ICCV 2023 Papers

This paper presents a novel object-centric contact representation ContactGen for hand-object interaction. The ContactGen comprises 3 components: a contact map indicates the contact location, a part map represents the contact hand part, and a direction map tells the contact direction within each part. Given an input object, we propose a conditional generative model to predict ContactGen and adopt model-based optimization to predict diverse and geometrically feasible grasps. Experimental results demonstrate our method can generate high-fidelity and diverse human grasps for various objects.

Learning-based multi-view stereo (MVS) methods deal with predicting accurate depth maps to achieve an accurate and complete 3D representation. Despite the excellent performance, existing methods ignore the fact that a suitable depth geometry is also critical in MVS. In this paper, we demonstrate that different depth geometries have significant performance gaps, even using the same depth prediction error. Therefore, we introduce an ideal depth geometry composed of Saddle-Shaped Cells, whose predicted depth map oscillates upward and downward around the ground-truth surface, rather than maintaining a continuous and smooth depth plane. To achieve it, we develop a coarse-to-fine framework called Dual-MVSNet (DMVSNet), which can produce an oscillating depth plane. Technically, we predict two depth values for each pixel (Dual-Depth) and propose a novel loss function and a checkerboard-shaped selecting strategy to constrain the predicted depth geometry. Compared to existing methods, DMVSNet achieves a high rank on the DTU benchmark and obtains the top performance on challenging scenes of Tanks and Temples, demonstrating its strong performance and generalization ability. Our method also points to a new research direction for considering depth geometry in MVS.

Transparent objects are commonly seen in indoor scenes but are hard to estimate. Currently, commercial depth cameras face difficulties in estimating the depth of transparent objects due to the light reflection and refraction on their surface. As a result, they tend to make a noisy and incorrect depth value for transparent objects. These incorrect depth data make the traditional RGB-D SLAM method fails in reconstructing the scenes that contain transparent objects. An exact depth value of the transparent object is required to restore in advance and it is essential that the depth value of the transparent object must keep consistent in different views, or the reconstruction result will be distorted. Previous depth prediction methods of transparent objects can restore these missing depth values but none of them can provide a good result in reconstruction due to the inconsistency prediction. In this work, we propose a real-time reconstruction method using a novel stereo-based depth prediction network to keep the consistency of depth prediction in a sequence of images. Because there is no video dataset about transparent objects currently to train our model, we construct a synthetic RGB-D video dataset with different transparent objects. Moreover, to test generalization capability, we capture video from real scenes using the RealSense D435i RGB-D camera. We compare the metrics on our dataset and SLAM reconstruction results in both synthetic scenes and real scenes with the previous methods. Experiments show our significant improvement in accuracy on depth prediction and scene reconstruction.

Unsupervised domain adaptation aims to transfer knowledge from a fully-labeled source domain to an unlabeled target domain. However, in real-world scenarios, providing abundant labeled data even in the source domain can be infeasible due to the difficulty and high expense of annotation. To address this issue, recent works consider the Few-shot Unsupervised Domain Adaptation (FUDA) where only a few source samples are labeled, and conduct knowledge transfer via self-supervised learning methods. Yet existing methods generally overlook that the sparse label setting hinders learning reliable source knowledge for transfer. Additionally, the learning difficulty difference in target samples is different but ignored, leaving hard target samples poorly classified. To tackle both deficiencies, in this paper, we propose a novel Confidence-based Visual Dispersal Transfer learning method (C-VisDiT) for FUDA. Specifically, C-VisDiT consists of a cross-domain visual dispersal strategy that transfers only high-confidence source knowledge for model adaptation and an intra-domain visual dispersal strategy that guides the learning of hard target samples with easy ones. We conduct extensive experiments on Office-31, Office-Home, VisDA-C, and DomainNet benchmark datasets and the results demonstrate that the proposed C-VisDiT significantly outperforms state-of-the-art FUDA methods. Our code is available at https://github.com/Bostoncake/C-VisDiT.

Visual grounding aims at localizing the target object in image which is most related to the given free-form natural language query. As labeling the position of target object is labor-intensive, the weakly supervised methods, where only image-sentence annotations are required during model training have recently received increasing attention. Most of the existing weakly-supervised methods first generate region proposals via pre-trained object detectors and then employ either cross-modal similarity score or reconstruction loss as the criteria to select proposal from them. However, due to the cross-modal heterogeneous gap, these method often suffer from high confidence spurious association and model prone to error propagation. In this paper, we propose Confidence-aware Pseudo-label Learning (CPL) to overcome the above limitations. Specifically, we first adopt both the uni-modal and cross-modal pre-trained models and propose conditional prompt engineering to automatically generate multiple `descriptive, realistic and diverse' pseudo language queries for each region proposal, and then establish reliable cross-modal association for model training based on the uni-modal similarity score (between pseudo and real text queries). Secondly, we propose a confidence-aware pseudo label verification module which reduces the amount of noise encountered in the training process and the risk of error propagation. Experiments on five widely used datasets validate the efficacy of our proposed components and demonstrate state-of-the-art performance.

