Hakan Bilen

Titas Anciukevičius, Zexiang Xu, Matthew Fisher et al.

Diffusion models currently achieve state-of-the-art performance for both conditional and unconditional image generation. However, so far, image diffusion models do not support tasks required for 3D understanding, such as view-consistent 3D generation or single-view object reconstruction. In this paper, we present RenderDiffusion, the first diffusion model for 3D generation and inference, trained using only monocular 2D supervision. Central to our method is a novel image denoising architecture that generates and renders an intermediate three-dimensional representation of a scene in each denoising step. This enforces a strong inductive structure within the diffusion process, providing a 3D consistent representation while only requiring 2D supervision. The resulting 3D representation can be rendered from any view. We evaluate RenderDiffusion on FFHQ, AFHQ, ShapeNet and CLEVR datasets, showing competitive performance for generation of 3D scenes and inference of 3D scenes from 2D images. Additionally, our diffusion-based approach allows us to use 2D inpainting to edit 3D scenes.

Mustafa Taha Koçyiğit, Timothy M. Hospedales, Hakan Bilen

Recently the focus of the computer vision community has shifted from expensive supervised learning towards self-supervised learning of visual representations. While the performance gap between supervised and self-supervised has been narrowing, the time for training self-supervised deep networks remains an order of magnitude larger than its supervised counterparts, which hinders progress, imposes carbon cost, and limits societal benefits to institutions with substantial resources. Motivated by these issues, this paper investigates reducing the training time of recent self-supervised methods by various model-agnostic strategies that have not been used for this problem. In particular, we study three strategies: an extendable cyclic learning rate schedule, a matching progressive augmentation magnitude and image resolutions schedule, and a hard positive mining strategy based on augmentation difficulty. We show that all three methods combined lead up to 2.7 times speed-up in the training time of several self-supervised methods while retaining comparable performance to the standard self-supervised learning setting.

Yu Yang, Xiaotian Cheng, Chang Liu et al.

In recent years, generative adversarial networks (GANs) have been an actively studied topic and shown to successfully produce high-quality realistic images in various domains. The controllable synthesis ability of GAN generators suggests that they maintain informative, disentangled, and explainable image representations, but leveraging and transferring their representations to downstream tasks is largely unexplored. In this paper, we propose to distill knowledge from GAN generators by squeezing and spanning their representations. We squeeze the generator features into representations that are invariant to semantic-preserving transformations through a network before they are distilled into the student network. We span the distilled representation of the synthetic domain to the real domain by also using real training data to remedy the mode collapse of GANs and boost the student network performance in a real domain. Experiments justify the efficacy of our method and reveal its great significance in self-supervised representation learning. Code is available at https://github.com/yangyu12/squeeze-and-span.

Bo Zhao, Hakan Bilen

Remarkable progress has been achieved in synthesizing photo-realistic images with generative adversarial networks (GANs). Recently, GANs are utilized as the training sample generator when obtaining or storing real training data is expensive even infeasible. However, traditional GANs generated images are not as informative as the real training samples when being used to train deep neural networks. In this paper, we propose a novel method to synthesize Informative Training samples with GAN (IT-GAN). Specifically, we freeze a pre-trained GAN model and learn the informative latent vectors that correspond to informative training samples. The synthesized images are required to preserve information for training deep neural networks rather than visual reality or fidelity. Experiments verify that the deep neural networks can learn faster and achieve better performance when being trained with our IT-GAN generated images. We also show that our method is a promising solution to dataset condensation problem.

Kai Wang, Bo Zhao, Xiangyu Peng et al.

Face recognition, as one of the most successful applications in artificial intelligence, has been widely used in security, administration, advertising, and healthcare. However, the privacy issues of public face datasets have attracted increasing attention in recent years. Previous works simply mask most areas of faces or synthesize samples using generative models to construct privacy-preserving face datasets, which overlooks the trade-off between privacy protection and data utility. In this paper, we propose a novel framework FaceMAE, where the face privacy and recognition performance are considered simultaneously. Firstly, randomly masked face images are used to train the reconstruction module in FaceMAE. We tailor the instance relation matching (IRM) module to minimize the distribution gap between real faces and FaceMAE reconstructed ones. During the deployment phase, we use trained FaceMAE to reconstruct images from masked faces of unseen identities without extra training. The risk of privacy leakage is measured based on face retrieval between reconstructed and original datasets. Experiments prove that the identities of reconstructed images are difficult to be retrieved. We also perform sufficient privacy-preserving face recognition on several public face datasets (i.e. CASIA-WebFace and WebFace260M). Compared to previous state of the arts, FaceMAE consistently \textbf{reduces at least 50\% error rate} on LFW, CFP-FP and AgeDB.

Wei-Hong Li, Steven McDonagh, Ales Leonardis et al.

Deep neural networks have become a standard building block for designing models that can perform multiple dense computer vision tasks such as depth estimation and semantic segmentation thanks to their ability to capture complex correlations in high dimensional feature space across tasks. However, the cross-task correlations that are learned in the unstructured feature space can be extremely noisy and susceptible to overfitting, consequently hurting performance. We propose to address this problem by introducing a structured 3D-aware regularizer which interfaces multiple tasks through the projection of features extracted from an image encoder to a shared 3D feature space and decodes them into their task output space through differentiable rendering. We show that the proposed method is architecture agnostic and can be plugged into various prior multi-task backbones to improve their performance; as we evidence using standard benchmarks NYUv2 and PASCAL-Context.

