CVPR 2023 Papers

Data augmentation (DA) is an efficient strategy for improving the performance of deep neural networks. Recent DA strategies have demonstrated utility in single image super-resolution (SR). Little research has, however, focused on the DA strategy for light field SR, in which multi-view information utilization is required. For the first time in light field SR, we propose a potent DA strategy called CutMIB to improve the performance of existing light field SR networks while keeping their structures unchanged. Specifically, CutMIB first cuts low-resolution (LR) patches from each view at the same location. Then CutMIB blends all LR patches to generate the blended patch and finally pastes the blended patch to the corresponding regions of high-resolution light field views, and vice versa. By doing so, CutMIB enables light field SR networks to learn from implicit geometric information during the training stage. Experimental results demonstrate that CutMIB can improve the reconstruction performance and the angular consistency of existing light field SR networks. We further verify the effectiveness of CutMIB on real-world light field SR and light field denoising. The implementation code is available at https://github.com/zeyuxiao1997/CutMIB.

We propose Cut-and-LEaRn (CutLER), a simple approach for training unsupervised object detection and segmentation models. We leverage the property of self-supervised models to 'discover' objects without supervision and amplify it to train a state-of-the-art localization model without any human labels. CutLER first uses our proposed MaskCut approach to generate coarse masks for multiple objects in an image, and then learns a detector on these masks using our robust loss function. We further improve performance by self-training the model on its predictions. Compared to prior work, CutLER is simpler, compatible with different detection architectures, and detects multiple objects. CutLER is also a zero-shot unsupervised detector and improves detection performance AP_50 by over 2.7x on 11 benchmarks across domains like video frames, paintings, sketches, etc. With finetuning, CutLER serves as a low-shot detector surpassing MoCo-v2 by 7.3% AP^box and 6.6% AP^mask on COCO when training with 5% labels.

To address the challenges of long-tailed classification, researchers have proposed several approaches to reduce model bias, most of which assume that classes with few samples are weak classes. However, recent studies have shown that tail classes are not always hard to learn, and model bias has been observed on sample-balanced datasets, suggesting the existence of other factors that affect model bias. In this work, we systematically propose a series of geometric measures for perceptual manifolds in deep neural networks, and then explore the effect of the geometric characteristics of perceptual manifolds on classification difficulty and how learning shapes the geometric characteristics of perceptual manifolds. An unanticipated finding is that the correlation between the class accuracy and the separation degree of perceptual manifolds gradually decreases during training, while the negative correlation with the curvature gradually increases, implying that curvature imbalance leads to model bias. Therefore, we propose curvature regularization to facilitate the model to learn curvature-balanced and flatter perceptual manifolds. Evaluations on multiple long-tailed and non-long-tailed datasets show the excellent performance and exciting generality of our approach, especially in achieving significant performance improvements based on current state-of-the-art techniques. Our work reminds researchers to pay attention to model bias not only on long-tailed datasets but also on non-long-tailed and even data-balanced datasets, which can improve model performance from another perspective.

This paper explores the potential of curriculum learning in LiDAR-based 3D object detection by proposing a curricular object manipulation (COM) framework. The framework embeds the curricular training strategy into both the loss design and the augmentation process. For the loss design, we propose the COMLoss to dynamically predict object-level difficulties and emphasize objects of different difficulties based on training stages. On top of the widely-used augmentation technique called GT-Aug in LiDAR detection tasks, we propose a novel COMAug strategy which first clusters objects in ground-truth database based on well-designed heuristics. Group-level difficulties rather than individual ones are then predicted and updated during training for stable results. Model performance and generalization capabilities can be improved by sampling and augmenting progressively more difficult objects into the training points. Extensive experiments and ablation studies reveal the superior and generality of the proposed framework. The code is available at https://github.com/ZZY816/COM.

Considering the ill-posed nature, contrastive regularization has been developed for single image dehazing, introducing the information from negative images as a lower bound. However, the contrastive samples are nonconsensual, as the negatives are usually represented distantly from the clear (i.e., positive) image, leaving the solution space still under-constricted. Moreover, the interpretability of deep dehazing models is underexplored towards the physics of the hazing process. In this paper, we propose a novel curricular contrastive regularization targeted at a consensual contrastive space as opposed to a non-consensual one. Our negatives, which provide better lower-bound constraints, can be assembled from 1) the hazy image, and 2) corresponding restorations by other existing methods. Further, due to the different similarities between the embeddings of the clear image and negatives, the learning difficulty of the multiple components is intrinsically imbalanced. To tackle this issue, we customize a curriculum learning strategy to reweight the importance of different negatives. In addition, to improve the interpretability in the feature space, we build a physics-aware dual-branch unit according to the atmospheric scattering model. With the unit, as well as curricular contrastive regularization, we establish our dehazing network, named C2PNet. Extensive experiments demonstrate that our C2PNet significantly outperforms state-of-the-art methods, with extreme PSNR boosts of 3.94dB and 1.50dB, respectively, on SOTS-indoor and SOTS-outdoor datasets. Code is available at https://github.com/YuZheng9/C2PNet.

