CVPR 2024 Papers

Listening head generation aims to synthesize a non-verbal responsive listener head by modeling the correlation between the speaker and the listener in dynamic conversion. The applications of listener agent generation in virtual interaction have promoted many works achieving diverse and fine-grained motion generation. However they can only manipulate motions through simple emotional labels but cannot freely control the listener's motions. Since listener agents should have human-like attributes (e.g. identity personality) which can be freely customized by users this limits their realism. In this paper we propose a user-friendly framework called CustomListener to realize the free-form text prior guided listener generation. To achieve speaker-listener coordination we design a Static to Dynamic Portrait module (SDP) which interacts with speaker information to transform static text into dynamic portrait token with completion rhythm and amplitude information. To achieve coherence between segments we design a Past Guided Generation module (PGG) to maintain the consistency of customized listener attributes through the motion prior and utilize a diffusion-based structure conditioned on the portrait token and the motion prior to realize the controllable generation. To train and evaluate our model we have constructed two text-annotated listening head datasets based on ViCo and RealTalk which provide text-video paired labels. Extensive experiments have verified the effectiveness of our model.

Modern depth sensors such as LiDAR operate by sweeping laser-beams across the scene resulting in a point cloud with notable 1D curve-like structures. In this work we introduce a new point cloud processing scheme and backbone called CurveCloudNet which takes advantage of the curve-like structure inherent to these sensors. While existing backbones discard the rich 1D traversal patterns and rely on generic 3D operations CurveCloudNet parameterizes the point cloud as a collection of polylines (dubbed a "curve cloud") establishing a local surface-aware ordering on the points. By reasoning along curves CurveCloudNet captures lightweight curve-aware priors to efficiently and accurately reason in several diverse 3D environments. We evaluate CurveCloudNet on multiple synthetic and real datasets that exhibit distinct 3D size and structure. We demonstrate that CurveCloudNet outperforms both point-based and sparse-voxel backbones in various segmentation settings notably scaling to large scenes better than point-based alternatives while exhibiting improved single-object performance over sparse-voxel alternatives. In all CurveCloudNet is an efficient and accurate backbone that can handle a larger variety of 3D environments than past works.

Referring image segmentation (RIS) aims to precisely segment referents in images through corresponding natural language expressions yet relying on cost-intensive mask annotations. Weakly supervised RIS thus learns from image-text pairs to pixel-level semantics which is challenging for segmenting fine-grained masks. A natural approach to enhancing segmentation precision is to empower weakly supervised RIS with the image segmentation foundation model SAM. Nevertheless we observe that simply integrating SAM yields limited benefits and can even lead to performance regression due to the inevitable noise issues and challenges in excessive focus on object parts. In this paper we present an innovative framework Point PrompTing (PPT) incorporated with the proposed multi-source curriculum learning strategy to address these challenges. Specifically the core of PPT is a point generator that not only harnesses CLIP's text-image alignment capability and SAM's powerful mask generation ability but also generates negative point prompts to address the noisy and excessive focus issues inherently and effectively. In addition we introduce a curriculum learning strategy with object-centric images to help PPT gradually learn from simpler yet precise semantic alignment to more complex RIS. Experiments demonstrate that our PPT significantly and consistently outperforms prior weakly supervised techniques on mIoU by 11.34% 14.14% and 6.97% across RefCOCO RefCOCO+ and G-Ref respectively.

In this paper we introduce VoteCut an innovative method for unsupervised object discovery that leverages feature representations from multiple self-supervised models. VoteCut employs normalized-cut based graph partitioning clustering and a pixel voting approach. Additionally We present CuVLER (Cut-Vote-and-LEaRn) a zero-shot model trained using pseudo-labels generated by VoteCut and a novel soft target loss to refine segmentation accuracy. Through rigorous evaluations across multiple datasets and several unsupervised setups our methods demonstrate significant improvements in comparison to previous state-of-the-art models. Our ablation studies further highlight the contributions of each component revealing the robustness and efficacy of our approach. Collectively VoteCut and CuVLER pave the way for future advancements in image segmentation.