Wei-Hong Li, Xialei Liu, Hakan Bilen

We propose a unified look at jointly learning multiple vision tasks and visual domains through universal representations, a single deep neural network. Learning multiple problems simultaneously involves minimizing a weighted sum of multiple loss functions with different magnitudes and characteristics and thus results in unbalanced state of one loss dominating the optimization and poor results compared to learning a separate model for each problem. To this end, we propose distilling knowledge of multiple task/domain-specific networks into a single deep neural network after aligning its representations with the task/domain-specific ones through small capacity adapters. We rigorously show that universal representations achieve state-of-the-art performances in learning of multiple dense prediction problems in NYU-v2 and Cityscapes, multiple image classification problems from diverse domains in Visual Decathlon Dataset and cross-domain few-shot learning in MetaDataset. Finally we also conduct multiple analysis through ablation and qualitative studies.

Thibaut Goldsborough, Ben Philps, Alan O'Callaghan et al.

Cell and nucleus segmentation are fundamental tasks for quantitative bioimage analysis. Despite progress in recent years, biologists and other domain experts still require novel algorithms to handle increasingly large and complex real-world datasets. These algorithms must not only achieve state-of-the-art accuracy, but also be optimized for efficiency, portability and user-friendliness. Here, we introduce InstanSeg: a novel embedding-based instance segmentation pipeline designed to identify cells and nuclei in microscopy images. Using six public cell segmentation datasets, we demonstrate that InstanSeg can significantly improve accuracy when compared to the most widely used alternative methods, while reducing the processing time by at least 60%. Furthermore, InstanSeg is designed to be fully serializable as TorchScript and supports GPU acceleration on a range of hardware. We provide an open-source implementation of InstanSeg in Python, in addition to a user-friendly, interactive QuPath extension for inference written in Java. Our code and pre-trained models are available at https://github.com/instanseg/instanseg .

Yu Yang, Xiaotian Cheng, Hakan Bilen et al.

The success of state-of-the-art deep neural networks heavily relies on the presence of large-scale labelled datasets, which are extremely expensive and time-consuming to annotate. This paper focuses on tackling semi-supervised part segmentation tasks by generating high-quality images with a pre-trained GAN and labelling the generated images with an automatic annotator. In particular, we formulate the annotator learning as a learning-to-learn problem. Given a pre-trained GAN, the annotator learns to label object parts in a set of randomly generated images such that a part segmentation model trained on these synthetic images with their predicted labels obtains low segmentation error on a small validation set of manually labelled images. We further reduce this nested-loop optimization problem to a simple gradient matching problem and efficiently solve it with an iterative algorithm. We show that our method can learn annotators from a broad range of labelled images including real images, generated images, and even analytically rendered images. Our method is evaluated with semi-supervised part segmentation tasks and significantly outperforms other semi-supervised competitors when the amount of labelled examples is extremely limited.

Thomas Walker, Octave Mariotti, Amir Vaxman et al.

We introduce Explicit Neural Surfaces (ENS), an efficient smooth surface representation that directly encodes topology with a deformation field from a known base domain. We apply this representation to reconstruct explicit surfaces from multiple views, where we use a series of neural deformation fields to progressively transform the base domain into a target shape. By using meshes as discrete surface proxies, we train the deformation fields through efficient differentiable rasterization. Using a fixed base domain allows us to have Laplace-Beltrami eigenfunctions as an intrinsic positional encoding alongside standard extrinsic Fourier features, with which our approach can capture fine surface details. Compared to implicit surfaces, ENS trains faster and has several orders of magnitude faster inference times. The explicit nature of our approach also allows higher-quality mesh extraction whilst maintaining competitive surface reconstruction performance and real-time capabilities.

Davide Moltisanti, Frank Keller, Hakan Bilen et al.

The goal of this work is to understand the way actions are performed in videos. That is, given a video, we aim to predict an adverb indicating a modification applied to the action (e.g. cut "finely"). We cast this problem as a regression task. We measure textual relationships between verbs and adverbs to generate a regression target representing the action change we aim to learn. We test our approach on a range of datasets and achieve state-of-the-art results on both adverb prediction and antonym classification. Furthermore, we outperform previous work when we lift two commonly assumed conditions: the availability of action labels during testing and the pairing of adverbs as antonyms. Existing datasets for adverb recognition are either noisy, which makes learning difficult, or contain actions whose appearance is not influenced by adverbs, which makes evaluation less reliable. To address this, we collect a new high quality dataset: Adverbs in Recipes (AIR). We focus on instructional recipes videos, curating a set of actions that exhibit meaningful visual changes when performed differently. Videos in AIR are more tightly trimmed and were manually reviewed by multiple annotators to ensure high labelling quality. Results show that models learn better from AIR given its cleaner videos. At the same time, adverb prediction on AIR is challenging, demonstrating that there is considerable room for improvement.

Arushi Goel, Basura Fernando, Frank Keller et al.

Coreference resolution aims to identify words and phrases which refer to same entity in a text, a core task in natural language processing. In this paper, we extend this task to resolving coreferences in long-form narrations of visual scenes. First we introduce a new dataset with annotated coreference chains and their bounding boxes, as most existing image-text datasets only contain short sentences without coreferring expressions or labeled chains. We propose a new technique that learns to identify coreference chains using weak supervision, only from image-text pairs and a regularization using prior linguistic knowledge. Our model yields large performance gains over several strong baselines in resolving coreferences. We also show that coreference resolution helps improving grounding narratives in images.

