Vladimir Pavlovic

Seonghyeon Moon, Samuel S. Sohn, Honglu Zhou et al.

FSS(Few-shot segmentation) aims to segment a target class using a small number of labeled images(support set). To extract information relevant to the target class, a dominant approach in best-performing FSS methods removes background features using a support mask. We observe that this feature excision through a limiting support mask introduces an information bottleneck in several challenging FSS cases, e.g., for small targets and/or inaccurate target boundaries. To this end, we present a novel method(MSI), which maximizes the support-set information by exploiting two complementary sources of features to generate super correlation maps. We validate the effectiveness of our approach by instantiating it into three recent and strong FSS methods. Experimental results on several publicly available FSS benchmarks show that our proposed method consistently improves performance by visible margins and leads to faster convergence. Our code and trained models are available at: https://github.com/moonsh/MSI-Maximize-Support-Set-Information

Seonghyeon Moon, Samuel S. Sohn, Honglu Zhou et al.

We study few-shot semantic segmentation that aims to segment a target object from a query image when provided with a few annotated support images of the target class. Several recent methods resort to a feature masking (FM) technique to discard irrelevant feature activations which eventually facilitates the reliable prediction of segmentation mask. A fundamental limitation of FM is the inability to preserve the fine-grained spatial details that affect the accuracy of segmentation mask, especially for small target objects. In this paper, we develop a simple, effective, and efficient approach to enhance feature masking (FM). We dub the enhanced FM as hybrid masking (HM). Specifically, we compensate for the loss of fine-grained spatial details in FM technique by investigating and leveraging a complementary basic input masking method. Experiments have been conducted on three publicly available benchmarks with strong few-shot segmentation (FSS) baselines. We empirically show improved performance against the current state-of-the-art methods by visible margins across different benchmarks. Our code and trained models are available at: https://github.com/moonsh/HM-Hybrid-Masking

Jianfeng Wang, Thomas Lukasiewicz, Daniela Massiceti et al. · oxford

Semi-supervised learning (SSL) has been widely explored in recent years, and it is an effective way of leveraging unlabeled data to reduce the reliance on labeled data. In this work, we adjust neural processes (NPs) to the semi-supervised image classification task, resulting in a new method named NP-Match. NP-Match is suited to this task for two reasons. Firstly, NP-Match implicitly compares data points when making predictions, and as a result, the prediction of each unlabeled data point is affected by the labeled data points that are similar to it, which improves the quality of pseudo-labels. Secondly, NP-Match is able to estimate uncertainty that can be used as a tool for selecting unlabeled samples with reliable pseudo-labels. Compared with uncertainty-based SSL methods implemented with Monte Carlo (MC) dropout, NP-Match estimates uncertainty with much less computational overhead, which can save time at both the training and the testing phases. We conducted extensive experiments on four public datasets, and NP-Match outperforms state-of-the-art (SOTA) results or achieves competitive results on them, which shows the effectiveness of NP-Match and its potential for SSL.

Jianfeng Wang, Daniela Massiceti, Xiaolin Hu et al. · oxford

Semi-supervised semantic segmentation involves assigning pixel-wise labels to unlabeled images at training time. This is useful in a wide range of real-world applications where collecting pixel-wise labels is not feasible in time or cost. Current approaches to semi-supervised semantic segmentation work by predicting pseudo-labels for each pixel from a class-wise probability distribution output by a model. If the predicted probability distribution is incorrect, however, this leads to poor segmentation results, which can have knock-on consequences in safety critical systems, like medical images or self-driving cars. It is, therefore, important to understand what a model does not know, which is mainly achieved by uncertainty quantification. Recently, neural processes (NPs) have been explored in semi-supervised image classification, and they have been a computationally efficient and effective method for uncertainty quantification. In this work, we move one step forward by adapting NPs to semi-supervised semantic segmentation, resulting in a new model called NP-SemiSeg. We experimentally evaluated NP-SemiSeg on the public benchmarks PASCAL VOC 2012 and Cityscapes, with different training settings, and the results verify its effectiveness.

Yuting Wang, Velibor Ilic, Jiatong Li et al.

Object detection (OD), a crucial vision task, remains challenged by the lack of large training datasets with precise object localization labels. In this work, we propose ALWOD, a new framework that addresses this problem by fusing active learning (AL) with weakly and semi-supervised object detection paradigms. Because the performance of AL critically depends on the model initialization, we propose a new auxiliary image generator strategy that utilizes an extremely small labeled set, coupled with a large weakly tagged set of images, as a warm-start for AL. We then propose a new AL acquisition function, another critical factor in AL success, that leverages the student-teacher OD pair disagreement and uncertainty to effectively propose the most informative images to annotate. Finally, to complete the AL loop, we introduce a new labeling task delegated to human annotators, based on selection and correction of model-proposed detections, which is both rapid and effective in labeling the informative images. We demonstrate, across several challenging benchmarks, that ALWOD significantly narrows the gap between the ODs trained on few partially labeled but strategically selected image instances and those that rely on the fully-labeled data. Our code is publicly available on https://github.com/seqam-lab/ALWOD.

Pritish Sahu, Kalliopi Basioti, Vladimir Pavlovic

We present a novel computational model, "SAViR-T", for the family of visual reasoning problems embodied in the Raven's Progressive Matrices (RPM). Our model considers explicit spatial semantics of visual elements within each image in the puzzle, encoded as spatio-visual tokens, and learns the intra-image as well as the inter-image token dependencies, highly relevant for the visual reasoning task. Token-wise relationship, modeled through a transformer-based SAViR-T architecture, extract group (row or column) driven representations by leveraging the group-rule coherence and use this as the inductive bias to extract the underlying rule representations in the top two row (or column) per token in the RPM. We use this relation representations to locate the correct choice image that completes the last row or column for the RPM. Extensive experiments across both synthetic RPM benchmarks, including RAVEN, I-RAVEN, RAVEN-FAIR, and PGM, and the natural image-based "V-PROM" demonstrate that SAViR-T sets a new state-of-the-art for visual reasoning, exceeding prior models' performance by a considerable margin.

Kalliopi Basioti, Mohamed A. Abdelsalam, Federico Fancellu et al.

