PRG: Prompt-Based Distillation Without Annotation via Proxy Relational Graph

In this paper, we propose a new distillation method for extracting knowledge from Large Foundation Models (LFM) into lightweight models, introducing a novel supervision mode that does not require manually annotated data. While LFMs exhibit exceptional zero-shot classification abilities across datasets, relying solely on LFM-generated embeddings for distillation poses two main challenges: LFM's task-irrelevant knowledge and the high density of features. The transfer of task-irrelevant knowledge could compromise the student model's discriminative capabilities, and the high density of features within target domains obstructs the extraction of discriminative knowledge essential for the task. To address this issue, we introduce the Proxy Relational Graph (PRG) method. We initially extract task-relevant knowledge from LFMs by calculating a weighted average of logits obtained through text prompt embeddings. Then we construct sample-class proxy graphs for LFM and student models, respectively, to model the correlation between samples and class proxies. Then, we achieve the distillation of selective knowledge by aligning the relational graphs produced by both the LFM and the student model. Specifically, the distillation from LFM to the student model is achieved through two types of alignment: 1) aligning the sample nodes produced by the student model with those produced by the LFM, and 2) aligning the edge relationships in the student model's graph with those in the LFM's graph. Our experimental results validate the effectiveness of PRG, demonstrating its ability to leverage the extensive knowledge base of LFMs while skillfully circumventing their inherent limitations in focused learning scenarios. Notably, in our annotation-free framework, PRG achieves an accuracy of 76.23\% (T: 77.9\%) on CIFAR-100 and 72.44\% (T: 75.3\%) on the ImageNet-1K.

TexRO: Generating Delicate Textures of 3D Models by Recursive Optimization

This paper presents TexRO, a novel method for generating delicate textures of a known 3D mesh by optimizing its UV texture. The key contributions are two-fold. We propose an optimal viewpoint selection strategy, that finds the most miniature set of viewpoints covering all the faces of a mesh. Our viewpoint selection strategy guarantees the completeness of a generated result. We propose a recursive optimization pipeline that optimizes a UV texture at increasing resolutions, with an adaptive denoising method that re-uses existing textures for new texture generation. Through extensive experimentation, we demonstrate the superior performance of TexRO in terms of texture quality, detail preservation, visual consistency, and, notably runtime speed, outperforming other current methods. The broad applicability of TexRO is further confirmed through its successful use on diverse 3D models.

GEA: Reconstructing Expressive 3D Gaussian Avatar from Monocular Video

This paper presents GEA, a novel method for creating expressive 3D avatars with high-fidelity reconstructions of body and hands based on 3D Gaussians. The key contributions are twofold. First, we design a two-stage pose estimation method to obtain an accurate SMPL-X pose from input images, providing a correct mapping between the pixels of a training image and the SMPL-X model. It uses an attention-aware network and an optimization scheme to align the normal and silhouette between the estimated SMPL-X body and the real body in the image. Second, we propose an iterative re-initialization strategy to handle unbalanced aggregation and initialization bias faced by Gaussian representation. This strategy iteratively redistributes the avatar's Gaussian points, making it evenly distributed near the human body surface by applying meshing, resampling and re-Gaussian operations. As a result, higher-quality rendering can be achieved. Extensive experimental analyses validate the effectiveness of the proposed model, demonstrating that it achieves state-of-the-art performance in photorealistic novel view synthesis while offering fine-grained control over the human body and hand pose. Project page: https://3d-aigc.github.io/GEA/.

Memory-based Jitter: Improving Visual Recognition on Long-tailed Data with Diversity In Memory

This paper considers deep visual recognition on long-tailed data, with the majority categories only occupying relatively few samples. The tail categories are prone to lack of within-class diversity, which compromises the representative ability of the learned visual concepts. A radical solution is to augment the tail categories with higher diversity. To this end, we introduce a simple and reliable method named Memory-based Jitter (MBJ) to gain extra diversity for the tail data. We observe that the deep model keeps on jittering from one historical edition to another, even when it already approaches convergence. The ``jitter'' means the small variations between historical models. We argue that such jitter largely originates from the within-class diversity of the overall data and thus encodes the within-class distribution pattern. To utilize such jitter for tail data augmentation, we store the jitter among historical models into a memory bank and get the so-called Memory-based Jitter. With slight modifications, MBJ is applicable for two fundamental visual recognition tasks, \emph{i.e.}, image classification and deep metric learning (on long-tailed data). On image classification, MBJ collects the historical embeddings to learn an accurate classifier. In contrast, on deep metric learning, it collects the historical prototypes of each class to learn a robust deep embedding. Under both scenarios, MBJ enforces higher concentration on tail classes, so as to compensate for their lack of diversity. Extensive experiments on three long-tailed classification benchmarks and two deep metric learning benchmarks (person re-identification, in particular) demonstrate the significant improvement. Moreover, the achieved performance are on par with the state-of-the-art on both tasks.

Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspective

This paper considers learning deep features from long-tailed data. We observe that in the deep feature space, the head classes and the tail classes present different distribution patterns. The head classes have a relatively large spatial span, while the tail classes have significantly small spatial span, due to the lack of intra-class diversity. This uneven distribution between head and tail classes distorts the overall feature space, which compromises the discriminative ability of the learned features. Intuitively, we seek to expand the distribution of the tail classes by transferring from the head classes, so as to alleviate the distortion of the feature space. To this end, we propose to construct each feature into a "feature cloud". If a sample belongs to a tail class, the corresponding feature cloud will have relatively large distribution range, in compensation to its lack of diversity. It allows each tail sample to push the samples from other classes far away, recovering the intra-class diversity of tail classes. Extensive experimental evaluations on person re-identification and face recognition tasks confirm the effectiveness of our method.

Identity Preserving Generative Adversarial Network for Cross-Domain Person Re-identification

Person re-identification is to retrieval pedestrian images from no-overlap camera views detected by pedestrian detectors. Most existing person re-identification (re-ID) models often fail to generalize well from the source domain where the models are trained to a new target domain without labels, because of the bias between the source and target domain. This issue significantly limits the scalability and usability of the models in the real world. Providing a labeled source training set and an unlabeled target training set, the aim of this paper is to improve the generalization ability of re-ID models to the target domain. To this end, we propose an image generative network named identity preserving generative adversarial network (IPGAN). The proposed method has two excellent properties: 1) only a single model is employed to translate the labeled images from the source domain to the target camera domains in an unsupervised manner; 2) The identity information of images from the source domain is preserved before and after translation. Furthermore, we propose IBN-reID model for the person re-identification task. It has better generalization ability than baseline models, especially in the cases without any domain adaptation. The IBN-reID model is trained on the translated images by supervised methods. Experimental results on Market-1501 and DukeMTMC-reID show that the images generated by IPGAN are more suitable for cross-domain person re-identification. Very competitive re-ID accuracy is achieved by our method.