论文检索

Generative Models

Seungwoo Yoo, Juil Koo, Kyeongmin Yeo, Minhyuk Sung

We propose a novel method for learning representations of poses for 3D deformable objects, which specializes in 1) disentangling pose information from the object's identity, 2) facilitating the learning of pose variations, and 3) transferring pose information to other object identities. Based on these properties, our method enables the generation of 3D deformable objects with diversity in both identities and poses, using variations of a single object. It does not require explicit shape parameterization such as skeletons or joints, point-level or shape-level correspondence supervision, or variations of the target object for pose transfer.To achieve pose disentanglement, compactness for generative models, and transferability, we first design the pose extractor to represent the pose as a keypoint-based hybrid representation and the pose applier to learn an implicit deformation field. To better distill pose information from the object's geometry, we propose the implicit pose applier to output an intrinsic mesh property, the face Jacobian. Once the extracted pose information is transferred to the target object, the pose applier is fine-tuned in a self-supervised manner to better describe the target object's shapes with pose variations. The extracted poses are also used to train a cascaded diffusion model to enable the generation of novel poses.Our experiments with the DeformThings4D and Human datasets demonstrate state-of-the-art performance in pose transfer and the ability to generate diverse deformed shapes with various objects and poses.

Deep Learning · Self-Supervised Learning

Jeongwoo Shin, Inseo Lee, Junho Lee, Joonseok Lee

Masked Autoencoder (MAE) is a self-supervised approach for representation learning, widely applicable to a variety of downstream tasks in computer vision. In spite of its success, it is still not fully uncovered what and how MAE exactly learns. In this paper, with an in-depth analysis, we discover that MAE intrinsically learns pattern-based patch-level clustering from surprisingly early stages of pre-training. Upon this understanding, we propose self-guided masked autoencoder, which internally generates informed mask by utilizing its progress in patch clustering, substituting the naive random masking of the vanilla MAE. Our approach significantly boosts its learning process without relying on any external models or supplementary information, keeping the benefit of self-supervised nature of MAE intact. Comprehensive experiments on various downstream tasks verify the effectiveness of the proposed method.

Deep Learning · Self-Supervised Learning

Zhiqiang Chen, Guofan Fan, Jinying Gao, Lei Ma, Bo Lei, Tiejun Huang, Shan Yu

The human brain exhibits a strong ability to spontaneously associate different visual attributes of the same or similar visual scene, such as associating sketches and graffiti with real-world visual objects, usually without supervising information. In contrast, in the field of artificial intelligence, controllable generation methods like ControlNet heavily rely on annotated training datasets such as depth maps, semantic segmentation maps, and poses, which limits the method’s scalability. Inspired by the neural mechanisms that may contribute to the brain’s associative power, specifically the cortical modularization and hippocampal pattern completion, here we propose a self-supervised controllable generation (SCG) framework. Firstly, we introduce an equivariance constraint to promote inter-module independence and intra-module correlation in a modular autoencoder network, thereby achieving functional specialization. Subsequently, based on these specialized modules, we employ a self-supervised pattern completion approach for controllable generation training. Experimental results demonstrate that the proposed modular autoencoder effectively achieves functional specialization, including the modular processing of color, brightness, and edge detection, and exhibits brain-like features including orientation selectivity, color antagonism, and center-surround receptive fields. Through self-supervised training, associative generation capabilities spontaneously emerge in SCG, demonstrating excellent zero-shot generalization ability to various tasks such as superresolution, dehaze and associative or conditional generation on painting, sketches, and ancient graffiti. Compared to the previous representative method ControlNet, our proposed approach not only demonstrates superior robustness in more challenging high-noise scenarios but also possesses more promising scalability potential due to its self-supervised manner. Codes are released on Github and Gitee.

