The significant amount of manual efforts in annotating pixel-level labels has triggered the advancement of unsupervised saliency learning. However without supervision signals state-of-the-art methods can only infer region-level saliency. In this paper we propose to explore the unsupervised salient instance detection (USID) problem for a more fine-grained visual understanding. Our key observation is that self-supervised transformer features may exhibit local similarities as well as different levels of contrast to other regions which provide informative cues to identify salient instances. Hence we propose SCoCo a novel network that models saliency coherence and contrast for USID. SCoCo includes two novel modules: (1) a global background adaptation (GBA) module with a scene-level contrastive loss to extract salient regions from the scene by searching the adaptive "saliency threshold" in the self-supervised transformer features and (2) a locality-aware similarity (LAS) module with an instance-level contrastive loss to group salient regions into instances by modeling the in-region saliency coherence and cross-region saliency contrasts. Extensive experiments show that SCoCo outperforms state-of-the-art weakly-supervised SID methods and carefully designed unsupervised baselines and has comparable performances to fully-supervised SID methods.
论文检索
输入标题、作者或关键词，从 2,715 篇学术成果中精准定位
DensePose provides a pixel-accurate association of images with 3D mesh coordinates but does not provide a 3D mesh while Human Mesh Reconstruction (HMR) systems have high 2D reprojection error as measured by DensePose localization metrics. In this work we introduce MeshPose to jointly tackle DensePose and HMR. For this we first introduce new losses that allow us to use weak DensePose supervision to accurately localize in 2D a subset of the mesh vertices ('VertexPose'). We then lift these vertices to 3D yielding a low-poly body mesh ('MeshPose'). Our system is trained in an end-to-end manner and is the first HMR method to attain competitive DensePose accuracy while also being lightweight and amenable to efficient inference making it suitable for real-time AR applications.
With the escalating complexity and investment cost of training deep neural networks safeguarding them from unauthorized usage and intellectual property theft has become imperative. Especially the rampant misuse of prediction APIs to replicate models without access to the original data or architecture poses grave security threats. Diverse defense strategies have emerged to address these vulnerabilities yet these defenses either incur heavy inference overheads or assume idealized attack scenarios. To address these challenges we revisit the utilization of noise transition matrix as an efficient perturbation technique which injects noise into predicted posteriors in a linear manner and integrates seamlessly into existing systems with minimal overhead for model stealing defense. Provably with such perturbed posteriors the attacker's cloning process degrades into learning from noisy data. Toward optimizing the noise transition matrix we proposed a novel bi-level optimization training framework which performs fidelity on the victim model while the surrogate model adversarially. Comprehensive experimental results demonstrate that our method effectively thwarts model stealing attacks and achieves minimal utility trade-offs outperforming existing state-of-the-art defenses.
Post-training quantization (PTQ) converts a pre-trained full-precision (FP) model into a quantized model in a training-free manner. Determining suitable quantization parameters such as scaling factors and weight rounding is the primary strategy for mitigating the impact of quantization noise (calibration) and restoring the performance of the quantized models. However the existing activation calibration methods have never considered information degradation between pre- (FP) and post-quantized activations. In this study we introduce a well-defined distributional metric from information theory mutual information into PTQ calibration. We aim to calibrate the quantized activations by maximizing the mutual information between the pre- and post-quantized activations. To realize this goal we establish a contrastive learning (CL) framework for the PTQ calibration where the quantization parameters are optimized through a self-supervised proxy task. Specifically by leveraging CL during the PTQ process we can benefit from pulling the positive pairs of quantized and FP activations collected from the same input samples while pushing negative pairs from different samples. Thanks to the ingeniously designed critic function we avoid the unwanted but often-encountered collision solution in CL especially in calibration scenarios where the amount of calibration data is limited. Additionally we provide a theoretical guarantee that minimizing our designed loss is equivalent to maximizing the desired mutual information. Consequently the quantized activations retain more information which ultimately enhances the performance of the quantized network. Experimental results show that our method can effectively serve as an add-on module to existing SoTA PTQ methods.
