论文检索

Zehan Wang, Haifeng Huang, Yang Zhao, Linjun Li, Xize Cheng, Yichen Zhu, Aoxiong Yin, Zhou Zhao

3D visual grounding involves finding a target object in a 3D scene that corresponds to a given sentence query. Although many approaches have been proposed and achieved impressive performance, they all require dense object-sentence pair annotations in 3D point clouds, which are both time-consuming and expensive. To address the problem that fine-grained annotated data is difficult to obtain, we propose to leverage weakly supervised annotations to learn the 3D visual grounding model, i.e., only coarse scene-sentence correspondences are used to learn object-sentence links. To accomplish this, we design a novel semantic matching model that analyzes the semantic similarity between object proposals and sentences in a coarse-to-fine manner. Specifically, we first extract object proposals and coarsely select the top-K candidates based on feature and class similarity matrices. Next, we reconstruct the masked keywords of the sentence using each candidate one by one, and the reconstructed accuracy finely reflects the semantic similarity of each candidate to the query. Additionally, we distill the coarse-to-fine semantic matching knowledge into a typical two-stage 3D visual grounding model, which reduces inference costs and improves performance by taking full advantage of the well-studied structure of the existing architectures. We conduct extensive experiments on ScanRefer, Nr3D, and Sr3D, which demonstrate the effectiveness of our proposed method.

Vadim Sushko, Ruyu Wang, Juergen Gall

The task of few-shot GAN adaptation aims to adapt a pre-trained GAN model to a small dataset with very few training images. While existing methods perform well when the dataset for pre-training is structurally similar to the target dataset, the approaches suffer from training instabilities or memorization issues when the objects in the two domains have a very different structure. To mitigate this limitation, we propose a new smoothness similarity regularization that transfers the inherently learned smoothness of the pre-trained GAN to the few-shot target domain even if the two domains are very different. We evaluate our approach by adapting an unconditional and a class-conditional GAN to diverse few-shot target domains. Our proposed method significantly outperforms prior few-shot GAN adaptation methods in the challenging case of structurally dissimilar source-target domains, while performing on par with the state of the art for similar source-target domains.

Hee-Seon Kim, Minji Son, Minbeom Kim, Myung-Joon Kwon, Changick Kim

As video analysis using deep learning models becomes more widespread, the vulnerability of such models to adversarial attacks is becoming a pressing concern. In particular, Universal Adversarial Perturbation (UAP) poses a significant threat, as a single perturbation can mislead deep learning models on entire datasets. We propose a novel video UAP using image data and image model. This enables us to take advantage of the rich image data and image model-based studies available for video applications. However, there is a challenge that image models are limited in their ability to analyze the temporal aspects of videos, which is crucial for a successful video attack. To address this challenge, we introduce the Breaking Temporal Consistancy (BTC) method, which is the first attempt to incorporate temporal information into video attacks using image models. We aim to generate adversarial videos that have opposite patterns to the original. Specifically, BTC-UAP minimizes the feature similarity between neighboring frames in videos. Our approach is simple but effective at attacking unseen video models. Additionally, it is applicable to videos of varying lengths and invariant to temporal shifts. Our approach surpasses existing methods in terms of effectiveness on various datasets, including ImageNet, UCF-101, and Kinetics-400.

Nissim Maruani, Roman Klokov, Maks Ovsjanikov, Pierre Alliez, Mathieu Desbrun

In stark contrast to the case of images, finding a concise, learnable discrete representation of 3D surfaces remains a challenge. In particular, while polygon meshes are arguably the most common surface representation used in geometry processing, their irregular and combinatorial structure often make them unsuitable for learning-based applications. In this work, we present VoroMesh, a novel and differentiable of watertight 3D shape surfaces. From a set of 3D points (called generators) and their associated occupancy, we define our boundary representation through the Voronoi diagram of the generators as the subset of Voronoi faces whose two associated (equidistant) generators are of opposite occupancy: the resulting polygon mesh forms a watertight approximation of the target shape's boundary. To learn the position of the generators, we propose a novel loss function, dubbed VoroLoss, that minimizes the distance from ground truth surface samples to the closest faces of the Voronoi diagram which does not require an explicit construction of the entire Voronoi diagram. A direct optimization of the Voroloss to obtain generators on the Thingi32 dataset demonstrates the geometric efficiency of our representation compared to axiomatic meshing algorithms and recent learning-based mesh representations. We further use VoroMesh in a learning-based mesh prediction task from input SDF grids on the ABC dataset, and show comparable performance to state-of-the-art methods while guaranteeing closed output surfaces free of self-intersections.