Jinhui Ye, Xing Wang, Wenxiang Jiao, Junwei Liang, Hui Xiong

Gloss-free sign language translation (SLT) aims to develop well-performing SLT systems with no requirement for the costly gloss annotations, but currently still lags behind gloss-based approaches significantly. In this paper, we identify **a representation density problem** that could be a bottleneck in restricting the performance of gloss-free SLT. Specifically, the representation density problem describes that the visual representations of semantically distinct sign gestures tend to be closely packed together in feature space, which makes gloss-free methods struggle with distinguishing different sign gestures and suffer from a sharp performance drop. To address the representation density problem, we introduce a simple but effective contrastive learning strategy, namely SignCL, which encourages gloss-free models to learn more discriminative feature representation in a self-supervised manner. Our experiments demonstrate that the proposed SignCL can significantly reduce the representation density and improve performance across various translation frameworks. Specifically, SignCLachieves a significant improvement in BLEU score for the Sign Language Transformer and GFSLT-VLP on the CSL-Daily dataset by 39\% and 46\%, respectively, without any increase of model parameters. Compared to Sign2GPT, a state-of-the-art method based on large-scale pre-trained vision and language models, SignCLachieves better performance with only 35\% of its parameters. We will release our code and model to facilitate further research.

Deep Learning · Self-Supervised Learning

Jaemyung Yu, Jaehyun Choi, DongJae Lee, HyeongGwon Hong, Junmo Kim

Unsupervised representation learning has significantly advanced various machine learning tasks. In the computer vision domain, state-of-the-art approaches utilize transformations like random crop and color jitter to achieve invariant representations, embedding semantically the same inputs despite transformations. However, this can degrade performance in tasks requiring precise features, such as localization or flower classification. To address this, recent research incorporates equivariant representation learning, which captures transformation-sensitive information. However, current methods depend on transformation labels and thus struggle with interdependency and complex transformations. We propose Self-supervised Transformation Learning (STL), replacing transformation labels with transformation representations derived from image pairs. The proposed method ensures transformation representation is image-invariant and learns corresponding equivariant transformations, enhancing performance without increased batch complexity. We demonstrate the approach’s effectiveness across diverse classification and detection tasks, outperforming existing methods in 7 out of 11 benchmarks and excelling in detection. By integrating complex transformations like AugMix, unusable by prior equivariant methods, this approach enhances performance across tasks, underscoring its adaptability and resilience. Additionally, its compatibility with various base models highlights its flexibility and broad applicability. The code is available at https://github.com/jaemyung-u/stl.

Optimization · Large Scale, Parallel and Distributed

Mingyi Li, Xiao Zhang, Qi Wang, Tengfei LIU, Ruofan Wu, Weiqiang Wang, Fuzhen Zhuang, Hui Xiong, Dongxiao Yu

Due to the heterogeneous architectures and class skew, the global representation models training in resource-adaptive federated self-supervised learning face with tricky challenges: $\textit{deviated representation abilities}$ and $\textit{inconsistent representation spaces}$. In this work, we are the first to propose a multi-teacher knowledge distillation framework, namely $\textit{FedMKD}$, to learn global representations with whole class knowledge from heterogeneous clients even under extreme class skew. Firstly, the adaptive knowledge integration mechanism is designed to learn better representations from all heterogeneous models with deviated representation abilities. Then the weighted combination of the self-supervised loss and the distillation loss can support the global model to encode all classes from clients into a unified space. Besides, the global knowledge anchored alignment module can make the local representation spaces close to the global spaces, which further improves the representation abilities of local ones. Finally, extensive experiments conducted on two datasets demonstrate the effectiveness of $\textit{FedMKD}$ which outperforms state-of-the-art baselines 4.78\% under linear evaluation on average.

Miscellaneous Aspects of Machine Learning · Transfer, Multitask and Meta-learning

Duo Wang, Yuan Zuo, Fengzhi Li, Junjie Wu

Zero-shot graph machine learning, especially with graph neural networks (GNNs), has garnered significant interest due to the challenge of scarce labeled data. While methods like self-supervised learning and graph prompt learning have been extensively explored, they often rely on fine-tuning with task-specific labels, limiting their effectiveness in zero-shot scenarios. Inspired by the zero-shot capabilities of instruction-fine-tuned large language models (LLMs), we introduce a novel framework named Token Embedding-Aligned Graph Language Model (TEA-GLM) that leverages LLMs as cross-dataset and cross-task zero-shot learners for graph machine learning. Concretely, we pretrain a GNN, aligning its representations with token embeddings of an LLM. We then train a linear projector that transforms the GNN's representations into a fixed number of graph token embeddings without tuning the LLM. A unified instruction is designed for various graph tasks at different levels, such as node classification (node-level) and link prediction (edge-level). These design choices collectively enhance our method's effectiveness in zero-shot learning, setting it apart from existing methods. Experiments show that our graph token embeddings help the LLM predictor achieve state-of-the-art performance on unseen datasets and tasks compared to other methods using LLMs as predictors. Our code is available at https://github.com/W-rudder/TEA-GLM.

