CVPR 2024 论文列表

In this paper we present a few-shot text-to-video framework LAMP which enables a text-to-image diffusion model to Learn A specific Motion Pattern with 8 16 videos on a single GPU. Unlike existing methods which require a large number of training resources or learn motions that are precisely aligned with template videos it achieves a trade-off between the degree of generation freedom and the resource costs for model training. Specifically we design a motion-content decoupled pipeline that uses an off-the-shelf text-to-image model for content generation so that our tuned video diffusion model mainly focuses on motion learning. The well-developed text-to-image techniques can provide visually pleasing and diverse content as generation conditions which highly improves video quality and generation freedom. To capture the features of temporal dimension we expand the pre-trained 2D convolution layers of the T2I model to our novel temporal-spatial motion learning layers and modify the attention blocks to the temporal level. Additionally we develop an effective inference trick shared-noise sampling which can improve the stability of videos without computational costs. Our method can also be flexibly applied to other tasks e.g. real-world image animation and video editing. Extensive experiments demonstrate that LAMP can effectively learn the motion pattern on limited data and generate high-quality videos. The code and models are available at https://rq-wu.github.io/projects/LAMP.

Neural Radiance Field (NeRF) has achieved superior performance for novel view synthesis by modeling the scene with a Multi-Layer Perception (MLP) and a volume rendering procedure however when fewer known views are given (i.e. few-shot view synthesis) the model is prone to overfit the given views. To handle this issue previous efforts have been made towards leveraging learned priors or introducing additional regularizations. In contrast in this paper we for the first time provide an orthogonal method from the perspective of network structure. Given the observation that trivially reducing the number of model parameters alleviates the overfitting issue but at the cost of missing details we propose the multi-input MLP (mi-MLP) that incorporates the inputs (i.e. location and viewing direction) of the vanilla MLP into each layer to prevent the overfitting issue without harming detailed synthesis. To further reduce the artifacts we propose to model colors and volume density separately and present two regularization terms. Extensive experiments on multiple datasets demonstrate that: 1) although the proposed mi-MLP is easy to implement it is surprisingly effective as it boosts the PSNR of the baseline from 14.73 to 24.23. 2) the overall framework achieves state-of-the-art results on a wide range of benchmarks. We will release the code upon publication.

In order to mimic the human few-shot learning (FSL) ability better and to make FSL closer to real-world applications this paper proposes a practical FSL (pFSL) setting. pFSL is based on unsupervised pre-trained models (analogous to human prior knowledge) and recognizes many novel classes simultaneously. Compared to traditional FSL pFSL is simpler in its formulation easier to evaluate more challenging and more practical. To cope with the rarity of training examples this paper proposes IbM2 an instance-based max-margin method not only for the new pFSL setting but also works well in traditional FSL scenarios. Based on the Gaussian Annulus Theorem IbM2 converts random noise applied to the instances into a mechanism to achieve maximum margin in the many-way pFSL (or traditional FSL) recognition task. Experiments with various self-supervised pre-training methods and diverse many- or few-way FSL tasks show that IbM2 almost always leads to improvements compared to its respective baseline methods and in most cases the improvements are significant. With both the new pFSL setting and novel IbM2 method this paper shows that practical few-shot learning is both viable and promising.

Generalized Zero-Shot Learning (GZSL) methods often assume that the unseen classes are similar to seen classes and thus perform poor when unseen classes are dissimilar to seen classes. Although some existing GZSL approaches can alleviate this issue by leveraging additional semantic information from test unseen classes their generalization ability to dissimilar unseen classes is still unsatisfactory. This motivates us to study GZSL in the more practical setting where unseen classes can be either similar or dissimilar to seen classes. In this paper we propose a simple yet effective GZSL framework by exploring diverse semantics from external class names (DSECN) which is simultaneously robust on the similar and dissimilar unseen classes. This is achieved by introducing diverse semantics from external class names and aligning the introduced semantics to visual space using the classification head of pre-trained network. Furthermore we show that the design idea of DSECN can easily be integrate into other advanced GZSL approaches such as the generative-based ones and enhance their robustness for dissimilar unseen classes. Extensive experiments in the practical setting including both similar and dissimilar unseen classes show that our method significantly outperforms the state-of-the-art approaches on all datasets and can be trained very efficiently.

