Vector font synthesis is a challenging and ongoing problem in the fields of Computer Vision and Computer Graphics. The recently-proposed DeepVecFont achieved state-of-the-art performance by exploiting information of both the image and sequence modalities of vector fonts. However, it has limited capability for handling long sequence data and heavily relies on an image-guided outline refinement post-processing. Thus, vector glyphs synthesized by DeepVecFont still often contain some distortions and artifacts and cannot rival human-designed results. To address the above problems, this paper proposes an enhanced version of DeepVecFont mainly by making the following three novel technical contributions. First, we adopt Transformers instead of RNNs to process sequential data and design a relaxation representation for vector outlines, markedly improving the model's capability and stability of synthesizing long and complex outlines. Second, we propose to sample auxiliary points in addition to control points to precisely align the generated and target B\'ezier curves or lines. Finally, to alleviate error accumulation in the sequential generation process, we develop a context-based self-refinement module based on another Transformer-based decoder to remove artifacts in the initially synthesized glyphs. Both qualitative and quantitative results demonstrate that the proposed method effectively resolves those intrinsic problems of the original DeepVecFont and outperforms existing approaches in generating English and Chinese vector fonts with complicated structures and diverse styles.
Prompt-OVD is an efficient and effective framework for open-vocabulary object detection that utilizes class embeddings from CLIP as prompts, guiding the Transformer decoder to detect objects in both base and novel classes. Additionally, our novel RoI-based masked attention and RoI pruning techniques help leverage the zero-shot classification ability of the Vision Transformer-based CLIP, resulting in improved detection performance at minimal computational cost. Our experiments on the OV-COCO and OVLVIS datasets demonstrate that Prompt-OVD achieves an impressive 21.2 times faster inference speed than the first end-to-end open-vocabulary detection method (OV-DETR), while also achieving higher APs than four two-stage-based methods operating within similar inference time ranges. Code will be made available soon.
Generalized Zero-Shot Learning (GZSL) identifies unseen categories by knowledge transferred from the seen domain, relying on the intrinsic interactions between visual and semantic information. Prior works mainly localize regions corresponding to the sharing attributes. When various visual appearances correspond to the same attribute, the sharing attributes inevitably introduce semantic ambiguity, hampering the exploration of accurate semantic-visual interactions. In this paper, we deploy the dual semantic-visual transformer module (DSVTM) to progressively model the correspondences between attribute prototypes and visual features, constituting a progressive semantic-visual mutual adaption (PSVMA) network for semantic disambiguation and knowledge transferability improvement. Specifically, DSVTM devises an instance-motivated semantic encoder that learns instance-centric prototypes to adapt to different images, enabling the recast of the unmatched semantic-visual pair into the matched one. Then, a semantic-motivated instance decoder strengthens accurate cross-domain interactions between the matched pair for semantic-related instance adaption, encouraging the generation of unambiguous visual representations. Moreover, to mitigate the bias towards seen classes in GZSL, a debiasing loss is proposed to pursue response consistency between seen and unseen predictions. The PSVMA consistently yields superior performances against other state-of-the-art methods. Code will be available at: https://github.com/ManLiuCoder/PSVMA.
Predicting human gaze is important in Human-Computer Interaction (HCI). However, to practically serve HCI applications, gaze prediction models must be scalable, fast, and accurate in their spatial and temporal gaze predictions. Recent scanpath prediction models focus on goal-directed attention (search). Such models are limited in their application due to a common approach relying on trained target detectors for all possible objects, and the availability of human gaze data for their training (both not scalable). In response, we pose a new task called ZeroGaze, a new variant of zero-shot learning where gaze is predicted for never-before-searched objects, and we develop a novel model, Gazeformer, to solve the ZeroGaze problem. In contrast to existing methods using object detector modules, Gazeformer encodes the target using a natural language model, thus leveraging semantic similarities in scanpath prediction. We use a transformer-based encoder-decoder architecture because transformers are particularly useful for generating contextual representations. Gazeformer surpasses other models by a large margin on the ZeroGaze setting. It also outperforms existing target-detection models on standard gaze prediction for both target-present and target-absent search tasks. In addition to its improved performance, Gazeformer is more than five times faster than the state-of-the-art target-present visual search model.
