Test-time adaptation updates pretrained models on the fly to handle distribution shifts in test data. While existing research has focused on stable optimization during adaptation, less attention has been given to enhancing model representations for adaptation capability. To address this gap, we propose Test-Time Ensemble (TTE) grounded in the intriguing property of linear mode connectivity. TTE leverages ensemble strategies during adaptation: 1) adaptively averaging the parameter weights of assorted test-time adapted models and 2) incorporating dropout to further promote representation diversity. These strategies encapsulate model diversity into a single model, avoiding computational burden associated with managing multiple models. Besides, we propose a robust knowledge distillation scheme to prevent model collapse, ensuring stable optimization and preserving the ensemble benefits during adaptation. Notably, TTE integrates seamlessly with existing TTA approaches, advancing their adaptation capabilities. In extensive experiments, integration with TTE consistently outperformed baseline models across various challenging scenarios, demonstrating its effectiveness and general applicability.

With the continual expansion of face datasets, feature-based distillation prevails for large-scale face recognition. In this work, we attempt to remove identity supervision in student training, to spare the GPU memory from saving massive class centers. However, this naive removal leads to inferior distillation result. We carefully inspect the performance degradation from the perspective of intrinsic dimension, and argue that the gap in intrinsic dimension, namely the intrinsic gap, is intimately connected to the infamous capacity gap problem. By constraining the teacher's search space with reverse distillation, we narrow the intrinsic gap and unleash the potential of feature-only distillation. Remarkably, the proposed reverse distillation creates universally student-friendly teacher that demonstrates outstanding student improvement. We further enhance its effectiveness by designing a student proxy to better bridge the intrinsic gap. As a result, the proposed method surpasses state-of-the-art distillation techniques with identity supervision on various face recognition benchmarks, and the improvements are consistent across different teacher-student pairs.

Unsupervised image-to-image translation has gained considerable attention due to recent impressive advances in generative adversarial networks (GANs). This paper presents a simple but effective regularization technique for improving GAN-based image-to-image translation. To generate images with realistic local semantics and structures, we propose an auxiliary self-supervision loss that enforces point-wise consistency of the overlapping region between a pair of patches cropped from a single real image during training the discriminator of a GAN. Our experiment shows that the proposed dense consistency regularization improves performance substantially on various image-to-image translation scenarios. It also leads to extra performance gains through the combination with instance-level regularization methods. Furthermore, we verify that the proposed model captures domain-specific characteristics more effectively with only a small fraction of training data.

Metric learning has attracted significant attention in the past decades, because of its appealing advances in various real-world tasks, e.g., person re-identification and face recognition. Traditional supervised metric learning attempts to seek a discriminative metric, which could minimize the pairwise distance of within-class data samples, while maximizing the pairwise distance of data samples from various classes. However, it is still a challenge to build a robust and discriminative metric, especially for corrupted data in the real-world application. In this paper, we propose a Robust Discriminative Metric Learning algorithm through fast low-rank representation and denoising strategy. To be specific, the metric learning problem is guided by a discriminative regularization by incorporating the pair-wise or class-wise information. Moreover, the low-rank basis learning is jointly optimized with the metric to better uncover the global data structure and remove noise. Furthermore, the fast low-rank representation is implemented to mitigate the computational burden and ensure the scalability on large-scale datasets. Finally, we evaluate our learned metric on several challenging tasks, e.g., face recognition/verification, object recognition, image clustering, and person re-identification. The experimental results verify the effectiveness of our proposed algorithm in comparison to many metric learning algorithms, even deep learning ones.

Spoofing using photographs or videos is one of the most common methods of attacking face recognition and verification systems. In this paper, we propose a real-time and nonintrusive method based on the diffusion speed of a single image to address this problem. In particular, inspired by the observation that the difference in surface properties between a live face and a fake one is efficiently revealed in the diffusion speed, we exploit antispoofing features by utilizing the total variation flow scheme. More specifically, we propose defining the local patterns of the diffusion speed, the so-called local speed patterns, as our features, which are input into the linear SVM classifier to determine whether the given face is fake or not. One important advantage of the proposed method is that, in contrast to previous approaches, it accurately identifies diverse malicious attacks regardless of the medium of the image, e.g., paper or screen. Moreover, the proposed method does not require any specific user action. Experimental results on various data sets show that the proposed method is effective for face liveness detection as compared with previous approaches proposed in studies in the literature.

In this letter, we propose a novel method to extract illumination-invariant features for face recognition and verification under varying illuminations. Inspired by the fact that normalized coefficients of the singular value decomposition (SVD) are insensitive to different illumination conditions, we exploit a simple, yet powerful scheme for describing underlying structures of faces, so-called SVD face. In contrast to previous approaches still suffering from the loss of details, our SVD face greatly preserves textures of the original image based on the relaxation of SVD coefficients. Theoretical analysis shows that our SVD face is an illumination-invariant measure and has an ability to discover meaningful components (e.g., eyes, mouth, etc.) of face images while suppressing the effect of various illuminations. Experimental results on both Yale B and our illuminated face (IF) datasets demonstrate that the SVD face is effective for face recognition and verification compared to previous approaches proposed in literature.

Forensic characterization of devices is important in many situations such as establishing the trust and verifying authenticity of data and the device that created it. Current forensic identification techniques for digital cameras, scanners and printers are highly reliable due to the fact that each of these devices cannot escape inherent electro-mechanical properties which add "signatures" to the data they produce. In this paper we will describe the sensor forensics work going on at Purdue University.

An efficient image resizing algorithm in the compressed domain with mixed field/frame-mode macroblocks is proposed. A 16/spl times/16 field/frame-mode macroblock is converted into an 8/spl times/8 reduced block in the discrete cosine transform (DCT) domain using a modified inverse DCT (IDGT) kernel which performs stronger lowpass filtering than the simple truncation in the DCT domain. Experimental results show that the proposed algorithm provides the resized image quality similar to an existing method with significantly lower computational complexity.