Crowd counting is a fundamental problem in crowd analysis which is typically accomplished by estimating a crowd density map and summing over the density values. However this approach suffers from background noise accumulation and loss of density due to the use of broad Gaussian kernels to create the ground truth density maps. This issue can be overcome by narrowing the Gaussian kernel. However existing approaches perform poorly when trained with ground truth density maps with broad kernels. To deal with this limitation we propose using conditional diffusion models to predict density maps as diffusion models show high fidelity to training data during generation. With that we present CrowdDiff that generates the crowd density map as a reverse diffusion process. Furthermore as the intermediate time steps of the diffusion process are noisy we incorporate a regression branch for direct crowd estimation only during training to improve the feature learning. In addition owing to the stochastic nature of the diffusion model we introduce producing multiple density maps to improve the counting performance contrary to the existing crowd counting pipelines. We conduct extensive experiments on publicly available datasets to validate the effectiveness of our method. CrowdDiff outperforms existing \sota crowd counting methods on several public crowd analysis benchmarks with significant improvements. CrowdDiff project is available at: https://dylran.github.io/crowddiff.github.io.

Learning joint and coordinated features across modalities is essential for many audio-visual tasks. Existing pre-training methods primarily focus on global information neglecting fine-grained features and positions leading to suboptimal performance in dense prediction tasks. To address this issue we take a further step towards region-aware audio-visual pre-training and propose CrossMAE which excels in Cross-modality interaction and region alignment. Specifically we devise two masked autoencoding (MAE) pretext tasks at both pixel and embedding levels namely Cross-Conditioned Reconstruction and Cross-Embedding Reconstruction. Taking the visual modality as an example (the same goes for audio) in Cross-Conditioned Reconstruction the visual modality reconstructs the input image pixels conditioned on audio Attentive Tokens. As for the more challenging Cross-Embedding Reconstruction unmasked visual tokens reconstruct complete audio features under the guidance of learnable queries implying positional information which effectively enhances the interaction between modalities and exploits fine-grained semantics. Experimental results demonstrate that CrossMAE achieves state-of-the-art performance not only in classification and retrieval but also in dense prediction tasks. Furthermore we dive into the mechanism of modal interaction and region alignment of CrossMAE highlighting the effectiveness of the proposed components.

Knowledge Distillation (KD) has been validated as an effective model compression technique for learning compact object detectors. Existing state-of-the-art KD methods for object detection are mostly based on feature imitation. In this paper we present a general and effective prediction mimicking distillation scheme called CrossKD which delivers the intermediate features of the student's detection head to the teacher's detection head. The resulting cross-head predictions are then forced to mimic the teacher's predictions. This manner relieves the student's head from receiving contradictory supervision signals from the annotations and the teacher's predictions greatly improving the student's detection performance. Moreover as mimicking the teacher's predictions is the target of KD CrossKD offers more task-oriented information in contrast with feature imitation. On MS COCO with only prediction mimicking losses applied our CrossKD boosts the average precision of GFL ResNet-50 with 1x training schedule from 40.2 to 43.7 outperforming all existing KD methods. In addition our method also works well when distilling detectors with heterogeneous backbones.

Human perception and understanding is a major domain of computer vision which like many other vision subdomains recently stands to gain from the use of large models pre-trained on large datasets. We hypothesize that the most common pre-training strategy of relying on general purpose object-centric image datasets such as ImageNet is limited by an important domain shift. On the other hand collecting domain-specific ground truth such as 2D or 3D labels does not scale well. Therefore we propose a pre-training approach based on self-supervised learning that works on human-centric data using only images. Our method uses pairs of images of humans: the first is partially masked and the model is trained to reconstruct the masked parts given the visible ones and a second image. It relies on both stereoscopic (cross-view) pairs and temporal (cross-pose) pairs taken from videos in order to learn priors about 3D as well as human motion. We pre-train a model for body-centric tasks and one for hand-centric tasks. With a generic transformer architecture these models outperform existing self-supervised pre-training methods on a wide set of human-centric downstream tasks and obtain state-of-the-art performance for instance when fine-tuning for model-based and model-free human mesh recovery.