Graph Neural Networks

Zhibiao Wang, Xiao Wang, Haoyue Deng, Nian Liu, Shirui Pan, Chunming Hu

Graph self-supervised learning, as a powerful pre-training paradigm for Graph Neural Networks (GNNs) without labels, has received considerable attention. We have witnessed the success of graph self-supervised learning on pre-training the parameters of GNNs, leading many not to doubt that whether the learned GNNs parameters are all useful. In this paper, by presenting the experimental evidence and analysis, we surprisingly discover that the graph self-supervised learning models are highly redundant at both of neuron and layer levels, e.g., even randomly removing 51.6\% of parameters, the performance of graph self-supervised learning models still retains at least 96.2\%. This discovery implies that the parameters of graph self-supervised models can be largely reduced, making simultaneously fine-tuning both graph self-supervised learning models and prediction layers more feasible. Therefore, we further design a novel graph pre-training and fine-tuning paradigm called SLImming DE-correlation Fine-tuning (SLIDE). The effectiveness of SLIDE is verified through extensive experiments on various benchmarks, and the performance can be even improved with fewer parameters of models in most cases. For example, in comparison with full fine-tuning GraphMAE on Amazon-Computers dataset, even randomly reducing 40\% of parameters, we can still achieve the improvement of 0.24\% and 0.27\% for Micro-F1 and Macro-F1 scores respectively.

Graph Neural Networks

YUJIE MO, Zhihe Lu, Runpeng Yu, Xiaofeng Zhu, Xinchao Wang

Self-supervised heterogeneous graph learning (SHGL) has shown promising potential in diverse scenarios. However, while existing SHGL methods share a similar essential with clustering approaches, they encounter two significant limitations: (i) noise in graph structures is often introduced during the message-passing process to weaken node representations, and (ii) cluster-level information may be inadequately captured and leveraged, diminishing the performance in downstream tasks. In this paper, we address these limitations by theoretically revisiting SHGL from the spectral clustering perspective and introducing a novel framework enhanced by rank and dual consistency constraints. Specifically, our framework incorporates a rank-constrained spectral clustering method that refines the affinity matrix to exclude noise effectively. Additionally, we integrate node-level and cluster-level consistency constraints that concurrently capture invariant and clustering information to facilitate learning in downstream tasks. We theoretically demonstrate that the learned representations are divided into distinct partitions based on the number of classes and exhibit enhanced generalization ability across tasks. Experimental results affirm the superiority of our method, showcasing remarkable improvements in several downstream tasks compared to existing methods.

Shentong Mo, Peter Tong

In recent advancements in unsupervised visual representation learning, the Joint-Embedding Predictive Architecture (JEPA) has emerged as a significant method for extracting visual features from unlabeled imagery through an innovative masking strategy. Despite its success, two primary limitations have been identified: the inefficacy of Exponential Moving Average (EMA) from I-JEPA in preventing entire collapse and the inadequacy of I-JEPA prediction in accurately learning the mean of patch representations. Addressing these challenges, this study introduces a novel framework, namely C-JEPA (Contrastive-JEPA), which integrates the Image-based Joint-Embedding Predictive Architecture with the Variance-Invariance-Covariance Regularization (VICReg) strategy. This integration is designed to effectively learn the variance/covariance for preventing entire collapse and ensuring invariance in the mean of augmented views, thereby overcoming the identified limitations. Through empirical and theoretical evaluations, our work demonstrates that C-JEPA significantly enhances the stability and quality of visual representation learning. When pre-trained on the ImageNet-1K dataset, C-JEPA exhibits rapid and improved convergence in both linear probing and fine-tuning performance metrics.

