Yifan Jiang

Zhendong Wang, Yifan Jiang, Huangjie Zheng et al. · apple-ml, microsoft-research

Diffusion models are powerful, but they require a lot of time and data to train. We propose Patch Diffusion, a generic patch-wise training framework, to significantly reduce the training time costs while improving data efficiency, which thus helps democratize diffusion model training to broader users. At the core of our innovations is a new conditional score function at the patch level, where the patch location in the original image is included as additional coordinate channels, while the patch size is randomized and diversified throughout training to encode the cross-region dependency at multiple scales. Sampling with our method is as easy as in the original diffusion model. Through Patch Diffusion, we could achieve $\mathbf{\ge 2\times}$ faster training, while maintaining comparable or better generation quality. Patch Diffusion meanwhile improves the performance of diffusion models trained on relatively small datasets, $e.g.$, as few as 5,000 images to train from scratch. We achieve outstanding FID scores in line with state-of-the-art benchmarks: 1.77 on CelebA-64$\times$64, 1.93 on AFHQv2-Wild-64$\times$64, and 2.72 on ImageNet-256$\times$256. We share our code and pre-trained models at https://github.com/Zhendong-Wang/Patch-Diffusion.

Qiucheng Wu, Yifan Jiang, Junru Wu et al. · gatech

The disentanglement of StyleGAN latent space has paved the way for realistic and controllable image editing, but does StyleGAN know anything about temporal motion, as it was only trained on static images? To study the motion features in the latent space of StyleGAN, in this paper, we hypothesize and demonstrate that a series of meaningful, natural, and versatile small, local movements (referred to as "micromotion", such as expression, head movement, and aging effect) can be represented in low-rank spaces extracted from the latent space of a conventionally pre-trained StyleGAN-v2 model for face generation, with the guidance of proper "anchors" in the form of either short text or video clips. Starting from one target face image, with the editing direction decoded from the low-rank space, its micromotion features can be represented as simple as an affine transformation over its latent feature. Perhaps more surprisingly, such micromotion subspace, even learned from just single target face, can be painlessly transferred to other unseen face images, even those from vastly different domains (such as oil painting, cartoon, and sculpture faces). It demonstrates that the local feature geometry corresponding to one type of micromotion is aligned across different face subjects, and hence that StyleGAN-v2 is indeed "secretly" aware of the subject-disentangled feature variations caused by that micromotion. We present various successful examples of applying our low-dimensional micromotion subspace technique to directly and effortlessly manipulate faces, showing high robustness, low computational overhead, and impressive domain transferability. Our codes are available at https://github.com/wuqiuche/micromotion-StyleGAN.

Dejia Xu, Yifan Jiang, Peihao Wang et al. · gatech

Despite the rapid development of Neural Radiance Field (NeRF), the necessity of dense covers largely prohibits its wider applications. While several recent works have attempted to address this issue, they either operate with sparse views (yet still, a few of them) or on simple objects/scenes. In this work, we consider a more ambitious task: training neural radiance field, over realistically complex visual scenes, by "looking only once", i.e., using only a single view. To attain this goal, we present a Single View NeRF (SinNeRF) framework consisting of thoughtfully designed semantic and geometry regularizations. Specifically, SinNeRF constructs a semi-supervised learning process, where we introduce and propagate geometry pseudo labels and semantic pseudo labels to guide the progressive training process. Extensive experiments are conducted on complex scene benchmarks, including NeRF synthetic dataset, Local Light Field Fusion dataset, and DTU dataset. We show that even without pre-training on multi-view datasets, SinNeRF can yield photo-realistic novel-view synthesis results. Under the single image setting, SinNeRF significantly outperforms the current state-of-the-art NeRF baselines in all cases. Project page: https://vita-group.github.io/SinNeRF/

Zhiwen Fan, Yifan Jiang, Peihao Wang et al.