Face parsing is defined as the per-pixel labeling of images containing human faces. The labels are defined to identify key facial regions like eyes, lips, nose, hair, etc. In this work, we make use of the structural consistency of the human face to propose a lightweight face-parsing method using a Local Implicit Function network, FP-LIIF. We propose a simple architecture having a convolutional encoder and a pixel MLP decoder that uses 1/26th number of parameters compared to the state-of-the-art models and yet matches or outperforms state-of-the-art models on multiple datasets, like CelebAMask-HQ and LaPa. We do not use any pretraining, and compared to other works, our network can also generate segmentation at different resolutions without any changes in the input resolution. This work enables the use of facial segmentation on low-compute or low-bandwidth devices because of its higher FPS and smaller model size.
3D automatic annotation has received increased attention since manually annotating 3D point clouds is laborious. However, existing methods are usually complicated, e.g., pipelined training for 3D foreground/background segmentation, cylindrical object proposals, and point completion. Furthermore, they often overlook the inter-object feature relation that is particularly informative to hard samples for 3D annotation. To this end, we propose a simple yet effective end-to-end Context-Aware Transformer (CAT) as an automated 3D-box labeler to generate precise 3D box annotations from 2D boxes, trained with a small number of human annotations. We adopt the general encoder-decoder architecture, where the CAT encoder consists of an intra-object encoder (local) and an inter-object encoder (global), performing self-attention along the sequence and batch dimensions, respectively. The former models intra-object interactions among points, and the latter extracts feature relations among different objects, thus boosting scene-level understanding. Via local and global encoders, CAT can generate high-quality 3D box annotations with a streamlined workflow, allowing it to outperform existing state-of-the-art by up to 1.79% 3D AP on the hard task of the KITTI test set.
Dense prediction tasks are a fundamental class of problems in computer vision. As supervised methods suffer from high pixel-wise labeling cost, a few-shot learning solution that can learn any dense task from a few labeled images is desired. Yet, current few-shot learning methods target a restricted set of tasks such as semantic segmentation, presumably due to challenges in designing a general and unified model that is able to flexibly and efficiently adapt to arbitrary tasks of unseen semantics. We propose Visual Token Matching (VTM), a universal few-shot learner for arbitrary dense prediction tasks. It employs non-parametric matching on patch-level embedded tokens of images and labels that encapsulates all tasks. Also, VTM flexibly adapts to any task with a tiny amount of task-specific parameters that modulate the matching algorithm. We implement VTM as a powerful hierarchical encoder-decoder architecture involving ViT backbones where token matching is performed at multiple feature hierarchies. We experiment VTM on a challenging variant of Taskonomy dataset and observe that it robustly few-shot learns various unseen dense prediction tasks. Surprisingly, it is competitive with fully supervised baselines using only 10 labeled examples of novel tasks (0.004% of full supervision) and sometimes outperforms using 0.1% of full supervision. Codes are available at https://github.com/GitGyun/visual_token_matching.
We propose a new formulation of temporal action detection (TAD) with denoising diffusion, DiffTAD in short. Taking as input random temporal proposals, it can yield action proposals accurately given an untrimmed long video. This presents a generative modeling perspective, against previous discriminative learning manners. This capability is achieved by first diffusing the ground-truth proposals to random ones (i.e., the forward/noising process) and then learning to reverse the noising process (i.e., the backward/denoising process). Concretely, we establish the denoising process in the Transformer decoder (e.g., DETR) by introducing a temporal location query design with faster convergence in training. We further propose a cross-step selective conditioning algorithm for inference acceleration. Extensive evaluations on ActivityNet and THUMOS show that our DiffTAD achieves top performance compared to previous art alternatives. The code will be made available at https://github.com/sauradip/DiffusionTAD.
Beta-VAE is a very classical model for disentangled representation learning, the use of an expanding bottleneck that allow information into the decoder gradually is key to representation disentanglement as well as high-quality reconstruction. During recent experiments on such fascinating structure, we discovered that the total amount of latent variables can affect the representation learnt by the network: with very few latent variables, the network tend to learn the most important or principal variables, acting like a PCA; with very large numbers of latent variables, the variables tend to be more disentangled, and act like an ICA. Our assumption is that the competition between latent variables while trying to gain the most information bandwidth can lead to this phenomenon.
Generative image modeling enables a wide range of applications but raises ethical concerns about responsible deployment. This paper introduces an active strategy combining image watermarking and Latent Diffusion Models. The goal is for all generated images to conceal an invisible watermark allowing for future detection and/or identification. The method quickly fine-tunes the latent decoder of the image generator, conditioned on a binary signature. A pre-trained watermark extractor recovers the hidden signature from any generated image and a statistical test then determines whether it comes from the generative model. We evaluate the invisibility and robustness of the watermarks on a variety of generation tasks, showing that Stable Signature works even after the images are modified. For instance, it detects the origin of an image generated from a text prompt, then cropped to keep $10\%$ of the content, with $90$+$\%$ accuracy at a false positive rate below 10$^{-6}$.
