Nikos Komodakis

Ioannis Kakogeorgiou, Spyros Gidaris, Bill Psomas et al.

Transformers and masked language modeling are quickly being adopted and explored in computer vision as vision transformers and masked image modeling (MIM). In this work, we argue that image token masking differs from token masking in text, due to the amount and correlation of tokens in an image. In particular, to generate a challenging pretext task for MIM, we advocate a shift from random masking to informed masking. We develop and exhibit this idea in the context of distillation-based MIM, where a teacher transformer encoder generates an attention map, which we use to guide masking for the student. We thus introduce a novel masking strategy, called attention-guided masking (AttMask), and we demonstrate its effectiveness over random masking for dense distillation-based MIM as well as plain distillation-based self-supervised learning on classification tokens. We confirm that AttMask accelerates the learning process and improves the performance on a variety of downstream tasks. We provide the implementation code at https://github.com/gkakogeorgiou/attmask.

Spyros Gidaris, Andrei Bursuc, Oriane Simeoni et al.

Self-supervised learning can be used for mitigating the greedy needs of Vision Transformer networks for very large fully-annotated datasets. Different classes of self-supervised learning offer representations with either good contextual reasoning properties, e.g., using masked image modeling strategies, or invariance to image perturbations, e.g., with contrastive methods. In this work, we propose a single-stage and standalone method, MOCA, which unifies both desired properties using novel mask-and-predict objectives defined with high-level features (instead of pixel-level details). Moreover, we show how to effectively employ both learning paradigms in a synergistic and computation-efficient way. Doing so, we achieve new state-of-the-art results on low-shot settings and strong experimental results in various evaluation protocols with a training that is at least 3 times faster than prior methods. We provide the implementation code at https://github.com/valeoai/MOCA.

Efstathios Karypidis, Spyros Gidaris, Nikos Komodakis

Accurate future video prediction requires both high visual fidelity and consistent scene semantics, particularly in complex dynamic environments such as autonomous driving. We present Re2Pix, a hierarchical video prediction framework that decomposes forecasting into two stages: semantic representation prediction and representation-guided visual synthesis. Instead of directly predicting future RGB frames, our approach first forecasts future scene structure in the feature space of a frozen vision foundation model, and then conditions a latent diffusion model on these predicted representations to render photorealistic frames. This decomposition enables the model to focus first on scene dynamics and then on appearance generation. A key challenge arises from the train-test mismatch between ground-truth representations available during training and predicted ones used at inference. To address this, we introduce two conditioning strategies, nested dropout and mixed supervision, that improve robustness to imperfect autoregressive predictions. Experiments on challenging driving benchmarks demonstrate that the proposed semantics-first design significantly improves temporal semantic consistency, perceptual quality, and training efficiency compared to strong diffusion baselines. We provide the implementation code at https://github.com/Sta8is/Re2Pix

Panagiotis Koletsis, Vasilis Efthymiou, Maria Vakalopoulou et al.

In recent years, significant advances in computer vision have also propelled progress in remote sensing. Concurrently, the use of drones has expanded, with many organizations incorporating them into their operations. Most drones are equipped by default with RGB cameras, which are both robust and among the easiest sensors to use and interpret. The body of literature on optical remote sensing is vast, encompassing diverse tasks, capabilities, and methodologies. Each task or methodology could warrant a dedicated survey. This work provides a comprehensive overview of the capabilities of the field, while also presenting key information, such as datasets and insights. It aims to serve as a guide for researchers entering the field, offering high-level insights and helping them focus on areas most relevant to their interests. To the best of our knowledge, no existing survey addresses this holistic perspective.