Octave Mariotti, Oisin Mac Aodha, Hakan Bilen

Understanding the 3D world without supervision is currently a major challenge in computer vision as the annotations required to supervise deep networks for tasks in this domain are expensive to obtain on a large scale. In this paper, we address the problem of unsupervised viewpoint estimation. We formulate this as a self-supervised learning task, where image reconstruction provides the supervision needed to predict the camera viewpoint. Specifically, we make use of pairs of images of the same object at training time, from unknown viewpoints, to self-supervise training by combining the viewpoint information from one image with the appearance information from the other. We demonstrate that using a perspective spatial transformer allows efficient viewpoint learning, outperforming existing unsupervised approaches on synthetic data, and obtains competitive results on the challenging PASCAL3D+ dataset.

Octave Mariotti, Oisin Mac Aodha, Hakan Bilen

We introduce ViewNeRF, a Neural Radiance Field-based viewpoint estimation method that learns to predict category-level viewpoints directly from images during training. While NeRF is usually trained with ground-truth camera poses, multiple extensions have been proposed to reduce the need for this expensive supervision. Nonetheless, most of these methods still struggle in complex settings with large camera movements, and are restricted to single scenes, i.e. they cannot be trained on a collection of scenes depicting the same object category. To address these issues, our method uses an analysis by synthesis approach, combining a conditional NeRF with a viewpoint predictor and a scene encoder in order to produce self-supervised reconstructions for whole object categories. Rather than focusing on high fidelity reconstruction, we target efficient and accurate viewpoint prediction in complex scenarios, e.g. 360° rotation on real data. Our model shows competitive results on synthetic and real datasets, both for single scenes and multi-instance collections.

Shuyang Wu, Yifu Qiu, Ines P. Nearchou et al.

Multiple-instance Learning (MIL) is commonly used to undertake computational pathology (CPath) tasks, and the use of multi-scale patches allows diverse features across scales to be learned. Previous studies using multi-scale features in clinical applications rely on multiple inputs across magnifications with late feature fusion, which does not retain the link between features across scales while the inputs are dependent on arbitrary, manufacturer-defined magnifications, being inflexible and computationally expensive. In this paper, we propose the Multi-scale Pyramidal Network (MSPN), which is plug-and-play over attention-based MIL that introduces progressive multi-scale analysis on WSI. Our MSPN consists of (1) grid-based remapping that uses high magnification features to derive coarse features and (2) the coarse guidance network (CGN) that learns coarse contexts. We benchmark MSPN as an add-on module to 4 attention-based frameworks using 4 clinically relevant tasks across 3 types of foundation model, as well as the pre-trained MIL framework. We show that MSPN consistently improves MIL across the compared configurations and tasks, while being lightweight and easy-to-use.

Zhipeng Du, Duolikun Danier, Jan Eric Lenssen et al.

In this paper, we focus on online zero-shot monocular 3D instance segmentation, a novel practical setting where existing approaches fail to perform because they rely on posed RGB-D sequences. To overcome this limitation, we leverage CUT3R, a recent Reconstructive Foundation Model (RFM), to provide reliable geometric priors from a single RGB stream. We propose MoonSeg3R, which introduces three key components: (1) a self-supervised query refinement module with spatial-semantic distillation that transforms segmentation masks from 2D visual foundation models (VFMs) into discriminative 3D queries; (2) a 3D query index memory that provides temporal consistency by retrieving contextual queries; and (3) a state-distribution token from CUT3R that acts as a mask identity descriptor to strengthen cross-frame fusion. Experiments on ScanNet200 and SceneNN show that MoonSeg3R is the first method to enable online monocular 3D segmentation and achieves performance competitive with state-of-the-art RGB-D-based systems. Code and models will be released.

Samuel Garcin, Thomas Walker, Steven McDonagh et al.

Interactive world models continually generate video by responding to a user's actions, enabling open-ended generation capabilities. However, existing models typically lack a 3D representation of the environment, meaning 3D consistency must be implicitly learned from data, and spatial memory is restricted to limited temporal context windows. This results in an unrealistic user experience and presents significant obstacles to down-stream tasks such as training agents. To address this, we present PERSIST, a new paradigm of world model which simulates the evolution of a latent 3D scene: environment, camera, and renderer. This allows us to synthesize new frames with persistent spatial memory and consistent geometry. Both quantitative metrics and a qualitative user study show substantial improvements in spatial memory, 3D consistency, and long-horizon stability over existing methods, enabling coherent, evolving 3D worlds. We further demonstrate novel capabilities, including synthesising diverse 3D environments from a single image, as well as enabling fine-grained, geometry-aware control over generated experiences by supporting environment editing and specification directly in 3D space. Project page: https://francelico.github.io/persist.github.io

Arushi Goel, Basura Fernando, Frank Keller et al.

In this paper, we study multimodal coreference resolution, specifically where a longer descriptive text, i.e., a narration is paired with an image. This poses significant challenges due to fine-grained image-text alignment, inherent ambiguity present in narrative language, and unavailability of large annotated training sets. To tackle these challenges, we present a data efficient semi-supervised approach that utilizes image-narration pairs to resolve coreferences and narrative grounding in a multimodal context. Our approach incorporates losses for both labeled and unlabeled data within a cross-modal framework. Our evaluation shows that the proposed approach outperforms strong baselines both quantitatively and qualitatively, for the tasks of coreference resolution and narrative grounding.

Kai Wang, Bo Zhao, Xiangyu Peng et al.