The impact of a drop on a solid surface is an important phenomenon that has various implications and applications. However, the multiphase nature of this phenomenon causes complications in the prediction of its morphological evolution, especially when the drop splashes. While most machine-learning-based drop-impact studies have centred around physical parameters, this study used a computer-vision strategy by training an encoder-decoder to predict the drop morphologies using image data. Herein, we show that this trained encoder-decoder is able to successfully generate videos that show the morphologies of splashing and non-splashing drops. Remarkably, in each frame of these generated videos, the spreading diameter of the drop was found to be in good agreement with that of the actual videos. Moreover, there was also a high accuracy in splashing/non-splashing prediction. These findings demonstrate the ability of the trained encoder-decoder to generate videos that can accurately represent the drop morphologies. This approach provides a faster and cheaper alternative to experimental and numerical studies.
Unlike most previous HOI methods that focus on learning better human-object features, we propose a novel and complementary approach called category query learning. Such queries are explicitly associated to interaction categories, converted to image specific category representation via a transformer decoder, and learnt via an auxiliary image-level classification task. This idea is motivated by an earlier multi-label image classification method, but is for the first time applied for the challenging human-object interaction classification task. Our method is simple, general and effective. It is validated on three representative HOI baselines and achieves new state-of-the-art results on two benchmarks.
The problem of document structure reconstruction refers to converting digital or scanned documents into corresponding semantic structures. Most existing works mainly focus on splitting the boundary of each element in a single document page, neglecting the reconstruction of semantic structure in multi-page documents. This paper introduces hierarchical reconstruction of document structures as a novel task suitable for NLP and CV fields. To better evaluate the system performance on the new task, we built a large-scale dataset named HRDoc, which consists of 2,500 multi-page documents with nearly 2 million semantic units. Every document in HRDoc has line-level annotations including categories and relations obtained from rule-based extractors and human annotators. Moreover, we proposed an encoder-decoder-based hierarchical document structure parsing system (DSPS) to tackle this problem. By adopting a multi-modal bidirectional encoder and a structure-aware GRU decoder with soft-mask operation, the DSPS model surpass the baseline method by a large margin. All scripts and datasets will be made publicly available at https://github.com/jfma-USTC/HRDoc.
Anomaly detection is widely used in network intrusion detection, autonomous driving, medical diagnosis, credit card frauds, etc. However, several key challenges remain open, such as lack of ground truth labels, presence of complex temporal patterns, and generalizing over different datasets. This paper proposes TSI-GAN, an unsupervised anomaly detection model for time-series that can learn complex temporal patterns automatically and generalize well, i.e., no need for choosing dataset-specific parameters, making statistical assumptions about underlying data, or changing model architectures. To achieve these goals, we convert each input time-series into a sequence of 2D images using two encoding techniques with the intent of capturing temporal patterns and various types of deviance. Moreover, we design a reconstructive GAN that uses convolutional layers in an encoder-decoder network and employs cycle-consistency loss during training to ensure that inverse mappings are accurate as well. In addition, we also instrument a Hodrick-Prescott filter in post-processing to mitigate false positives. We evaluate TSI-GAN using 250 well-curated and harder-than-usual datasets and compare with 8 state-of-the-art baseline methods. The results demonstrate the superiority of TSI-GAN to all the baselines, offering an overall performance improvement of 13% and 31% over the second-best performer MERLIN and the third-best performer LSTM-AE, respectively.
Despite increasingly realistic image quality, recent 3D image generative models often operate on 3D volumes of fixed extent with limited camera motions. We investigate the task of unconditionally synthesizing unbounded nature scenes, enabling arbitrarily large camera motion while maintaining a persistent 3D world model. Our scene representation consists of an extendable, planar scene layout grid, which can be rendered from arbitrary camera poses via a 3D decoder and volume rendering, and a panoramic skydome. Based on this representation, we learn a generative world model solely from single-view internet photos. Our method enables simulating long flights through 3D landscapes, while maintaining global scene consistency--for instance, returning to the starting point yields the same view of the scene. Our approach enables scene extrapolation beyond the fixed bounds of current 3D generative models, while also supporting a persistent, camera-independent world representation that stands in contrast to auto-regressive 3D prediction models. Our project page: https://chail.github.io/persistent-nature/.