Learned reweighting (LRW) approaches to supervised learning use an optimization criterion to assign weights for training instances in order to maximize performance on a representative validation dataset. We pose and formalize the problem of optimized selection of the validation set used in LRW training to improve classifier generalization. In particular we show that using hard-to-classify instances in the validation set has both a theoretical connection to and strong empirical evidence of generalization. We provide an efficient algorithm for training this meta-optimized model as well as a simple train-twice heuristic for careful comparative study. We demonstrate that LRW with easy validation data performs consistently worse than LRW with hard validation data establishing the validity of our meta-optimization problem. Our proposed algorithm outperforms a wide range of baselines on a range of datasets and domain shift challenges (Imagenet-1K CIFAR-100 Clothing-1M CAMELYON WILDS etc.) with 1% gains using VIT-B on Imagenet. We also show that using naturally hard examples for validation (Imagenet-R / Imagenet-A) in LRW training for Imagenet improves performance on both clean and naturally hard test instances by 1-2%. Secondary analyses show that using hard validation data in an LRW framework improves margins on test data hinting at the mechanism underlying our empirical gains. We believe this work opens up new research directions for the meta-optimization of meta-learning in a supervised learning context.

Out-of-distribution (OOD) detection methods often exploit auxiliary outliers to train model identifying OOD samples especially discovering challenging outliers from auxiliary outliers dataset to improve OOD detection. However they may still face limitations in effectively distinguishing between the most challenging OOD samples that are much like in-distribution (ID) data i.e. ID-like samples. To this end we propose a novel OOD detection framework that discovers ID-like outliers using CLIP from the vicinity space of the ID samples thus helping to identify these most challenging OOD samples. Then a prompt learning framework is proposed that utilizes the identified ID-like outliers to further leverage the capabilities of CLIP for OOD detection. Benefiting from the powerful CLIP we only need a small number of ID samples to learn the prompts of the model without exposing other auxiliary outlier datasets. By focusing on the most challenging ID-like OOD samples and elegantly exploiting the capabilities of CLIP our method achieves superior few-shot learning performance on various real-world image datasets (e.g. in 4-shot OOD detection on the ImageNet-1k dataset our method reduces the average FPR95 by 12.16% and improves the average AUROC by 2.76% compared to state-of-the-art methods).

We present HumanNeRF-SE a simple yet effective method that synthesizes diverse novel pose images with simple input. Previous HumanNeRF works require a large number of optimizable parameters to fit the human images. Instead we reload these approaches by combining explicit and implicit human representations to design both generalized rigid deformation and specific non-rigid deformation. Our key insight is that explicit shape can reduce the sampling points used to fit implicit representation and frozen blending weights from SMPL constructing a generalized rigid deformation can effectively avoid overfitting and improve pose generalization performance. Our architecture involving both explicit and implicit representation is simple yet effective. Experiments demonstrate our model can synthesize images under arbitrary poses with few-shot input and increase the speed of synthesizing images by 15 times through a reduction in computational complexity without using any existing acceleration modules. Compared to the state-of-the-art HumanNeRF studies HumanNeRF-SE achieves better performance with fewer learnable parameters and less training time.

In this paper we present a method to reconstruct the world and multiple dynamic humans in 3D from a monocular video input. As a key idea we represent both the world and multiple humans via the recently emerging 3D Gaussian Splatting (3D-GS) representation enabling to conveniently and efficiently compose and render them together. In particular we address the scenarios with severely limited and sparse observations in 3D human reconstruction a common challenge encountered in the real world. To tackle this challenge we introduce a novel approach to optimize the 3D-GS representation in a canonical space by fusing the sparse cues in the common space where we leverage a pre-trained 2D diffusion model to synthesize unseen views while keeping the consistency with the observed 2D appearances. We demonstrate our method can reconstruct high-quality animatable 3D humans in various challenging examples in the presence of occlusion image crops few-shot and extremely sparse observations. After reconstruction our method is capable of not only rendering the scene in any novel views at arbitrary time instances but also editing the 3D scene by removing individual humans or applying different motions for each human. Through various experiments we demonstrate the quality and efficiency of our methods over alternative existing approaches.

It is challenging for Neural Radiance Fields (NeRFs) in the few-shot setting to reconstruct high-quality novel views and depth maps in 360^\circ outward-facing indoor scenes. The captured sparse views for these scenes usually contain large viewpoint variations. This greatly reduces the potential consistency between views leading NeRFs to degrade a lot in these scenarios. Existing methods usually leverage pretrained depth prediction models to improve NeRFs. However these methods cannot guarantee geometry consistency due to the inherent geometry ambiguity in the pretrained models thus limiting NeRFs' performance. In this work we present P\textsuperscript 2 NeRF to capture global and hierarchical geometry consistency priors from pretrained models thus facilitating few-shot NeRFs in 360^\circ outward-facing indoor scenes. On the one hand we propose a matching-based geometry warm-up strategy to provide global geometry consistency priors for NeRFs. This effectively avoids the overfitting of early training with sparse inputs. On the other hand we propose a group depth ranking loss and ray weight mask regularization based on the monocular depth estimation model. This provides hierarchical geometry consistency priors for NeRFs. As a result our approach can fully leverage the geometry consistency priors from pretrained models and help few-shot NeRFs achieve state-of-the-art performance on two challenging indoor datasets. Our code is released at https://github.com/XT5un/P2NeRF.