Lei Zhang, Zhibo Wang, Xiaowei Dong, Yunhe Feng, Xiaoyi Pang, Zhifei Zhang, Kui Ren

Network pruning aims to compress models while minimizing loss in accuracy. With the increasing focus on bias in AI systems, the bias inheriting or even magnification nature of traditional network pruning methods has raised a new perspective towards fairness-aware network pruning. Straightforward pruning plus debias methods and recent designs for monitoring disparities of demographic attributes during pruning have endeavored to enhance fairness in pruning. However, neither simple assembling of two tasks nor specifically designed pruning strategies could achieve the optimal trade-off among pruning ratio, accuracy, and fairness. This paper proposes an end-to-end learnable framework for fairness-aware network pruning, which optimizes both pruning and debias tasks jointly by adversarial training against those final evaluation metrics like accuracy for pruning, and disparate impact (DI) and equalized odds (DEO) for fairness. In other words, our fairness-aware adversarial pruning method would learn to prune without any handcraft rules. Therefore, our approach could flexibly adapt to variate network structures. Exhaustive experimentation demonstrates the generalization capacity of our approach, as well as superior performance on pruning and debias simultaneously. To highlight, the proposed method could preserve the SOTA pruning performance while significantly improving fairness by around 50% as compared to traditional pruning methods.

Nikola Đukić, Alan Lukežič, Vitjan Zavrtanik, Matej Kristan

We consider low-shot counting of arbitrary semantic categories in the image using only few annotated exemplars (few-shot) or no exemplars (no-shot). The standard few-shot pipeline follows extraction of appearance queries from exemplars and matching them with image features to infer the object counts. Existing methods extract queries by feature pooling which neglects the shape information (e.g., size and aspect) and leads to a reduced object localization accuracy and count estimates. We propose a Low-shot Object Counting network with iterative prototype Adaptation (LOCA). Our main contribution is the new object prototype extraction module, which iteratively fuses the exemplar shape and appearance information with image features. The module is easily adapted to zero-shot scenarios, enabling LOCA to cover the entire spectrum of low-shot counting problems. LOCA outperforms all recent state-of-the-art methods on FSC147 benchmark by 20-30% in RMSE on one-shot and few-shot and achieves state-of-the-art on zero-shot scenarios, while demonstrating better generalization capabilities. The code and models are available here: https://github.com/djukicn/loca.

Yulin Pan, Xiangteng He, Biao Gong, Yiliang Lv, Yujun Shen, Yuxin Peng, Deli Zhao

Video temporal grounding aims to pinpoint a video segment that matches the query description. Despite the recent advance in short-form videos (e.g., in minutes), temporal grounding in long videos (e.g., in hours) is still at its early stage. To address this challenge, a common practice is to employ a sliding window, yet can be inefficient and inflexible due to the limited number of frames within the window. In this work, we propose an end-to-end framework for fast temporal grounding, which is able to model an hours-long video with one-time network execution. Our pipeline is formulated in a coarse-to-fine manner, where we first extract context knowledge from non-overlapped video clips (i.e., anchors), and then supplement the anchors that highly response to the query with detailed content knowledge. Besides the remarkably high pipeline efficiency, another advantage of our approach is the capability of capturing long-range temporal correlation, thanks to modeling the entire video as a whole, and hence facilitates more accurate grounding. Experimental results suggest that, on the long-form video datasets MAD and Ego4d, our method significantly outperforms state-of-the-arts, and achieves 14.6x / 102.8x higher efficiency respectively.

Seyedalireza Khoshsirat, Chandra Kambhamettu

Answer grounding is the task of locating relevant visual evidence for the Visual Question Answering task. While a wide variety of attention methods have been introduced for this task, they suffer from the following three problems: designs that do not allow the usage of pre-trained networks and do not benefit from large data pre-training, custom designs that are not based on well-grounded previous designs, therefore limiting the learning power of the network, or complicated designs that make it challenging to re-implement or improve them. In this paper, we propose a novel architectural block, which we term Sentence Attention Block, to solve these problems. The proposed block re-calibrates channel-wise image feature-maps by explicitly modeling inter-dependencies between the image feature-maps and sentence embedding. We visually demonstrate how this block filters out irrelevant feature-maps channels based on sentence embedding. We start our design with a well-known attention method, and by making minor modifications, we improve the results to achieve state-of-the-art accuracy. The flexibility of our method makes it easy to use different pre-trained backbone networks, and its simplicity makes it easy to understand and be re-implemented. We demonstrate the effectiveness of our method on the TextVQA-X, VQS, VQA-X, and VizWiz-VQA-Grounding datasets. We perform multiple ablation studies to show the effectiveness of our design choices.