Many studies in vision tasks have aimed to create effective embedding spaces for single-label object prediction within an image. However, in reality, most objects possess multiple specific attributes, such as shape, color, and length, with each attribute composed of various classes. To apply models in real-world scenarios, it is essential to be able to distinguish between the granular components of an object. Conventional approaches to embedding multiple specific attributes into a single network often result in entanglement, where fine-grained features of each attribute cannot be identified separately. To address this problem, we propose a Conditional Cross-Attention Network that induces disentangled multi-space embeddings for various specific attributes with only a single backbone. Firstly, we employ a cross-attention mechanism to fuse and switch the information of conditions (specific attributes), and we demonstrate its effectiveness through a diverse visualization example. Secondly, we leverage the vision transformer for the first time to a fine-grained image retrieval task and present a simple yet effective framework compared to existing methods. Unlike previous studies where performance varied depending on the benchmark dataset, our proposed method achieved consistent state-of-the-art performance on the FashionAI, DARN, DeepFashion, and Zappos50K benchmark datasets.

In this paper, we address the problem of conditional scene decoration for 360deg images. Our method takes a 360deg background photograph of an indoor scene and generates decorated images of the same scene in the panorama view. To do this, we develop a 360-aware object layout generator that learns latent object vectors in the 360deg view to enable a variety of furniture arrangements for an input 360deg background image. We use this object layout to condition a generative adversarial network to synthesize images of an input scene. To further reinforce the generation capability of our model, we develop a simple yet effective scene emptier that removes the generated furniture and produces an emptied scene for our model to learn a cyclic constraint. We train the model on the Structure3D dataset and show that our model can generate diverse decorations with controllable object layout. Our method achieves state-of-the-art performance on the Structure3D dataset and generalizes well to the Zillow indoor scene dataset. Our user study confirms the immersive experiences provided by the realistic image quality and furniture layout in our generation results. Our implementation is available at https://github.com/kcshum/neural_360_decoration.git.

Generative Adversarial Networks (GANs) can produce photo-realistic results using an unconditional image-generation pipeline. However, the images generated by GANs (e.g., StyleGAN) are entangled in feature spaces, which makes it difficult to interpret and control the contents of images. In this paper, we present an encoder-decoder model that decomposes the entangled GAN space into a conceptual and hierarchical latent space in a self-supervised manner. The outputs of 3D morphable face models are leveraged to independently control image synthesis parameters like pose, expression, and illumination. For this purpose, a novel latent space decomposition pipeline is introduced using transformer networks and generative models. Later, this new space is used to optimize a transformer-based GAN space controller for face editing. In this work, a StyleGAN2 model for faces is utilized. Since our method manipulates only GAN features, the photo-realism of StyleGAN2 is fully preserved. The results demonstrate that our method qualitatively and quantitatively outperforms baselines in terms of identity preservation and editing precision.

A multitude of prevalent pre-trained models mark a major milestone in the development of artificial intelligence, while fine-tuning has been a common practice that enables pre-trained models to figure prominently in a wide array of target datasets. Our empirical results reveal that off-the-shelf fine-tuning techniques are far from adequate to mitigate negative transfer caused by two types of underperforming features in a pre-trained model, including rare features and spuriously correlated features. Rooted in structural causal models of predictions after fine-tuning, we propose a Concept-wise fine-tuning (Concept-Tuning) approach which refines feature representations in the level of patches with each patch encoding a concept. Concept-Tuning minimizes the negative impacts of rare features and spuriously correlated features by (1) maximizing the mutual information between examples in the same category with regard to a slice of rare features (a patch) and (2) applying front-door adjustment via attention neural networks in channels and feature slices (patches). The proposed Concept-Tuning consistently and significantly (by up to 4.76%) improves prior state-of-the-art fine-tuning methods on eleven datasets, diverse pre-training strategies (supervised and self-supervised ones), various network architectures, and sample sizes in a target dataset.

Whole slide image (WSI) analysis has become increasingly important in the medical imaging community, enabling automated and objective diagnosis, prognosis, and therapeutic-response prediction. However, in clinical practice, the continuous progress of evolving WSI acquisition technology, the diversity of scanners, and different imaging protocols hamper the utility of WSI analysis models. In this paper, we propose the FIRST continual learning framework for WSI analysis, named ConSlide, to tackle the challenges of enormous image size, utilization of hierarchical structure, and catastrophic forgetting by progressive model updating on multiple sequential datasets. Our framework contains three key components. The Hierarchical Interaction Transformer (HIT) is proposed to model and utilize the hierarchical structural knowledge of WSI. The BreakupReorganize (BuRo) rehearsal method is developed for WSI data replay with efficient region storing buffer and WSI reorganizing operation. The asynchronous updating mechanism is devised to encourage the network to learn generic and specific knowledge respectively during the replay stage, based on a nested cross-scale similarity learning (CSSL) module. We evaluated the proposed ConSlide on four public WSI datasets from TCGA projects. It performs best over other state-of-the-art methods with a fair WSI-based continual learning setting and achieves a better trade-off of the overall performance and forgetting on previous tasks.

