Qiang Qiu

Gaurav Patel, Jan Allebach, Qiang Qiu

This paper looks at semi-supervised learning (SSL) for image-based text recognition. One of the most popular SSL approaches is pseudo-labeling (PL). PL approaches assign labels to unlabeled data before re-training the model with a combination of labeled and pseudo-labeled data. However, PL methods are severely degraded by noise and are prone to over-fitting to noisy labels, due to the inclusion of erroneous high confidence pseudo-labels generated from poorly calibrated models, thus, rendering threshold-based selection ineffective. Moreover, the combinatorial complexity of the hypothesis space and the error accumulation due to multiple incorrect autoregressive steps posit pseudo-labeling challenging for sequence models. To this end, we propose a pseudo-label generation and an uncertainty-based data selection framework for semi-supervised text recognition. We first use Beam-Search inference to yield highly probable hypotheses to assign pseudo-labels to the unlabelled examples. Then we adopt an ensemble of models, sampled by applying dropout, to obtain a robust estimate of the uncertainty associated with the prediction, considering both the character-level and word-level predictive distribution to select good quality pseudo-labels. Extensive experiments on several benchmark handwriting and scene-text datasets show that our method outperforms the baseline approaches and the previous state-of-the-art semi-supervised text-recognition methods.

Ze Wang, Jiang Wang, Zicheng Liu et al.

In this paper, we show that a binary latent space can be explored for compact yet expressive image representations. We model the bi-directional mappings between an image and the corresponding latent binary representation by training an auto-encoder with a Bernoulli encoding distribution. On the one hand, the binary latent space provides a compact discrete image representation of which the distribution can be modeled more efficiently than pixels or continuous latent representations. On the other hand, we now represent each image patch as a binary vector instead of an index of a learned cookbook as in discrete image representations with vector quantization. In this way, we obtain binary latent representations that allow for better image quality and high-resolution image representations without any multi-stage hierarchy in the latent space. In this binary latent space, images can now be generated effectively using a binary latent diffusion model tailored specifically for modeling the prior over the binary image representations. We present both conditional and unconditional image generation experiments with multiple datasets, and show that the proposed method performs comparably to state-of-the-art methods while dramatically improving the sampling efficiency to as few as 16 steps without using any test-time acceleration. The proposed framework can also be seamlessly scaled to $1024 \times 1024$ high-resolution image generation without resorting to latent hierarchy or multi-stage refinements.

Ze Wang, Jiang Wang, Zicheng Liu et al.

Motivated by the fact that forward and backward passes of a deep network naturally form symmetric mappings between input and output representations, we introduce a simple yet effective self-supervised vision model pretraining framework inspired by energy-based models (EBMs). In the proposed framework, we model energy estimation and data restoration as the forward and backward passes of a single network without any auxiliary components, e.g., an extra decoder. For the forward pass, we fit a network to an energy function that assigns low energy scores to samples that belong to an unlabeled dataset, and high energy otherwise. For the backward pass, we restore data from corrupted versions iteratively using gradient-based optimization along the direction of energy minimization. In this way, we naturally fold the encoder-decoder architecture widely used in masked image modeling into the forward and backward passes of a single vision model. Thus, our framework now accepts a wide range of pretext tasks with different data corruption methods, and permits models to be pretrained from masked image modeling, patch sorting, and image restoration, including super-resolution, denoising, and colorization. We support our findings with extensive experiments, and show the proposed method delivers comparable and even better performance with remarkably fewer epochs of training compared to the state-of-the-art self-supervised vision model pretraining methods. Our findings shed light on further exploring self-supervised vision model pretraining and pretext tasks beyond masked image modeling.

Pengyuan Guo, Zhonghao Mai, Zhengtong Xu et al.

Recent advances in vision-language models (VLMs) have enabled increasing progress in real-world robot manipulation. However, long-horizon manipulation in unstructured environments requires VLMs to reason about changing scene states, action constraints, and execution outcomes, which remains difficult with natural language reasoning alone. We present PLanAR, a planning-language-grounded robot agent framework for open-vocabulary, long-horizon manipulation. PLanAR uses a planning-language interface to define the VLM reasoning space: object predicates represent scene states, action schemas specify robot skills with preconditions and effects, and symbolic plans provide executable intermediate representations. This interface enables stepwise verification: after each action, PLanAR uses onboard observations to check whether the expected symbolic effects have been achieved, allowing the VLM-based agent to update task states, detect failures, and replan when execution deviates from expectation. Across robot embodiments, VLM backends, and tasks including stacking, crossword solving, and long-horizon kitchen workflows, PLanAR demonstrates strong real-world capability while revealing key limitations of current VLMs in embodied reasoning.