In recent research significant attention has been devoted to the open-vocabulary object detection task aiming to generalize beyond the limited number of classes labeled during training and detect objects described by arbitrary category names at inference. Compared with conventional object detection open vocabulary object detection largely extends the object detection categories. However it relies on calculating the similarity between image regions and a set of arbitrary category names with a pretrained vision-and-language model. This implies that despite its open-set nature the task still needs the predefined object categories during the inference stage. This raises the question: What if we do not have exact knowledge of object categories during inference? In this paper we call such a new setting as generative open-ended object detection which is a more general and practical problem. To address it we formulate object detection as a generative problem and propose a simple framework named GenerateU which can detect dense objects and generate their names in a free-form way. Particularly we employ Deformable DETR as a region proposal generator with a language model translating visual regions to object names. To assess the free-form object detection task we introduce an evaluation method designed to quantitatively measure the performance of generative outcomes. Extensive experiments demonstrate strong zero-shot detection performance of our GenerateU. For example on the LVIS dataset our GenerateU achieves comparable results to the open-vocabulary object detection method GLIP even though the category names are not seen by GenerateU during inference. Code is available at: https://github.com/FoundationVision/GenerateU.
Estimating the 6D object pose from a single RGB image often involves noise and indeterminacy due to challenges such as occlusions and cluttered backgrounds. Meanwhile diffusion models have shown appealing performance in generating high-quality images from random noise with high indeterminacy through step-by-step denoising. Inspired by their denoising capability we propose a novel diffusion-based framework (6D-Diff) to handle the noise and indeterminacy in object pose estimation for better performance. In our framework to establish accurate 2D-3D correspondence we formulate 2D keypoints detection as a reverse diffusion (denoising) process. To facilitate such a denoising process we design a Mixture-of-Cauchy-based forward diffusion process and condition the reverse process on the object appearance features. Extensive experiments on the LM-O and YCB-V datasets demonstrate the effectiveness of our framework.
Pre-trained vision-language models (VLMs) have achieved high performance on various downstream tasks which have been widely used for visual grounding tasks in a weakly supervised manner. However despite the performance gains contributed by large vision and language pre-training we find that state-of-the-art VLMs struggle with compositional reasoning on grounding tasks. To demonstrate this we propose Attribute Relation and Priority grounding (ARPGrounding) benchmark to test VLMs' compositional reasoning ability on visual grounding tasks. ARPGrounding contains 11425 samples and evaluates the compositional understanding of VLMs in three dimensions: 1) attribute denoting comprehension of objects' properties; 2) relation indicating an understanding of relation between objects; 3) priority reflecting an awareness of the part of speech associated with nouns. Using the ARPGrounding benchmark we evaluate several mainstream VLMs. We empirically find that these models perform quite well on conventional visual grounding datasets achieving performance comparable to or surpassing state-of-the-art methods but showing strong deficiencies in compositional reasoning. Furthermore we propose a composition-aware fine-tuning pipeline demonstrating the potential to leverage cost-effective image-text annotations for enhancing the compositional understanding of VLMs in grounding tasks.
OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning
PDF ↗We present a novel multimodal multitask network and associated training algorithm. The method is capable of ingesting data from approximately 12 different modalities namely image video audio text depth point cloud time series tabular graph X-ray infrared IMU and hyperspectral. The proposed approach utilizes modality specialized tokenizers a shared transformer architecture and cross-attention mechanisms to project the data from different modalities into a unified embedding space. It addresses multimodal and multitask scenarios by incorporating modality-specific task heads for different tasks in respective modalities. We propose a novel pretraining strategy with iterative modality switching to initialize the network and a training algorithm which trades off fully joint training over all modalities with training on pairs of modalities at a time. We provide comprehensive evaluation across 25 datasets from 12 modalities and show state of the art performances demonstrating the effectiveness of the proposed architecture pretraining strategy and adapted multitask training.