Controllable Image Captioning (CIC) aims at generating natural language descriptions for an image, conditioned on information provided by end users, e.g., regions, entities or events of interest. However, available image-language datasets mainly contain captions that describe the entirety of an image, making them ineffective for training CIC models that can potentially attend to any subset of regions or relationships. To tackle this challenge, we propose a novel, fully automatic method to sample additional focused and visually grounded captions using a unified structured semantic representation built on top of the existing set of captions associated with an image. We leverage Abstract Meaning Representation (AMR), a cross-lingual graph-based semantic formalism, to encode all possible spatio-semantic relations between entities, beyond the typical spatial-relations-only focus of current methods. We use this Structured Semantic Augmentation (SSA) framework to augment existing image-caption datasets with the grounded controlled captions, increasing their spatial and semantic diversity and focal coverage. We then develop a new model, CIC-BART-SSA, specifically tailored for the CIC task, that sources its control signals from SSA-diversified datasets. We empirically show that, compared to SOTA CIC models, CIC-BART-SSA generates captions that are superior in diversity and text quality, are competitive in controllability, and, importantly, minimize the gap between broad and highly focused controlled captioning performance by efficiently generalizing to the challenging highly focused scenarios. Code is available at https://github.com/SamsungLabs/CIC-BART-SSA.

Che-Jui Chang, Danrui Li, Deep Patel et al.

The study of complex human interactions and group activities has become a focal point in human-centric computer vision. However, progress in related tasks is often hindered by the challenges of obtaining large-scale labeled datasets from real-world scenarios. To address the limitation, we introduce M3Act, a synthetic data generator for multi-view multi-group multi-person human atomic actions and group activities. Powered by Unity Engine, M3Act features multiple semantic groups, highly diverse and photorealistic images, and a comprehensive set of annotations, which facilitates the learning of human-centered tasks across single-person, multi-person, and multi-group conditions. We demonstrate the advantages of M3Act across three core experiments. The results suggest our synthetic dataset can significantly improve the performance of several downstream methods and replace real-world datasets to reduce cost. Notably, M3Act improves the state-of-the-art MOTRv2 on DanceTrack dataset, leading to a hop on the leaderboard from 10th to 2nd place. Moreover, M3Act opens new research for controllable 3D group activity generation. We define multiple metrics and propose a competitive baseline for the novel task. Our code and data are available at our project page: http://cjerry1243.github.io/M3Act.

Mohamed Ashraf Abdelsalam, Zhan Shi, Federico Fancellu et al.

The success of scene graphs for visual scene understanding has brought attention to the benefits of abstracting a visual input (e.g., image) into a structured representation, where entities (people and objects) are nodes connected by edges specifying their relations. Building these representations, however, requires expensive manual annotation in the form of images paired with their scene graphs or frames. These formalisms remain limited in the nature of entities and relations they can capture. In this paper, we propose to leverage a widely-used meaning representation in the field of natural language processing, the Abstract Meaning Representation (AMR), to address these shortcomings. Compared to scene graphs, which largely emphasize spatial relationships, our visual AMR graphs are more linguistically informed, with a focus on higher-level semantic concepts extrapolated from visual input. Moreover, they allow us to generate meta-AMR graphs to unify information contained in multiple image descriptions under one representation. Through extensive experimentation and analysis, we demonstrate that we can re-purpose an existing text-to-AMR parser to parse images into AMRs. Our findings point to important future research directions for improved scene understanding.

Yuting Wang, Ricardo Guerrero, Vladimir Pavlovic

Weakly-supervised object detection (WSOD) models attempt to leverage image-level annotations in lieu of accurate but costly-to-obtain object localization labels. This oftentimes leads to substandard object detection and localization at inference time. To tackle this issue, we propose D2DF2WOD, a Dual-Domain Fully-to-Weakly Supervised Object Detection framework that leverages synthetic data, annotated with precise object localization, to supplement a natural image target domain, where only image-level labels are available. In its warm-up domain adaptation stage, the model learns a fully-supervised object detector (FSOD) to improve the precision of the object proposals in the target domain, and at the same time learns target-domain-specific and detection-aware proposal features. In its main WSOD stage, a WSOD model is specifically tuned to the target domain. The feature extractor and the object proposal generator of the WSOD model are built upon the fine-tuned FSOD model. We test D2DF2WOD on five dual-domain image benchmarks. The results show that our method results in consistently improved object detection and localization compared with state-of-the-art methods.

Tunyu Zhang, Xinxi Zhang, Ligong Han et al.

Diffusion large language models (DLLMs) have the potential to enable fast text generation by decoding multiple tokens in parallel. However, in practice, their inference efficiency is constrained by the need for many refinement steps, while aggressively reducing the number of steps leads to a substantial degradation in generation quality. To alleviate this, we propose a trajectory self-distillation framework that improves few-step decoding by distilling the model's own generative trajectories. We incorporate Direct Discriminative Optimization (DDO), a reverse-KL objective that promotes mode-seeking distillation and encourages the student to concentrate on high-probability teacher modes. Across benchmarks, our approach consistently outperforms strong few-step baselines and standard training under tight step budgets. Although full-step decoding remains superior, we substantially narrow the gap, establishing a strong foundation towards practical few-step DLLMs. The source code is available at https://github.com/Tyrion58/T3D.

Gang Qiao, Kaidong Hu, Seonghyeon Moon et al.

Learning-based approaches to modeling crowd motion have become increasingly successful but require training and evaluation on large datasets, coupled with complex model selection and parameter tuning. To circumvent this tremendously time-consuming process, we propose a novel scoring method, which characterizes generalization of models trained on source crowd scenarios and applied to target crowd scenarios using a training-free, model-agnostic Interaction + Diversity Quantification score, ISDQ. The Interaction component aims to characterize the difficulty of scenario domains, while the diversity of a scenario domain is captured in the Diversity score. Both scores can be computed in a computation tractable manner. Our experimental results validate the efficacy of the proposed method on several simulated and real-world (source,target) generalization tasks, demonstrating its potential to select optimal domain pairs before training and testing a model.

Liwei Che, Zhiyu Xue, Yihao Quan et al.

