Mrityunjoy Gain

Avi Deb Raha, Apurba Adhikary, Mrityunjoy Gain et al.

In this study, we explore the efficacy of advanced pre-trained architectures, such as Vision Transformers (ViT), ConvNeXt, and Swin Transformers in enhancing Federated Domain Generalization. These architectures capture global contextual features and model long-range dependencies, making them promising candidates for improving cross-domain generalization. We conduct a broad study with in-depth analysis and systematically evaluate different variants of these architectures, using extensive pre-training datasets such as ImageNet-1K, ImageNet-21K, JFT-300M, and ImageNet-22K. Additionally, we compare self-supervised and supervised pre-training strategies to assess their impact on FDG performance. Our findings suggest that self-supervised techniques, which focus on reconstructing masked image patches, can better capture the intrinsic structure of images, thereby outperforming their supervised counterparts. Comprehensive evaluations on the Office-Home and PACS datasets demonstrate that adopting advanced architectures pre-trained on larger datasets establishes new benchmarks, achieving average accuracies of 84.46\% and 92.55\%, respectively. Additionally, we observe that certain variants of these advanced models, despite having fewer parameters, outperform larger ResNet models. This highlights the critical role of utilizing sophisticated architectures and diverse pre-training strategies to enhance FDG performance, especially in scenarios with limited computational resources where model efficiency is crucial. Our results indicate that federated learning systems can become more adaptable and efficient by leveraging these advanced methods, offering valuable insights for future research in FDG.

Mrityunjoy Gain, Avi Deb Raha, Rameswar Debnath

Automatic colorization of gray images with objects of different colors and sizes is challenging due to inter- and intra-object color variation and the small area of the main objects due to extensive backgrounds. The learning process often favors dominant features, resulting in a biased model. In this paper, we formulate the colorization problem into a multinomial classification problem and then apply a weighted function to classes. We propose a set of formulas to transform color values into color classes and vice versa. Class optimization and balancing feature distribution are the keys for good performance. Observing class appearance on various extremely large-scale real-time images in practice, we propose 215 color classes for our colorization task. During training, we propose a class-weighted function based on true class appearance in each batch to ensure proper color saturation of individual objects. We establish a trade-off between major and minor classes to provide orthodox class prediction by eliminating major classes' dominance over minor classes. As we apply regularization to enhance the stability of the minor class, occasional minor noise may appear at the object's edges. We propose a novel object-selective color harmonization method empowered by the SAM to refine and enhance these edges. We propose a new color image evaluation metric, the Chromatic Number Ratio (CNR), to quantify the richness of color components. We compare our proposed model with state-of-the-art models using five different datasets: ADE, Celeba, COCO, Oxford 102 Flower, and ImageNet, in both qualitative and quantitative approaches. The experimental results show that our proposed model outstrips other models in visualization and CNR measurement criteria while maintaining satisfactory performance in regression (MSE, PSNR), similarity (SSIM, LPIPS, UIQI), and generative criteria (FID).

Mrityunjoy Gain, Avi Deb Raha, Rameswar Debnath

In this paper, we formulate the colorization problem into a multinomial classification problem and then apply a weighted function to classes. We propose a set of formulas to transform color values into color classes and vice versa. To optimize the classes, we experiment with different bin sizes for color class transformation. Observing class appearance, standard deviation, and model parameters on various extremely large-scale real-time images in practice we propose 532 color classes for our classification task. During training, we propose a class-weighted function based on true class appearance in each batch to ensure proper saturation of individual objects. We adjust the weights of the major classes, which are more frequently observed, by lowering them, while escalating the weights of the minor classes, which are less commonly observed. In our class re-weight formula, we propose a hyper-parameter for finding the optimal trade-off between the major and minor appeared classes. As we apply regularization to enhance the stability of the minor class, occasional minor noise may appear at the object's edges. We propose a novel object-selective color harmonization method empowered by the Segment Anything Model (SAM) to refine and enhance these edges. We propose two new color image evaluation metrics, the Color Class Activation Ratio (CCAR), and the True Activation Ratio (TAR), to quantify the richness of color components. We compare our proposed model with state-of-the-art models using six different dataset: Place, ADE, Celeba, COCO, Oxford 102 Flower, and ImageNet, in qualitative and quantitative approaches. The experimental results show that our proposed model outstrips other models in visualization, CNR and in our proposed CCAR and TAR measurement criteria while maintaining satisfactory performance in regression (MSE, PSNR), similarity (SSIM, LPIPS, UIUI), and generative criteria (FID).

Sumit Kumar Dam, Mrityunjoy Gain, Eui-Nam Huh et al.

Implicit Neural Representations (INRs) have emerged as a powerful alternative to traditional pixel-based formats by modeling images as continuous functions over spatial coordinates. A key challenge, however, lies in the spectral bias of neural networks, which tend to favor low-frequency components while struggling to capture high-frequency (HF) details such as sharp edges and fine textures. While prior approaches have addressed this limitation through architectural modifications or specialized activation functions, we propose an orthogonal direction by directly guiding the training process. Specifically, we introduce a two-stage training strategy where a neighbor-aware soft mask adaptively assigns higher weights to pixels with strong local variations, encouraging early focus on fine details. The model then transitions to full-image training. Experimental results show that our approach consistently improves reconstruction quality and complements existing INR methods. As a pioneering attempt to assign frequency-aware importance to pixels in image INR, our work offers a new avenue for mitigating the spectral bias problem.

Mrityunjoy Gain, Kitae Kim, Avi Deb Raha et al.

In this paper, we propose the FedFeat+ framework, which distinctively separates feature extraction from classification. We develop a two-tiered model training process: following local training, clients transmit their weights and some features extracted from the feature extractor from the final local epochs to the server. The server aggregates these models using the FedAvg method and subsequently retrains the global classifier utilizing the shared features. The classifier retraining process enhances the model's understanding of the holistic view of the data distribution, ensuring better generalization across diverse datasets. This improved generalization enables the classifier to adaptively influence the feature extractor during subsequent local training epochs. We establish a balance between enhancing model accuracy and safeguarding individual privacy through the implementation of differential privacy mechanisms. By incorporating noise into the feature vectors shared with the server, we ensure that sensitive data remains confidential. We present a comprehensive convergence analysis, along with theoretical reasoning regarding performance enhancement and privacy preservation. We validate our approach through empirical evaluations conducted on benchmark datasets, including CIFAR-10, CIFAR-100, MNIST, and FMNIST, achieving high accuracy while adhering to stringent privacy guarantees. The experimental results demonstrate that the FedFeat+ framework, despite using only a lightweight two-layer CNN classifier, outperforms the FedAvg method in both IID and non-IID scenarios, achieving accuracy improvements ranging from 3.92 % to 12.34 % across CIFAR-10, CIFAR-100, and Fashion-MNIST datasets.