Dataset condensation aims at reducing the network training effort through condensing a cumbersome training set into a compact synthetic one. State-of-the-art approaches largely rely on learning the synthetic data by matching the gradients between the real and synthetic data batches. Despite the intuitive motivation and promising results, such gradient-based methods, by nature, easily overfit to a biased set of samples that produce dominant gradients, and thus lack global supervision of data distribution. In this paper, we propose a novel scheme to Condense dataset by Aligning FEatures (CAFE), which explicitly attempts to preserve the real-feature distribution as well as the discriminant power of the resulting synthetic set, lending itself to strong generalization capability to various architectures. At the heart of our approach is an effective strategy to align features from the real and synthetic data across various scales, while accounting for the classification of real samples. Our scheme is further backed up by a novel dynamic bi-level optimization, which adaptively adjusts parameter updates to prevent over-/under-fitting. We validate the proposed CAFE across various datasets, and demonstrate that it generally outperforms the state of the art: on the SVHN dataset, for example, the performance gain is up to 11%. Extensive experiments and analyses verify the effectiveness and necessity of proposed designs.

Yu Cheng, Arushi Goel, Hakan Bilen

Answering complex visual questions like `Which red furniture can be used for sitting?' requires multi-step reasoning, including object recognition, attribute filtering, and relational understanding. Recent work improves interpretability in multimodal large language models (MLLMs) by decomposing tasks into sub-task programs, but these methods are computationally expensive and less accurate due to poor adaptation to target data. To address this, we introduce VISTAR (Visually Interpretable Subtask-Aware Reasoning Model), a subtask-driven training framework that enhances both interpretability and reasoning by generating textual and visual explanations within MLLMs. Instead of relying on external models, VISTAR fine-tunes MLLMs to produce structured Subtask-of-Thought rationales (step-by-step reasoning sequences). Experiments on two benchmarks show that VISTAR consistently improves reasoning accuracy while maintaining interpretability. Our code and dataset will be available at https://github.com/ChengJade/VISTAR.

Wei-Hong Li, Xialei Liu, Hakan Bilen

In this paper, we look at the problem of few-shot classification that aims to learn a classifier for previously unseen classes and domains from few labeled samples. Recent methods use adaptation networks for aligning their features to new domains or select the relevant features from multiple domain-specific feature extractors. In this work, we propose to learn a single set of universal deep representations by distilling knowledge of multiple separately trained networks after co-aligning their features with the help of adapters and centered kernel alignment. We show that the universal representations can be further refined for previously unseen domains by an efficient adaptation step in a similar spirit to distance learning methods. We rigorously evaluate our model in the recent Meta-Dataset benchmark and demonstrate that it significantly outperforms the previous methods while being more efficient. Our code will be available at https://github.com/VICO-UoE/URL.

James Thewlis, Samuel Albanie, Hakan Bilen et al.

Equivariance to random image transformations is an effective method to learn landmarks of object categories, such as the eyes and the nose in faces, without manual supervision. However, this method does not explicitly guarantee that the learned landmarks are consistent with changes between different instances of the same object, such as different facial identities. In this paper, we develop a new perspective on the equivariance approach by noting that dense landmark detectors can be interpreted as local image descriptors equipped with invariance to intra-category variations. We then propose a direct method to enforce such an invariance in the standard equivariant loss. We do so by exchanging descriptor vectors between images of different object instances prior to matching them geometrically. In this manner, the same vectors must work regardless of the specific object identity considered. We use this approach to learn vectors that can simultaneously be interpreted as local descriptors and dense landmarks, combining the advantages of both. Experiments on standard benchmarks show that this approach can match, and in some cases surpass state-of-the-art performance amongst existing methods that learn landmarks without supervision. Code is available at www.robots.ox.ac.uk/~vgg/research/DVE/.

Octave Mariotti, Oisin Mac Aodha, Hakan Bilen

Recent progress in self-supervised representation learning has resulted in models that are capable of extracting image features that are not only effective at encoding image level, but also pixel-level, semantics. These features have been shown to be effective for dense visual semantic correspondence estimation, even outperforming fully-supervised methods. Nevertheless, current self-supervised approaches still fail in the presence of challenging image characteristics such as symmetries and repeated parts. To address these limitations, we propose a new approach for semantic correspondence estimation that supplements discriminative self-supervised features with 3D understanding via a weak geometric spherical prior. Compared to more involved 3D pipelines, our model only requires weak viewpoint information, and the simplicity of our spherical representation enables us to inject informative geometric priors into the model during training. We propose a new evaluation metric that better accounts for repeated part and symmetry-induced mistakes. We present results on the challenging SPair-71k dataset, where we show that our approach demonstrates is capable of distinguishing between symmetric views and repeated parts across many object categories, and also demonstrate that we can generalize to unseen classes on the AwA dataset.

Zekai Li, Xinhao Zhong, Samir Khaki et al.

In recent years, dataset distillation has provided a reliable solution for data compression, where models trained on the resulting smaller synthetic datasets achieve performance comparable to those trained on the original datasets. To further improve the performance of synthetic datasets, various training pipelines and optimization objectives have been proposed, greatly advancing the field of dataset distillation. Recent decoupled dataset distillation methods introduce soft labels and stronger data augmentation during the post-evaluation phase and scale dataset distillation up to larger datasets (e.g., ImageNet-1K). However, this raises a question: Is accuracy still a reliable metric to fairly evaluate dataset distillation methods? Our empirical findings suggest that the performance improvements of these methods often stem from additional techniques rather than the inherent quality of the images themselves, with even randomly sampled images achieving superior results. Such misaligned evaluation settings severely hinder the development of DD. Therefore, we propose DD-Ranking, a unified evaluation framework, along with new general evaluation metrics to uncover the true performance improvements achieved by different methods. By refocusing on the actual information enhancement of distilled datasets, DD-Ranking provides a more comprehensive and fair evaluation standard for future research advancements.