Yifei Chen, Dapeng Chen, Ruijin Liu, Hao Li, Wei Peng

Visual-Language Models (VLMs) have significantly advanced video action recognition. Supervised by the semantics of action labels, recent works adapt the visual branch of VLMs to learn video representations. Despite the effectiveness proved by these works, we believe that the potential of VLMs has yet to be fully harnessed. In light of this, we exploit the semantic units (SU) hiding behind the action labels and leverage their correlations with fine-grained items in frames for more accurate action recognition. SUs are entities extracted from the language descriptions of the entire action set, including body parts, objects, scenes, and motions. To further enhance the alignments between visual contents and the SUs, we introduce a multi-region module (MRA) to the visual branch of the VLM. The MRA allows the perception of region-aware visual features beyond the original global feature. Our method adaptively attends to and selects relevant SUs with visual features of frames. With a cross-modal decoder, the selected SUs serve to decode spatiotemporal video representations. In summary, the SUs as the medium can boost discriminative ability and transferability. Specifically, in fully-supervised learning, our method achieved 87.8% top-1 accuracy on Kinetics-400. In K=2 few-shot experiments, our method surpassed the previous state-of-the-art by +7.1% and +15.0% on HMDB-51 and UCF-101, respectively.

Chaorui Deng, Qi Chen, Pengda Qin, Da Chen, Qi Wu

In text-video retrieval, recent works have benefited from the powerful learning capabilities of pre-trained text-image foundation models (e.g., CLIP) by adapting them to the video domain. A critical problem for them is how to effectively capture the rich semantics inside the video using the image encoder of CLIP. To tackle this, state-of-the-art methods adopt complex cross-modal modeling techniques to fuse the text information into video frame representations, which, however, incurs severe efficiency issues in large-scale retrieval systems as the video representations must be recomputed online for every text query. In this paper, we discard this problematic cross-modal fusion process and aim to learn semantically-enhanced representations purely from the video, so that the video representations can be computed offline and reused for different texts. Concretely, we first introduce a spatial-temporal "Prompt Cube" into the CLIP image encoder and iteratively switch it within the encoder layers to efficiently incorporate the global video semantics into frame representations. We then propose to apply an auxiliary video captioning objective to train the frame representations, which facilitates the learning of detailed video semantics by providing fine-grained guidance in the semantic space. With a naive temporal fusion strategy (i.e., mean-pooling) on the enhanced frame representations, we obtain state-of-the-art performances on three benchmark datasets, i.e., MSR-VTT, MSVD, and LSMDC.

Sharath Girish, Abhinav Shrivastava, Kamal Gupta

Implicit Neural Representations (INR) or neural fields have emerged as a popular framework to encode multimedia signals such as images and radiance fields while retaining high-quality. Recently, learnable feature grids such as Instant-NGP have allowed significant speed-up in the training as well as the sampling of INRs by replacing a large neural network with a multi-resolution look-up table of feature vectors and a much smaller neural network. However, these feature grids come at the expense of large memory consumption which can be a bottleneck for storage and streaming applications. In this work, we propose SHACIRA, a simple yet effective task-agnostic framework for compressing such feature grids with no additional post-hoc pruning/quantization stages. We reparameterize feature grids with quantized latent weights and apply entropy regularization in the latent space to achieve high levels of compression across various domains. Quantitative and qualitative results on diverse datasets consisting of images, videos, and radiance fields, show that our approach outperforms existing INR approaches without the need for any large datasets or domain-specific heuristics. Our project page is available at https://shacira.github.io

Ryuichiro Hataya, Han Bao, Hiromi Arai

Recently proposed large-scale text-to-image generative models such as DALLE 2, Midjourney, and StableDiffusion can generate high-quality and realistic images from users' prompts. Not limited to the research community, ordinary Internet users enjoy these generative models, and consequently, a tremendous amount of generated images have been shared on the Internet. Meanwhile, today's success of deep learning in the computer vision field owes a lot to images collected from the Internet. These trends lead us to a research question: "will such generated images impact the quality of future datasets and the performance of computer vision models positively or negatively?" This paper empirically answers this question by simulating contamination. Namely, we generate ImageNet-scale and COCO-scale datasets using a state-of-the-art generative model and evaluate models trained with "contaminated" datasets on various tasks, including image classification and image generation. Throughout experiments, we conclude that generated images negatively affect downstream performance, while the significance depends on tasks and the amount of generated images. The generated datasets and the codes for experiments will be publicly released for future research. Generated datasets and source codes are available from https://github.com/moskomule/dataset-contamination.