Zhengtong Xu, Qiang Qiu, Yu She

In the era of generative AI, integrating video generation models into robotics opens new possibilities for the general-purpose robot agent. This paper introduces imitation learning with latent video planning (VILP). We propose a latent video diffusion model to generate predictive robot videos that adhere to temporal consistency to a good degree. Our method is able to generate highly time-aligned videos from multiple views, which is crucial for robot policy learning. Our video generation model is highly time-efficient. For example, it can generate videos from two distinct perspectives, each consisting of six frames with a resolution of 96x160 pixels, at a rate of 5 Hz. In the experiments, we demonstrate that VILP outperforms the existing video generation robot policy across several metrics: training costs, inference speed, temporal consistency of generated videos, and the performance of the policy. We also compared our method with other imitation learning methods. Our findings indicate that VILP can rely less on extensive high-quality task-specific robot action data while still maintaining robust performance. In addition, VILP possesses robust capabilities in representing multi-modal action distributions. Our paper provides a practical example of how to effectively integrate video generation models into robot policies, potentially offering insights for related fields and directions. For more details, please refer to our open-source repository https://github.com/ZhengtongXu/VILP.

Jeeyung Kim, Erfan Esmaeili, Qiang Qiu

In text-to-image diffusion models, the cross-attention map of each text token indicates the specific image regions attended. Comparing these maps of syntactically related tokens provides insights into how well the generated image reflects the text prompt. For example, in the prompt, "a black car and a white clock", the cross-attention maps for "black" and "car" should focus on overlapping regions to depict a black car, while "car" and "clock" should not. Incorrect overlapping in the maps generally produces generation flaws such as missing objects and incorrect attribute binding. Our study makes the key observations investigating this issue in the existing text-to-image models:(1) the similarity in text embeddings between different tokens -- used as conditioning inputs -- can cause their cross-attention maps to focus on the same image regions; and (2) text embeddings often fail to faithfully capture syntactic relations already within text attention maps. As a result, such syntactic relationships can be overlooked in cross-attention module, leading to inaccurate image generation. To address this, we propose a method that directly transfers syntactic relations from the text attention maps to the cross-attention module via a test-time optimization. Our approach leverages this inherent yet unexploited information within text attention maps to enhance image-text semantic alignment across diverse prompts, without relying on external guidance.

Taewook Kim, Ze Wang, Zhengyuan Yang et al.

Text-to-image diffusion models have demonstrated tremendous success in synthesizing visually stunning images given textual instructions. Despite remarkable progress in creating high-fidelity visuals, text-to-image models can still struggle with precisely rendering subjects, such as text spelling. To address this challenge, this paper explores using additional conditions of an image that provides visual guidance of the particular subjects for diffusion models to generate. In addition, this reference condition empowers the model to be conditioned in ways that the vocabularies of the text tokenizer cannot adequately represent, and further extends the model's generalization to novel capabilities such as generating non-English text spellings. We develop several small-scale expert plugins that efficiently endow a Stable Diffusion model with the capability to take different references. Each plugin is trained with auxiliary networks and loss functions customized for applications such as English scene-text generation, multi-lingual scene-text generation, and logo-image generation. Our expert plugins demonstrate superior results than the existing methods on all tasks, each containing only 28.55M trainable parameters.

Wei Chen, Qiang Qiu

Data heterogeneity is one of the major challenges in federated learning (FL), which results in substantial client variance and slow convergence. In this study, we propose a novel solution: decomposing a convolutional filter in FL into a linear combination of filter subspace elements, i.e., filter atoms. This simple technique transforms global filter aggregation in FL into aggregating filter atoms and their atom coefficients. The key advantage here involves mathematically generating numerous cross-terms by expanding the product of two weighted sums from filter atom and atom coefficient. These cross-terms effectively emulate many additional latent clients, significantly reducing model variance, which is validated by our theoretical analysis and empirical observation. Furthermore, our method permits different training schemes for filter atoms and atom coefficients for highly adaptive model personalization and communication efficiency. Empirical results on benchmark datasets demonstrate that our filter decomposition technique substantially improves the accuracy of FL methods, confirming its efficacy in addressing data heterogeneity.