Counting serves as a simple but powerful test of a Large Vision-Language Model's (LVLM's) reasoning; it forces the model to identify each individual object and then add them all up. In this study, we investigate how LVLMs implement counting using controlled synthetic and real-world benchmarks, combined with mechanistic analyses. Our results show that LVLMs display a human-like counting behavior, with precise performance on small numerosities and noisy estimation for larger quantities. We introduce two novel interpretability methods, Visual Activation Patching and HeadLens, and use them to uncover a structured "counting circuit" that is largely shared across a variety of visual reasoning tasks. Building on these insights, we propose a lightweight intervention strategy that exploits simple and abundantly available synthetic images to fine-tune arbitrary pretrained LVLMs exclusively on counting. Despite the narrow scope of this fine-tuning, the intervention not only enhances counting accuracy on in-distribution synthetic data, but also yields an average improvement of +8.36% on out-of-distribution counting benchmarks and an average gain of +1.54% on complex, general visual reasoning tasks for Qwen2.5-VL. These findings highlight the central, influential role of counting in visual reasoning and suggest a potential pathway for improving overall visual reasoning capabilities through targeted enhancement of counting mechanisms.

Minghao Guo, Qingyue Jiao, Zeru Shi et al.

Long-term agent memory is increasingly multimodal, yet existing evaluations rarely test whether agents preserve the visual evidence needed for later reasoning. In prior work, many visually grounded questions can be answered using only captions or textual traces, allowing answers to be inferred without preserving the fine-grained visual evidence. Meanwhile, harder cases that require reasoning over changing visual states are largely absent. Therefore, we introduce MemEye, a framework that evaluates memory capabilities from two dimensions: one measures the granularity of decisive visual evidence (from scene-level to pixel-level evidence), and the other measures how retrieved evidence must be used (from single evidence to evolutionary synthesis). Under this framework, we construct a new benchmark across 8 life-scenario tasks, with ablation-driven validation gates for assessing answerability, shortcut resistance, visual necessity, and reasoning structure. By evaluating 13 memory methods across 4 VLM backbones, we show that current architectures still struggle to preserve fine-grained visual details and reason about state changes over time. Our findings show that long-term multimodal memory depends on evidence routing, temporal tracking, and detail extraction.

Issam H. Laradji, Mark Schmidt, Vladimir Pavlovic et al.

Deep Gaussian processes (DGP) have appealing Bayesian properties, can handle variable-sized data, and learn deep features. Their limitation is that they do not scale well with the size of the data. Existing approaches address this using a deep random feature (DRF) expansion model, which makes inference tractable by approximating DGPs. However, DRF is not suitable for variable-sized input data such as trees, graphs, and sequences. We introduce the GP-DRF, a novel Bayesian model with an input layer of GPs, followed by DRF layers. The key advantage is that the combination of GP and DRF leads to a tractable model that can both handle a variable-sized input as well as learn deep long-range dependency structures of the data. We provide a novel efficient method to simultaneously infer the posterior of GP's latent vectors and infer the posterior of DRF's internal weights and random frequencies. Our experiments show that GP-DRF outperforms the standard GP model and DRF model across many datasets. Furthermore, they demonstrate that GP-DRF enables improved uncertainty quantification compared to GP and DRF alone, with respect to a Bhattacharyya distance assessment. Source code is available at https://github.com/IssamLaradji/GP_DRF.

Alen Mrdovic, Qingze, Liu et al.

Diffusion models for multi-agent trajectory prediction are limited by iterative denoising, which causes inference latency that hinders their use in time-critical settings like autonomous driving. Fast-sampling variants using DDIM and informed initial noise distributions partially alleviate this issue, but they either fail to achieve true single-step generation or are constrained by the chosen noise distribution. Consistency Models (CMs) offer high-quality one-step generation by mapping noise directly to data, but are difficult to train from scratch . We propose ECTraj, an enhanced CM pipeline with improved training and conditional generation for trajectory prediction. Our framework extends the student-teacher consistency training scheme: the student produces standard outputs, while the teacher explicitly fuses its predictions with parts of the ground truth to give stronger supervision. We also exploit CMs' direct denoising for top-K multi-shot generation during training. Combining conditional generation with this enhanced consistency objective yields faster inference and improved prediction accuracy, establishing competitive new benchmarks on the large-scale Argoverse 2 dataset.

Jiatong Li, Kalliopi Basioti, Vladimir Pavlovic

A large amount of procedural videos on the web show how to complete various tasks. These tasks can often be accomplished in different ways and step orderings, with some steps able to be performed simultaneously, while others are constrained to be completed in a specific order. Flow graphs can be used to illustrate the step relationships of a task. Current task-based methods try to learn a single flow graph for all available videos of a specific task. The extracted flow graphs tend to be too abstract, failing to capture detailed step descriptions. In this work, our aim is to learn accurate and rich flow graphs by extracting them from a single video. We propose Box2Flow, an instance-based method to predict a step flow graph from a given procedural video. In detail, we extract bounding boxes from videos, predict pairwise edge probabilities between step pairs, and build the flow graph with a spanning tree algorithm. Experiments on MM-ReS and YouCookII show our method can extract flow graphs effectively.

Qingze, Liu, Danrui Li et al.

Accurate prediction of human or vehicle trajectories with good diversity that captures their stochastic nature is an essential task for many applications. However, many trajectory prediction models produce unreasonable trajectory samples that focus on improving diversity or accuracy while neglecting other key requirements, such as collision avoidance with the surrounding environment. In this work, we propose TrajDiffuse, a planning-based trajectory prediction method using a novel guided conditional diffusion model. We form the trajectory prediction problem as a denoising impaint task and design a map-based guidance term for the diffusion process. TrajDiffuse is able to generate trajectory predictions that match or exceed the accuracy and diversity of the SOTA, while adhering almost perfectly to environmental constraints. We demonstrate the utility of our model through experiments on the nuScenes and PFSD datasets and provide an extensive benchmark analysis against the SOTA methods.

Liwei Che, Tony Qingze Liu, Jing Jia et al.

Despite their remarkable potential, Large Vision-Language Models (LVLMs) still face challenges with object hallucination, a problem where their generated outputs mistakenly incorporate objects that do not actually exist. Although most works focus on addressing this issue within the language-model backbone, our work shifts the focus to the image input source, investigating how specific image tokens contribute to hallucinations. Our analysis reveals a striking finding: a small subset of image tokens with high attention scores are the primary drivers of object hallucination. By removing these hallucinatory image tokens (only 1.5% of all image tokens), the issue can be effectively mitigated. This finding holds consistently across different models and datasets. Building on this insight, we introduce EAZY, a novel, training-free method that automatically identifies and Eliminates hAllucinations by Zeroing out hallucinatorY image tokens. We utilize EAZY for unsupervised object hallucination detection, achieving 15% improvement compared to previous methods. Additionally, EAZY demonstrates remarkable effectiveness in mitigating hallucinations while preserving model utility and seamlessly adapting to various LVLM architectures.