Deep Learning · Self-Supervised Learning

Jialong Zuo, Ying Nie, Hanyu Zhou, Huaxin Zhang, Haoyu Wang, Tianyu Guo, Nong Sang, Changxin Gao

Recent researches have proven that pre-training on large-scale person images extracted from internet videos is an effective way in learning better representations for person re-identification. However, these researches are mostly confined to pre-training at the instance-level or single-video tracklet-level. They ignore the identity-invariance in images of the same person across different videos, which is a key focus in person re-identification. To address this issue, we propose a Cross-video Identity-cOrrelating pre-traiNing (CION) framework. Defining a noise concept that comprehensively considers both intra-identity consistency and inter-identity discrimination, CION seeks the identity correlation from cross-video images by modeling it as a progressive multi-level denoising problem. Furthermore, an identity-guided self-distillation loss is proposed to implement better large-scale pre-training by mining the identity-invariance within person images. We conduct extensive experiments to verify the superiority of our CION in terms of efficiency and performance. CION achieves significantly leading performance with even fewer training samples. For example, compared with the previous state-of-the-art ISR, CION with the same ResNet50-IBN achieves higher mAP of 93.3% and 74.3% on Market1501 and MSMT17, while only utilizing 8% training samples. Finally, with CION demonstrating superior model-agnostic ability, we contribute a model zoo named ReIDZoo to meet diverse research and application needs in this field. It contains a series of CION pre-trained models with spanning structures and parameters, totaling 32 models with 10 different structures, including GhostNet, ConvNext, RepViT, FastViT and so on. The code and models will be open-sourced.

Neuroscience, Cognitive Science

Abhiram Iyer, Sarthak Chandra, Sugandha Sharma, Ila Fiete

Grid cells in the medial entorhinal cortex create remarkable periodic maps of explored space during navigation. Recent studies show that they form similar maps of abstract cognitive spaces. Examples of such abstract environments include auditory tone sequences in which the pitch is continuously varied or images in which abstract features are continuously deformed (e.g., a cartoon bird whose legs stretch and shrink). Here, we hypothesize that the brain generalizes how it maps spatial domains to mapping abstract spaces. To sidestep the computational cost of learning representations for each high-dimensional sensory input, the brain extracts self-consistent, low-dimensional descriptions of displacements across abstract spaces, leveraging the spatial velocity integration of grid cells to efficiently build maps of different domains.Our neural network model for abstract velocity extraction factorizes the content of these abstract domains from displacements within the domains to generate content-independent and self-consistent, low-dimensional velocity estimates. Crucially, it uses a self-supervised geometric consistency constraint that requires displacements along closed loop trajectories to sum to zero, an integration that is itself performed by the downstream grid cell circuit over learning. This process results in high fidelity estimates of velocities and allowed transitions in abstract domains, a crucial prerequisite for efficient map generation in these high-dimensional environments. We also show how our method outperforms traditional dimensionality reduction and deep-learning based motion extraction networks on the same set of tasks.This is the first neural network model to explain how grid cells can flexibly represent different abstract spaces and makes the novel prediction that they should do so while maintaining their population correlation and manifold structure across domains. Fundamentally, our model sheds light on the mechanistic origins of cognitive flexibility and transfer of representations across vastly different domains in brains, providing a potential self-supervised learning (SSL) framework for leveraging similar ideas in transfer learning and data-efficient generalization in machine learning and robotics.

Deep Learning · Self-Supervised Learning

Xiangdong Zhang, Shaofeng Zhang, Junchi Yan

Masked autoencoder has been widely explored in point cloud self-supervised learning, whereby the point cloud is generally divided into visible and masked parts. These methods typically include an encoder accepting visible patches (normalized) and corresponding patch centers (position) as input, with the decoder accepting the output of the encoder and the centers (position) of the masked parts to reconstruct each point in the masked patches. Then, the pre-trained encoders are used for downstream tasks. In this paper, we show a motivating empirical result that when directly feeding the centers of masked patches to the decoder without information from the encoder, it still reconstructs well. In other words, the centers of patches are important and the reconstruction objective does not necessarily rely on representations of the encoder, thus preventing the encoder from learning semantic representations. Based on this key observation, we propose a simple yet effective method, $i.e.$, learning to \textbf{P}redict \textbf{C}enters for \textbf{P}oint \textbf{M}asked \textbf{A}uto\textbf{E}ncoders (\textbf{PCP-MAE}) which guides the model to learn to predict the significant centers and use the predicted centers to replace the directly provided centers. Specifically, we propose a Predicting Center Module (PCM) that shares parameters with the original encoder with extra cross-attention to predict centers. Our method is of high pre-training efficiency compared to other alternatives and achieves great improvement over Point-MAE, particularly surpassing it by \textbf{5.50\% on OBJ-BG, 6.03\% on OBJ-ONLY, and 5.17\% on PB-T50-RS} for 3D object classification on the ScanObjectNN dataset. The code is available at \url{https://github.com/aHapBean/PCP-MAE}.