Theodoros Kouzelis, Spyros Gidaris, Nikos Komodakis

Joint image-feature generative modeling has recently emerged as an effective strategy for improving diffusion training by coupling low-level VAE latents with high-level semantic features extracted from pre-trained visual encoders. However, existing approaches rely on a fixed representation space, constructed independently of the generative objective and kept unchanged during training. We argue that the representation space guiding diffusion should itself adapt to the generative task. To this end, we propose Coevolving Representation Diffusion (CoReDi), a framework in which the semantic representation space evolves during training by learning a lightweight linear projection jointly with the diffusion model. While naively optimizing this projection leads to degenerate solutions, we show that stable coevolution can be achieved through a combination of stop-gradient targets, normalization, and targeted regularization that prevents feature collapse. This formulation enables the semantic space to progressively specialize to the needs of image synthesis, improving its complementarity with image latents. We apply CoReDi to both VAE latent diffusion and pixel-space diffusion, demonstrating that adaptive semantic representations improve generative modeling across both settings. Experiments show that CoReDi achieves faster convergence and higher sample quality compared to joint diffusion models operating in fixed representation spaces.

Tilemachos Aravanis, Vladan Stojnić, Bill Psomas et al.

Open-vocabulary segmentation (OVS) extends the zero-shot recognition capabilities of vision-language models (VLMs) to pixel-level prediction, enabling segmentation of arbitrary categories specified by text prompts. Despite recent progress, OVS lags behind fully supervised approaches due to two challenges: the coarse image-level supervision used to train VLMs and the semantic ambiguity of natural language. We address these limitations by introducing a few-shot setting that augments textual prompts with a support set of pixel-annotated images. Building on this, we propose a retrieval-augmented test-time adapter that learns a lightweight, per-image classifier by fusing textual and visual support features. Unlike prior methods relying on late, hand-crafted fusion, our approach performs learned, per-query fusion, achieving stronger synergy between modalities. The method supports continually expanding support sets, and applies to fine-grained tasks such as personalized segmentation. Experiments show that we significantly narrow the gap between zero-shot and supervised segmentation while preserving open-vocabulary ability.

Efstathios Karypidis, Ioannis Kakogeorgiou, Spyros Gidaris et al.

Predicting future dynamics is crucial for applications like autonomous driving and robotics, where understanding the environment is key. Existing pixel-level methods are computationally expensive and often focus on irrelevant details. To address these challenges, we introduce DINO-Foresight, a novel framework that operates in the semantic feature space of pretrained Vision Foundation Models (VFMs). Our approach trains a masked feature transformer in a self-supervised manner to predict the evolution of VFM features over time. By forecasting these features, we can apply off-the-shelf, task-specific heads for various scene understanding tasks. In this framework, VFM features are treated as a latent space, to which different heads attach to perform specific tasks for future-frame analysis. Extensive experiments show that our framework outperforms existing methods, demonstrating its robustness and scalability. Additionally, we highlight how intermediate transformer representations in DINO-Foresight improve downstream task performance, offering a promising path for the self-supervised enhancement of VFM features. We provide the implementation code at https://github.com/Sta8is/DINO-Foresight .

Anastasios Gerontopoulos, Spyros Gidaris, Nikos Komodakis

Multi-token prediction has emerged as a promising objective for improving language model pretraining, but its benefits have not consistently generalized to other settings such as fine-tuning. In this paper, we propose MuToR, a simple and effective approach to multi-token prediction that interleaves learnable register tokens into the input sequence, each tasked with predicting future targets. Compared to existing methods, MuToR offers several key advantages: it introduces only a negligible number of additional parameters, requires no architectural changes--ensuring compatibility with off-the-shelf pretrained language models--and remains aligned with the next-token pretraining objective, making it especially well-suited for supervised fine-tuning. Moreover, it naturally supports scalable prediction horizons. We demonstrate the effectiveness and versatility of MuToR across a range of use cases, including supervised fine-tuning, parameter-efficient fine-tuning (PEFT), and pretraining, on challenging generative tasks in both language and vision domains. Our code will be available at: https://github.com/nasosger/MuToR.

Efstathios Karypidis, Ioannis Kakogeorgiou, Spyros Gidaris et al.