NAYER: Noisy Layer Data Generation for Efficient and Effective Data-free Knowledge Distillation
PDF ↗Data-Free Knowledge Distillation (DFKD) has made significant recent strides by transferring knowledge from a teacher neural network to a student neural network without accessing the original data. Nonetheless existing approaches encounter a significant challenge when attempting to generate samples from random noise inputs which inherently lack meaningful information. Consequently these models struggle to effectively map this noise to the ground-truth sample distribution resulting in prolonging training times and low-quality outputs. In this paper we propose a novel Noisy Layer Generation method (NAYER) which relocates the random source from the input to a noisy layer and utilizes the meaningful constant label-text embedding (LTE) as the input. LTE is generated by using the language model once and then it is stored in memory for all subsequent training processes. The significance of LTE lies in its ability to contain substantial meaningful inter-class information enabling the generation of high-quality samples with only a few training steps. Simultaneously the noisy layer plays a key role in addressing the issue of diversity in sample generation by preventing the model from overemphasizing the constrained label information. By reinitializing the noisy layer in each iteration we aim to facilitate the generation of diverse samples while still retaining the method's efficiency thanks to the ease of learning provided by LTE. Experiments carried out on multiple datasets demonstrate that our NAYER not only outperforms the state-of-the-art methods but also achieves speeds 5 to 15 times faster than previous approaches. The code is available at https://github.com/tmtuan1307/nayer.
Visual content creation has aroused a surge of interest given its applications in mobile photography and AR/VR. Portrait style transfer and 3D recovery from monocular images as two representative tasks have so far evolved independently. In this paper we make a connection between the two and tackle the challenging task of 3D portrait stylization - modeling high-fidelity 3D stylized avatars from captured 2D portrait images. However naively combining the techniques from the two isolated areas may suffer from either inadequate stylization or absence of 3D assets. To this end we propose 3DToonify a new framework that introduces a progressive training scheme to achieve 3D style adaption on spatial neural representation (SNR). SNR is constructed with implicit fields and they are dynamically optimized by the progressive training scheme which consists of three stages: guided prior learning deformable geometry adaption and explicit texture adaption. In this way stylized geometry and texture are learned in SNR in an explicit and structured way with only a single stylized exemplar needed. Moreover our method obtains style-adaptive underlying structures (i.e. deformable geometry and exaggerated texture) and view-consistent stylized avatar rendering from arbitrary novel viewpoints. Both qualitative and quantitative experiments have been conducted to demonstrate the effectiveness and superiority of our method for automatically generating exemplar-guided 3D stylized avatars.
Different from a unimodal model whose input is from a single modality the input (called multi-modal input) of a multi-modal model is from multiple modalities such as image 3D points audio text etc. Similar to unimodal models many existing studies show that a multi-modal model is also vulnerable to adversarial perturbation where an attacker could add small perturbation to all modalities of a multi-modal input such that the multi-modal model makes incorrect predictions for it. Existing certified defenses are mostly designed for unimodal models which achieve sub-optimal certified robustness guarantees when extended to multi-modal models as shown in our experimental results. In our work we propose MMCert the first certified defense against adversarial attacks to a multi-modal model. We derive a lower bound on the performance of our MMCert under arbitrary adversarial attacks with bounded perturbations to both modalities (e.g. in the context of auto-driving we bound the number of changed pixels in both RGB image and depth image). We evaluate our MMCert using two benchmark datasets: one for the multi-modal road segmentation task and the other for the multi-modal emotion recognition task. Moreover we compare our MMCert with a state-of-the-art certified defense extended from unimodal models. Our experimental results show that our MMCert outperforms the baseline.
Deep neural networks are prone to capture correlations between spurious attributes and class labels leading to low accuracy on some combinations of class labels and spurious attribute values. When a spurious attribute represents a protected class these low-accuracy groups can manifest discriminatory bias. Existing methods attempting to improve worst-group accuracy assume the training data validation data or both are reliably labeled by the spurious attribute. But a model may be perceived to be biased towards a concept that is not represented by pre-existing labels on the training data. In these situations the spurious attribute must be defined with external information. We propose Concept Correction a framework that represents a concept as a curated set of images from any source then labels each training sample by its similarity to the concept set to control spurious correlations. For example concept sets representing gender can be used to measure and control gender bias even without explicit labels. We demonstrate and evaluate an instance of the framework as Concept DRO which uses concept sets to estimate group labels then uses these labels to train with a state of the art distributively robust optimization objective. We show that Concept DRO outperforms existing methods that do not require labels of spurious attributes by up to 33.1% on three image classification datasets and is competitive with the best methods that assume access to labels. We consider how the size and quality of the concept set influences performance and find that even smaller manually curated sets of noisy AI-generated images are effective at controlling spurious correlations suggesting that high-quality reusable concept sets are easy to create and effective in reducing bias.
