For few-shot semantic segmentation, the primary task is to extract class-specific intrinsic information from limited labeled data. However, the semantic ambiguity and inter-class similarity of previous methods limit the accuracy of pixel-level foreground-background classification. To alleviate these issues, we propose the Relevant Intrinsic Feature Enhancement Network (RiFeNet). To improve the semantic consistency of foreground instances, we propose an unlabeled branch as an efficient data utilization method, which teaches the model how to extract intrinsic features robust to intra-class differences. Notably, during testing, the proposed unlabeled branch is excluded without extra unlabeled data and computation. Furthermore, we extend the inter-class variability between foreground and background by proposing a novel multi-level prototype generation and interaction module. The different-grained complementarity between global and local prototypes allows for better distinction between similar categories. The qualitative and quantitative performance of RiFeNet surpasses the state-of-the-art methods on PASCAL-5i and COCO benchmarks.
论文检索
输入标题、作者或关键词，从 2,866 篇学术成果中精准定位
Generative diffusion prior captured from the off-the-shelf denoising diffusion generative model has recently attained significant interest. However, several attempts have been made to adopt diffusion models to noisy inverse problems either fail to achieve satisfactory results or require a few thousand iterations to achieve high-quality reconstructions. In this work, we propose a diffusion-based image restoration with error contraction and error correction (DiffECC) method. Two strategies are introduced to contract the restoration error in the posterior sampling process. First, we combine existing CNN-based approaches with diffusion models to ensure data consistency from the beginning. Second, to amplify the error contraction effects of the noise, a restart sampling algorithm is designed. In the error correction strategy, the estimation-correction idea is proposed on both the data term and the prior term. Solving them iteratively within the diffusion sampling framework leads to superior image generation results. Experimental results for image restoration tasks such as super-resolution (SR), Gaussian deblurring, and motion deblurring demonstrate that our approach can reconstruct high-quality images compared with state-of-the-art sampling-based diffusion models.
Omnipotent Distillation with LLMs for Weakly-Supervised Natural Language Video Localization: When Divergence Meets Consistency
PDF ↗Natural language video localization plays a pivotal role in video understanding, and leveraging weakly-labeled data is considered a promising approach to circumvent the laborintensive process of manual annotations. However, this approach encounters two significant challenges: 1) limited input distribution, namely that the limited writing styles of the language query, annotated by human annotators, hinder the model’s generalization to real-world scenarios with diverse vocabularies and sentence structures; 2) the incomplete ground truth, whose supervision guidance is insufficient. To overcome these challenges, we propose an omnipotent distillation algorithm with large language models (LLM). The distribution of the input sample is enriched to obtain diverse multi-view versions while a consistency then comes to regularize the consistency of their results for distillation. Specifically, we first train our teacher model with the proposed intra-model agreement, where multiple sub-models are supervised by each other. Then, we leverage the LLM to paraphrase the language query and distill the teacher model to a lightweight student model by enforcing the consistency between the localization results of the paraphrased sentence and the original one. In addition, to assess the generalization of the model across different dimensions of language variation, we create extensive datasets by building upon existing datasets. Our experiments demonstrate substantial performance improvements adaptively to diverse kinds of language queries.
This paper for the first time leverages multi-modal videos for weakly-supervised temporal video grounding. As labeling the video moment is labor-intensive and subjective, the weakly-supervised approaches have gained increasing attention in recent years. However, these approaches could inherently compromise performance due to inadequate supervision. Therefore, to tackle this challenge, we for the first time pay attention to exploiting complementary information extracted from multi-modal videos (e.g., RGB frames, optical flows), where richer supervision is naturally introduced in the weaklysupervised context. Our motivation is that by integrating different modalities of the videos, the model is learned from synergic supervision and thereby can attain superior generalization capability. However, addressing multiple modalities† would also inevitably introduce additional computational overhead, and might become inapplicable if a particular modality is inaccessible. To solve this issue, we adopt a novel route: building a multi-modal distillation algorithm to capitalize on the multi-modal knowledge as supervision for model training, while still being able to work with only the single modal input during inference. As such, we can utilize the benefits brought by the supplementary nature of multiple modalities, without compromising the applicability in practical scenarios. Specifically, we first propose a cross-modal mutual learning framework and train a sophisticated teacher model to learn collaboratively from the multi-modal videos. Then we identify two sorts of knowledge from the teacher model, i.e., temporal boundaries and semantic activation map. And we devise a local-global distillation algorithm to transfer this knowledge to a student model of single-modal input at both local and global levels. Extensive experiments on large-scale datasets demonstrate that our method achieves state-of-the-art performance with/without multi-modal inputs.