Haoyu Dong, Ze Wang, Qiang Qiu et al.

Image retrieval relies heavily on the quality of the data modeling and the distance measurement in the feature space. Building on the concept of image manifold, we first propose to represent the feature space of images, learned via neural networks, as a graph. Neighborhoods in the feature space are now defined by the geodesic distance between images, represented as graph vertices or manifold samples. When limited images are available, this manifold is sparsely sampled, making the geodesic computation and the corresponding retrieval harder. To address this, we augment the manifold samples with geometrically aligned text, thereby using a plethora of sentences to teach us about images. In addition to extensive results on standard datasets illustrating the power of text to help in image retrieval, a new public dataset based on CLEVR is introduced to quantify the semantic similarity between visual data and text data. The experimental results show that the joint embedding manifold is a robust representation, allowing it to be a better basis to perform image retrieval given only an image and a textual instruction on the desired modifications over the image

Hieu Nguyen, Hui Li, Qiang Qiu et al.

A robust single-shot 3D shape reconstruction technique integrating the fringe projection profilometry (FPP) technique with the deep convolutional neural networks (CNNs) is proposed in this letter. The input of the proposed technique is a single FPP image, and the training and validation data sets are prepared by using the conventional multi-frequency FPP technique. Unlike the conventional 3D shape reconstruction methods which involve complex algorithms and intensive computation, the proposed approach uses an end-to-end network architecture to directly carry out the transformation of a 2D images to its corresponding 3D shape. Experiments have been conducted to demonstrate the validity and robustness of the proposed technique. It is capable of satisfying various 3D shape reconstruction demands in scientific research and engineering applications.

Ze Wang, Zehao Xiao, Kai Xie et al.

Crowd counting usually addressed by density estimation becomes an increasingly important topic in computer vision due to its widespread applications in video surveillance, urban planning, and intelligence gathering. However, it is essentially a challenging task because of the greatly varied sizes of objects, coupled with severe occlusions and vague appearance of extremely small individuals. Existing methods heavily rely on multi-column learning architectures to extract multi-scale features, which however suffer from heavy computational cost, especially undesired for crowd counting. In this paper, we propose the single-column counting network (SCNet) for efficient crowd counting without relying on multi-column networks. SCNet consists of residual fusion modules (RFMs) for multi-scale feature extraction, a pyramid pooling module (PPM) for information fusion, and a sub-pixel convolutional module (SPCM) followed by a bilinear upsampling layer for resolution recovery. Those proposed modules enable our SCNet to fully capture multi-scale features in a compact single-column architecture and estimate high-resolution density map in an efficient way. In addition, we provide a principled paradigm for density map generation and data augmentation for training, which shows further improved performance. Extensive experiments on three benchmark datasets show that our SCNet delivers new state-of-the-art performance and surpasses previous methods by large margins, which demonstrates the great effectiveness of SCNet as a single-column network for crowd counting.

Albert Gong, Qiang Qiu, Guillermo Sapiro

In this paper we introduce an ensemble method for convolutional neural network (CNN), called "virtual branching," which can be implemented with nearly no additional parameters and computation on top of standard CNNs. We propose our method in the context of person re-identification (re-ID). Our CNN model consists of shared bottom layers, followed by "virtual" branches, where neurons from a block of regular convolutional and fully-connected layers are partitioned into multiple sets. Each virtual branch is trained with different data to specialize in different aspects, e.g., a specific body region or pose orientation. In this way, robust ensemble representations are obtained against human body misalignment, deformations, or variations in viewing angles, at nearly no any additional cost. The proposed method achieves competitive performance on multiple person re-ID benchmark datasets, including Market-1501, CUHK03, and DukeMTMC-reID.

Wei Zhu, Qiang Qiu, Jiaji Huang et al.

