor of the computations required by Global Self-Attention (GSA). Finally, we formulate our method for TI-CL, called Adapter Incremental Continual Learning (AI-CL), as a combination of the "parameter-efficient" Convolutional Adapter and the "compute-efficient" FTA. Experiments on ESC-50, SpeechCommandsV2 (SCv2), and Audio-Visual Event (AVE) benchmarks show that our proposed method prevents catastrophic forgetting in TI-CL while maintaining a lower computational budget.

Flexible-modal Deception Detection with Audio-Visual Adapter

Detecting deception by human behaviors is vital in many fields such as custom security and multimedia anti-fraud. Recently, audio-visual deception detection attracts more attention due to its better performance than using only a single modality. However, in real-world multi-modal settings, the integrity of data can be an issue (e.g., sometimes only partial modalities are available). The missing modality might lead to a decrease in performance, but the model still learns the features of the missed modality. In this paper, to further improve the performance and overcome the missing modality problem, we propose a novel Transformer-based framework with an Audio-Visual Adapter (AVA) to fuse temporal features across two modalities efficiently. Extensive experiments conducted on two benchmark datasets demonstrate that the proposed method can achieve superior performance compared with other multi-modal fusion methods under flexible-modal (multiple and missing modalities) settings.

Towards Photo-Realistic Virtual Try-On by Adaptively Generating$\leftrightarrow$Preserving Image Content

Image visual try-on aims at transferring a target clothing image onto a reference person, and has become a hot topic in recent years. Prior arts usually focus on preserving the character of a clothing image (e.g. texture, logo, embroidery) when warping it to arbitrary human pose. However, it remains a big challenge to generate photo-realistic try-on images when large occlusions and human poses are presented in the reference person. To address this issue, we propose a novel visual try-on network, namely Adaptive Content Generating and Preserving Network (ACGPN). In particular, ACGPN first predicts semantic layout of the reference image that will be changed after try-on (e.g. long sleeve shirt$\rightarrow$arm, arm$\rightarrow$jacket), and then determines whether its image content needs to be generated or preserved according to the predicted semantic layout, leading to photo-realistic try-on and rich clothing details. ACGPN generally involves three major modules. First, a semantic layout generation module utilizes semantic segmentation of the reference image to progressively predict the desired semantic layout after try-on. Second, a clothes warping module warps clothing images according to the generated semantic layout, where a second-order difference constraint is introduced to stabilize the warping process during training. Third, an inpainting module for content fusion integrates all information (e.g. reference image, semantic layout, warped clothes) to adaptively produce each semantic part of human body. In comparison to the state-of-the-art methods, ACGPN can generate photo-realistic images with much better perceptual quality and richer fine-details.