Training a linear classifier or lightweight model on top of pretrained vision model outputs so-called 'frozen features' leads to impressive performance on a number of downstream few-shot tasks. Currently frozen features are not modified during training. On the other hand when networks are trained directly on images data augmentation is a standard recipe that improves performance with no substantial overhead. In this paper we conduct an extensive pilot study on few-shot image classification that explores applying data augmentations in the frozen feature space dubbed 'frozen feature augmentation (FroFA)' covering twenty augmentations in total. Our study demonstrates that adopting a deceptively simple pointwise FroFA such as brightness can improve few-shot performance consistently across three network architectures three large pretraining datasets and eight transfer datasets.

The Segment Anything Model (SAM) marks a notable milestone in segmentation models highlighted by its robust zero-shot capabilities and ability to handle diverse prompts. SAM follows a pipeline that separates interactive segmentation into image preprocessing through a large encoder and interactive inference via a lightweight decoder ensuring efficient real-time performance. However SAM faces stability issues in challenging samples upon this pipeline. These issues arise from two main factors. Firstly the image preprocessing disables SAM to dynamically use image-level zoom-in strategies to refocus on the target object during interaction. Secondly the lightweight decoder struggles to sufficiently integrate interactive information with image embeddings. To address these two limitations we propose FocSAM with a pipeline redesigned on two pivotal aspects. First we propose Dynamic Window Multi-head Self-Attention (Dwin-MSA) to dynamically refocus SAM's image embeddings on the target object. Dwin-MSA localizes attention computations around the target object enhancing object-related embeddings with minimal computational overhead. Second we propose Pixel-wise Dynamic ReLU (P-DyReLU) to enable sufficient integration of interactive information from a few initial clicks that have significant impacts on the overall segmentation results. Experimentally FocSAM augments SAM's interactive segmentation performance to match the existing state-of-the-art method in segmentation quality requiring only about 5.6% of this method's inference time on CPUs. Code is available at https://github.com/YouHuang67/focsam.

Cross-domain few-shot learning (CDFSL) aims to acquire knowledge from limited training data in the target domain by leveraging prior knowledge transferred from source domains with abundant training samples. CDFSL faces challenges in transferring knowledge across dissimilar domains and fine-tuning models with limited training data. To address these challenges we initially extend the analysis of loss landscapes from the parameter space to the representation space which allows us to simultaneously interpret the transferring and fine-tuning difficulties of CDFSL models. We observe that sharp minima in the loss landscapes of the representation space result in representations that are hard to transfer and fine-tune. Moreover existing flatness-based methods have limited generalization ability due to their short-range flatness. To enhance the transferability and facilitate fine-tuning we introduce a simple yet effective approach to achieve long-range flattening of the minima in the loss landscape. This approach considers representations that are differently normalized as minima in the loss landscape and flattens the high-loss region in the middle by randomly sampling interpolated representations. We implement this method as a new normalization layer that replaces the original one in both CNNs and ViTs. This layer is simple and lightweight introducing only a minimal number of additional parameters. Experimental results on 8 datasets demonstrate that our approach outperforms state-of-the-art methods in terms of average accuracy. Moreover our method achieves performance improvements of up to 9% compared to the current best approaches on individual datasets. Our code will be released.

Even when using large multi-modal foundation models few-shot learning is still challenging -- if there is no proper inductive bias it is nearly impossible to keep the nuanced class attributes while removing the visually prominent attributes that spuriously correlate with class labels. To this end we find an inductive bias that the time-steps of a Diffusion Model (DM) can isolate the nuanced class attributes i.e. as the forward diffusion adds noise to an image at each time-step nuanced attributes are usually lost at an earlier time-step than the spurious attributes that are visually prominent. Building on this we propose Time-step Few-shot (TiF) learner. We train class-specific low-rank adapters for a text-conditioned DM to make up for the lost attributes such that images can be accurately reconstructed from their noisy ones given a prompt. Hence at a small time-step the adapter and prompt are essentially a parameterization of only the nuanced class attributes. For a test image we can use the parameterization to only extract the nuanced class attributes for classification. TiF learner significantly outperforms OpenCLIP and its adapters on a variety of fine-grained and customized few-shot learning tasks. Codes are in https://github.com/yue-zhongqi/tif.