Recently, despite the unprecedented success of large pre-trained visual-language models (VLMs) on a wide range of downstream tasks, the real-world unsupervised domain adaptation (UDA) problem is still not well explored. Therefore, in this paper, we first experimentally demonstrate that the unsupervised-trained VLMs can significantly reduce the distribution discrepancy between source and target domains, thereby improving the performance of UDA. However, a major challenge for directly deploying such models on downstream UDA tasks is prompt engineering, which requires aligning the domain knowledge of source and target domains, since the performance of UDA is severely influenced by a good domain-invariant representation. We further propose a Prompt-based Distribution Alignment (PDA) method to incorporate the domain knowledge into prompt learning. Specifically, PDA employs a two-branch prompt-tuning paradigm, namely base branch and alignment branch. The base branch focuses on integrating class-related representation into prompts, ensuring discrimination among different classes. To further minimize domain discrepancy, for the alignment branch, we construct feature banks for both the source and target domains and propose image-guided feature tuning (IFT) to make the input attend to feature banks, which effectively integrates self-enhanced and cross-domain features into the model. In this way, these two branches can be mutually promoted to enhance the adaptation of VLMs for UDA. We conduct extensive experiments on three benchmarks to demonstrate that our proposed PDA achieves state-of-the-art performance. The code is available at https://github.com/BaiShuanghao/Prompt-based-Distribution-Alignment.
Deepfake technology has given rise to a spectrum of novel and compelling applications. Unfortunately, the widespread proliferation of high-fidelity fake videos has led to pervasive confusion and deception, shattering our faith that seeing is believing. One aspect that has been overlooked so far is that current deepfake detection approaches may easily fall into the trap of overfitting, focusing only on forgery clues within one or a few local regions. Moreover, existing works heavily rely on neural networks to extract forgery features, lacking theoretical constraints guaranteeing that sufficient forgery clues are extracted and superfluous features are eliminated. These deficiencies culminate in unsatisfactory accuracy and limited generalizability in real-life scenarios. In this paper, we try to tackle these challenges through three designs: (1) We present a novel framework to capture broader forgery clues by extracting multiple non-overlapping local representations and fusing them into a global semantic-rich feature. (2) Based on the information bottleneck theory, we derive Local Information Loss to guarantee the orthogonality of local representations while preserving comprehensive task-relevant information. (3) Further, to fuse the local representations and remove task-irrelevant information, we arrive at a Global Information Loss through the theoretical analysis of mutual information. Empirically, our method achieves state-of-the-art performance on five benchmark datasets. Our code is available at https://github.com/QingyuLiu/Exposing-the-Deception, hoping to inspire researchers.
We propose DocFormerv2, a multi-modal transformer for Visual Document Understanding (VDU). The VDU domain entails understanding documents (beyond mere OCR predictions) e.g., extracting information from a form, VQA for documents and other tasks. VDU is challenging as it needs a model to make sense of multiple modalities (visual, language and spatial) to make a prediction. Our approach, termed DocFormerv2 is an encoder-decoder transformer which takes as input - vision, language and spatial features. DocFormerv2 is pre-trained with unsupervised tasks employed asymmetrically i.e., two novel document tasks on encoder and one on the auto-regressive decoder. The unsupervised tasks have been carefully designed to ensure that the pre-training encourages local-feature alignment between multiple modalities. DocFormerv2 when evaluated on nine challenging datasets shows state-of-the-art performance on all over strong baselines - On TabFact (+4.3%), InfoVQA (+1.4%), FUNSD (+1.0%). Furthermore, to show generalization capabilities, on three VQA tasks involving scene-text, DocFormerv2 outperforms previous comparably-sized models and even does better than much larger models (such as GIT2, PaLI and Flamingo) on these tasks. Extensive ablations show that due to its novel pre-training tasks, DocFormerv2 understands multiple modalities better than prior-art in VDU.
Comparing the Robustness of Modern No-Reference Image- and Video-Quality Metrics to Adversarial Attacks
PDF ↗Nowadays, neural-network-based image- and video-quality metrics perform better than traditional methods. However, they also became more vulnerable to adversarial attacks that increase metrics' scores without improving visual quality. The existing benchmarks of quality metrics compare their performance in terms of correlation with subjective quality and calculation time. Nonetheless, the adversarial robustness of image-quality metrics is also an area worth researching. This paper analyses modern metrics' robustness to different adversarial attacks. We adapted adversarial attacks from computer vision tasks and compared attacks' efficiency against 15 no-reference image- and video-quality metrics. Some metrics showed high resistance to adversarial attacks, which makes their usage in benchmarks safer than vulnerable metrics. The benchmark accepts submissions of new metrics for researchers who want to make their metrics more robust to attacks or to find such metrics for their needs. The latest results can be found online: https://videoprocessing.ai/benchmarks/metrics-robustness.html.