Semantic future prediction is important for autonomous systems navigating dynamic environments. This paper introduces FUTURIST, a method for multimodal future semantic prediction that uses a unified and efficient visual sequence transformer architecture. Our approach incorporates a multimodal masked visual modeling objective and a novel masking mechanism designed for multimodal training. This allows the model to effectively integrate visible information from various modalities, improving prediction accuracy. Additionally, we propose a VAE-free hierarchical tokenization process, which reduces computational complexity, streamlines the training pipeline, and enables end-to-end training with high-resolution, multimodal inputs. We validate FUTURIST on the Cityscapes dataset, demonstrating state-of-the-art performance in future semantic segmentation for both short- and mid-term forecasting. We provide the implementation code at https://github.com/Sta8is/FUTURIST .

Dmitriy Shopkhoev, Ammar Ali, Magauiya Zhussip et al.

We introduce ReplaceMe, a generalized training-free depth pruning method that effectively replaces transformer blocks with a linear operation, while maintaining high performance for low compression ratios. In contrast to conventional pruning approaches that require additional training or fine-tuning, our approach requires only a small calibration dataset that is used to estimate a linear transformation, which approximates the pruned blocks. The estimated linear mapping can be seamlessly merged with the remaining transformer blocks, eliminating the need for any additional network parameters. Our experiments show that ReplaceMe consistently outperforms other training-free approaches and remains highly competitive with state-of-the-art pruning methods that involve extensive retraining/fine-tuning and architectural modifications. Applied to several large language models (LLMs), ReplaceMe achieves up to 25% pruning while retaining approximately 90% of the original model's performance on open benchmarks - without any training or healing steps, resulting in minimal computational overhead (see Fig.1). We provide an open-source library implementing ReplaceMe alongside several state-of-the-art depth pruning techniques, available at https://github.com/mts-ai/ReplaceMe.

Bill Psomas, Dionysis Christopoulos, Eirini Baltzi et al.

As fine-tuning becomes increasingly impractical at scale, probing is emerging as the preferred evaluation protocol. Yet, the standard linear probing fails to adequately reflect the potential of models whose pre-training optimizes representations of patch tokens rather than an explicit global representation. This motivates the need for attentive probing, an alternative that uses attention to selectively aggregate patch-level features. Despite its growing adoption, attentive probing remains under-explored, with existing methods suffering from excessive parameterization and poor computational efficiency. In this work, we revisit attentive probing through the lens of the accuracy vs. parameter efficiency trade-off. We present the first comprehensive study of existing methods, analyzing their design choices and benchmarking their performance. Building on this, we propose efficient probing (EP), a simple yet effective multi-query cross-attention mechanism that eliminates redundant projections and reduces the number of trainable parameters. Despite its simplicity, EP outperforms linear probing and prior attentive probing approaches across seven benchmarks, generalizes well to diverse pre-training paradigms, and delivers strong low-shot and layer-wise gains. Beyond evaluation, our analysis uncovers emerging properties of EP, such as complementary attention maps, which open new directions for leveraging probing beyond protocol design. Code available at https://github.com/billpsomas/efficient-probing.

Spyros Gidaris, Andrei Bursuc, Gilles Puy et al.

Learning image representations without human supervision is an important and active research field. Several recent approaches have successfully leveraged the idea of making such a representation invariant under different types of perturbations, especially via contrastive-based instance discrimination training. Although effective visual representations should indeed exhibit such invariances, there are other important characteristics, such as encoding contextual reasoning skills, for which alternative reconstruction-based approaches might be better suited. With this in mind, we propose a teacher-student scheme to learn representations by training a convolutional net to reconstruct a bag-of-visual-words (BoW) representation of an image, given as input a perturbed version of that same image. Our strategy performs an online training of both the teacher network (whose role is to generate the BoW targets) and the student network (whose role is to learn representations), along with an online update of the visual-words vocabulary (used for the BoW targets). This idea effectively enables fully online BoW-guided unsupervised learning. Extensive experiments demonstrate the interest of our BoW-based strategy which surpasses previous state-of-the-art methods (including contrastive-based ones) in several applications. For instance, in downstream tasks such Pascal object detection, Pascal classification and Places205 classification, our method improves over all prior unsupervised approaches, thus establishing new state-of-the-art results that are also significantly better even than those of supervised pre-training. We provide the implementation code at https://github.com/valeoai/obow.