Branislava Lalic, Dinh Viet Cuong, Mina Petric et al.

Vector-borne diseases continue to pose a significant health threat globally with more than 3 billion people at risk each year. Despite some limitations, mechanistic dynamic models are a popular approach to representing biological processes using ordinary differential equations where the parameters describe the different development and survival rates. Recent advances in population modelling have seen the combination of these mechanistic models with machine learning. One approach is physics-informed neural networks (PINNs) whereby the machine learning framework embeds physical, biological, or chemical laws into neural networks trained on observed or measured data. This enables forward simulations, predicting system behaviour from given parameters and inputs, and inverse modelling, improving parameterisation of existing parameters and estimating unknown or latent variables. In this paper, we focus on improving the parameterisation of biological processes in mechanistic models using PINNs to determine inverse parameters. In comparing mechanistic and PINN models, our experiments offer important insights into the strengths and weaknesses of both approaches but demonstrated that the PINN approach generally outperforms the dynamic model. For a deeper understanding of the performance of PINN models, a final validation was used to investigate how modifications to PINN architectures affect the performance of the framework. By varying only a single component at a time and keeping all other factors constant, we are able to observe the effect of each change.

Kalliopi Basioti, Pritish Sahu, Qingze Tony Liu et al.

Raven's Progressive Matrices (RPMs) is an established benchmark to examine the ability to perform high-level abstract visual reasoning (AVR). Despite the current success of algorithms that solve this task, humans can generalize beyond a given puzzle and create new puzzles given a set of rules, whereas machines remain locked in solving a fixed puzzle from a curated choice list. We propose Generative Visual Puzzles (GenVP), a framework to model the entire RPM generation process, a substantially more challenging task. Our model's capability spans from generating multiple solutions for one specific problem prompt to creating complete new puzzles out of the desired set of rules. Experiments on five different datasets indicate that GenVP achieves state-of-the-art (SOTA) performance both in puzzle-solving accuracy and out-of-distribution (OOD) generalization in 22 OOD scenarios. Compared to SOTA generative approaches, which struggle to solve RPMs when the feasible solution space increases, GenVP efficiently generalizes to these challenging setups. Moreover, our model demonstrates the ability to produce a wide range of complete RPMs given a set of abstract rules by effectively capturing the relationships between abstract rules and visual object properties.

Che-Jui Chang, Qingze Tony Liu, Honglu Zhou et al.

Recent advances in generative modeling and tokenization have driven significant progress in text-to-motion generation, leading to enhanced quality and realism in generated motions. However, effectively leveraging textual information for conditional motion generation remains an open challenge. We observe that current approaches, primarily relying on fixed-length text embeddings (e.g., CLIP) for global semantic injection, struggle to capture the composite nature of human motion, resulting in suboptimal motion quality and controllability. To address this limitation, we propose the Composite Aware Semantic Injection Mechanism (CASIM), comprising a composite-aware semantic encoder and a text-motion aligner that learns the dynamic correspondence between text and motion tokens. Notably, CASIM is model and representation-agnostic, readily integrating with both autoregressive and diffusion-based methods. Experiments on HumanML3D and KIT benchmarks demonstrate that CASIM consistently improves motion quality, text-motion alignment, and retrieval scores across state-of-the-art methods. Qualitative analyses further highlight the superiority of our composite-aware approach over fixed-length semantic injection, enabling precise motion control from text prompts and stronger generalization to unseen text inputs.

Mihee Lee, Samuel S. Sohn, Seonghyeon Moon et al.

Accurate long-term trajectory prediction in complex scenes, where multiple agents (e.g., pedestrians or vehicles) interact with each other and the environment while attempting to accomplish diverse and often unknown goals, is a challenging stochastic forecasting problem. In this work, we propose MUSE, a new probabilistic modeling framework based on a cascade of Conditional VAEs, which tackles the long-term, uncertain trajectory prediction task using a coarse-to-fine multi-factor forecasting architecture. In its Macro stage, the model learns a joint pixel-space representation of two key factors, the underlying environment and the agent movements, to predict the long and short-term motion goals. Conditioned on them, the Micro stage learns a fine-grained spatio-temporal representation for the prediction of individual agent trajectories. The VAE backbones across the two stages make it possible to naturally account for the joint uncertainty at both levels of granularity. As a result, MUSE offers diverse and simultaneously more accurate predictions compared to the current state-of-the-art. We demonstrate these assertions through a comprehensive set of experiments on nuScenes and SDD benchmarks as well as PFSD, a new synthetic dataset, which challenges the forecasting ability of models on complex agent-environment interaction scenarios.

Fangda Han, Guoyao Hao, Ricardo Guerrero et al.

Multi-attribute conditional image generation is a challenging problem in computervision. We propose Multi-attribute Pizza Generator (MPG), a conditional Generative Neural Network (GAN) framework for synthesizing images from a trichotomy of attributes: content, view-geometry, and implicit visual style. We design MPG by extending the state-of-the-art StyleGAN2, using a new conditioning technique that guides the intermediate feature maps to learn multi-scale multi-attribute entangled representationsof controlling attributes. Because of the complex nature of the multi-attribute image generation problem, we regularize the image generation by predicting the explicit conditioning attributes (ingredients and view). To synthesize a pizza image with view attributesoutside the range of natural training images, we design a CGI pizza dataset PizzaView using 3D pizza models and employ it to train a view attribute regressor to regularize the generation process, bridging the real and CGI training datasets. To verify the efficacy of MPG, we test it on Pizza10, a carefully annotated multi-ingredient pizza image dataset. MPG can successfully generate photo-realistic pizza images with desired ingredients and view attributes, beyond the range of those observed in real-world training data.