High-resolution representation is essential for achieving good performance in human pose estimation models. To obtain such features, existing works utilize high-resolution input images or fine-grained image tokens. However, this dense high-resolution representation brings a significant computational burden. In this paper, we address the following question: "Only sparse human keypoint locations are detected for human pose estimation, is it really necessary to describe the whole image in a dense, high-resolution manner?" Based on dynamic transformer models, we propose a framework that only uses Sparse High-resolution Representations for human Pose estimation (SHaRPose). In detail, SHaRPose consists of two stages. At the coarse stage, the relations between image regions and keypoints are dynamically mined while a coarse estimation is generated. Then, a quality predictor is applied to decide whether the coarse estimation results should be refined. At the fine stage, SHaRPose builds sparse high-resolution representations only on the regions related to the keypoints and provides refined high-precision human pose estimations. Extensive experiments demonstrate the outstanding performance of the proposed method. Specifically, compared to the state-of-the-art method ViTPose, our model SHaRPose-Base achieves 77.4 AP (+0.5 AP) on the COCO validation set and 76.7 AP (+0.5 AP) on the COCO test-dev set, and infers at a speed of 1.4x faster than ViTPose-Base. Code is available at https://github.com/AnxQ/sharpose.
With the increasing importance of video data in real-world applications, there is a rising need for efficient object detection methods that utilize temporal information. While existing video object detection (VOD) techniques employ various strategies to address this challenge, they typically depend on locally adjacent frames or randomly sampled images within a clip. Although recent Transformer-based VOD methods have shown promising results, their reliance on multiple inputs and additional network complexity to incorporate temporal information limits their practical applicability. In this paper, we propose a novel approach to single image object detection, called Context Enhanced TRansformer (CETR), by incorporating temporal context into DETR using a newly designed memory module. To efficiently store temporal information, we construct a class-wise memory that collects contextual information across data. Additionally, we present a classification-based sampling technique to selectively utilize the relevant memory for the current image. In the testing, We introduce a test-time memory adaptation method that updates individual memory functions by considering the test distribution. Experiments with CityCam and ImageNet VID datasets exhibit the efficiency of the framework on various video systems. The project page and code will be made available at: https://ku-cvlab.github.io/CETR.
Recent progresses in large-scale text-to-image models have yielded remarkable accomplishments, finding various applications in art domain. However, expressing unique characteristics of an artwork (e.g. brushwork, colortone, or composition) with text prompts alone may encounter limitations due to the inherent constraints of verbal description. To this end, we introduce DreamStyle, a novel framework designed for artistic image synthesis, proficient in both text-to-image synthesis and style transfer. DreamStyle optimizes a multi-stage textual embedding with a context-aware text prompt, resulting in prominent image quality. In addition, with content and style guidance, DreamStyle exhibits flexibility to accommodate a range of style references. Experimental results demonstrate its superior performance across multiple scenarios, suggesting its promising potential in artistic product creation. Project page: https://nmhkahn.github.io/dreamstyler/
Personality detection is a fundamental task for user psychology research. One of the biggest challenges in personality detection lies in the quantitative limitation of labeled data collected by completing the personality questionnaire, which is very time-consuming and labor-intensive. Most of the existing works are mainly devoted to learning the rich representations of posts based on labeled data. However, they still suffer from the inherent weakness of the amount limitation of labels, which potentially restricts the capability of the model to deal with unseen data. In this paper, we construct a heterogeneous personality graph for each labeled and unlabeled user and develop a novel psycholinguistic augmented graph neural network to detect personality in a semi-supervised manner, namely Semi-PerGCN. Specifically, our model first explores a supervised Personality Graph Neural Network (PGNN) to refine labeled user representation on the heterogeneous graph. For the remaining massive unlabeled users, we utilize the empirical psychological knowledge of the Linguistic Inquiry and Word Count (LIWC) lexicon for multi-view graph augmentation and perform unsupervised graph consistent constraints on the parameters shared PGNN. During the learning process of finite labeled users, noise-invariant learning on a large scale of unlabeled users is combined to enhance the generalization ability. Extensive experiments on three real-world datasets, Youtube, PAN2015, and MyPersonality demonstrate the effectiveness of our Semi-PerGCN in personality detection, especially in scenarios with limited labeled users.