Representing visual signals by implicit representation (e.g., a coordinate based deep network) has prevailed among many vision tasks. This work explores a new intriguing direction: training a stylized implicit representation, using a generalized approach that can apply to various 2D and 3D scenarios. We conduct a pilot study on a variety of implicit functions, including 2D coordinate-based representation, neural radiance field, and signed distance function. Our solution is a Unified Implicit Neural Stylization framework, dubbed INS. In contrary to vanilla implicit representation, INS decouples the ordinary implicit function into a style implicit module and a content implicit module, in order to separately encode the representations from the style image and input scenes. An amalgamation module is then applied to aggregate these information and synthesize the stylized output. To regularize the geometry in 3D scenes, we propose a novel self-distillation geometry consistency loss which preserves the geometry fidelity of the stylized scenes. Comprehensive experiments are conducted on multiple task settings, including novel view synthesis of complex scenes, stylization for implicit surfaces, and fitting images using MLPs. We further demonstrate that the learned representation is continuous not only spatially but also style-wise, leading to effortlessly interpolating between different styles and generating images with new mixed styles. Please refer to the video on our project page for more view synthesis results: https://zhiwenfan.github.io/INS.

Dejia Xu, Peihao Wang, Yifan Jiang et al.

Implicit Neural Representations (INRs) encoding continuous multi-media data via multi-layer perceptrons has shown undebatable promise in various computer vision tasks. Despite many successful applications, editing and processing an INR remains intractable as signals are represented by latent parameters of a neural network. Existing works manipulate such continuous representations via processing on their discretized instance, which breaks down the compactness and continuous nature of INR. In this work, we present a pilot study on the question: how to directly modify an INR without explicit decoding? We answer this question by proposing an implicit neural signal processing network, dubbed INSP-Net, via differential operators on INR. Our key insight is that spatial gradients of neural networks can be computed analytically and are invariant to translation, while mathematically we show that any continuous convolution filter can be uniformly approximated by a linear combination of high-order differential operators. With these two knobs, INSP-Net instantiates the signal processing operator as a weighted composition of computational graphs corresponding to the high-order derivatives of INRs, where the weighting parameters can be data-driven learned. Based on our proposed INSP-Net, we further build the first Convolutional Neural Network (CNN) that implicitly runs on INRs, named INSP-ConvNet. Our experiments validate the expressiveness of INSP-Net and INSP-ConvNet in fitting low-level image and geometry processing kernels (e.g. blurring, deblurring, denoising, inpainting, and smoothening) as well as for high-level tasks on implicit fields such as image classification.

Zhiwen Fan, Panwang Pan, Peihao Wang et al.

In the field of novel-view synthesis, the necessity of knowing camera poses (e.g., via Structure from Motion) before rendering has been a common practice. However, the consistent acquisition of accurate camera poses remains elusive, and errors in pose extraction can adversely impact the view synthesis process. To address this challenge, we introduce PF-GRT, a new Pose-Free framework for Generalizable Rendering Transformer, eliminating the need for pre-computed camera poses and instead leveraging feature-matching learned directly from data. PF-GRT is parameterized using a local relative coordinate system, where one of the source images is set as the origin. An OmniView Transformer is designed for fusing multi-view cues under the pose-free setting, where unposed-view fusion and origin-centric aggregation are performed. The 3D point feature along target ray is sampled by projecting onto the selected origin plane. The final pixel intensities are modulated and decoded using another Transformer. PF-GRT demonstrates an impressive ability to generalize to new scenes that were not encountered during the training phase, without the need of pre-computing camera poses. Our experiments with zero-shot rendering on the LLFF, RealEstate-10k, Shiny, and Blender datasets reveal that it produces superior quality in generating photo-realistic images. Moreover, it demonstrates robustness against noise in test camera poses. Code is available at https://zhiwenfan.github.io/PF-GRT/.

Yifan Jiang, Peter Hedman, Ben Mildenhall et al.

Neural Radiance Fields (NeRFs) are a powerful representation for modeling a 3D scene as a continuous function. Though NeRF is able to render complex 3D scenes with view-dependent effects, few efforts have been devoted to exploring its limits in a high-resolution setting. Specifically, existing NeRF-based methods face several limitations when reconstructing high-resolution real scenes, including a very large number of parameters, misaligned input data, and overly smooth details. In this work, we conduct the first pilot study on training NeRF with high-resolution data and propose the corresponding solutions: 1) marrying the multilayer perceptron (MLP) with convolutional layers which can encode more neighborhood information while reducing the total number of parameters; 2) a novel training strategy to address misalignment caused by moving objects or small camera calibration errors; and 3) a high-frequency aware loss. Our approach is nearly free without introducing obvious training/testing costs, while experiments on different datasets demonstrate that it can recover more high-frequency details compared with the current state-of-the-art NeRF models. Project page: \url{https://yifanjiang.net/alignerf.}

Dejia Xu, Yifan Jiang, Peihao Wang et al.