Cross-Domain Few-Shot Segmentation (CD-FSS) poses the challenge of segmenting novel categories from a distinct domain using only limited exemplars. In this paper we undertake a comprehensive study of CD-FSS and uncover two crucial insights: (i) the necessity of a fine-tuning stage to effectively transfer the learned meta-knowledge across domains and (ii) the overfitting risk during the naive fine-tuning due to the scarcity of novel category examples. With these insights we propose a novel cross-domain fine-tuning strategy that addresses the challenging CD-FSS tasks. We first design Bi-directional Few-shot Prediction (BFP) which establishes support-query correspondence in a bi-directional manner crafting augmented supervision to reduce the overfitting risk. Then we further extend BFP into Iterative Few-shot Adaptor (IFA) which is a recursive framework to capture the support-query correspondence iteratively targeting maximal exploitation of supervisory signals from the sparse novel category samples. Extensive empirical evaluations show that our method significantly outperforms the state-of-the-arts (+7.8%) which verifies that IFA tackles the cross-domain challenges and mitigates the overfitting simultaneously. The code is available at: https://github.com/niejiahao1998/IFA.

Accurate 3D neuron segmentation from electron microscopy (EM) volumes is crucial for neuroscience research. However the complex neuron morphology often leads to over-merge and over-segmentation results. Recent advancements utilize 3D CNNs to predict a 3D affinity map with improved accuracy but suffer from two challenges: high computational cost and limited input size especially for practical deployment for large-scale EM volumes. To address these challenges we propose a novel method to leverage lightweight 2D CNNs for efficient neuron segmentation. Our method employs a 2D Y-shape network to generate two embedding maps from adjacent 2D sections which are then converted into an affinity map by measuring their embedding distance. While the 2D network better captures pixel dependencies inside sections with larger input sizes it overlooks inter-section dependencies. To overcome this we introduce a cross-dimension affinity distillation (CAD) strategy that transfers inter-section dependency knowledge from a 3D teacher network to the 2D student network by ensuring consistency between their output affinity maps. Additionally we design a feature grafting interaction (FGI) module to enhance knowledge transfer by grafting embedding maps from the 2D student onto those from the 3D teacher. Extensive experiments on multiple EM neuron segmentation datasets including a newly built one by ourselves demonstrate that our method achieves superior performance over state-of-the-art methods with only 1/20 inference latency.

Recently there has been a surge in face personalization techniques benefiting from the advanced capabilities of pretrained text-to-image diffusion models. Among these a notable method is Textual Inversion which generates personalized images by inverting given images into textual embeddings. However methods based on Textual Inversion still struggle with balancing the trade-off between reconstruction quality and editability. In this study we examine this issue through the lens of initialization. Upon closely examining traditional initialization methods we identified a significant disparity between the initial and learned embeddings in terms of both scale and orientation. The scale of the learned embedding can be up to 100 times greater than that of the initial embedding. Such a significant change in the embedding could increase the risk of overfitting thereby compromising the editability. Driven by this observation we introduce a novel initialization method termed Cross Initialization that significantly narrows the gap between the initial and learned embeddings. This method not only improves both reconstruction and editability but also reduces the optimization steps from 5000 to 320. Furthermore we apply a regularization term to keep the learned embedding close to the initial embedding. We show that when combined with Cross Initialization this regularization term can effectively improve editability. We provide comprehensive empirical evidence to demonstrate the superior performance of our method compared to the baseline methods. Notably in our experiments Cross Initialization is the only method that successfully edits an individual's facial expression. Additionally a fast version of our method allows for capturing an input image in roughly 26 seconds while surpassing the baseline methods in terms of both reconstruction and editability. Code is available at https://github.com/lyuPang/CrossInitialization.