Neural image compression methods have seen increasingly strong performance in recent years. However, they suffer orders of magnitude higher computational complexity compared to traditional codecs, which hinders their real-world deployment. This paper takes a step forward in closing this gap in decoding complexity by adopting shallow or even linear decoding transforms. To compensate for the resulting drop in compression performance, we exploit the often asymmetrical computation budget between encoding and decoding, by adopting more powerful encoder networks and iterative encoding. We theoretically formalize the intuition behind, and our experimental results establish a new frontier in the trade-off between rate-distortion and decoding complexity for neural image compression. Specifically, we achieve rate-distortion performance competitive with the established mean-scale hyperprior architecture of Minnen et al. (2018) at less than 50K decoding FLOPs/pixel, reducing the baseline's overall decoding complexity by 80%, or over 90% for the synthesis transform alone. Our code can be found at https://github.com/mandt-lab/shallow-ntc.

Backdoor attacks against deep learning have been widely studied. Various attack techniques have been proposed for different domains and paradigms, e.g., image, point cloud, natural language processing, transfer learning, etc. These works normally adopt the data poisoning strategy to embed the backdoor. They randomly select samples from the benign training set for poisoning, without considering the distinct contribution of each sample to the backdoor effectiveness, making the attack less optimal. A recent work (IJCAI-22) proposed to use the forgetting score to measure the importance of each poisoned sample and then filter out redundant data for effective backdoor training. However, this method is empirically designed without theoretical proofing. It is also very time-consuming as it needs to go through almost all the training stages for data selection. To address such limitations, we propose a novel confidence-based scoring methodology, which can efficiently measure the contribution of each poisoning sample based on the distance posteriors. We further introduce a greedy search algorithm to find the most informative samples for backdoor injection more promptly. Experimental evaluations on both 2D image and 3D point cloud classification tasks show that our approach can achieve comparable performance or even surpass the forgetting score-based searching method while requiring only several extra epochs' computation of a standard training process.

Scene Graph Generation (SGG) aims to detect all the visual relation triplets <sub, pred, obj> in a given image. With the emergence of various advanced techniques for better utilizing both the intrinsic and extrinsic information in each relation triplet, SGG has achieved great progress over the recent years. However, due to the ubiquitous long-tailed predicate distributions, today's SGG models are still easily biased to the head predicates. Currently, the most prevalent debiasing solutions for SGG are re-balancing methods, e.g., changing the distributions of original training samples. In this paper, we argue that all existing re-balancing strategies fail to increase the diversity of the relation triplet features of each predicate, which is critical for robust SGG. To this end, we propose a novel Compositional Feature Augmentation (CFA) strategy, which is the first unbiased SGG work to mitigate the bias issue from the perspective of increasing the diversity of triplet features. Specifically, we first decompose each relation triplet feature into two components: intrinsic feature and extrinsic feature, which correspond to the intrinsic characteristics and extrinsic contexts of a relation triplet, respectively. Then, we design two different feature augmentation modules to enrich the feature diversity of original relation triplets by replacing or mixing up either their intrinsic or extrinsic features from other samples. Due to its model-agnostic nature, CFA can be seamlessly incorporated into any SGG model. Extensive ablations have shown that CFA can achieve a new state-of-the-art performance on the trade-off between different metrics.

Continual domain shift poses a significant challenge in real-world applications, particularly in situations where labeled data is not available for new domains. The challenge of acquiring knowledge in this problem setting is referred to as unsupervised continual domain shift learning. Existing methods for domain adaptation and generalization have limitations in addressing this issue, as they focus either on adapting to a specific domain or generalizing to unseen domains, but not both. In this paper, we propose Complementary Domain Adaptation and Generalization (CoDAG), a simple yet effective learning framework that combines domain adaptation and generalization in a complementary manner to achieve three major goals of unsupervised continual domain shift learning: adapting to a current domain, generalizing to unseen domains, and preventing forgetting of previously seen domains. Our approach is model-agnostic, meaning that it is compatible with any existing domain adaptation and generalization algorithms. We evaluate CoDAG on several benchmark datasets and demonstrate that our model outperforms state-of-the-art models in all datasets and evaluation metrics, highlighting its effectiveness and robustness in handling unsupervised continual domain shift learning.