Virtual reality and augmented reality (XR) bring increasing demand for 3D content. However, creating high-quality 3D content requires tedious work that a human expert must do. In this work, we study the challenging task of lifting a single image to a 3D object and, for the first time, demonstrate the ability to generate a plausible 3D object with 360° views that correspond well with the given reference image. By conditioning on the reference image, our model can fulfill the everlasting curiosity for synthesizing novel views of objects from images. Our technique sheds light on a promising direction of easing the workflows for 3D artists and XR designers. We propose a novel framework, dubbed NeuralLift-360, that utilizes a depth-aware neural radiance representation (NeRF) and learns to craft the scene guided by denoising diffusion models. By introducing a ranking loss, our NeuralLift-360 can be guided with rough depth estimation in the wild. We also adopt a CLIP-guided sampling strategy for the diffusion prior to provide coherent guidance. Extensive experiments demonstrate that our NeuralLift-360 significantly outperforms existing state-of-the-art baselines. Project page: https://vita-group.github.io/NeuralLift-360/

Zhiwen Fan, Peihao Wang, Yifan Jiang et al.

Neural volumetric representations have shown the potential that Multi-layer Perceptrons (MLPs) can be optimized with multi-view calibrated images to represent scene geometry and appearance, without explicit 3D supervision. Object segmentation can enrich many downstream applications based on the learned radiance field. However, introducing hand-crafted segmentation to define regions of interest in a complex real-world scene is non-trivial and expensive as it acquires per view annotation. This paper carries out the exploration of self-supervised learning for object segmentation using NeRF for complex real-world scenes. Our framework, called NeRF with Self-supervised Object Segmentation NeRF-SOS, couples object segmentation and neural radiance field to segment objects in any view within a scene. By proposing a novel collaborative contrastive loss in both appearance and geometry levels, NeRF-SOS encourages NeRF models to distill compact geometry-aware segmentation clusters from their density fields and the self-supervised pre-trained 2D visual features. The self-supervised object segmentation framework can be applied to various NeRF models that both lead to photo-realistic rendering results and convincing segmentation maps for both indoor and outdoor scenarios. Extensive results on the LLFF, Tank & Temple, and BlendedMVS datasets validate the effectiveness of NeRF-SOS. It consistently surpasses other 2D-based self-supervised baselines and predicts finer semantics masks than existing supervised counterparts. Please refer to the video on our project page for more details:https://zhiwenfan.github.io/NeRF-SOS.

Vidit Goel, Elia Peruzzo, Yifan Jiang et al.

Generative image editing has recently witnessed extremely fast-paced growth. Some works use high-level conditioning such as text, while others use low-level conditioning. Nevertheless, most of them lack fine-grained control over the properties of the different objects present in the image, i.e. object-level image editing. In this work, we tackle the task by perceiving the images as an amalgamation of various objects and aim to control the properties of each object in a fine-grained manner. Out of these properties, we identify structure and appearance as the most intuitive to understand and useful for editing purposes. We propose PAIR Diffusion, a generic framework that can enable a diffusion model to control the structure and appearance properties of each object in the image. We show that having control over the properties of each object in an image leads to comprehensive editing capabilities. Our framework allows for various object-level editing operations on real images such as reference image-based appearance editing, free-form shape editing, adding objects, and variations. Thanks to our design, we do not require any inversion step. Additionally, we propose multimodal classifier-free guidance which enables editing images using both reference images and text when using our approach with foundational diffusion models. We validate the above claims by extensively evaluating our framework on both unconditional and foundational diffusion models. Please refer to https://vidit98.github.io/publication/conference-paper/pair_diff.html for code and model release.