Supervised crowd counting relies heavily on costly manual labeling, which is difficult and expensive, especially in dense scenes. To alleviate the problem, we propose a novel unsupervised framework for crowd counting, named CrowdCLIP. The core idea is built on two observations: 1) the recent contrastive pre-trained vision-language model (CLIP) has presented impressive performance on various downstream tasks; 2) there is a natural mapping between crowd patches and count text. To the best of our knowledge, CrowdCLIP is the first to investigate the vision-language knowledge to solve the counting problem. Specifically, in the training stage, we exploit the multi-modal ranking loss by constructing ranking text prompts to match the size-sorted crowd patches to guide the image encoder learning. In the testing stage, to deal with the diversity of image patches, we propose a simple yet effective progressive filtering strategy to first select the highly potential crowd patches and then map them into the language space with various counting intervals. Extensive experiments on five challenging datasets demonstrate that the proposed CrowdCLIP achieves superior performance compared to previous unsupervised state-of-the-art counting methods. Notably, CrowdCLIP even surpasses some popular fully-supervised methods under the cross-dataset setting. The source code will be available at https://github.com/dk-liang/CrowdCLIP.

Image-based multi-person reconstruction in wide-field large scenes is critical for crowd analysis and security alert. However, existing methods cannot deal with large scenes containing hundreds of people, which encounter the challenges of large number of people, large variations in human scale, and complex spatial distribution. In this paper, we propose Crowd3D, the first framework to reconstruct the 3D poses, shapes and locations of hundreds of people with global consistency from a single large-scene image. The core of our approach is to convert the problem of complex crowd localization into pixel localization with the help of our newly defined concept, Human-scene Virtual Interaction Point (HVIP). To reconstruct the crowd with global consistency, we propose a progressive reconstruction network based on HVIP by pre-estimating a scene-level camera and a ground plane. To deal with a large number of persons and various human sizes, we also design an adaptive human-centric cropping scheme. Besides, we contribute a benchmark dataset, LargeCrowd, for crowd reconstruction in a large scene. Experimental results demonstrate the effectiveness of the proposed method. The code and the dataset are available at http://cic.tju.edu.cn/faculty/likun/projects/Crowd3D.

Existing image captioning methods are under the assumption that the training and testing data are from the same domain or that the data from the target domain (i.e., the domain that testing data lie in) are accessible. However, this assumption is invalid in real-world applications where the data from the target domain is inaccessible. In this paper, we introduce a new setting called Domain Generalization for Image Captioning (DGIC), where the data from the target domain is unseen in the learning process. We first construct a benchmark dataset for DGIC, which helps us to investigate models' domain generalization (DG) ability on unseen domains. With the support of the new benchmark, we further propose a new framework called language-guided semantic metric learning (LSML) for the DGIC setting. Experiments on multiple datasets demonstrate the challenge of the task and the effectiveness of our newly proposed benchmark and LSML framework.

Text-to-image person retrieval aims to identify the target person based on a given textual description query. The primary challenge is to learn the mapping of visual and textual modalities into a common latent space. Prior works have attempted to address this challenge by leveraging separately pre-trained unimodal models to extract visual and textual features. However, these approaches lack the necessary underlying alignment capabilities required to match multimodal data effectively. Besides, these works use prior information to explore explicit part alignments, which may lead to the distortion of intra-modality information. To alleviate these issues, we present IRRA: a cross-modal Implicit Relation Reasoning and Aligning framework that learns relations between local visual-textual tokens and enhances global image-text matching without requiring additional prior supervision. Specifically, we first design an Implicit Relation Reasoning module in a masked language modeling paradigm. This achieves cross-modal interaction by integrating the visual cues into the textual tokens with a cross-modal multimodal interaction encoder. Secondly, to globally align the visual and textual embeddings, Similarity Distribution Matching is proposed to minimize the KL divergence between image-text similarity distributions and the normalized label matching distributions. The proposed method achieves new state-of-the-art results on all three public datasets, with a notable margin of about 3%-9% for Rank-1 accuracy compared to prior methods.