Partial-label learning (PLL) is an important weakly supervised learning problem which allows each training example to have a candidate label set instead of a single ground-truth label. Identification-based methods have been widely explored to tackle label ambiguity issues in PLL which regard the true label as a latent variable to be identified. However identifying the true labels accurately and completely remains challenging causing noise in pseudo labels during model training. In this paper we propose a new method called CroSel which leverages historical predictions from the model to identify true labels for most training examples. First we introduce a cross selection strategy which enables two deep models to select true labels of partially labeled data for each other. Besides we propose a novel consistency regularization term called co-mix to avoid sample waste and tiny noise caused by false selection. In this way CroSel can pick out the true labels of most examples with high precision. Extensive experiments demonstrate the superiority of CroSel which consistently outperforms previous state-of-the-art methods on benchmark datasets. Additionally our method achieves over 90% accuracy and quantity for selecting true labels on CIFAR-type datasets under various settings.

Over the past decade most methods in visual place recognition (VPR) have used neural networks to produce feature representations. These networks typically produce a global representation of a place image using only this image itself and neglect the cross-image variations (e.g. viewpoint and illumination) which limits their robustness in challenging scenes. In this paper we propose a robust global representation method with cross-image correlation awareness for VPR named CricaVPR. Our method uses the attention mechanism to correlate multiple images within a batch. These images can be taken in the same place with different conditions or viewpoints or even captured from different places. Therefore our method can utilize the cross-image variations as a cue to guide the representation learning which ensures more robust features are produced. To further facilitate the robustness we propose a multi-scale convolution-enhanced adaptation method to adapt pre-trained visual foundation models to the VPR task which introduces the multi-scale local information to further enhance the cross-image correlation-aware representation. Experimental results show that our method outperforms state-of-the-art methods by a large margin with significantly less training time. The code is released at https://github.com/Lu-Feng/CricaVPR.

Point cloud matching a crucial technique in computer vision medical and robotics fields is primarily concerned with finding correspondences between pairs of point clouds or voxels. In some practical scenarios emphasizing local differences is crucial for accurately identifying a correct match thereby enhancing the overall robustness and reliability of the matching process. Commonly used shape descriptors have several limitations and often fail to provide meaningful local insights about the paired geometries. In this work we propose a new technique based on graph Laplacian eigenmaps to match point clouds by taking into account fine local structures. To deal with the order and sign ambiguity of Laplacian eigenmaps we introduce a new operator called Coupled Laplacian that allows to easily generate aligned eigenspaces for multiple registered geometries. We show that the similarity between those aligned high-dimensional spaces provides a locally meaningful score to match shapes. We firstly evaluate the performance of the proposed technique in a point-wise manner focusing on the task of object anomaly localization on the MVTec 3D-AD dataset. Additionally we define a new medical task called automatic Bone Side Estimation (BSE) which we address through a global similarity score derived from coupled eigenspaces. In order to test it we propose a benchmark collecting bone surface structures from various public datasets. Our matching technique based on Coupled Laplacian outperforms other methods by reaching an impressive accuracy on both tasks.

State-of-the-art personalized text-to-image generation systems are usually trained on a few reference images to learn novel visual representations. However this is likely to incur infringement of copyright for the reference image owners when these images are personal and publicly available. Recent progress has been made in protecting these images from unauthorized use by adding protective noises. Yet current protection methods work under the assumption that these protected images are not changed which is in contradiction to the fact that most public platforms intend to modify user-uploaded content e.g. image compression. This paper introduces a robust watermarking method namely InMark to protect images from unauthorized learning. Inspired by influence functions the proposed method forges protective watermarks on more important pixels for these reference images from both heuristic and statistical perspectives. In this way the personal semantics of these images are under protection even if these images are modified to some extent. Extensive experiments demonstrate that the proposed InMark outperforms previous state-of-the-art methods in both protective performance and robustness.