Pritish Sahu, Kalliopi Basioti, Vladimir Pavlovic

Computational learning approaches to solving visual reasoning tests, such as Raven's Progressive Matrices (RPM), critically depend on the ability to identify the visual concepts used in the test (i.e., the representation) as well as the latent rules based on those concepts (i.e., the reasoning). However, learning of representation and reasoning is a challenging and ill-posed task, often approached in a stage-wise manner (first representation, then reasoning). In this work, we propose an end-to-end joint representation-reasoning learning framework, which leverages a weak form of inductive bias to improve both tasks together. Specifically, we introduce a general generative graphical model for RPMs, GM-RPM, and apply it to solve the reasoning test. We accomplish this using a novel learning framework Disentangling based Abstract Reasoning Network (DAReN) based on the principles of GM-RPM. We perform an empirical evaluation of DAReN over several benchmark datasets. DAReN shows consistent improvement over state-of-the-art (SOTA) models on both the reasoning and the disentanglement tasks. This demonstrates the strong correlation between disentangled latent representation and the ability to solve abstract visual reasoning tasks.

Malihe Alikhani, Fangda Han, Hareesh Ravi et al.

Common image-text joint understanding techniques presume that images and the associated text can universally be characterized by a single implicit model. However, co-occurring images and text can be related in qualitatively different ways, and explicitly modeling it could improve the performance of current joint understanding models. In this paper, we train a Cross-Modal Coherence Modelfor text-to-image retrieval task. Our analysis shows that models trained with image--text coherence relations can retrieve images originally paired with target text more often than coherence-agnostic models. We also show via human evaluation that images retrieved by the proposed coherence-aware model are preferred over a coherence-agnostic baseline by a huge margin. Our findings provide insights into the ways that different modalities communicate and the role of coherence relations in capturing commonsense inferences in text and imagery.

Minyoung Kim, Vladimir Pavlovic

Variational autoencoder (VAE) is a very successful generative model whose key element is the so called amortized inference network, which can perform test time inference using a single feed forward pass. Unfortunately, this comes at the cost of degraded accuracy in posterior approximation, often underperforming the instance-wise variational optimization. Although the latest semi-amortized approaches mitigate the issue by performing a few variational optimization updates starting from the VAE's amortized inference output, they inherently suffer from computational overhead for inference at test time. In this paper, we address the problem in a completely different way by considering a random inference model, where we model the mean and variance functions of the variational posterior as random Gaussian processes (GP). The motivation is that the deviation of the VAE's amortized posterior distribution from the true posterior can be regarded as random noise, which allows us to take into account the uncertainty in posterior approximation in a principled manner. In particular, our model can quantify the difficulty in posterior approximation by a Gaussian variational density. Inference in our GP model is done by a single feed forward pass through the network, significantly faster than semi-amortized methods. We show that our approach attains higher test data likelihood than the state-of-the-arts on several benchmark datasets.

Hai X. Pham, Ricardo Guerrero, Jiatong Li et al.

Despite the abundance of multi-modal data, such as image-text pairs, there has been little effort in understanding the individual entities and their different roles in the construction of these data instances. In this work, we endeavour to discover the entities and their corresponding importance in cooking recipes automaticall} as a visual-linguistic association problem. More specifically, we introduce a novel cross-modal learning framework to jointly model the latent representations of images and text in the food image-recipe association and retrieval tasks. This model allows one to discover complex functional and hierarchical relationships between images and text, and among textual parts of a recipe including title, ingredients and cooking instructions. Our experiments show that by making use of efficient tree-structured Long Short-Term Memory as the text encoder in our computational cross-modal retrieval framework, we are not only able to identify the main ingredients and cooking actions in the recipe descriptions without explicit supervision, but we can also learn more meaningful feature representations of food recipes, appropriate for challenging cross-modal retrieval and recipe adaption tasks.

Mihee Lee, Vladimir Pavlovic

Multi-modal generative models represent an important family of deep models, whose goal is to facilitate representation learning on data with multiple views or modalities. However, current deep multi-modal models focus on the inference of shared representations, while neglecting the important private aspects of data within individual modalities. In this paper, we introduce a disentangled multi-modal variational autoencoder (DMVAE) that utilizes disentangled VAE strategy to separate the private and shared latent spaces of multiple modalities. We specifically consider the instance where the latent factor may be of both continuous and discrete nature, leading to the family of general hybrid DMVAE models. We demonstrate the utility of DMVAE on a semi-supervised learning task, where one of the modalities contains partial data labels, both relevant and irrelevant to the other modality. Our experiments on several benchmarks indicate the importance of the private-shared disentanglement as well as the hybrid latent representation.

Fangda Han, Guoyao Hao, Ricardo Guerrero et al.

Multilabel conditional image generation is a challenging problem in computer vision. In this work we propose Multi-ingredient Pizza Generator (MPG), a conditional Generative Neural Network (GAN) framework for synthesizing multilabel images. We design MPG based on a state-of-the-art GAN structure called StyleGAN2, in which we develop a new conditioning technique by enforcing intermediate feature maps to learn scalewise label information. Because of the complex nature of the multilabel image generation problem, we also regularize synthetic image by predicting the corresponding ingredients as well as encourage the discriminator to distinguish between matched image and mismatched image. To verify the efficacy of MPG, we test it on Pizza10, which is a carefully annotated multi-ingredient pizza image dataset. MPG can successfully generate photo-realist pizza images with desired ingredients. The framework can be easily extend to other multilabel image generation scenarios.

Ricardo Guerrero, Hai Xuan Pham, Vladimir Pavlovic

Computational food analysis (CFA) naturally requires multi-modal evidence of a particular food, e.g., images, recipe text, etc. A key to making CFA possible is multi-modal shared representation learning, which aims to create a joint representation of the multiple views (text and image) of the data. In this work we propose a method for food domain cross-modal shared representation learning that preserves the vast semantic richness present in the food data. Our proposed method employs an effective transformer-based multilingual recipe encoder coupled with a traditional image embedding architecture. Here, we propose the use of imperfect multilingual translations to effectively regularize the model while at the same time adding functionality across multiple languages and alphabets. Experimental analysis on the public Recipe1M dataset shows that the representation learned via the proposed method significantly outperforms the current state-of-the-arts (SOTA) on retrieval tasks. Furthermore, the representational power of the learned representation is demonstrated through a generative food image synthesis model conditioned on recipe embeddings. Synthesized images can effectively reproduce the visual appearance of paired samples, indicating that the learned representation captures the joint semantics of both the textual recipe and its visual content, thus narrowing the modality gap.