Few-shot object detection (FSOD) aims to detect objects with only a few training examples. Visual feature extraction and query-support similarity learning are the two critical components. Existing works are usually developed based on ImageNet pre-trained vision backbones and design sophisticated metric-learning networks for few-shot learning but still have inferior accuracy. In this work we study few-shot object detection using modern foundation models. First vision-only contrastive pre-trained DINOv2 model is used for the vision backbone which shows strong transferable performance without tuning the parameters. Second Large Language Model (LLM) is employed for contextualized few-shot learning with the input of all classes and query image proposals. Language instructions are carefully designed to prompt the LLM to classify each proposal in context. The contextual information include proposal-proposal relations proposal-class relations and class-class relations which can largely promote few-shot learning. We comprehensively evaluate the proposed model (FM-FSOD) in multiple FSOD benchmarks achieving state-of-the-arts performance.

While previous studies have demonstrated successful 3D object shape completion with a sufficient number of points they often fail in scenarios when a few points e.g. tens of points are observed. Surprisingly via entropy analysis we find that even a few points e.g. 64 points could retain substantial information to help recover the 3D shape of the object. To address the challenge of shape completion with very sparse point clouds we then propose Few-point Shape Completion (FSC) model which contains a novel dual-branch feature extractor for handling extremely sparse inputs coupled with an extensive branch for maximal point utilization with a saliency branch for dynamic importance assignment. This model is further bolstered by a two-stage revision network that refines both the extracted features and the decoder output enhancing the detail and authenticity of the completed point cloud. Our experiments demonstrate the feasibility of recovering 3D shapes from a few points. The proposed Few-point Shape Completion (FSC) model outperforms previous methods on both few-point inputs and many-point inputs and shows good generalizability to different object categories.

CLIP has demonstrated marked progress in visual recognition due to its powerful pre-training on large-scale image-text pairs. However it still remains a critical challenge: how to transfer image-level knowledge into pixel-level understanding tasks such as semantic segmentation. In this paper to solve the mentioned challenge we analyze the gap between the capability of the CLIP model and the requirement of the zero-shot semantic segmentation task. Based on our analysis and observations we propose a novel method for zero-shot semantic segmentation dubbed CLIP-RC (CLIP with Regional Clues) bringing two main insights. On the one hand a region-level bridge is necessary to provide fine-grained semantics. On the other hand overfitting should be mitigated during the training stage. Benefiting from the above discoveries CLIP-RC achieves state-of-the-art performance on various zero-shot semantic segmentation benchmarks including PASCAL VOC PASCAL Context and COCO-Stuff 164K. Code will be available at https://github.com/Jittor/JSeg.

Few-shot image generation as an important yet challenging visual task still suffers from the trade-off between generation quality and diversity. According to the principle of feature-matching learning existing fusion-based methods usually fuse different features by using similarity measurements or attention mechanisms which may match features inaccurately and lead to artifacts in the texture and structure of generated images. In this paper we propose an exact Fusion via Feature Distribution matching Generative Adversarial Network (F2DGAN) for few-shot image generation. The rationale behind this is that feature distribution matching is much more reliable than feature matching to explore the statistical characters in image feature space for limited real-world data. To model feature distributions from only a few examples for feature fusion we design a novel variational feature distribution matching fusion module to perform exact fusion by empirical cumulative distribution functions. Specifically we employ a variational autoencoder to transform deep image features into distributions and fuse different features exactly by applying histogram matching. Additionally we formulate two effective losses to guide the matching process for better fitting our fusion strategy. Extensive experiments compared with state-of-the-art methods on three public datasets demonstrate the superiority of F2DGAN for few-shot image generation in terms of generation quality and diversity and the effectiveness of data augmentation in downstream classification tasks.

Head avatars animated by visual signals have gained popularity particularly in cross-driving synthesis where the driver differs from the animated character a challenging but highly practical approach. The recently presented MegaPortraits model has demonstrated state-of-the-art results in this domain. We conduct a deep examination and evaluation of this model with a particular focus on its latent space for facial expression descriptors and uncover several limitations with its ability to express intense face motions. Head avatars animated by visual signals have gained popularity particularly in cross-driving synthesis where the driver differs from the animated character a challenging but highly practical approach. The recently presented MegaPortraits model has demonstrated state-of-the-art results in this domain. We conduct a deep examination and evaluation of this model with a particular focus on its latent space for facial expression descriptors and uncover several limitations with its ability to express intense face motions. To address these limitations we propose substantial changes in both training pipeline and model architecture to introduce our EMOPortraits model where we: Enhance the model's capability to faithfully support intense asymmetric face expressions setting a new state-of-the-art result in the emotion transfer task surpassing previous methods in both metrics and quality. Incorporate speech-driven mode to our model achieving top-tier performance in audio-driven facial animation making it possible to drive source identity through diverse modalities including visual signal audio or a blend of both.Furthermore we propose a novel multi-view video dataset featuring a wide range of intense and asymmetric facial expressions filling the gap with absence of such data in existing datasets.