Deep neural networks have proved very successful on archetypal tasks for which large training sets are available, but when the training data are scarce, their performance suffers from overfitting. Many existing methods of reducing overfitting are data-independent, and their efficacy is often limited when the training set is very small. Data-dependent regularizations are mostly motivated by the observation that data of interest lie close to a manifold, which is typically hard to parametrize explicitly and often requires human input of tangent vectors. These methods typically only focus on the geometry of the input data, and do not necessarily encourage the networks to produce geometrically meaningful features. To resolve this, we propose a new framework, the Low-Dimensional-Manifold-regularized neural Network (LDMNet), which incorporates a feature regularization method that focuses on the geometry of both the input data and the output features. In LDMNet, we regularize the network by encouraging the combination of the input data and the output features to sample a collection of low dimensional manifolds, which are searched efficiently without explicit parametrization. To achieve this, we directly use the manifold dimension as a regularization term in a variational functional. The resulting Euler-Lagrange equation is a Laplace-Beltrami equation over a point cloud, which is solved by the point integral method without increasing the computational complexity. We demonstrate two benefits of LDMNet in the experiments. First, we show that LDMNet significantly outperforms widely-used network regularizers such as weight decay and DropOut. Second, we show that LDMNet can be designed to extract common features of an object imaged via different modalities, which proves to be very useful in real-world applications such as cross-spectral face recognition.

Yi Zhu, Yanzhao Zhou, Qixiang Ye et al.

Weakly supervised object localization remains challenging, where only image labels instead of bounding boxes are available during training. Object proposal is an effective component in localization, but often computationally expensive and incapable of joint optimization with some of the remaining modules. In this paper, to the best of our knowledge, we for the first time integrate weakly supervised object proposal into convolutional neural networks (CNNs) in an end-to-end learning manner. We design a network component, Soft Proposal (SP), to be plugged into any standard convolutional architecture to introduce the nearly cost-free object proposal, orders of magnitude faster than state-of-the-art methods. In the SP-augmented CNNs, referred to as Soft Proposal Networks (SPNs), iteratively evolved object proposals are generated based on the deep feature maps then projected back, and further jointly optimized with network parameters, with image-level supervision only. Through the unified learning process, SPNs learn better object-centric filters, discover more discriminative visual evidence, and suppress background interference, significantly boosting both weakly supervised object localization and classification performance. We report the best results on popular benchmarks, including PASCAL VOC, MS COCO, and ImageNet.

Qixiang Ye, Tianliang Zhang, Qiang Qiu et al.

In this paper, a self-learning approach is proposed towards solving scene-specific pedestrian detection problem without any human' annotation involved. The self-learning approach is deployed as progressive steps of object discovery, object enforcement, and label propagation. In the learning procedure, object locations in each frame are treated as latent variables that are solved with a progressive latent model (PLM). Compared with conventional latent models, the proposed PLM incorporates a spatial regularization term to reduce ambiguities in object proposals and to enforce object localization, and also a graph-based label propagation to discover harder instances in adjacent frames. With the difference of convex (DC) objective functions, PLM can be efficiently optimized with a concave-convex programming and thus guaranteeing the stability of self-learning. Extensive experiments demonstrate that even without annotation the proposed self-learning approach outperforms weakly supervised learning approaches, while achieving comparable performance with transfer learning and fully supervised approaches.

Jiaji Huang, Qiang Qiu, Robert Calderbank et al.

Deep neural networks have proved very successful in domains where large training sets are available, but when the number of training samples is small, their performance suffers from overfitting. Prior methods of reducing overfitting such as weight decay, Dropout and DropConnect are data-independent. This paper proposes a new method, GraphConnect, that is data-dependent, and is motivated by the observation that data of interest lie close to a manifold. The new method encourages the relationships between the learned decisions to resemble a graph representing the manifold structure. Essentially GraphConnect is designed to learn attributes that are present in data samples in contrast to weight decay, Dropout and DropConnect which are simply designed to make it more difficult to fit to random error or noise. Empirical Rademacher complexity is used to connect the generalization error of the neural network to spectral properties of the graph learned from the input data. This framework is used to show that GraphConnect is superior to weight decay. Experimental results on several benchmark datasets validate the theoretical analysis, and show that when the number of training samples is small, GraphConnect is able to significantly improve performance over weight decay.

Jiaji Huang, Qiang Qiu, Robert Calderbank et al.