Ling-Hao Chen, JiaWei Zhang, Yewen Li, Yiren Pang, Xiaobo Xia, Tongliang Liu

Human motion prediction is a classical problem in computer vision and computer graphics, which has a wide range of practical applications. Previous effects achieve great empirical performance based on an encoding-decoding style. The methods of this style work by first encoding previous motions to latent representations and then decoding the latent representations into predicted motions. However, in practice, they are still unsatisfactory due to several issues, including complicated loss constraints, cumbersome training processes, and scarce switch of different categories of motions in prediction. In this paper, to address the above issues, we jump out of the foregoing style and propose a novel framework from a new perspective. Specifically, our framework works in a masked completion fashion. In the training stage, we learn a motion diffusion model that generates motions from random noise. In the inference stage, with a denoising procedure, we make motion prediction conditioning on observed motions to output more continuous and controllable predictions. The proposed framework enjoys promising algorithmic properties, which only needs one loss in optimization and is trained in an end-to-end manner. Additionally, it accomplishes the switch of different categories of motions effectively, which is significant in realistic tasks, e.g., the animation task. Comprehensive experiments on benchmarks confirm the superiority of the proposed framework. The project page is available at https://lhchen.top/Human-MAC.

Yunji Kim, Jiyoung Lee, Jin-Hwa Kim, Jung-Woo Ha, Jun-Yan Zhu

Existing text-to-image diffusion models struggle to synthesize realistic images given dense captions, where each text prompt provides a detailed description for a specific image region. To address this, we propose DenseDiffusion, a training-free method that adapts a pre-trained text-to-image model to handle such dense captions while offering control over the scene layout. We first analyze the relationship between generated images' layouts and the pre-trained model's intermediate attention maps. Next, we develop an attention modulation method that guides objects to appear in specific regions according to layout guidance. Without requiring additional fine-tuning or datasets, we improve image generation performance given dense captions regarding both automatic and human evaluation scores. In addition, we achieve similar-quality visual results with models specifically trained with layout conditions.

Mitchell Keren Taraday, Chaim Baskin

Deep Neural Networks (DNNs) have revolutionized visual classification tasks over the last decade. The training phase of deep-learning-based algorithms, however, often requires a vast amount of reliable annotated data. While reliability collecting such amount of labeled data usually yields to an exhaustive, expensive process, for many applications, acquiring massive datasets with imperfect annotations is straightforward. For instance, crawling search engines and online websites can generate a boatload amount of noisy labeled data. Hence, solving the problem of learning with noisy labels (LNL) is of paramount importance. Traditional LNL methods have successfully handled datasets with artificially injected noise, but they still fall short of adequately handling real-world noise. With the increasing use of meta-learning in the diverse fields of machine learning, researchers have tried to leverage auxiliary small clean datasets to meta-correct the training labels. Nonetheless, existing meta-label correction approaches are not fully exploiting their potential. In this study, we propose EMLC, an enhanced meta-label correction approach for the LNL problem. We re-examine the meta-learning process and introduce faster and more accurate meta-gradient derivations. We propose a novel teacher architecture tailored explicitly for the LNL problem, equipped with novel training objectives. EMLC outperforms prior approaches and achieves state-of-the-art results in all standard benchmarks. Notably, EMLC enhances the previous art on the noisy real-world dataset Clothing1M by 0.87%. Our publicly available code can be found at the following link: https://github.com/iccv23anonymous/Enhanced-Meta-Label-Correction

Xinyue Huo, Lingxi Xie, Wengang Zhou, Houqiang Li, Qi Tian

We study unsupervised domain adaptation (UDA) for semantic segmentation. Currently, a popular UDA framework lies in self-training which endows the model with two-fold abilities: (i) learning reliable semantics from the labeled images in the source domain, and (ii) adapting to the target domain via generating pseudo labels on the unlabeled images. We find that, by decreasing/increasing the proportion of training samples from the target domain, the 'learning ability' is strengthened/weakened while the 'adapting ability' goes in the opposite direction, implying a conflict between these two abilities, especially for a single model. To alleviate the issue, we propose a novel dual teacher-student (DTS) framework and equip it with a bidirectional learning strategy. By increasing the proportion of target-domain data, the second teacher-student model learns to 'Focus on Your Target' while the first model is not affected. DTS is easily plugged into existing self-training approaches. In a standard UDA scenario (training on synthetic, labeled data and real, unlabeled data), DTS shows consistent gains over the baselines and sets new state-of-the-art results of 76.5% and 75.1% mIoUs on GTAv-Cityscapes and SYNTHIA-Cityscapes, respectively. The implementation is available at https://github.com/xinyuehuo/DTS.