Most video restoration networks are slow, have high computational load, and can't be used for real-time video enhancement. In this work, we design an efficient and fast framework to perform real-time video enhancement for practical use-cases like live video calls and video streams. Our proposed method, called Recurrent Bottleneck Mixer Network (ReBotNet), employs a dual-branch framework. The first branch learns spatio-temporal features by tokenizing the input frames along the spatial and temporal dimensions using a ConvNext-based encoder and processing these abstract tokens using a bottleneck mixer. To further improve temporal consistency, the second branch employs a mixer directly on tokens extracted from individual frames. A common decoder then merges the features form the two branches to predict the enhanced frame. In addition, we propose a recurrent training approach where the last frame's prediction is leveraged to efficiently enhance the current frame while improving temporal consistency. To evaluate our method, we curate two new datasets that emulate real-world video call and streaming scenarios, and show extensive results on multiple datasets where ReBotNet outperforms existing approaches with lower computations, reduced memory requirements, and faster inference time.
The field of vision and language has witnessed a proliferation of pre-trained foundation models. Most existing methods are independently pre-trained with contrastive objective like CLIP, image-to-text generative objective like PaLI, or text-to-image generative objective like Parti. However, the three objectives can be pre-trained on the same data, image-text pairs, and intuitively they complement each other as contrasting provides global alignment capacity and generation grants fine-grained understanding. In this work, we present a Contrastive Bi-directional Image-Text generation model (CoBIT), which attempts to unify the three pre-training objectives in one framework. Specifically, CoBIT employs a novel unicoder-decoder structure, consisting of an image unicoder, a text unicoder and a cross-modal decoder. The image/text unicoders can switch between encoding and decoding in different tasks, enabling flexibility and shared knowledge that benefits both image-to-text and text-to-image generations. CoBIT achieves superior performance in image understanding, image-text understanding (Retrieval, Captioning, VQA, SNLI-VE) and text-based content creation, particularly in zero-shot scenarios. For instance, 82.7% in zero-shot ImageNet classification, 9.37 FID score in zero-shot text-to-image generation and 44.8 CIDEr in zero-shot captioning.
This paper introduces a general model called CIPNN - Continuous Indeterminate Probability Neural Network, and this model is based on IPNN, which is used for discrete latent random variables. Currently, posterior of continuous latent variables is regarded as intractable, with the new theory proposed by IPNN this problem can be solved. Our contributions are Four-fold. First, we derive the analytical solution of the posterior calculation of continuous latent random variables and propose a general classification model (CIPNN). Second, we propose a general auto-encoder called CIPAE - Continuous Indeterminate Probability Auto-Encoder, the decoder part is not a neural network and uses a fully probabilistic inference model for the first time. Third, we propose a new method to visualize the latent random variables, we use one of N dimensional latent variables as a decoder to reconstruct the input image, which can work even for classification tasks, in this way, we can see what each latent variable has learned. Fourth, IPNN has shown great classification capability, CIPNN has pushed this classification capability to infinity. Theoretical advantages are reflected in experimental results.
Various recent experimental results show that large language models (LLM) exhibit emergent abilities that are not present in small models. System performance is greatly improved after passing a certain critical threshold of scale. In this letter, we provide a simple explanation for such a phase transition phenomenon. For this, we model an LLM as a sequence-to-sequence random function. Instead of using instant generation at each step, we use a list decoder that keeps a list of candidate sequences at each step and defers the generation of the output sequence at the end. We show that there is a critical threshold such that the expected number of erroneous candidate sequences remains bounded when an LLM is below the threshold, and it grows exponentially when an LLM is above the threshold. Such a threshold is related to the basic reproduction number in a contagious disease.
Predicting the next location is a highly valuable and common need in many location-based services such as destination prediction and route planning. The goal of next location recommendation is to predict the next point-of-interest a user might go to based on the user's historical trajectory. Most existing models learn mobility patterns merely from users' historical check-in sequences while overlooking the significance of user preference modeling. In this work, a novel Point-of-Interest Transformer (POIFormer) with contrastive user preference modeling is developed for end-to-end next location recommendation. This model consists of three major modules: history encoder, query generator, and preference decoder. History encoder is designed to model mobility patterns from historical check-in sequences, while query generator explicitly learns user preferences to generate user-specific intention queries. Finally, preference decoder combines the intention queries and historical information to predict the user's next location. Extensive comparisons with representative schemes and ablation studies on four real-world datasets demonstrate the effectiveness and superiority of the proposed scheme under various settings.