Han Chen, Yifan Jiang, Hanseok Ko

Graph convolutional networks (GCNs), which can model the human body skeletons as spatial and temporal graphs, have shown remarkable potential in skeleton-based action recognition. However, in the existing GCN-based methods, graph-structured representation of the human skeleton makes it difficult to be fused with other modalities, especially in the early stages. This may limit their scalability and performance in action recognition tasks. In addition, the pose information, which naturally contains informative and discriminative clues for action recognition, is rarely explored together with skeleton data in existing methods. In this work, we propose pose-guided GCN (PG-GCN), a multi-modal framework for high-performance human action recognition. In particular, a multi-stream network is constructed to simultaneously explore the robust features from both the pose and skeleton data, while a dynamic attention module is designed for early-stage feature fusion. The core idea of this module is to utilize a trainable graph to aggregate features from the skeleton stream with that of the pose stream, which leads to a network with more robust feature representation ability. Extensive experiments show that the proposed PG-GCN can achieve state-of-the-art performance on the NTU RGB+D 60 and NTU RGB+D 120 datasets.

Prateek Chhikara, Dhiraj Chaurasia, Yifan Jiang et al.

Food computing has emerged as a prominent multidisciplinary field of research in recent years. An ambitious goal of food computing is to develop end-to-end intelligent systems capable of autonomously producing recipe information for a food image. Current image-to-recipe methods are retrieval-based and their success depends heavily on the dataset size and diversity, as well as the quality of learned embeddings. Meanwhile, the emergence of powerful attention-based vision and language models presents a promising avenue for accurate and generalizable recipe generation, which has yet to be extensively explored. This paper proposes FIRE, a novel multimodal methodology tailored to recipe generation in the food computing domain, which generates the food title, ingredients, and cooking instructions based on input food images. FIRE leverages the BLIP model to generate titles, utilizes a Vision Transformer with a decoder for ingredient extraction, and employs the T5 model to generate recipes incorporating titles and ingredients as inputs. We showcase two practical applications that can benefit from integrating FIRE with large language model prompting: recipe customization to fit recipes to user preferences and recipe-to-code transformation to enable automated cooking processes. Our experimental findings validate the efficacy of our proposed approach, underscoring its potential for future advancements and widespread adoption in food computing.

Yifan Jiang, Han Chen, Hanseok Ko

Recently, skeleton-based human action has become a hot research topic because the compact representation of human skeletons brings new blood to this research domain. As a result, researchers began to notice the importance of using RGB or other sensors to analyze human action by extracting skeleton information. Leveraging the rapid development of deep learning (DL), a significant number of skeleton-based human action approaches have been presented with fine-designed DL structures recently. However, a well-trained DL model always demands high-quality and sufficient data, which is hard to obtain without costing high expenses and human labor. In this paper, we introduce a novel data augmentation method for skeleton-based action recognition tasks, which can effectively generate high-quality and diverse sequential actions. In order to obtain natural and realistic action sequences, we propose denoising diffusion probabilistic models (DDPMs) that can generate a series of synthetic action sequences, and their generation process is precisely guided by a spatial-temporal transformer (ST-Trans). Experimental results show that our method outperforms the state-of-the-art (SOTA) motion generation approaches on different naturality and diversity metrics. It proves that its high-quality synthetic data can also be effectively deployed to existing action recognition models with significant performance improvement.

Yifan Jiang, Filip Ilievski, Kaixin Ma et al.

The success of language models has inspired the NLP community to attend to tasks that require implicit and complex reasoning, relying on human-like commonsense mechanisms. While such vertical thinking tasks have been relatively popular, lateral thinking puzzles have received little attention. To bridge this gap, we devise BRAINTEASER: a multiple-choice Question Answering task designed to test the model's ability to exhibit lateral thinking and defy default commonsense associations. We design a three-step procedure for creating the first lateral thinking benchmark, consisting of data collection, distractor generation, and generation of adversarial examples, leading to 1,100 puzzles with high-quality annotations. To assess the consistency of lateral reasoning by models, we enrich BRAINTEASER based on a semantic and contextual reconstruction of its questions. Our experiments with state-of-the-art instruction- and commonsense language models reveal a significant gap between human and model performance, which is further widened when consistency across adversarial formats is considered. We make all of our code and data available to stimulate work on developing and evaluating lateral thinking models.