Duolikun Danier, Mehmet Aygün, Changjian Li et al.

Large-scale pre-trained vision models are becoming increasingly prevalent, offering expressive and generalizable visual representations that benefit various downstream tasks. Recent studies on the emergent properties of these models have revealed their high-level geometric understanding, in particular in the context of depth perception. However, it remains unclear how depth perception arises in these models without explicit depth supervision provided during pre-training. To investigate this, we examine whether the monocular depth cues, similar to those used by the human visual system, emerge in these models. We introduce a new benchmark, DepthCues, designed to evaluate depth cue understanding, and present findings across 20 diverse and representative pre-trained vision models. Our analysis shows that human-like depth cues emerge in more recent larger models. We also explore enhancing depth perception in large vision models by fine-tuning on DepthCues, and find that even without dense depth supervision, this improves depth estimation. To support further research, our benchmark and evaluation code will be made publicly available for studying depth perception in vision models.

Octave Mariotti, Zhipeng Du, Yash Bhalgat et al.

Semantic correspondence (SC) aims to establish semantically meaningful matches across different instances of an object category. We illustrate how recent supervised SC methods remain limited in their ability to generalize beyond sparsely annotated training keypoints, effectively acting as keypoint detectors. To address this, we propose a novel approach for learning dense correspondences by lifting 2D keypoints into a canonical 3D space using monocular depth estimation. Our method constructs a continuous canonical manifold that captures object geometry without requiring explicit 3D supervision or camera annotations. Additionally, we introduce SPair-U, an extension of SPair-71k with novel keypoint annotations, to better assess generalization. Experiments not only demonstrate that our model significantly outperforms supervised baselines on unseen keypoints, highlighting its effectiveness in learning robust correspondences, but that unsupervised baselines outperform supervised counterparts when generalized across different datasets.

Thomas Walker, Octave Mariotti, Amir Vaxman et al.

Positional encodings are a common component of neural scene reconstruction methods, and provide a way to bias the learning of neural fields towards coarser or finer representations. Current neural surface reconstruction methods use a "one-size-fits-all" approach to encoding, choosing a fixed set of encoding functions, and therefore bias, across all scenes. Current state-of-the-art surface reconstruction approaches leverage grid-based multi-resolution hash encoding in order to recover high-detail geometry. We propose a learned approach which allows the network to choose its encoding basis as a function of space, by masking the contribution of features stored at separate grid resolutions. The resulting spatially adaptive approach allows the network to fit a wider range of frequencies without introducing noise. We test our approach on standard benchmark surface reconstruction datasets and achieve state-of-the-art performance on two benchmark datasets.

Duolikun Danier, Ge Gao, Steven McDonagh et al.

Video generation models have made significant progress in generating realistic content, enabling applications in simulation, gaming, and film making. However, current generated videos still contain visual artifacts arising from 3D inconsistencies, e.g., objects and structures deforming under changes in camera pose, which can undermine user experience and simulation fidelity. Motivated by recent findings on representation alignment for diffusion models, we hypothesize that improving the multi-view consistency of video diffusion representations will yield more 3D-consistent video generation. Through detailed analysis on multiple recent camera-controlled video diffusion models we reveal strong correlations between 3D-consistent representations and videos. We also propose ViCoDR, a new approach for improving the 3D consistency of video models by learning multi-view consistent diffusion representations. We evaluate ViCoDR on camera controlled image-to-video, text-to-video, and multi-view generation models, demonstrating significant improvements in the 3D consistency of the generated videos. Project page: https://danier97.github.io/ViCoDR.

Jianning Deng, Kartic Subr, Hakan Bilen

We present a novel self-supervised framework for learning articulated object representations from sparse-view, unposed images. Unlike prior methods that require dense multi-view observations and ground-truth camera poses, our approach operates with as few as four views per articulation and no camera supervision. To address the inherent challenges, we first reconstruct each articulation independently using recent advances in sparse-view 3D reconstruction, then learn a deformation field that establishes dense correspondences across poses. A progressive disentanglement strategy further separates static from moving parts, enabling robust separation of camera and object motion. Finally, we jointly optimize geometry, appearance, and kinematics with a self-supervised loss that enforces cross-view and cross-pose consistency. Experiments on the standard benchmark and real-world examples demonstrate that our method produces accurate and detailed articulated object representations under significantly weaker input assumptions than existing approaches.

Jakub Zadrożny, Hakan Bilen

We introduce HumMorph, a novel generalized approach to free-viewpoint rendering of dynamic human bodies with explicit pose control. HumMorph renders a human actor in any specified pose given a few observed views (starting from just one) in arbitrary poses. Our method enables fast inference as it relies only on feed-forward passes through the model. We first construct a coarse representation of the actor in the canonical T-pose, which combines visual features from individual partial observations and fills missing information using learned prior knowledge. The coarse representation is complemented by fine-grained pixel-aligned features extracted directly from the observed views, which provide high-resolution appearance information. We show that HumMorph is competitive with the state-of-the-art when only a single input view is available, however, we achieve results with significantly better visual quality given just 2 monocular observations. Moreover, previous generalized methods assume access to accurate body shape and pose parameters obtained using synchronized multi-camera setups. In contrast, we consider a more practical scenario where these body parameters are noisily estimated directly from the observed views. Our experimental results demonstrate that our architecture is more robust to errors in the noisy parameters and clearly outperforms the state of the art in this setting.