Spyros Gidaris, Nikos Komodakis

Given an initial recognition model already trained on a set of base classes, the goal of this work is to develop a meta-model for few-shot learning. The meta-model, given as input some novel classes with few training examples per class, must properly adapt the existing recognition model into a new model that can correctly classify in a unified way both the novel and the base classes. To accomplish this goal it must learn to output the appropriate classification weight vectors for those two types of classes. To build our meta-model we make use of two main innovations: we propose the use of a Denoising Autoencoder network (DAE) that (during training) takes as input a set of classification weights corrupted with Gaussian noise and learns to reconstruct the target-discriminative classification weights. In this case, the injected noise on the classification weights serves the role of regularizing the weight generating meta-model. Furthermore, in order to capture the co-dependencies between different classes in a given task instance of our meta-model, we propose to implement the DAE model as a Graph Neural Network (GNN). In order to verify the efficacy of our approach, we extensively evaluate it on ImageNet based few-shot benchmarks and we report strong results that surpass prior approaches. The code and models of our paper will be published on: https://github.com/gidariss/wDAE_GNN_FewShot

Xu Shell Hu, Sergey Zagoruyko, Nikos Komodakis

We propose to impose symmetry in neural network parameters to improve parameter usage and make use of dedicated convolution and matrix multiplication routines. Due to significant reduction in the number of parameters as a result of the symmetry constraints, one would expect a dramatic drop in accuracy. Surprisingly, we show that this is not the case, and, depending on network size, symmetry can have little or no negative effect on network accuracy, especially in deep overparameterized networks. We propose several ways to impose local symmetry in recurrent and convolutional neural networks, and show that our symmetry parameterizations satisfy universal approximation property for single hidden layer networks. We extensively evaluate these parameterizations on CIFAR, ImageNet and language modeling datasets, showing significant benefits from the use of symmetry. For instance, our ResNet-101 with channel-wise symmetry has almost 25% less parameters and only 0.2% accuracy loss on ImageNet. Code for our experiments is available at https://github.com/hushell/deep-symmetry

Spyros Gidaris, Nikos Komodakis

The human visual system has the remarkably ability to be able to effortlessly learn novel concepts from only a few examples. Mimicking the same behavior on machine learning vision systems is an interesting and very challenging research problem with many practical advantages on real world vision applications. In this context, the goal of our work is to devise a few-shot visual learning system that during test time it will be able to efficiently learn novel categories from only a few training data while at the same time it will not forget the initial categories on which it was trained (here called base categories). To achieve that goal we propose (a) to extend an object recognition system with an attention based few-shot classification weight generator, and (b) to redesign the classifier of a ConvNet model as the cosine similarity function between feature representations and classification weight vectors. The latter, apart from unifying the recognition of both novel and base categories, it also leads to feature representations that generalize better on "unseen" categories. We extensively evaluate our approach on Mini-ImageNet where we manage to improve the prior state-of-the-art on few-shot recognition (i.e., we achieve 56.20% and 73.00% on the 1-shot and 5-shot settings respectively) while at the same time we do not sacrifice any accuracy on the base categories, which is a characteristic that most prior approaches lack. Finally, we apply our approach on the recently introduced few-shot benchmark of Bharath and Girshick [4] where we also achieve state-of-the-art results. The code and models of our paper will be published on: https://github.com/gidariss/FewShotWithoutForgetting