Yifan Jiang, Hao Tang, Jen-Hao Rick Chang et al.

The task of novel view synthesis aims to generate unseen perspectives of an object or scene from a limited set of input images. Nevertheless, synthesizing novel views from a single image still remains a significant challenge in the realm of computer vision. Previous approaches tackle this problem by adopting mesh prediction, multi-plain image construction, or more advanced techniques such as neural radiance fields. Recently, a pre-trained diffusion model that is specifically designed for 2D image synthesis has demonstrated its capability in producing photorealistic novel views, if sufficiently optimized on a 3D finetuning task. Although the fidelity and generalizability are greatly improved, training such a powerful diffusion model requires a vast volume of training data and model parameters, resulting in a notoriously long time and high computational costs. To tackle this issue, we propose Efficient-3DiM, a simple but effective framework to learn a single-image novel-view synthesizer. Motivated by our in-depth analysis of the inference process of diffusion models, we propose several pragmatic strategies to reduce the training overhead to a manageable scale, including a crafted timestep sampling strategy, a superior 3D feature extractor, and an enhanced training scheme. When combined, our framework is able to reduce the total training time from 10 days to less than 1 day, significantly accelerating the training process under the same computational platform (one instance with 8 Nvidia A100 GPUs). Comprehensive experiments are conducted to demonstrate the efficiency and generalizability of our proposed method.

Yifan Jiang, Kriti Aggarwal, Tanmay Laud et al.

The rapid progress of Large Language Models (LLMs) has opened up new opportunities across various domains and applications; yet it also presents challenges related to potential misuse. To mitigate such risks, red teaming has been employed as a proactive security measure to probe language models for harmful outputs via jailbreak attacks. However, current jailbreak attack approaches are single-turn with explicit malicious queries that do not fully capture the complexity of real-world interactions. In reality, users can engage in multi-turn interactions with LLM-based chat assistants, allowing them to conceal their true intentions in a more covert manner. To bridge this gap, we, first, propose a new jailbreak approach, RED QUEEN ATTACK. This method constructs a multi-turn scenario, concealing the malicious intent under the guise of preventing harm. We craft 40 scenarios that vary in turns and select 14 harmful categories to generate 56k multi-turn attack data points. We conduct comprehensive experiments on the RED QUEEN ATTACK with four representative LLM families of different sizes. Our experiments reveal that all LLMs are vulnerable to RED QUEEN ATTACK, reaching 87.62% attack success rate on GPT-4o and 75.4% on Llama3-70B. Further analysis reveals that larger models are more susceptible to the RED QUEEN ATTACK, with multi-turn structures and concealment strategies contributing to its success. To prioritize safety, we introduce a straightforward mitigation strategy called RED QUEEN GUARD, which aligns LLMs to effectively counter adversarial attacks. This approach reduces the attack success rate to below 1% while maintaining the model's performance across standard benchmarks. Full implementation and dataset are publicly accessible at https://github.com/kriti-hippo/red_queen.

Yifan Jiang, Zezheng Feng, Hongjun Wang et al.

In recent years, deep learning approaches have been proved good performance in traffic flow prediction, many complex models have been proposed to make traffic flow prediction more accurate. However, lacking transparency limits the domain experts on understanding when and where the input data mainly impact the results. Most urban experts and planners can only adjust traffic based on their own experience and can not react effectively toward the potential traffic jam. To tackle this problem, we adapt Shapley value and present a visualization analysis system , which can provide experts with the interpretation of traffic flow prediction. TrafPS consists of three layers, from data process to results computation and visualization. We design three visualization views in TrafPS to support the prediction analysis process. One demonstration shows that the TrafPS supports an effective analytical pipeline on interpreting the prediction flow to users and provides an intuitive visualization for decision making.

Koen Kraaijveld, Yifan Jiang, Kaixin Ma et al.