Vision-Language models (VLMs) have excelled in the image-domain--- especially in zero-shot settings--- thanks to the availability of vast pretraining data (i.e. paired image-text samples). However for videos such paired data is not as abundant. Therefore video-VLMs are usually designed by adapting pretrained image-VLMs to the video-domain instead of training from scratch. All such recipes rely on augmenting visual embeddings with temporal information (i.e. image --> video) often keeping text embeddings unchanged or even being discarded. In this paper we argue the contrary that better video-VLMs can be designed by focusing more on augmenting text rather than visual information. More specifically we introduce Video-conditioned Text Representations (VicTR): a form of text embeddings optimized w.r.t. visual embeddings creating a more-flexible contrastive latent space. Our model can further make use of freely-available semantic information in the form of visually-grounded auxiliary text (e.g. object or scene information). We evaluate our model on few-shot zero-shot (HMDB-51 UCF-101) short-form (Kinetics-400) and long-form (Charades) activity recognition benchmarks showing strong performance among video-VLMs.
In this paper we tackle the problem of self-supervised video alignment and activity progress prediction using in-the-wild videos. Our proposed self-supervised representation learning method carefully addresses different action orderings redundant actions and background frames to generate improved video representations compared to previous methods. Our model generalizes temporal cycle-consistency learning to allow for more flexibility in determining cycle-consistent neighbors. More specifically to handle repeated actions we propose a multi-neighbor cycle consistency and a multi-cycle-back regression loss by finding multiple soft nearest neighbors using a Gaussian Mixture Model. To handle background and redundant frames we introduce a context-dependent drop function in our framework discouraging the alignment of droppable frames. On the other hand to learn from videos of multiple activities jointly we propose a multi-head crosstask network allowing us to embed a video and estimate progress without knowing its activity label. Experiments on multiple datasets show that our method outperforms the state-of-the-art for video alignment and progress prediction.
Advancements in 3D Gaussian Splatting have significantly accelerated 3D reconstruction and generation. However it may require a large number of Gaussians which creates a substantial memory footprint. This paper introduces GES (Generalized Exponential Splatting) a novel representation that employs Generalized Exponential Function (GEF) to model 3D scenes requiring far fewer particles to represent a scene and thus significantly outperforming Gaussian Splatting methods in efficiency with a plug-and-play replacement ability for Gaussian-based utilities. GES is validated theoretically and empirically in both principled 1D setup and realistic 3D scenes. It is shown to represent signals with sharp edges more accurately which are typically challenging for Gaussians due to their inherent low-pass characteristics. Our empirical analysis demonstrates that GEF outperforms Gaussians in fitting natural-occurring signals (E.g. squares triangles parabolic signals) thereby reducing the need for extensive splitting operations that increase the memory footprint of Gaussian Splatting. With the aid of a frequency-modulated loss GES achieves competitive performance in novel-view synthesis benchmarks while requiring less than half the memory storage of Gaussian Splatting and increasing the rendering speed by up to 39%. The code is available on the project website https://abdullahamdi.com/ges .
Monocular 3D human mesh estimation is an ill-posed problem characterized by inherent ambiguity and occlusion. While recent probabilistic methods propose generating multiple solutions little attention is paid to obtaining high-quality estimates from them. To address this limitation we introduce ScoreHypo a versatile framework by first leverages our novel HypoNet to generate multiple hypotheses followed by employing a meticulously designed scorer ScoreNet to evaluate and select high-quality estimates. ScoreHypo formulates the estimation process as a reverse denoising process where HypoNet produces a diverse set of plausible estimates that effectively align with the image cues. Subsequently ScoreNet is employed to rigorously evaluate and rank these estimates based on their quality and finally identify superior ones. Experimental results demonstrate that HypoNet outperforms existing state-of-the-art probabilistic methods as a multi-hypothesis mesh estimator. Moreover the estimates selected by ScoreNet significantly outperform random generation or simple averaging. Notably the trained ScoreNet exhibits generalizability as it can effectively score existing methods and significantly reduce their errors by more than 15%. Code and models are available at https://xy02-05.github.io/ScoreHypo.