This paper studies the problem of recovering cameras from a set of fundamental matrices. A set of fundamental matrices is said to be compatible if a set of cameras exists for which they are the fundamental matrices. We focus on the complete graph, where fundamental matrices for each pair of cameras are given. Previous work has established necessary and sufficient conditions for compatibility as rank and eigenvalue conditions on the n-view fundamental matrix obtained by concatenating the individual fundamental matrices. In this work, we show that the eigenvalue condition is redundant in the generic and collinear cases. We provide explicit homogeneous polynomials that describe necessary and sufficient conditions for compatibility in terms of the fundamental matrices and their epipoles. In this direction, we find that quadruple-wise compatibility is enough to ensure global compatibility for any number of cameras. We demonstrate that for four cameras, compatibility is generically described by triple-wise conditions and one additional equation involving all fundamental matrices.

Reducing communication overhead in federated learning (FL) is challenging but crucial for large-scale distributed privacy-preserving machine learning. While methods utilizing sparsification or other techniques can largely reduce the communication overhead, the convergence rate is also greatly compromised. In this paper, we propose a novel method named Single-Step Synthetic Features Compressor (3SFC) to achieve communication-efficient FL by directly constructing a tiny synthetic dataset containing synthetic features based on raw gradients. Therefore, 3SFC can achieve an extremely low compression rate when the constructed synthetic dataset contains only one data sample. Additionally, the compressing phase of 3SFC utilizes a similarity-based objective function so that it can be optimized with just one step, considerably improving its performance and robustness. To minimize the compressing error, error feedback (EF) is also incorporated into 3SFC. Experiments on multiple datasets and models suggest that 3SFC has significantly better convergence rates compared to competing methods with lower compression rates (i.e., up to 0.02%). Furthermore, ablation studies and visualizations show that 3SFC can carry more information than competing methods for every communication round, further validating its effectiveness.

Federated learning is a popular collaborative learning approach that enables clients to train a global model without sharing their local data. Vertical federated learning (VFL) deals with scenarios in which the data on clients have different feature spaces but share some overlapping samples. Existing VFL approaches suffer from high communication costs and cannot deal efficiently with limited overlapping samples commonly seen in the real world. We propose a practical vertical federated learning (VFL) framework called one-shot VFL that can solve the communication bottleneck and the problem of limited overlapping samples simultaneously based on semi-supervised learning. We also propose few-shot VFL to improve the accuracy further with just one more communication round between the server and the clients. In our proposed framework, the clients only need to communicate with the server once or only a few times. We evaluate the proposed VFL framework on both image and tabular datasets. Our methods can improve the accuracy by more than 46.5% and reduce the communication cost by more than 330xcompared with state-of-the-art VFL methods when evaluated on CIFAR-10. Our code is publicly available.

The sample selection approach is popular in learning with noisy labels. The state-of-the-art methods train two deep networks simultaneously for sample selection, which aims to employ their different learning abilities. To prevent two networks from converging to a consensus, their divergence should be maintained. Prior work presents that the divergence can be kept by locating the disagreement data on which the prediction labels of the two networks are different. However, this procedure is sample-inefficient for generalization, which means that only a few clean examples can be utilized in training. In this paper, to address the issue, we propose a simple yet effective method called CoDis. In particular, we select possibly clean data that simultaneously have high-discrepancy prediction probabilities between two networks. As selected data have high discrepancies in probabilities, the divergence of two networks can be maintained by training on such data. Additionally, the condition of high discrepancies is milder than disagreement, which allows more data to be considered for training, and makes our method more sample-efficient. Moreover, we show that the proposed method enables to mine hard clean examples to help generalization. Empirical results show that CoDis is superior to multiple baselines in the robustness of trained models.

Human pose transfer synthesizes new view(s) of a person for a given pose. Recent work achieves this via self-reconstruction, which disentangles a person's pose and texture information by breaking down the person into several parts, then recombines them to reconstruct the person. However, this part-level disentanglement preserves some pose information that can create unwanted artifacts. In this paper, we propose Pose Transfer by Permuting Textures, a self-driven human pose transfer approach that disentangles pose from texture at the patch-level. Specifically, we remove pose from an input image by permuting image patches so only texture information remains. Then we reconstruct the input image by sampling from the permuted textures to achieve patch-level disentanglement. To reduce the noise and recover clothing shape information from the permuted patches, we employ encoders with multiple kernel sizes in a triple branch network. Extensive experiments on DeepFashion and Market-1501 show that our model improves the quality of generated images in terms of FID, LPIPS and SSIM over other self-driven methods, and even outperforming some fully-supervised methods. A user study also shows that among self-driven approaches, images generated by our method are preferred in 68% of cases over prior work. Code is available at https://github.com/NannanLi999/pt_square.