While visual question-answering (VQA) benchmarks have catalyzed the development of reasoning techniques, they have focused on vertical thinking. Effective problem-solving also necessitates lateral thinking, which remains understudied in AI and has not been used to test visual perception systems. To bridge this gap, we formulate visual lateral thinking as a multiple-choice question-answering task and describe a three-step taxonomy-driven methodology for instantiating task examples. Then, we develop COLUMBUS, a synthetic benchmark that applies the task pipeline to create QA sets with text and icon rebus puzzles based on publicly available collections of compounds and common phrases. COLUMBUS comprises over 1,000 puzzles, each with four answer candidates. While the SotA vision-language models (VLMs) achieve decent performance, our evaluation demonstrates a substantial gap between humans and models. VLMs benefit from human-curated descriptions but struggle to self-generate such representations at the right level of abstraction.

Yifan Jiang, Filip Ilievski, Kaixin Ma

Stories about everyday situations are an essential part of human communication, motivating the need to develop AI agents that can reliably understand these stories. Despite the long list of supervised methods for story completion and procedural understanding, current AI has no mechanisms to automatically track and explain procedures in unseen stories. To bridge this gap, we study the ability of AI models to transfer procedural knowledge to novel narrative tasks in a transparent manner. We design LEAP: a comprehensive framework that integrates state-of-the-art modeling architectures, training regimes, and augmentation strategies based on both natural and synthetic stories. To address the lack of densely annotated training data, we devise a robust automatic labeler based on few-shot prompting to enhance the augmented data. Our experiments with in- and out-of-domain tasks reveal insights into the interplay of different architectures, training regimes, and augmentation strategies. LEAP's labeler has a clear positive impact on out-of-domain datasets, while the resulting dense annotation provides native explainability.

Pangbo Ban, Yifan Jiang, Tianran Liu et al.

To what extent do pre-trained language models grasp semantic knowledge regarding the phenomenon of distributivity? In this paper, we introduce DistNLI, a new diagnostic dataset for natural language inference that targets the semantic difference arising from distributivity, and employ the causal mediation analysis framework to quantify the model behavior and explore the underlying mechanism in this semantically-related task. We find that the extent of models' understanding is associated with model size and vocabulary size. We also provide insights into how models encode such high-level semantic knowledge.

Zhendong Wang, Yifan Jiang, Yadong Lu et al.

We present Prompt Diffusion, a framework for enabling in-context learning in diffusion-based generative models. Given a pair of task-specific example images, such as depth from/to image and scribble from/to image, and a text guidance, our model automatically understands the underlying task and performs the same task on a new query image following the text guidance. To achieve this, we propose a vision-language prompt that can model a wide range of vision-language tasks and a diffusion model that takes it as input. The diffusion model is trained jointly over six different tasks using these prompts. The resulting Prompt Diffusion model is the first diffusion-based vision-language foundation model capable of in-context learning. It demonstrates high-quality in-context generation on the trained tasks and generalizes effectively to new, unseen vision tasks with their respective prompts. Our model also shows compelling text-guided image editing results. Our framework aims to facilitate research into in-context learning for computer vision. We share our code and pre-trained models at https://github.com/Zhendong-Wang/Prompt-Diffusion.

Yifan Jiang, Filip Ilievski, Kaixin Ma

While vertical thinking relies on logical and commonsense reasoning, lateral thinking requires systems to defy commonsense associations and overwrite them through unconventional thinking. Lateral thinking has been shown to be challenging for current models but has received little attention. A recent benchmark, BRAINTEASER, aims to evaluate current models' lateral thinking ability in a zero-shot setting. In this paper, we split the original benchmark to also support fine-tuning setting and present SemEval Task 9: BRAIN-TEASER(S), the first task at this competition designed to test the system's reasoning and lateral thinking ability. As a popular task, BRAINTEASER(S)'s two subtasks receive 483 team submissions from 182 participants during the competition. This paper provides a fine-grained system analysis of the competition results, together with a reflection on what this means for the ability of the systems to reason laterally. We hope that the BRAINTEASER(S) subtasks and findings in this paper can stimulate future work on lateral thinking and robust reasoning by computational models.

Yifan Jiang, Jiarui Zhang, Kexuan Sun et al.