Minyoung Kim, Ricardo Guerrero, Vladimir Pavlovic

We deal with the problem of learning the underlying disentangled latent factors that are shared between the paired bi-modal data in cross-modal retrieval. Our assumption is that the data in both modalities are complex, structured, and high dimensional (e.g., image and text), for which the conventional deep auto-encoding latent variable models such as the Variational Autoencoder (VAE) often suffer from difficulty of accurate decoder training or realistic synthesis. A suboptimally trained decoder can potentially harm the model's capability of identifying the true factors. In this paper we propose a novel idea of the implicit decoder, which completely removes the ambient data decoding module from a latent variable model, via implicit encoder inversion that is achieved by Jacobian regularization of the low-dimensional embedding function. Motivated from the recent Identifiable VAE (IVAE) model, we modify it to incorporate the query modality data as conditioning auxiliary input, which allows us to prove that the true parameters of the model can be identified under some regularity conditions. Tested on various datasets where the true factors are fully/partially available, our model is shown to identify the factors accurately, significantly outperforming conventional encoder-decoder latent variable models. We also test our model on the Recipe1M, the large-scale food image/recipe dataset, where the learned factors by our approach highly coincide with the most pronounced food factors that are widely agreed on, including savoriness, wateriness, and greenness.

Minyoung Kim, Vladimir Pavlovic

Inference networks of traditional Variational Autoencoders (VAEs) are typically amortized, resulting in relatively inaccurate posterior approximation compared to instance-wise variational optimization. Recent semi-amortized approaches were proposed to address this drawback; however, their iterative gradient update procedures can be computationally demanding. To address these issues, in this paper we introduce an accurate amortized inference algorithm. We propose a novel recursive mixture estimation algorithm for VAEs that iteratively augments the current mixture with new components so as to maximally reduce the divergence between the variational and the true posteriors. Using the functional gradient approach, we devise an intuitive learning criteria for selecting a new mixture component: the new component has to improve the data likelihood (lower bound) and, at the same time, be as divergent from the current mixture distribution as possible, thus increasing representational diversity. Compared to recently proposed boosted variational inference (BVI), our method relies on amortized inference in contrast to BVI's non-amortized single optimization instance. A crucial benefit of our approach is that the inference at test time requires a single feed-forward pass through the mixture inference network, making it significantly faster than the semi-amortized approaches. We show that our approach yields higher test data likelihood than the state-of-the-art on several benchmark datasets.

Jiatong Li, Fangda Han, Ricardo Guerrero et al.

Increased awareness of the impact of food consumption on health and lifestyle today has given rise to novel data-driven food analysis systems. Although these systems may recognize the ingredients, a detailed analysis of their amounts in the meal, which is paramount for estimating the correct nutrition, is usually ignored. In this paper, we study the novel and challenging problem of predicting the relative amount of each ingredient from a food image. We propose PITA, the Picture-to-Amount deep learning architecture to solve the problem. More specifically, we predict the ingredient amounts using a domain-driven Wasserstein loss from image-to-recipe cross-modal embeddings learned to align the two views of food data. Experiments on a dataset of recipes collected from the Internet show the model generates promising results and improves the baselines on this challenging task. A demo of our system and our data is availableat: foodai.cs.rutgers.edu.

Minyoung Kim, Vladimir Pavlovic

In deep representational learning, it is often desired to isolate a particular factor (termed {\em content}) from other factors (referred to as {\em style}). What constitutes the content is typically specified by users through explicit labels in the data, while all unlabeled/unknown factors are regarded as style. Recently, it has been shown that such content-labeled data can be effectively exploited by modifying the deep latent factor models (e.g., VAE) such that the style and content are well separated in the latent representations. However, the approach assumes that the content factor is categorical-valued (e.g., subject ID in face image data, or digit class in the MNIST dataset). In certain situations, the content is ordinal-valued, that is, the values the content factor takes are {\em ordered} rather than categorical, making content-labeled VAEs, including the latent space they infer, suboptimal. In this paper, we propose a novel extension of VAE that imposes a partially ordered set (poset) structure in the content latent space, while simultaneously making it aligned with the ordinal content values. To this end, instead of the iid Gaussian latent prior adopted in prior approaches, we introduce a conditional Gaussian spacing prior model. This model admits a tractable joint Gaussian prior, but also effectively places negligible density values on the content latent configurations that violate the poset constraint. To evaluate this model, we consider two specific ordinal structured problems: estimating a subject's age in a face image and elucidating the calorie amount in a food meal image. We demonstrate significant improvements in content-style separation over previous non-ordinal approaches.

Fangda Han, Ricardo Guerrero, Vladimir Pavlovic

In this work we propose a new computational framework, based on generative deep models, for synthesis of photo-realistic food meal images from textual list of its ingredients. Previous works on synthesis of images from text typically rely on pre-trained text models to extract text features, followed by generative neural networks (GAN) aimed to generate realistic images conditioned on the text features. These works mainly focus on generating spatially compact and well-defined categories of objects, such as birds or flowers, but meal images are significantly more complex, consisting of multiple ingredients whose appearance and spatial qualities are further modified by cooking methods. To generate real-like meal images from ingredients, we propose Cook Generative Adversarial Networks (CookGAN), CookGAN first builds an attention-based ingredients-image association model, which is then used to condition a generative neural network tasked with synthesizing meal images. Furthermore, a cycle-consistent constraint is added to further improve image quality and control appearance. Experiments show our model is able to generate meal images corresponding to the ingredients.

Samuel S. Sohn, Seonghyeon Moon, Honglu Zhou et al.

Predicting the behavior of crowds in complex environments is a key requirement in a multitude of application areas, including crowd and disaster management, architectural design, and urban planning. Given a crowd's immediate state, current approaches simulate crowd movement to arrive at a future state. However, most applications require the ability to predict hundreds of possible simulation outcomes (e.g., under different environment and crowd situations) at real-time rates, for which these approaches are prohibitively expensive. In this paper, we propose an approach to instantly predict the long-term flow of crowds in arbitrarily large, realistic environments. Central to our approach is a novel CAGE representation consisting of Capacity, Agent, Goal, and Environment-oriented information, which efficiently encodes and decodes crowd scenarios into compact, fixed-size representations that are environmentally lossless. We present a framework to facilitate the accurate and efficient prediction of crowd flow in never-before-seen crowd scenarios. We conduct a series of experiments to evaluate the efficacy of our approach and showcase positive results.