Shuyang Wu, Yifu Qiu, Ines P. Nearchou et al.

Multiple Instance Learning (MIL) for whole slide image (WSI) analysis in computational pathology often neglects instance-level learning as supervision is typically provided only at the bag level, hindering the integrated consideration of instance and bag-level information during the analysis. In this work, we present LadderMIL, a framework designed to improve MIL through two perspectives: (1) employing instance-level supervision and (2) learning inter-instance contextual information at bag level. Firstly, we propose a novel Coarse-to-Fine Self-Distillation (CFSD) paradigm that probes and distils a network trained with bag-level information to adaptively obtain instance-level labels which could effectively provide the instance-level supervision for the same network in a self-improving way. Secondly, to capture inter-instance contextual information in WSI, we propose a Contextual Encoding Generator (CEG), which encodes the contextual appearance of instances within a bag. We also theoretically and empirically prove the instance-level learnability of CFSD. Our LadderMIL is evaluated on multiple clinically relevant benchmarking tasks including breast cancer receptor status classification, multi-class subtype classification, tumour classification, and prognosis prediction. Average improvements of 8.1%, 11% and 2.4% in AUC, F1-score, and C-index, respectively, are demonstrated across the five benchmarks, compared to the best baseline.

Ankan Bhunia, Changjian Li, Hakan Bilen

This paper introduces a novel anomaly detection (AD) problem aimed at identifying `odd-looking' objects within a scene by comparing them to other objects present. Unlike traditional AD benchmarks with fixed anomaly criteria, our task detects anomalies specific to each scene by inferring a reference group of regular objects. To address occlusions, we use multiple views of each scene as input, construct 3D object-centric models for each instance from 2D views, enhancing these models with geometrically consistent part-aware representations. Anomalous objects are then detected through cross-instance comparison. We also introduce two new benchmarks, ToysAD-8K and PartsAD-15K as testbeds for future research in this task. We provide a comprehensive analysis of our method quantitatively and qualitatively on these benchmarks.

Ankan Bhunia, Changjian Li, Hakan Bilen

Automatic anomaly detection based on visual cues holds practical significance in various domains, such as manufacturing and product quality assessment. This paper introduces a new conditional anomaly detection problem, which involves identifying anomalies in a query image by comparing it to a reference shape. To address this challenge, we have created a large dataset, BrokenChairs-180K, consisting of around 180K images, with diverse anomalies, geometries, and textures paired with 8,143 reference 3D shapes. To tackle this task, we have proposed a novel transformer-based approach that explicitly learns the correspondence between the query image and reference 3D shape via feature alignment and leverages a customized attention mechanism for anomaly detection. Our approach has been rigorously evaluated through comprehensive experiments, serving as a benchmark for future research in this domain.

Jianning Deng, Kartic Subr, Hakan Bilen

We propose a novel unsupervised method to learn the pose and part-segmentation of articulated objects with rigid parts. Given two observations of an object in different articulation states, our method learns the geometry and appearance of object parts by using an implicit model from the first observation, distils the part segmentation and articulation from the second observation while rendering the latter observation. Additionally, to tackle the complexities in the joint optimization of part segmentation and articulation, we propose a voxel grid-based initialization strategy and a decoupled optimization procedure. Compared to the prior unsupervised work, our model obtains significantly better performance, and generalizes to objects with multiple parts while it can be efficiently from few views for the latter observation.

Davide Moltisanti, Hakan Bilen, Laura Sevilla-Lara et al.

We focus on the problem of recognising the end state of an action in an image, which is critical for understanding what action is performed and in which manner. We study this focusing on the task of predicting the coarseness of a cut, i.e., deciding whether an object was cut "coarsely" or "finely". No dataset with these annotated end states is available, so we propose an augmentation method to synthesise training data. We apply this method to cutting actions extracted from an existing action recognition dataset. Our method is object agnostic, i.e., it presupposes the location of the object but not its identity. Starting from less than a hundred images of a whole object, we can generate several thousands images simulating visually diverse cuts of different coarseness. We use our synthetic data to train a model based on UNet and test it on real images showing coarsely/finely cut objects. Results demonstrate that the model successfully recognises the end state of the cutting action despite the domain gap between training and testing, and that the model generalises well to unseen objects.

Yunlu Chen, Basura Fernando, Hakan Bilen et al.

In recent years, neural implicit representations have made remarkable progress in modeling of 3D shapes with arbitrary topology. In this work, we address two key limitations of such representations, in failing to capture local 3D geometric fine details, and to learn from and generalize to shapes with unseen 3D transformations. To this end, we introduce a novel family of graph implicit functions with equivariant layers that facilitates modeling fine local details and guaranteed robustness to various groups of geometric transformations, through local $k$-NN graph embeddings with sparse point set observations at multiple resolutions. Our method improves over the existing rotation-equivariant implicit function from 0.69 to 0.89 (IoU) on the ShapeNet reconstruction task. We also show that our equivariant implicit function can be extended to other types of similarity transformations and generalizes to unseen translations and scaling.