Large language models contain noisy general knowledge of the world, yet are hard to train or fine-tune. In contrast cognitive architectures have excellent interpretability and are flexible to update but require a lot of manual work to instantiate. In this work, we combine the best of both worlds: bootstrapping a cognitive-based model with the noisy knowledge encoded in large language models. Through an embodied agent doing kitchen tasks, we show that our proposed framework yields better efficiency compared to an agent entirely based on large language models. Our experiments also indicate that the cognitive agent bootstrapped using this framework can generalize to novel environments and be scaled to complex tasks.
Facial expression recognition (FER) models are typically trained on datasets with a fixed number of seven basic classes. However, recent research works (Cowen et al. 2021; Bryant et al. 2022; Kollias 2023) point out that there are far more expressions than the basic ones. Thus, when these models are deployed in the real world, they may encounter unknown classes, such as compound expressions that cannot be classified into existing basic classes. To address this issue, we propose the open-set FER task for the first time. Though there are many existing open-set recognition methods, we argue that they do not work well for open-set FER because FER data are all human faces with very small inter-class distances, which makes the open-set samples very similar to close-set samples. In this paper, we are the first to transform the disadvantage of small inter-class distance into an advantage by proposing a new way for open-set FER. Specifically, we find that small inter-class distance allows for sparsely distributed pseudo labels of open-set samples, which can be viewed as symmetric noisy labels. Based on this novel observation, we convert the open-set FER to a noisy label detection problem. We further propose a novel method that incorporates attention map consistency and cycle training to detect the open-set samples. Extensive experiments on various FER datasets demonstrate that our method clearly outperforms state-of-the-art open-set recognition methods by large margins. Code is available at https://github.com/zyh-uaiaaaa.
The de-occlusion problem, involving extracting clear background images by removing foreground occlusions, holds significant practical importance but poses considerable challenges. Most current research predominantly focuses on generating discrete images from calibrated camera arrays, but this approach often struggles with dense occlusions and fast motions due to limited perspectives and motion blur. To overcome these limitations, an effective solution requires the integration of multi-view visual information. The spike camera, as an innovative neuromorphic sensor, shows promise with its ultra-high temporal resolution and dynamic range. In this study, we propose a novel approach that utilizes a single spike camera for continuous multi-view imaging to address occlusion removal. By rapidly moving the spike camera, we capture a dense stream of spikes from occluded scenes. Our model, SpkOccNet, processes these spikes by integrating multi-view spatial-temporal information via long-short-window feature extractor (LSW) and employs a novel cross-view mutual attention-based module (CVA) for effective fusion and refinement. Additionally, to facilitate research in occlusion removal, we introduce the S-OCC dataset, which consists of real-world spike-based data. Experimental results demonstrate the efficiency and generalization capabilities of our model in effectively removing dense occlusions across diverse scenes. Public project page: https://github.com/Leozhangjiyuan/SpikeDeOcclusion.
DMMR: Cross-Subject Domain Generalization for EEG-Based Emotion Recognition via Denoising Mixed Mutual Reconstruction
PDF ↗Electroencephalography (EEG) has proven to be effective in emotion analysis. However, current methods struggle with individual variations, complicating the generalization of models trained on data from source subjects to unseen target subjects. To tackle this issue, we propose the Denoising Mixed Mutual Reconstruction (DMMR) model, employing a two-stage pre-training followed by fine-tuning approach. During the pre-training phase, DMMR leverages self-supervised learning through a multi-decoder autoencoder, which encodes and reconstructs features of one subject, aiming to generate features resembling those from other subjects within the same category, thereby encouraging the encoder to learn subject-invariant features. We introduce a hidden-layer mixed data augmentation approach to mitigate the limitations posed by the scarcity of source data, thereby extending the method to a two-stage process. To bolster stability against noise, we incorporate a noise injection method, named “Time Steps Shuffling”, into the input data. During the fine-tuning phase, an emotion classifier is integrated to extract emotion-related features. Experimental accuracy on the SEED and SEED-IV datasets reached 88.27% (±5.62) and 72.70% (±8.01), respectively, demonstrating state-of-the-art and comparable performance, thereby showcasing the superiority of DMMR. The proposed data augmentation and noise injection methods were observed to complementarily enhance accuracy and stability, thus alleviating the aforementioned issues.