Computational Biology

Zuobai Zhang, Pascal Notin, Yining Huang, Aurelie Lozano, Vijil Chenthamarakshan, Debora Marks, Payel Das, Jian Tang

Designing novel functional proteins crucially depends on accurately modeling their fitness landscape. Given the limited availability of functional annotations from wet-lab experiments, previous methods have primarily relied on self-supervised models trained on vast, unlabeled protein sequence or structure datasets. While initial protein representation learning studies solely focused on either sequence or structural features, recent hybrid architectures have sought to merge these modalities to harness their respective strengths. However, these sequence-structure models have so far achieved only incremental improvements when compared to the leading sequence-only approaches, highlighting unresolved challenges effectively leveraging these modalities together. Moreover, the function of certain proteins is highly dependent on the granular aspects of their surface topology, which have been overlooked by prior models.To address these limitations, we introduce the Sequence-Structure-Surface Fitness (**S3F**) model — a novel multimodal representation learning framework that integrates protein features across several scales. Our approach combines sequence representations from a protein language model with Geometric Vector Perceptron networks encoding protein backbone and detailed surface topology. The proposed method achieves state-of-the-art fitness prediction on the ProteinGym benchmark encompassing 217 substitution deep mutational scanning assays, and provides insights into the determinants of protein function.Our code is at https://github.com/DeepGraphLearning/S3F.

Computer Vision · Stereo

Liang Han, Junsheng Zhou, Yu-Shen Liu, Zhizhong Han

Novel view synthesis from sparse inputs is a vital yet challenging task in 3D computer vision. Previous methods explore 3D Gaussian Splatting with neural priors (e.g. depth priors) as an additional supervision, demonstrating promising quality and efficiency compared to the NeRF based methods. However, the neural priors from 2D pretrained models are often noisy and blurry, which struggle to precisely guide the learning of radiance fields. In this paper, We propose a novel method for synthesizing novel views from sparse views with Gaussian Splatting that does not require external prior as supervision. Our key idea lies in exploring the self-supervisions inherent in the binocular stereo consistency between each pair of binocular images constructed with disparity-guided image warping. To this end, we additionally introduce a Gaussian opacity constraint which regularizes the Gaussian locations and avoids Gaussian redundancy forimproving the robustness and efficiency of inferring 3D Gaussians from sparse views. Extensive experiments on the LLFF, DTU, and Blender datasets demonstrate that our method significantly outperforms the state-of-the-art methods.

Multimodal Models

Xin Wen, Bingchen Zhao, Yilun Chen, Jiangmiao Pang, Xiaojuan Qi

Severe data imbalance naturally exists among web-scale vision-language datasets. Despite this, we find CLIP pre-trained thereupon exhibits notable robustness to the data imbalance compared to supervised learning, and demonstrates significant effectiveness in learning generalizable representations. With an aim to investigate the reasons behind this finding, we conduct controlled experiments to study various underlying factors, and reveal that CLIP's pretext task forms a dynamic classification problem wherein only a subset of classes is present in training. This isolates the bias from dominant classes and implicitly balances the learning signal. Furthermore, the robustness and discriminability of CLIP improve with more descriptive language supervision, larger data scale, and broader open-world concepts, which are inaccessible to supervised learning. Our study not only uncovers the mechanisms behind CLIP's generalizability beyond data imbalance but also provides transferable insights for the research community. The findings are validated in both supervised and self-supervised learning, enabling models trained on imbalanced data to achieve CLIP-level performance on diverse recognition tasks. Code and data are available at: https://github.com/CVMI-Lab/clip-beyond-tail.