Behnam Gholami, Pritish Sahu, Minyoung Kim et al.

Domain Adaptation (DA), the process of effectively adapting task models learned on one domain, the source, to other related but distinct domains, the targets, with no or minimal retraining, is typically accomplished using the process of source-to-target manifold alignment. However, this process often leads to unsatisfactory adaptation performance, in part because it ignores the task-specific structure of the data. In this paper, we improve the performance of DA by introducing a discriminative discrepancy measure which takes advantage of auxiliary information available in the source and the target domains to better align the source and target distributions. Specifically, we leverage the cohesive clustering structure within individual data manifolds, associated with different tasks, to improve the alignment. This structure is explicit in the source, where the task labels are available, but is implicit in the target, making the problem challenging. We address the challenge by devising a deep DA framework, which combines a new task-driven domain alignment discriminator with domain regularizers that encourage the shared features as task-specific and domain invariant, and prompt the task model to be data structure preserving, guiding its decision boundaries through the low density data regions. We validate our framework on standard benchmarks, including Digits (MNIST, USPS, SVHN, MNIST-M), PACS, and VisDA. Our results show that our proposed model consistently outperforms the state-of-the-art in unsupervised domain adaptation.

Jiatong Li, Ricardo Guerrero, Vladimir Pavlovic

In this paper, we study the novel problem of not only predicting ingredients from a food image, but also predicting the relative amounts of the detected ingredients. We propose two prediction-based models using deep learning that output sparse and dense predictions, coupled with important semi-automatic multi-database integrative data pre-processing, to solve the problem. Experiments on a dataset of recipes collected from the Internet show the models generate encouraging experimental results.

Mihee Lee, Ognjen Rudovic, Vladimir Pavlovic et al.

Detecting facial action units (AU) is one of the fundamental steps in automatic recognition of facial expression of emotions and cognitive states. Though there have been a variety of approaches proposed for this task, most of these models are trained only for the specific target AUs, and as such they fail to easily adapt to the task of recognition of new AUs (i.e., those not initially used to train the target models). In this paper, we propose a deep learning approach for facial AU detection that can easily and in a fast manner adapt to a new AU or target subject by leveraging only a few labeled samples from the new task (either an AU or subject). To this end, we propose a modeling approach based on the notion of the model-agnostic meta-learning, originally proposed for the general image recognition/detection tasks (e.g., the character recognition from the Omniglot dataset). Specifically, each subject and/or AU is treated as a new learning task and the model learns to adapt based on the knowledge of the previous tasks (the AUs and subjects used to pre-train the target models). Thus, given a new subject or AU, this meta-knowledge (that is shared among training and test tasks) is used to adapt the model to the new task using the notion of deep learning and model-agnostic meta-learning. We show on two benchmark datasets (BP4D and DISFA) for facial AU detection that the proposed approach can be easily adapted to new tasks (AUs/subjects). Using only a few labeled examples from these tasks, the model achieves large improvements over the baselines (i.e., non-adapted models).

Minyoung Kim, Yuting Wang, Pritish Sahu et al.

We propose a family of novel hierarchical Bayesian deep auto-encoder models capable of identifying disentangled factors of variability in data. While many recent attempts at factor disentanglement have focused on sophisticated learning objectives within the VAE framework, their choice of a standard normal as the latent factor prior is both suboptimal and detrimental to performance. Our key observation is that the disentangled latent variables responsible for major sources of variability, the relevant factors, can be more appropriately modeled using long-tail distributions. The typical Gaussian priors are, on the other hand, better suited for modeling of nuisance factors. Motivated by this, we extend the VAE to a hierarchical Bayesian model by introducing hyper-priors on the variances of Gaussian latent priors, mimicking an infinite mixture, while maintaining tractable learning and inference of the traditional VAEs. This analysis signifies the importance of partitioning and treating in a different manner the latent dimensions corresponding to relevant factors and nuisances. Our proposed models, dubbed Bayes-Factor-VAEs, are shown to outperform existing methods both quantitatively and qualitatively in terms of latent disentanglement across several challenging benchmark tasks.

Fangda Han, Ricardo Guerrero, Vladimir Pavlovic

In this work we propose a new computational framework, based on generative deep models, for synthesis of photo-realistic food meal images from textual descriptions of its ingredients. Previous works on synthesis of images from text typically rely on pre-trained text models to extract text features, followed by a generative neural networks (GANs) aimed to generate realistic images conditioned on the text features. These works mainly focus on generating spatially compact and well-defined categories of objects, such as birds or flowers. In contrast, meal images are significantly more complex, consisting of multiple ingredients whose appearance and spatial qualities are further modified by cooking methods. We propose a method that first builds an attention-based ingredients-image association model, which is then used to condition a generative neural network tasked with synthesizing meal images. Furthermore, a cycle-consistent constraint is added to further improve image quality and control appearance. Extensive experiments show our model is able to generate meal image corresponding to the ingredients, which could be used to augment existing dataset for solving other computational food analysis problems.

Lu Sheng, Jianfei Cai, Tat-Jen Cham et al.

In this paper, we propose a generative framework that unifies depth-based 3D facial pose tracking and face model adaptation on-the-fly, in the unconstrained scenarios with heavy occlusions and arbitrary facial expression variations. Specifically, we introduce a statistical 3D morphable model that flexibly describes the distribution of points on the surface of the face model, with an efficient switchable online adaptation that gradually captures the identity of the tracked subject and rapidly constructs a suitable face model when the subject changes. Moreover, unlike prior art that employed ICP-based facial pose estimation, to improve robustness to occlusions, we propose a ray visibility constraint that regularizes the pose based on the face model's visibility with respect to the input point cloud. Ablation studies and experimental results on Biwi and ICT-3DHP datasets demonstrate that the proposed framework is effective and outperforms completing state-of-the-art depth-based methods.

Minyoung Kim, Pritish Sahu, Behnam Gholami et al.