Many recent efforts have been devoted to designing sophisticated deep learning structures, obtaining revolutionary results on benchmark datasets. The success of these deep learning methods mostly relies on an enormous volume of labeled training samples to learn a huge number of parameters in a network; therefore, understanding the generalization ability of a learned deep network cannot be overlooked, especially when restricted to a small training set, which is the case for many applications. In this paper, we propose a novel deep learning objective formulation that unifies both the classification and metric learning criteria. We then introduce a geometry-aware deep transform to enable a non-linear discriminative and robust feature transform, which shows competitive performance on small training sets for both synthetic and real-world data. We further support the proposed framework with a formal $(K,ε)$-robustness analysis.

Qiang Qiu, Guillermo Sapiro

This work introduces a transformation-based learner model for classification forests. The weak learner at each split node plays a crucial role in a classification tree. We propose to optimize the splitting objective by learning a linear transformation on subspaces using nuclear norm as the optimization criteria. The learned linear transformation restores a low-rank structure for data from the same class, and, at the same time, maximizes the separation between different classes, thereby improving the performance of the split function. Theoretical and experimental results support the proposed framework.

Qiang Qiu, Zhuolin Jiang, Rama Chellappa

We present an approach for dictionary learning of action attributes via information maximization. We unify the class distribution and appearance information into an objective function for learning a sparse dictionary of action attributes. The objective function maximizes the mutual information between what has been learned and what remains to be learned in terms of appearance information and class distribution for each dictionary atom. We propose a Gaussian Process (GP) model for sparse representation to optimize the dictionary objective function. The sparse coding property allows a kernel with compact support in GP to realize a very efficient dictionary learning process. Hence we can describe an action video by a set of compact and discriminative action attributes. More importantly, we can recognize modeled action categories in a sparse feature space, which can be generalized to unseen and unmodeled action categories. Experimental results demonstrate the effectiveness of our approach in action recognition and summarization.

Qiang Qiu, Guillermo Sapiro

We propose a low-rank transformation-learning framework to robustify subspace clustering. Many high-dimensional data, such as face images and motion sequences, lie in a union of low-dimensional subspaces. The subspace clustering problem has been extensively studied in the literature to partition such high-dimensional data into clusters corresponding to their underlying low-dimensional subspaces. However, low-dimensional intrinsic structures are often violated for real-world observations, as they can be corrupted by errors or deviate from ideal models. We propose to address this by learning a linear transformation on subspaces using matrix rank, via its convex surrogate nuclear norm, as the optimization criteria. The learned linear transformation restores a low-rank structure for data from the same subspace, and, at the same time, forces a high-rank structure for data from different subspaces. In this way, we reduce variations within the subspaces, and increase separations between the subspaces for more accurate subspace clustering. This proposed learned robust subspace clustering framework significantly enhances the performance of existing subspace clustering methods. To exploit the low-rank structures of the transformed subspaces, we further introduce a subspace clustering technique, called Robust Sparse Subspace Clustering, which efficiently combines robust PCA with sparse modeling. We also discuss the online learning of the transformation, and learning of the transformation while simultaneously reducing the data dimensionality. Extensive experiments using public datasets are presented, showing that the proposed approach significantly outperforms state-of-the-art subspace clustering methods.

Qiang Qiu, Rama Chellappa

Recognizing group activities is challenging due to the difficulties in isolating individual entities, finding the respective roles played by the individuals and representing the complex interactions among the participants. Individual actions and group activities in videos can be represented in a common framework as they share the following common feature: both are composed of a set of low-level features describing motions, e.g., optical flow for each pixel or a trajectory for each feature point, according to a set of composition constraints in both temporal and spatial dimensions. In this paper, we present a unified model to assess the similarity between two given individual or group activities. Our approach avoids explicit extraction of individual actors, identifying and representing the inter-person interactions. With the proposed approach, retrieval from a video database can be performed through Query-by-Example; and activities can be recognized by querying videos containing known activities. The suggested video matching process can be performed in an unsupervised manner. We demonstrate the performance of our approach by recognizing a set of human actions and football plays.

Qiang Qiu, Vishal M. Patel, Rama Chellappa

We present a two-stage approach for learning dictionaries for object classification tasks based on the principle of information maximization. The proposed method seeks a dictionary that is compact, discriminative, and generative. In the first stage, dictionary atoms are selected from an initial dictionary by maximizing the mutual information measure on dictionary compactness, discrimination and reconstruction. In the second stage, the selected dictionary atoms are updated for improved reconstructive and discriminative power using a simple gradient ascent algorithm on mutual information. Experiments using real datasets demonstrate the effectiveness of our approach for image classification tasks.