While multi-modal large language models (MLLMs) have shown significant progress on many popular visual reasoning benchmarks, whether they possess abstract visual reasoning abilities remains an open question. Similar to the Sudoku puzzles, abstract visual reasoning (AVR) problems require finding high-level patterns (e.g., repetition constraints) that control the input shapes (e.g., digits) in a specific task configuration (e.g., matrix). However, existing AVR benchmarks only considered a limited set of patterns (addition, conjunction), input shapes (rectangle, square), and task configurations (3 by 3 matrices). To evaluate MLLMs' reasoning abilities comprehensively, we introduce MARVEL, a multidimensional AVR benchmark with 770 puzzles composed of six core knowledge patterns, geometric and abstract shapes, and five different task configurations. To inspect whether the model accuracy is grounded in perception and reasoning, MARVEL complements the general AVR question with perception questions in a hierarchical evaluation framework. We conduct comprehensive experiments on MARVEL with nine representative MLLMs in zero-shot and few-shot settings. Our experiments reveal that all models show near-random performance on the AVR question, with significant performance gaps (40%) compared to humans across all patterns and task configurations. Further analysis of perception questions reveals that MLLMs struggle to comprehend the visual features (near-random performance) and even count the panels in the puzzle ( <45%), hindering their ability for abstract reasoning. We release our entire code and dataset.

Elia Peruzzo, Vidit Goel, Dejia Xu et al. · gatech

Recently, several works tackled the video editing task fostered by the success of large-scale text-to-image generative models. However, most of these methods holistically edit the frame using the text, exploiting the prior given by foundation diffusion models and focusing on improving the temporal consistency across frames. In this work, we introduce a framework that is object-centric and is designed to control both the object's appearance and, notably, to execute precise and explicit structural modifications on the object. We build our framework on a pre-trained image-conditioned diffusion model, integrate layers to handle the temporal dimension, and propose training strategies and architectural modifications to enable shape control. We evaluate our method on the image-driven video editing task showing similar performance to the state-of-the-art, and showcasing novel shape-editing capabilities. Further details, code and examples are available on our project page: https://helia95.github.io/vase-website/

Liangchen Song, Liangliang Cao, Jiatao Gu et al.

The advancement of text-driven 3D content editing has been blessed by the progress from 2D generative diffusion models. However, a major obstacle hindering the widespread adoption of 3D content editing is its time-intensive processing. This challenge arises from the iterative and refining steps required to achieve consistent 3D outputs from 2D image-based generative models. Recent state-of-the-art methods typically require optimization time ranging from tens of minutes to several hours to edit a 3D scene using a single GPU. In this work, we propose that by incorporating correspondence regularization into diffusion models, the process of 3D editing can be significantly accelerated. This approach is inspired by the notion that the estimated samples during diffusion should be multiview-consistent during the diffusion generation process. By leveraging this multiview consistency, we can edit 3D content at a much faster speed. In most scenarios, our proposed technique brings a 10$\times$ speed-up compared to the baseline method and completes the editing of a 3D scene in 2 minutes with comparable quality.

Zezheng Feng, Yifan Jiang, Hongjun Wang et al.

Recent achievements in deep learning (DL) have shown its potential for predicting traffic flows. Such predictions are beneficial for understanding the situation and making decisions in traffic control. However, most state-of-the-art DL models are considered "black boxes" with little to no transparency for end users with respect to the underlying mechanisms. Some previous work tried to "open the black boxes" and increase the interpretability of how predictions are generated. However, it still remains challenging to handle complex models on large-scale spatio-temporal data and discover salient spatial and temporal patterns that significantly influence traffic flows. To overcome the challenges, we present TrafPS, a visual analytics approach for interpreting traffic prediction outcomes to support decision-making in traffic management and urban planning. The measurements, region SHAP and trajectory SHAP, are proposed to quantify the impact of flow patterns on urban traffic at different levels. Based on the task requirement from the domain experts, we employ an interactive visual interface for multi-aspect exploration and analysis of significant flow patterns. Two real-world case studies demonstrate the effectiveness of TrafPS in identifying key routes and decision-making support for urban planning.

Mengshu Sun, Haoyu Ma, Guoliang Kang et al.