Yuran Sun, Alan William Dougherty, Zhuoying Zhang, Yi King Choi, Chuan Wu

Human pose estimation in videos has wide-ranging practical applications across various fields, many of which require fast inference on resource-scarce devices, necessitating the development of efficient and accurate algorithms. Previous works have demonstrated the feasibility of exploiting motion continuity to conduct pose estimation using sparsely sampled frames with transformer-based models. However, these methods only consider the temporal relation while neglecting spatial attention, and the complexity of dot product self-attention calculations in transformers are quadratically proportional to the embedding size. To address these limitations, we propose MixSynthFormer, a transformer encoder-like model with MLP-based mixed synthetic attention. By mixing synthesized spatial and temporal attentions, our model incorporates inter-joint and inter-frame importance and can accurately estimate human poses in an entire video sequence from sparsely sampled frames. Additionally, the flexible design of our model makes it versatile for other motion synthesis tasks. Our extensive experiments on 2D/3D pose estimation, body mesh recovery, and motion prediction validate the effectiveness and efficiency of MixSynthFormer.

Yanqing Liu, Jianyang Gu, Kai Wang, Zheng Zhu, Wei Jiang, Yang You

Dataset distillation aims to synthesize small datasets with little information loss from original large-scale ones for reducing storage and training costs. Recent state-of-the-art methods mainly constrain the sample synthesis process by matching synthetic images and the original ones regarding gradients, embedding distributions, or training trajectories. Although there are various matching objectives, currently the strategy for selecting original images is limited to naive random sampling. We argue that random sampling overlooks the evenness of the selected sample distribution, which may result in noisy or biased matching targets. Besides, the sample diversity is also not constrained by random sampling. These factors together lead to optimization instability in the distilling process and degrade the training efficiency. Accordingly, we propose a novel matching strategy named as Dataset distillation by REpresentAive Matching (DREAM), where only representative original images are selected for matching. DREAM is able to be easily plugged into popular dataset distillation frameworks and reduce the distilling iterations by more than 8 times without performance drop. Given sufficient training time, DREAM further provides significant improvements and achieves state-of-the-art performances.

Su-Kai Chen, Hung-Lin Yen, Yu-Lun Liu, Min-Hung Chen, Hou-Ning Hu, Wen-Hsiao Peng, Yen-Yu Lin

Deep learning is commonly used to produce impressive results in reconstructing HDR images from LDR images. LDR stack-based methods are used for single-image HDR reconstruction, generating an HDR image from a deep learning generated LDR stack. However, current methods generate the LDR stack with predetermined exposure values (EVs), which may limit the quality of HDR reconstruction. To address this, we propose the continuous exposure value representation (CEVR) model, which uses an implicit function to generate LDR images with arbitrary EVs, including those unseen during training. Our flexible approach generates a continuous stack with more images containing diverse EVs, significantly improving HDR reconstruction. We use a cycle training strategy to supervise the model in generating continuous EV LDR images without corresponding ground truths. Our CEVR model outperforms existing methods, as demonstrated by experimental results.

Ming Li, Jie Wu, Xionghui Wang, Chen Chen, Jie Qin, Xuefeng Xiao, Rui Wang, Min Zheng, Xin Pan

The paradigm of large-scale pre-training followed by downstream fine-tuning has been widely employed in various object detection algorithms. In this paper, we reveal discrepancies in data, model, and task between the pre-training and fine-tuning procedure in existing practices, which implicitly limit the detector's performance, generalization ability, and convergence speed. To this end, we propose AlignDet, a unified pre-training framework that can be adapted to various existing detectors to alleviate the discrepancies. AlignDet decouples the pre-training process into two stages, i.e., image-domain and box-domain pre-training. The image-domain pre-training optimizes the detection backbone to capture holistic visual abstraction, and box-domain pre-training learns instance-level semantics and task-aware concepts to initialize the parts out of the backbone. By incorporating the self-supervised pre-trained backbones, we can pre-train all modules for various detectors in an unsupervised paradigm. As depicted in Figure 1, extensive experiments demonstrate that AlignDet can achieve significant improvements across diverse protocols, such as detection algorithm, model backbone, data setting, and training schedule. For example, AlignDet improves FCOS by 5.3 mAP, RetinaNet by 2.1 mAP, Faster R-CNN by 3.3 mAP, and DETR by 2.3 mAP under fewer epochs.