Learning compact image embeddings that yield semantic similarities between images and that generalize to unseen test classes, is at the core of deep metric learning (DML). Finding a mapping from a rich, localized image feature map onto a compact embedding vector is challenging: Although similarity emerges between tuples of images, DML approaches marginalize out information in an individual image before considering another image to which similarity is to be computed. Instead, we propose during training to condition the embedding of an image on the image we want to compare it to. Rather than embedding by a simple pooling as in standard DML, we use cross-attention so that one image can identify relevant features in the other image. Consequently, the attention mechanism establishes a hierarchy of conditional embeddings that gradually incorporates information about the tuple to steer the representation of an individual image. The cross-attention layers bridge the gap between the original unconditional embedding and the final similarity and allow backpropagtion to update encodings more directly than through a lossy pooling layer. At test time we use the resulting improved unconditional embeddings, thus requiring no additional parameters or computational overhead. Experiments on established DML benchmarks show that our cross-attention conditional embedding during training improves the underlying standard DML pipeline significantly so that it outperforms the state-of-the-art.

Novel View Synthesis (NVS) aims at synthesizing an image from an arbitrary viewpoint using multi-view images and camera poses. Among the methods for NVS, Neural Radiance Fields (NeRF) is capable of NVS for an arbitrary resolution as it learns a continuous volumetric representation. However, radiance fields rely heavily on the spectral characteristics of coordinate-based networks. Thus, there is a limit to improving the performance of high-resolution novel view synthesis (HRNVS). To solve this problem, we propose a novel framework using cross-guided optimization of the single-image super-resolution (SISR) and radiance fields. We perform multi-view image super-resolution (MVSR) on train-view images during the radiance fields optimization process. It derives the updated SR result by fusing the feature map obtained from SISR and voxel-based uncertainty fields generated by integrated errors of train-view images. By repeating the updates during radiance fields optimization, train-view images for radiance fields optimization have multi-view consistency and high-frequency details simultaneously, ultimately improving the performance of HRNVS. Experiments of HRNVS and MVSR on various benchmark datasets show that the proposed method significantly surpasses existing methods.

Generative Adversarial Networks (GANs) are notoriously difficult to train especially for complex distributions and with limited data. This has driven the need for interpretable tools to audit trained networks, for example, to identify biases or ensure fairness. Existing GAN audit tools are restricted to coarse-grained, model-data comparisons based on summary statistics such as FID or recall. In this paper, we propose an alternative approach that compares a newly developed GAN against a prior baseline. To this end, we introduce Cross-GAN Auditing (xGA) that, given an established "reference" GAN and a newly proposed "client" GAN, jointly identifies semantic attributes that are either common across both GANs, novel to the client GAN, or missing from the client GAN. This provides both users and model developers an intuitive assessment of similarity and differences between GANs. We introduce novel metrics to evaluate attribute-based GAN auditing approaches and use these metrics to demonstrate quantitatively that xGA outperforms baseline approaches. We also include qualitative results that illustrate the common, novel and missing attributes identified by xGA from GANs trained on a variety of image datasets.

Neural captioners are typically trained to mimic human-generated references without optimizing for any specific communication goal, leading to problems such as the generation of vague captions. In this paper, we show that fine-tuning an out-of-the-box neural captioner with a self-supervised discriminative communication objective helps to recover a plain, visually descriptive language that is more informative about image contents. Given a target image, the system must learn to produce a description that enables an out-of-the-box text-conditioned image retriever to identify such image among a set of candidates. We experiment with the popular ClipCap captioner, also replicating the main results with BLIP. In terms of similarity to ground-truth human descriptions, the captions emerging from discriminative finetuning lag slightly behind those generated by the non-finetuned model, when the latter is trained and tested on the same caption dataset. However, when the model is used without further tuning to generate captions for out-of-domain datasets, our discriminatively-finetuned captioner generates descriptions that resemble human references more than those produced by the same captioner without finetuning. We further show that, on the Conceptual Captions dataset, discriminatively finetuned captions are more helpful than either vanilla ClipCap captions or ground-truth captions for human annotators tasked with an image discrimination task.

Recent advances in hand pose estimation have shed light on utilizing synthetic data to train neural networks, which however inevitably hinders generalization to real-world data due to domain gaps. To solve this problem, we present a framework for cross-domain semi-supervised hand pose estimation and target the challenging scenario of learning models from labelled multi-modal synthetic data and unlabelled real-world data. To that end, we propose a dual-modality network that exploits synthetic RGB and synthetic depth images. For pre-training, our network uses multi-modal contrastive learning and attention-fused supervision to learn effective representations of the RGB images. We then integrate a novel self-distillation technique during fine-tuning to reduce pseudo-label noise. Experiments show that the proposed method significantly improves 3D hand pose estimation and 2D keypoint detection on benchmarks.