Cognitive Diagnosis Modeling aims to infer students' proficiency level on knowledge concepts from their response logs. Existing methods typically model students’ response processes as the interaction between students and exercises or concepts based on hand-crafted or deeply-learned interaction functions. Despite their promising achievements, they fail to consider the relationship between students' cognitive states and affective states in learning, e.g., the feelings of frustration, boredom, or confusion with the learning content, which is insufficient for comprehensive cognitive diagnosis in intelligent education. To fill the research gap, we propose a novel Affect-aware Cognitive Diagnosis (ACD) model which can effectively diagnose the knowledge proficiency levels of students by taking into consideration the affective factors. Specifically, we first design a student affect perception module under the assumption that the affective state is jointly influenced by the student's affect trait and the difficulty of the exercise. Then, our inferred affective distribution is further used to estimate the student's subjective factors, i.e., guessing and slipping, respectively. Finally, we integrate the estimated guessing and slipping parameters with the basic neural cognitive diagnosis framework based on the DINA model, which facilitates the modeling of complex exercising interactions in a more accurate and interpretable fashion. Besides, we also extend our affect perception module in an unsupervised learning setting based on contrastive learning, thus significantly improving the compatibility of our ACD. To the best of our knowledge, we are the first to unify the cognition modeling and affect modeling into the same framework for student cognitive diagnosis. Extensive experiments on real-world datasets clearly demonstrate the effectiveness of our ACD. Our code is available at https://github.com/zeng-zhen/ACD.
The next generation of machine intelligence requires the capability of continual learning to acquire new knowledge without forgetting the old one while conserving limited computing resources. Spiking neural networks (SNNs), compared to artificial neural networks (ANNs), have more characteristics that align with biological neurons, which may be helpful as a potential gating function for knowledge maintenance in neural networks. Inspired by the selective sparse activation principle of context gating in biological systems, we present a novel SNN model with selective activation to achieve continual learning. The trace-based K-Winner-Take-All (K-WTA) and variable threshold components are designed to form the sparsity in selective activation in spatial and temporal dimensions of spiking neurons, which promotes the subpopulation of neuron activation to perform specific tasks. As a result, continual learning can be maintained by routing different tasks via different populations of neurons in the network. The experiments are conducted on MNIST and CIFAR10 datasets under the class incremental setting. The results show that the proposed SNN model achieves competitive performance similar to and even surpasses the other regularization-based methods deployed under traditional ANNs.
Spiking neural networks (SNNs) are emerging as an energy-efficient alternative to traditional artificial neural networks (ANNs) due to their unique spike-based event-driven nature. Coding is crucial in SNNs as it converts external input stimuli into spatio-temporal feature sequences. However, most existing deep SNNs rely on direct coding that generates powerless spike representation and lacks the temporal dynamics inherent in human vision. Hence, we introduce Gated Attention Coding (GAC), a plug-and-play module that leverages the multi-dimensional gated attention unit to efficiently encode inputs into powerful representations before feeding them into the SNN architecture. GAC functions as a preprocessing layer that does not disrupt the spike-driven nature of the SNN, making it amenable to efficient neuromorphic hardware implementation with minimal modifications. Through an observer model theoretical analysis, we demonstrate GAC's attention mechanism improves temporal dynamics and coding efficiency. Experiments on CIFAR10/100 and ImageNet datasets demonstrate that GAC achieves state-of-the-art accuracy with remarkable efficiency. Notably, we improve top-1 accuracy by 3.10% on CIFAR100 with only 6-time steps and 1.07% on ImageNet while reducing energy usage to 66.9% of the previous works. To our best knowledge, it is the first time to explore the attention-based dynamic coding scheme in deep SNNs, with exceptional effectiveness and efficiency on large-scale datasets. Code is available at https://github.com/bollossom/GAC.
Unveiling the Significance of Toddler-Inspired Reward Transition in Goal-Oriented Reinforcement Learning
PDF ↗Toddlers evolve from free exploration with sparse feedback to exploiting prior experiences for goal-directed learning with denser rewards. Drawing inspiration from this Toddler-Inspired Reward Transition, we set out to explore the implications of varying reward transitions when incorporated into Reinforcement Learning (RL) tasks. Central to our inquiry is the transition from sparse to potential-based dense rewards, which share optimal strategies regardless of reward changes. Through various experiments, including those in egocentric navigation and robotic arm manipulation tasks, we found that proper reward transitions significantly influence sample efficiency and success rates. Of particular note is the efficacy of the toddler-inspired Sparse-to-Dense (S2D) transition. Beyond these performance metrics, using Cross-Density Visualizer technique, we observed that transitions, especially the S2D, smooth the policy loss landscape, promoting wide minima that enhance generalization in RL models.