Co-salient object detection (CoSOD) aims to identify the common and salient (usually in the foreground) regions across a given group of images. Although achieving significant progress state-of-the-art CoSODs could be easily affected by some adversarial perturbations leading to substantial accuracy reduction. The adversarial perturbations can mislead CoSODs but do not change the high-level semantic information (e.g. concept) of the co-salient objects. In this paper we propose a novel robustness enhancement framework by first learning the concept of the co-salient objects based on the input group images and then leveraging this concept to purify adversarial perturbations which are subsequently fed to CoSODs for robustness enhancement. Specifically we propose CosalPure containing two modules i.e. group-image concept learning and concept-guided diffusion purification. For the first module we adopt a pre-trained text-to-image diffusion model to learn the concept of co-salient objects within group images where the learned concept is robust to adversarial examples. For the second module we map the adversarial image to the latent space and then perform diffusion generation by embedding the learned concept into the noise prediction function as an extra condition. Our method can effectively alleviate the influence of the SOTA adversarial attack containing different adversarial patterns including exposure and noise. The extensive results demonstrate that our method could enhance the robustness of CoSODs significantly.

Deformable image registration is a fundamental step for medical image analysis. Recently transformers have been used for registration and outperformed Convolutional Neural Networks (CNNs). Transformers can capture long-range dependence among image features which have been shown beneficial for registration. However due to the high computation/memory loads of self-attention transformers are typically used at downsampled feature resolutions and cannot capture fine-grained long-range dependence at the full image resolution. This limits deformable registration as it necessitates precise dense correspondence between each image pixel. Multi-layer Perceptrons (MLPs) without self-attention are efficient in computation/memory usage enabling the feasibility of capturing fine-grained long-range dependence at full resolution. Nevertheless MLPs have not been extensively explored for image registration and are lacking the consideration of inductive bias crucial for medical registration tasks. In this study we propose the first correlation-aware MLP-based registration network (CorrMLP) for deformable medical image registration. Our CorrMLP introduces a correlation-aware multi-window MLP block in a novel coarse-to-fine registration architecture which captures fine-grained multi-range dependence to perform correlation-aware coarse-to-fine registration. Extensive experiments with seven public medical datasets show that our CorrMLP outperforms state-of-the-art deformable registration methods.

Multimodal sentiment analysis (MSA) aims to understand human sentiment through multimodal data. Most MSA efforts are based on the assumption of modality completeness. However in real-world applications some practical factors cause uncertain modality missingness which drastically degrades the model's performance. To this end we propose a Correlation-decoupled Knowledge Distillation (CorrKD) framework for the MSA task under uncertain missing modalities. Specifically we present a sample-level contrastive distillation mechanism that transfers comprehensive knowledge containing cross-sample correlations to reconstruct missing semantics. Moreover a category-guided prototype distillation mechanism is introduced to capture cross-category correlations using category prototypes to align feature distributions and generate favorable joint representations. Eventually we design a response-disentangled consistency distillation strategy to optimize the sentiment decision boundaries of the student network through response disentanglement and mutual information maximization. Comprehensive experiments on three datasets indicate that our framework can achieve favorable improvements compared with several baselines.

This paper presents a simple but performant semi-supervised semantic segmentation approach called CorrMatch. Previous approaches mostly employ complicated training strategies to leverage unlabeled data but overlook the role of correlation maps in modeling the relationships between pairs of locations. We observe that the correlation maps not only enable clustering pixels of the same category easily but also contain good shape information which previous works have omitted. Motivated by these we aim to improve the use efficiency of unlabeled data by designing two novel label propagation strategies. First we propose to conduct pixel propagation by modeling the pairwise similarities of pixels to spread the high-confidence pixels and dig out more. Then we perform region propagation to enhance the pseudo labels with accurate class-agnostic masks extracted from the correlation maps. CorrMatch achieves great performance on popular segmentation benchmarks. Taking the DeepLabV3+ with ResNet-101 backbone as our segmentation model we receive a 76%+ mIoU score on the Pascal VOC 2012 dataset with only 92 annotated images. Code is available at https://github.com/BBBBchan/CorrMatch .