Learning dense visual representations without labels is an arduous task and more so from scene-centric data. We propose to tackle this challenging problem by proposing a Cross-view consistency objective with an Online Clustering mechanism (CrOC) to discover and segment the semantics of the views. In the absence of hand-crafted priors, the resulting method is more generalizable and does not require a cumbersome pre-processing step. More importantly, the clustering algorithm conjointly operates on the features of both views, thereby elegantly bypassing the issue of content not represented in both views and the ambiguous matching of objects from one crop to the other. We demonstrate excellent performance on linear and unsupervised segmentation transfer tasks on various datasets and similarly for video object segmentation. Our code and pre-trained models are publicly available at https://github.com/stegmuel/CrOC.

This paper solves the problem of learning dense visual correspondences between different object instances of the same category with only sparse annotations. We decompose this pixel-level semantic matching problem into two easier ones: (i) First, local feature descriptors of source and target images need to be mapped into shared semantic spaces to get coarse matching flows. (ii) Second, matching flows in low resolution should be refined to generate accurate point-to-point matching results. We propose asymmetric feature learning and matching flow super-resolution based on vision transformers to solve the above problems. The asymmetric feature learning module exploits a biased cross-attention mechanism to encode token features of source images with their target counterparts. Then matching flow in low resolutions is enhanced by a super-resolution network to get accurate correspondences. Our pipeline is built upon vision transformers and can be trained in an end-to-end manner. Extensive experimental results on several popular benchmarks, such as PF-PASCAL, PF-WILLOW, and SPair-71K, demonstrate that the proposed method can catch subtle semantic differences in pixels efficiently. Code is available on https://github.com/YXSUNMADMAX/ACTR.

We introduce Correlational Image Modeling (CIM), a novel but surprisingly effective approach to self-supervised visual pre-training. Our CIM performs a simple pretext task: we randomly crop image regions (exemplar) from an input image (context) and predict correlation maps between the exemplars and the context. Three key designs enable correlational image modeling as a nontrivial and meaningful self-supervisory task. First, to generate useful exemplar-context pairs, we consider cropping image regions with various scales, shapes, rotations, and transformations. Second, we employ a bootstrap learning framework that involves online and target networks. During pre-training, the former takes exemplars as inputs while the latter converts the context. Third, we model the output correlation maps via a simple cross-attention block, within which the context serves as queries and the exemplars offer values and keys. We show that CIM performs on par or better than the current state of the art on self-supervised and transfer benchmarks.

Deep learning in general domains has constantly been extended to domain-specific tasks requiring the recognition of fine-grained characteristics. However, real-world applications for fine-grained tasks suffer from two challenges: a high reliance on expert knowledge for annotation and necessity of a versatile model for various downstream tasks in a specific domain (e.g., prediction of categories, bounding boxes, or pixel-wise annotations). Fortunately, the recent self-supervised learning (SSL) is a promising approach to pretrain a model without annotations, serving as an effective initialization for any downstream tasks. Since SSL does not rely on the presence of annotation, in general, it utilizes the large-scale unlabeled dataset, referred to as an open-set. In this sense, we introduce a novel Open-Set Self-Supervised Learning problem under the assumption that a large-scale unlabeled open-set is available, as well as the fine-grained target dataset, during a pretraining phase. In our problem setup, it is crucial to consider the distribution mismatch between the open-set and target dataset. Hence, we propose SimCore algorithm to sample a coreset, the subset of an open-set that has a minimum distance to the target dataset in the latent space. We demonstrate that SimCore significantly improves representation learning performance through extensive experimental settings, including eleven fine-grained datasets and seven open-sets in various downstream tasks.

Edit fidelity is a significant issue in open-world controllable generative image editing. Recently, CLIP-based approaches have traded off simplicity to alleviate these problems by introducing spatial attention in a handpicked layer of a StyleGAN. In this paper, we propose CoralStyleCLIP, which incorporates a multi-layer attention-guided blending strategy in the feature space of StyleGAN2 for obtaining high-fidelity edits. We propose multiple forms of our co-optimized region and layer selection strategy to demonstrate the variation of time complexity with the quality of edits over different architectural intricacies while preserving simplicity. We conduct extensive experimental analysis and benchmark our method against state-of-the-art CLIP-based methods. Our findings suggest that CoralStyleCLIP results in high-quality edits while preserving the ease of use.