In unsupervised domain adaptation, it is widely known that the target domain error can be provably reduced by having a shared input representation that makes the source and target domains indistinguishable from each other. Very recently it has been studied that not just matching the marginal input distributions, but the alignment of output (class) distributions is also critical. The latter can be achieved by minimizing the maximum discrepancy of predictors (classifiers). In this paper, we adopt this principle, but propose a more systematic and effective way to achieve hypothesis consistency via Gaussian processes (GP). The GP allows us to define/induce a hypothesis space of the classifiers from the posterior distribution of the latent random functions, turning the learning into a simple large-margin posterior separation problem, far easier to solve than previous approaches based on adversarial minimax optimization. We formulate a learning objective that effectively pushes the posterior to minimize the maximum discrepancy. This is further shown to be equivalent to maximizing margins and minimizing uncertainty of the class predictions in the target domain, a well-established principle in classical (semi-)supervised learning. Empirical results demonstrate that our approach is comparable or superior to the existing methods on several benchmark domain adaptation datasets.

Minyoung Kim, Yuting Wang, Pritish Sahu et al.

We propose a novel VAE-based deep auto-encoder model that can learn disentangled latent representations in a fully unsupervised manner, endowed with the ability to identify all meaningful sources of variation and their cardinality. Our model, dubbed Relevance-Factor-VAE, leverages the total correlation (TC) in the latent space to achieve the disentanglement goal, but also addresses the key issue of existing approaches which cannot distinguish between meaningful and nuisance factors of latent variation, often the source of considerable degradation in disentanglement performance. We tackle this issue by introducing the so-called relevance indicator variables that can be automatically learned from data, together with the VAE parameters. Our model effectively focuses the TC loss onto the relevant factors only by tolerating large prior KL divergences, a desideratum justified by our semi-parametric theoretical analysis. Using a suite of disentanglement metrics, including a newly proposed one, as well as qualitative evidence, we demonstrate that our model outperforms existing methods across several challenging benchmark datasets.

Behnam Gholami, Pritish Sahu, Ognjen Rudovic et al.

Unsupervised domain adaptation (uDA) models focus on pairwise adaptation settings where there is a single, labeled, source and a single target domain. However, in many real-world settings one seeks to adapt to multiple, but somewhat similar, target domains. Applying pairwise adaptation approaches to this setting may be suboptimal, as they fail to leverage shared information among multiple domains. In this work we propose an information theoretic approach for domain adaptation in the novel context of multiple target domains with unlabeled instances and one source domain with labeled instances. Our model aims to find a shared latent space common to all domains, while simultaneously accounting for the remaining private, domain-specific factors. Disentanglement of shared and private information is accomplished using a unified information-theoretic approach, which also serves to establish a stronger link between the latent representations and the observed data. The resulting model, accompanied by an efficient optimization algorithm, allows simultaneous adaptation from a single source to multiple target domains. We test our approach on three challenging publicly-available datasets, showing that it outperforms several popular domain adaptation methods.

Hai X. Pham, Yuting Wang, Vladimir Pavlovic

This paper presents Generative Adversarial Talking Head (GATH), a novel deep generative neural network that enables fully automatic facial expression synthesis of an arbitrary portrait with continuous action unit (AU) coefficients. Specifically, our model directly manipulates image pixels to make the unseen subject in the still photo express various emotions controlled by values of facial AU coefficients, while maintaining her personal characteristics, such as facial geometry, skin color and hair style, as well as the original surrounding background. In contrast to prior work, GATH is purely data-driven and it requires neither a statistical face model nor image processing tricks to enact facial deformations. Additionally, our model is trained from unpaired data, where the input image, with its auxiliary identity label taken from abundance of still photos in the wild, and the target frame are from different persons. In order to effectively learn such model, we propose a novel weakly supervised adversarial learning framework that consists of a generator, a discriminator, a classifier and an action unit estimator. Our work gives rise to template-and-target-free expression editing, where still faces can be effortlessly animated with arbitrary AU coefficients provided by the user.

Hai X. Pham, Yuting Wang, Vladimir Pavlovic

We present a deep learning framework for real-time speech-driven 3D facial animation from just raw waveforms. Our deep neural network directly maps an input sequence of speech audio to a series of micro facial action unit activations and head rotations to drive a 3D blendshape face model. In particular, our deep model is able to learn the latent representations of time-varying contextual information and affective states within the speech. Hence, our model not only activates appropriate facial action units at inference to depict different utterance generating actions, in the form of lip movements, but also, without any assumption, automatically estimates emotional intensity of the speaker and reproduces her ever-changing affective states by adjusting strength of facial unit activations. For example, in a happy speech, the mouth opens wider than normal, while other facial units are relaxed; or in a surprised state, both eyebrows raise higher. Experiments on a diverse audiovisual corpus of different actors across a wide range of emotional states show interesting and promising results of our approach. Being speaker-independent, our generalized model is readily applicable to various tasks in human-machine interaction and animation.

Cuong D. Tran, Ognjen Rudovic, Vladimir Pavlovic

We study the task of unsupervised domain adaptation, where no labeled data from the target domain is provided during training time. To deal with the potential discrepancy between the source and target distributions, both in features and labels, we exploit a copula-based regression framework. The benefits of this approach are two-fold: (a) it allows us to model a broader range of conditional predictive densities beyond the common exponential family, (b) we show how to leverage Sklar's theorem, the essence of the copula formulation relating the joint density to the copula dependency functions, to find effective feature mappings that mitigate the domain mismatch. By transforming the data to a copula domain, we show on a number of benchmark datasets (including human emotion estimation), and using different regression models for prediction, that we can achieve a more robust and accurate estimation of target labels, compared to recently proposed feature transformation (adaptation) methods.

Robert Walecki, Ognjen, Rudovic et al.

We consider the task of automated estimation of facial expression intensity. This involves estimation of multiple output variables (facial action units --- AUs) that are structurally dependent. Their structure arises from statistically induced co-occurrence patterns of AU intensity levels. Modeling this structure is critical for improving the estimation performance; however, this performance is bounded by the quality of the input features extracted from face images. The goal of this paper is to model these structures and estimate complex feature representations simultaneously by combining conditional random field (CRF) encoded AU dependencies with deep learning. To this end, we propose a novel Copula CNN deep learning approach for modeling multivariate ordinal variables. Our model accounts for $ordinal$ structure in output variables and their $non$-$linear$ dependencies via copula functions modeled as cliques of a CRF. These are jointly optimized with deep CNN feature encoding layers using a newly introduced balanced batch iterative training algorithm. We demonstrate the effectiveness of our approach on the task of AU intensity estimation on two benchmark datasets. We show that joint learning of the deep features and the target output structure results in significant performance gains compared to existing deep structured models for analysis of facial expressions.