Wei-Hong Li, Xialei Liu, Hakan Bilen

Despite the recent advances in multi-task learning of dense prediction problems, most methods rely on expensive labelled datasets. In this paper, we present a label efficient approach and look at jointly learning of multiple dense prediction tasks on partially annotated data (i.e. not all the task labels are available for each image), which we call multi-task partially-supervised learning. We propose a multi-task training procedure that successfully leverages task relations to supervise its multi-task learning when data is partially annotated. In particular, we learn to map each task pair to a joint pairwise task-space which enables sharing information between them in a computationally efficient way through another network conditioned on task pairs, and avoids learning trivial cross-task relations by retaining high-level information about the input image. We rigorously demonstrate that our proposed method effectively exploits the images with unlabelled tasks and outperforms existing semi-supervised learning approaches and related methods on three standard benchmarks.

Arushi Goel, Basura Fernando, Frank Keller et al.

Scene graph generation (SGG) aims to capture a wide variety of interactions between pairs of objects, which is essential for full scene understanding. Existing SGG methods trained on the entire set of relations fail to acquire complex reasoning about visual and textual correlations due to various biases in training data. Learning on trivial relations that indicate generic spatial configuration like 'on' instead of informative relations such as 'parked on' does not enforce this complex reasoning, harming generalization. To address this problem, we propose a novel framework for SGG training that exploits relation labels based on their informativeness. Our model-agnostic training procedure imputes missing informative relations for less informative samples in the training data and trains a SGG model on the imputed labels along with existing annotations. We show that this approach can successfully be used in conjunction with state-of-the-art SGG methods and improves their performance significantly in multiple metrics on the standard Visual Genome benchmark. Furthermore, we obtain considerable improvements for unseen triplets in a more challenging zero-shot setting.

Bo Zhao, Hakan Bilen

Computational cost of training state-of-the-art deep models in many learning problems is rapidly increasing due to more sophisticated models and larger datasets. A recent promising direction for reducing training cost is dataset condensation that aims to replace the original large training set with a significantly smaller learned synthetic set while preserving the original information. While training deep models on the small set of condensed images can be extremely fast, their synthesis remains computationally expensive due to the complex bi-level optimization and second-order derivative computation. In this work, we propose a simple yet effective method that synthesizes condensed images by matching feature distributions of the synthetic and original training images in many sampled embedding spaces. Our method significantly reduces the synthesis cost while achieving comparable or better performance. Thanks to its efficiency, we apply our method to more realistic and larger datasets with sophisticated neural architectures and obtain a significant performance boost. We also show promising practical benefits of our method in continual learning and neural architecture search.

Wei-Hong Li, Xialei Liu, Hakan Bilen

In this paper, we look at the problem of cross-domain few-shot classification that aims to learn a classifier from previously unseen classes and domains with few labeled samples. Recent approaches broadly solve this problem by parameterizing their few-shot classifiers with task-agnostic and task-specific weights where the former is typically learned on a large training set and the latter is dynamically predicted through an auxiliary network conditioned on a small support set. In this work, we focus on the estimation of the latter, and propose to learn task-specific weights from scratch directly on a small support set, in contrast to dynamically estimating them. In particular, through systematic analysis, we show that task-specific weights through parametric adapters in matrix form with residual connections to multiple intermediate layers of a backbone network significantly improves the performance of the state-of-the-art models in the Meta-Dataset benchmark with minor additional cost.

Octave Mariotti, Hakan Bilen

There is a growing interest in developing computer vision methods that can learn from limited supervision. In this paper, we consider the problem of learning to predict camera viewpoints, where obtaining ground-truth annotations are expensive and require special equipment, from a limited number of labeled images. We propose a semi-supervised viewpoint estimation method that can learn to infer viewpoint information from unlabeled image pairs, where two images differ by a viewpoint change. In particular our method learns to synthesize the second image by combining the appearance from the first one and viewpoint from the second one. We demonstrate that our method significantly improves the supervised techniques, especially in the low-label regime and outperforms the state-of-the-art semi-supervised methods.

Yu Yang, Hakan Bilen, Qiran Zou et al.

Deep learning approaches heavily rely on high-quality human supervision which is nonetheless expensive, time-consuming, and error-prone, especially for image segmentation task. In this paper, we propose a method to automatically synthesize paired photo-realistic images and segmentation masks for the use of training a foreground-background segmentation network. In particular, we learn a generative adversarial network that decomposes an image into foreground and background layers, and avoid trivial decompositions by maximizing mutual information between generated images and latent variables. The improved layered GANs can synthesize higher quality datasets from which segmentation networks of higher performance can be learned. Moreover, the segmentation networks are employed to stabilize the training of layered GANs in return, which are further alternately trained with Layered GANs. Experiments on a variety of single-object datasets show that our method achieves competitive generation quality and segmentation performance compared to related methods.

Bo Zhao, Hakan Bilen

In many machine learning problems, large-scale datasets have become the de-facto standard to train state-of-the-art deep networks at the price of heavy computation load. In this paper, we focus on condensing large training sets into significantly smaller synthetic sets which can be used to train deep neural networks from scratch with minimum drop in performance. Inspired from the recent training set synthesis methods, we propose Differentiable Siamese Augmentation that enables effective use of data augmentation to synthesize more informative synthetic images and thus achieves better performance when training networks with augmentations. Experiments on multiple image classification benchmarks demonstrate that the proposed method obtains substantial gains over the state-of-the-art, 7% improvements on CIFAR10 and CIFAR100 datasets. We show with only less than 1% data that our method achieves 99.6%, 94.9%, 88.5%, 71.5% relative performance on MNIST, FashionMNIST, SVHN, CIFAR10 respectively. We also explore the use of our method in continual learning and neural architecture search, and show promising results.

Lucas Deecke, Lukas Ruff, Robert A. Vandermeulen et al.