Deep Learning · Self-Supervised Learning

Junlin He, Jinxiao Du, Wei Ma

Self-supervised learning (SSL) has rapidly advanced in recent years, approaching the performance of its supervised counterparts through the extraction of representations from unlabeled data. However, dimensional collapse, where a few large eigenvalues dominate the eigenspace, poses a significant obstacle for SSL. When dimensional collapse occurs on features (e.g. hidden features and representations), it prevents features from representing the full information of the data; when dimensional collapse occurs on weight matrices, their filters are self-related and redundant, limiting their expressive power.Existing studies have predominantly concentrated on the dimensional collapse of representations, neglecting whether this can sufficiently prevent the dimensional collapse of the weight matrices and hidden features. To this end, we first time propose a mitigation approach employing orthogonal regularization (OR) across the encoder, targeting both convolutional and linear layers during pretraining. OR promotes orthogonality within weight matrices, thus safeguarding against the dimensional collapse of weight matrices, hidden features, and representations. Our empirical investigations demonstrate that OR significantly enhances the performance of SSL methods across diverse benchmarks, yielding consistent gains with both CNNs and Transformer-based architectures.

Computer Vision · Image Generation

Xi Chen, Yutong Feng, Mengting Chen, Yiyang Wang, Shilong Zhang, Yu Liu, Yujun Shen, Hengshuang Zhao

Image editing serves as a practical yet challenging task considering the diverse demands from users, where one of the hardest parts is to precisely describe how the edited image should look like. In this work, we present a new form of editing, termed imitative editing, to help users exercise their creativity more conveniently. Concretely, to edit an image region of interest, users are free to directly draw inspiration from some in-the-wild references (e.g., some relative pictures come across online), without having to cope with the fit between the reference and the source. Such a design requires the system to automatically figure out what to expect from the reference to perform the editing. For this purpose, we propose a generative training framework, dubbed MimicBrush, which randomly selects two frames from a video clip, masks some regions of one frame, and learns to recover the masked regions using the information from the other frame. That way, our model, developed from a diffusion prior, is able to capture the semantic correspondence between separate images in a self-supervised manner. We experimentally show the effectiveness of our method under various test cases as well as its superiority over existing alternatives. We also construct a benchmark to facilitate further research.

Computer Vision

Ted Lentsch, Holger Caesar, Dariu Gavrila

Unsupervised 3D object detection methods have emerged to leverage vast amounts of data without requiring manual labels for training. Recent approaches rely on dynamic objects for learning to detect mobile objects but penalize the detections of static instances during training. Multiple rounds of (self) training are used to add detected static instances to the set of training targets; this procedure to improve performance is computationally expensive. To address this, we propose the method UNION. We use spatial clustering and self-supervised scene flow to obtain a set of static and dynamic object proposals from LiDAR. Subsequently, object proposals' visual appearances are encoded to distinguish static objects in the foreground and background by selecting static instances that are visually similar to dynamic objects. As a result, static and dynamic mobile objects are obtained together, and existing detectors can be trained with a single training. In addition, we extend 3D object discovery to detection by using object appearance-based cluster labels as pseudo-class labels for training object classification. We conduct extensive experiments on the nuScenes dataset and increase the state-of-the-art performance for unsupervised 3D object discovery, i.e. UNION more than doubles the average precision to 38.4. The code is available at github.com/TedLentsch/UNION.

Deep Learning · Self-Supervised Learning

Etai Littwin, Omid Saremi, Madhu Advani, Vimal Thilak, Preetum Nakkiran, Chen Huang, Joshua Susskind

Two competing paradigms exist for self-supervised learning of data representations. Joint Embedding Predictive Architectures (JEPAs) is a class of architectures in which semantically similar inputs are encoded into representations that are predictive of each other. A recent successful approach that falls under the JEPA framework is self-distillation, where an online encoder is trained to predict the output of the target encoder, sometimes with a lightweight predictor network. This is contrasted with the Masked Auto Encoder (MAE) paradigm, where an encoder and decoder are trained to reconstruct missing parts of the input in ambient space rather than its latent representation. A common motivation for using the JEPA approach over MAE is that the JEPA objective prioritizes abstract features over fine-grained pixel information (which can be unpredictable and uninformative). In this work, we seek to understand the mechanism behind this empirical observation by analyzing deep linear models. We uncover a surprising mechanism: in a simplified linear setting where both approaches learn similar representations, JEPAs are biased to learn high influence features, or features characterized by having high regression coefficients. Our results point to a distinct implicit bias of predicting in latent space that may shed light on its success in practice.