Existing counting tasks are limited to the class level which don't account for fine-grained details within the class. In real applications it often requires in-context or referring human input for counting target objects. Take urban analysis as an example fine-grained information such as traffic flow in different directions pedestrians and vehicles waiting or moving at different sides of the junction is more beneficial. Current settings of both class-specific and class-agnostic counting treat objects of the same class indifferently which pose limitations in real use cases. To this end we propose a new task named Referring Expression Counting (REC) which aims to count objects with different attributes within the same class. To evaluate the REC task we create a novel dataset named REC-8K which contains 8011 images and 17122 referring expressions. Experiments on REC-8K show that our proposed method achieves state-of-the-art performance compared with several text-based counting methods and an open-set object detection model. We also outperform prior models on the class agnostic counting (CAC) benchmark [36] for the zero-shot setting and perform on par with the few-shot methods. Code and dataset is available at https://github.com/sydai/referring-expression-counting.
Recent transformer-based architectures have shown impressive results in the field of image segmentation. Thanks to their flexibility they obtain outstanding performance in multiple segmentation tasks such as semantic and panoptic under a single unified framework. To achieve such impressive performance these architectures employ intensive operations and require substantial computational resources which are often not available especially on edge devices. To fill this gap we propose Prototype-based Efficient MaskFormer (PEM) an efficient transformer-based architecture that can operate in multiple segmentation tasks. PEM proposes a novel prototype-based cross-attention which leverages the redundancy of visual features to restrict the computation and improve the efficiency without harming the performance. In addition PEM introduces an efficient multi-scale feature pyramid network capable of extracting features that have high semantic content in an efficient way thanks to the combination of deformable convolutions and context-based self-modulation. We benchmark the proposed PEM architecture on two tasks semantic and panoptic segmentation evaluated on two different datasets Cityscapes and ADE20K. PEM demonstrates outstanding performance on every task and dataset outperforming task-specific architectures while being comparable and even better than computationally expensive baselines. Code is available at https://github.com/NiccoloCavagnero/PEM.
Intelligent generation of vector graphics has very promising applications in the fields of advertising and logo design artistic painting animation production etc. However current mainstream vector image generation methods lack the encoding of image appearance information that is associated with the original vector representation and therefore lose valid supervision signal from the strong correlation between the discrete vector parameter (drawing instruction) sequence and the target shape/structure of the corresponding pixel image. On the one hand the generation process based on pure vector domain completely ignores the similarity measurement between shape parameter (and their combination) and the paired pixel image appearance pattern; on the other hand two-stage methods (i.e. generation-and-vectorization) based on pixel diffusion followed by differentiable image-to-vector translation suffer from wrong error-correction signal caused by approximate gradients. To address the above issues we propose a novel generation framework based on dual-domain (vector-pixel) diffusion with cross-modality impulse signals from each other. First in each diffusion step the current representation extracted from the other domain is used as a condition variable to constrain the subsequent sampling operation yielding shape-aware new parameterizations; second independent supervision signals from both domains avoid the gradient error accumulation problem caused by cross-domain representation conversion. Extensive experimental results on popular benchmarks including font and icon datasets demonstrate the great advantages of our proposed framework in terms of generated shape quality.
Personalized Federated Learning (PFL) is proposed to find the greatest personalized models for each client. To avoid the central failure and communication bottleneck in the server-based FL we concentrate on the Decentralized Personalized Federated Learning (DPFL) that performs distributed model training in a Peer-to-Peer (P2P) manner. Most personalized works in DPFL are based on undirected and symmetric topologies however the data computation and communication resources heterogeneity result in large variances in the personalized models which lead the undirected aggregation to suboptimal personalized performance and unguaranteed convergence. To address these issues we propose a directed collaboration DPFL framework by incorporating stochastic gradient push and partial model personalized called Decentralized Federated Partial Gradient Push (DFedPGP). It personalizes the linear classifier in the modern deep model to customize the local solution and learns a consensus representation in a fully decentralized manner. Clients only share gradients with a subset of neighbors based on the directed and asymmetric topologies which guarantees flexible choices for resource efficiency and better convergence. Theoretically we show that the proposed DFedPGP achieves a superior convergence rate of O(1/?T) in the general non-convex setting and tighter connectivity among clients will speed up the convergence. The proposed method achieves state-of-the-art (SOTA) accuracy in both data and computation heterogeneity scenarios demonstrating the efficiency of the directed collaboration and partial gradient push.