Deep anomaly detection is a difficult task since, in high dimensions, it is hard to completely characterize a notion of "differentness" when given only examples of normality. In this paper we propose a novel approach to deep anomaly detection based on augmenting large pretrained networks with residual corrections that adjusts them to the task of anomaly detection. Our method gives rise to a highly parameter-efficient learning mechanism, enhances disentanglement of representations in the pretrained model, and outperforms all existing anomaly detection methods including other baselines utilizing pretrained networks. On the CIFAR-10 one-versus-rest benchmark, for example, our technique raises the state of the art from 96.1 to 99.0 mean AUC.

Wei-Hong Li, Hakan Bilen

Multi-task learning (MTL) is to learn one single model that performs multiple tasks for achieving good performance on all tasks and lower cost on computation. Learning such a model requires to jointly optimize losses of a set of tasks with different difficulty levels, magnitudes, and characteristics (e.g. cross-entropy, Euclidean loss), leading to the imbalance problem in multi-task learning. To address the imbalance problem, we propose a knowledge distillation based method in this work. We first learn a task-specific model for each task. We then learn the multi-task model for minimizing task-specific loss and for producing the same feature with task-specific models. As the task-specific network encodes different features, we introduce small task-specific adaptors to project multi-task features to the task-specific features. In this way, the adaptors align the task-specific feature and the multi-task feature, which enables a balanced parameter sharing across tasks. Extensive experimental results demonstrate that our method can optimize a multi-task learning model in a more balanced way and achieve better overall performance.

Bo Zhao, Konda Reddy Mopuri, Hakan Bilen

As the state-of-the-art machine learning methods in many fields rely on larger datasets, storing datasets and training models on them become significantly more expensive. This paper proposes a training set synthesis technique for data-efficient learning, called Dataset Condensation, that learns to condense large dataset into a small set of informative synthetic samples for training deep neural networks from scratch. We formulate this goal as a gradient matching problem between the gradients of deep neural network weights that are trained on the original and our synthetic data. We rigorously evaluate its performance in several computer vision benchmarks and demonstrate that it significantly outperforms the state-of-the-art methods. Finally we explore the use of our method in continual learning and neural architecture search and report promising gains when limited memory and computations are available.

Bo Zhao, Shixiang Tang, Dapeng Chen et al.

With the explosion of digital data in recent years, continuously learning new tasks from a stream of data without forgetting previously acquired knowledge has become increasingly important. In this paper, we propose a new continual learning (CL) setting, namely ``continual representation learning'', which focuses on learning better representation in a continuous way. We also provide two large-scale multi-step benchmarks for biometric identification, where the visual appearance of different classes are highly relevant. In contrast to requiring the model to recognize more learned classes, we aim to learn feature representation that can be better generalized to not only previously unseen images but also unseen classes/identities. For the new setting, we propose a novel approach that performs the knowledge distillation over a large number of identities by applying the neighbourhood selection and consistency relaxation strategies to improve scalability and flexibility of the continual learning model. We demonstrate that existing CL methods can improve the representation in the new setting, and our method achieves better results than the competitors.

Lucas Deecke, Timothy Hospedales, Hakan Bilen

A practical shortcoming of deep neural networks is their specialization to a single task and domain. While recent techniques in domain adaptation and multi-domain learning enable the learning of more domain-agnostic features, their success relies on the presence of domain labels, typically requiring manual annotation and careful curation of datasets. Here we focus on a less explored, but more realistic case: learning from data from multiple domains, without access to domain annotations. In this scenario, standard model training leads to the overfitting of large domains, while disregarding smaller ones. We address this limitation via dynamic residual adapters, an adaptive gating mechanism that helps account for latent domains, coupled with an augmentation strategy inspired by recent style transfer techniques. Our proposed approach is examined on image classification tasks containing multiple latent domains, and we showcase its ability to obtain robust performance across these. Dynamic residual adapters significantly outperform off-the-shelf networks with much larger capacity, and can be incorporated seamlessly with existing architectures in an end-to-end manner.

Bo Zhao, Konda Reddy Mopuri, Hakan Bilen

It is widely believed that sharing gradients will not leak private training data in distributed learning systems such as Collaborative Learning and Federated Learning, etc. Recently, Zhu et al. presented an approach which shows the possibility to obtain private training data from the publicly shared gradients. In their Deep Leakage from Gradient (DLG) method, they synthesize the dummy data and corresponding labels with the supervision of shared gradients. However, DLG has difficulty in convergence and discovering the ground-truth labels consistently. In this paper, we find that sharing gradients definitely leaks the ground-truth labels. We propose a simple but reliable approach to extract accurate data from the gradients. Particularly, our approach can certainly extract the ground-truth labels as opposed to DLG, hence we name it Improved DLG (iDLG). Our approach is valid for any differentiable model trained with cross-entropy loss over one-hot labels. We mathematically illustrate how our method can extract ground-truth labels from the gradients and empirically demonstrate the advantages over DLG.

Wei-Hong Li, Chuan-Sheng Foo, Hakan Bilen

Recent semi-supervised learning methods have shown to achieve comparable results to their supervised counterparts while using only a small portion of labels in image classification tasks thanks to their regularization strategies. In this paper, we take a more direct approach for semi-supervised learning and propose learning to impute the labels of unlabeled samples such that a network achieves better generalization when it is trained on these labels. We pose the problem in a learning-to-learn formulation which can easily be incorporated to the state-of-the-art semi-supervised techniques and boost their performance especially when the labels are limited. We demonstrate that our method is applicable to both classification and regression problems including image classification and facial landmark detection tasks.