The transformer architectures with attention mechanisms have obtained success in Nature Language Processing (NLP), and Vision Transformers (ViTs) have recently extended the application domains to various vision tasks. While achieving high performance, ViTs suffer from large model size and high computation complexity that hinders the deployment of them on edge devices. To achieve high throughput on hardware and preserve the model accuracy simultaneously, we propose VAQF, a framework that builds inference accelerators on FPGA platforms for quantized ViTs with binary weights and low-precision activations. Given the model structure and the desired frame rate, VAQF will automatically output the required quantization precision for activations as well as the optimized parameter settings of the accelerator that fulfill the hardware requirements. The implementations are developed with Vivado High-Level Synthesis (HLS) on the Xilinx ZCU102 FPGA board, and the evaluation results with the DeiT-base model indicate that a frame rate requirement of 24 frames per second (FPS) is satisfied with 8-bit activation quantization, and a target of 30 FPS is met with 6-bit activation quantization. To the best of our knowledge, this is the first time quantization has been incorporated into ViT acceleration on FPGAs with the help of a fully automatic framework to guide the quantization strategy on the software side and the accelerator implementations on the hardware side given the target frame rate. Very small compilation time cost is incurred compared with quantization training, and the generated accelerators show the capability of achieving real-time execution for state-of-the-art ViT models on FPGAs.

Yifan Jiang, Bartlomiej Wronski, Ben Mildenhall et al.

Most image denoising networks apply a single set of static convolutional kernels across the entire input image. This is sub-optimal for natural images, as they often consist of heterogeneous visual patterns. Dynamic convolution tries to address this issue by using per-pixel convolution kernels, but this greatly increases computational cost. In this work, we present Malleable Convolution (MalleConv), which performs spatial-varying processing with minimal computational overhead. MalleConv uses a smaller set of spatially-varying convolution kernels, a compromise between static and per-pixel convolution kernels. These spatially-varying kernels are produced by an efficient predictor network running on a downsampled input, making them much more efficient to compute than per-pixel kernels produced by a full-resolution image, and also enlarging the network's receptive field compared with static kernels. These kernels are then jointly upsampled and applied to a full-resolution feature map through an efficient on-the-fly slicing operator with minimum memory overhead. To demonstrate the effectiveness of MalleConv, we use it to build an efficient denoising network we call MalleNet. MalleNet achieves high-quality results without very deep architectures, making it 8.9x faster than the best performing denoising algorithms while achieving similar visual quality. We also show that a single MalleConv layer added to a standard convolution-based backbone can significantly reduce the computational cost or boost image quality at a similar cost. More information is on our project page: \url{https://yifanjiang.net/MalleConv.html}

Yifan Jiang, Xinyu Gong, Junru Wu et al.

Efficient video architecture is the key to deploying video recognition systems on devices with limited computing resources. Unfortunately, existing video architectures are often computationally intensive and not suitable for such applications. The recent X3D work presents a new family of efficient video models by expanding a hand-crafted image architecture along multiple axes, such as space, time, width, and depth. Although operating in a conceptually large space, X3D searches one axis at a time, and merely explored a small set of 30 architectures in total, which does not sufficiently explore the space. This paper bypasses existing 2D architectures, and directly searched for 3D architectures in a fine-grained space, where block type, filter number, expansion ratio and attention block are jointly searched. A probabilistic neural architecture search method is adopted to efficiently search in such a large space. Evaluations on Kinetics and Something-Something-V2 benchmarks confirm our AutoX3D models outperform existing ones in accuracy up to 1.3% under similar FLOPs, and reduce the computational cost up to x1.74 when reaching similar performance.

Han Chen, Yifan Jiang, Hanseok Ko

Due to the fast processing-speed and robustness it can achieve, skeleton-based action recognition has recently received the attention of the computer vision community. The recent Convolutional Neural Network (CNN)-based methods have shown commendable performance in learning spatio-temporal representations for skeleton sequence, which use skeleton image as input to a CNN. Since the CNN-based methods mainly encoding the temporal and skeleton joints simply as rows and columns, respectively, the latent correlation related to all joints may be lost caused by the 2D convolution. To solve this problem, we propose a novel CNN-based method with adversarial training for action recognition. We introduce a two-level domain adversarial learning to align the features of skeleton images from different view angles or subjects, respectively, thus further improve the generalization. We evaluated our proposed method on NTU RGB+D. It achieves competitive results compared with state-of-the-art methods and 2.4$\%$, 1.9$\%$ accuracy gain than the baseline for cross-subject and cross-view.