Spyros Gidaris, Praveer Singh, Nikos Komodakis

Over the last years, deep convolutional neural networks (ConvNets) have transformed the field of computer vision thanks to their unparalleled capacity to learn high level semantic image features. However, in order to successfully learn those features, they usually require massive amounts of manually labeled data, which is both expensive and impractical to scale. Therefore, unsupervised semantic feature learning, i.e., learning without requiring manual annotation effort, is of crucial importance in order to successfully harvest the vast amount of visual data that are available today. In our work we propose to learn image features by training ConvNets to recognize the 2d rotation that is applied to the image that it gets as input. We demonstrate both qualitatively and quantitatively that this apparently simple task actually provides a very powerful supervisory signal for semantic feature learning. We exhaustively evaluate our method in various unsupervised feature learning benchmarks and we exhibit in all of them state-of-the-art performance. Specifically, our results on those benchmarks demonstrate dramatic improvements w.r.t. prior state-of-the-art approaches in unsupervised representation learning and thus significantly close the gap with supervised feature learning. For instance, in PASCAL VOC 2007 detection task our unsupervised pre-trained AlexNet model achieves the state-of-the-art (among unsupervised methods) mAP of 54.4% that is only 2.4 points lower from the supervised case. We get similarly striking results when we transfer our unsupervised learned features on various other tasks, such as ImageNet classification, PASCAL classification, PASCAL segmentation, and CIFAR-10 classification. The code and models of our paper will be published on: https://github.com/gidariss/FeatureLearningRotNet .

Sergey Zagoruyko, Nikos Komodakis

Deep neural networks with skip-connections, such as ResNet, show excellent performance in various image classification benchmarks. It is though observed that the initial motivation behind them - training deeper networks - does not actually hold true, and the benefits come from increased capacity, rather than from depth. Motivated by this, and inspired from ResNet, we propose a simple Dirac weight parameterization, which allows us to train very deep plain networks without explicit skip-connections, and achieve nearly the same performance. This parameterization has a minor computational cost at training time and no cost at all at inference, as both Dirac parameterization and batch normalization can be folded into convolutional filters, so that network becomes a simple chain of convolution-ReLU pairs. We are able to match ResNet-1001 accuracy on CIFAR-10 with 28-layer wider plain DiracNet, and closely match ResNets on ImageNet. Our parameterization also mostly eliminates the need of careful initialization in residual and non-residual networks. The code and models for our experiments are available at https://github.com/szagoruyko/diracnets

Martin Simonovsky, Nikos Komodakis

A number of problems can be formulated as prediction on graph-structured data. In this work, we generalize the convolution operator from regular grids to arbitrary graphs while avoiding the spectral domain, which allows us to handle graphs of varying size and connectivity. To move beyond a simple diffusion, filter weights are conditioned on the specific edge labels in the neighborhood of a vertex. Together with the proper choice of graph coarsening, we explore constructing deep neural networks for graph classification. In particular, we demonstrate the generality of our formulation in point cloud classification, where we set the new state of the art, and on a graph classification dataset, where we outperform other deep learning approaches. The source code is available at https://github.com/mys007/ecc

Sergey Zagoruyko, Nikos Komodakis

Attention plays a critical role in human visual experience. Furthermore, it has recently been demonstrated that attention can also play an important role in the context of applying artificial neural networks to a variety of tasks from fields such as computer vision and NLP. In this work we show that, by properly defining attention for convolutional neural networks, we can actually use this type of information in order to significantly improve the performance of a student CNN network by forcing it to mimic the attention maps of a powerful teacher network. To that end, we propose several novel methods of transferring attention, showing consistent improvement across a variety of datasets and convolutional neural network architectures. Code and models for our experiments are available at https://github.com/szagoruyko/attention-transfer

Spyros Gidaris, Nikos Komodakis

The problem of computing category agnostic bounding box proposals is utilized as a core component in many computer vision tasks and thus has lately attracted a lot of attention. In this work we propose a new approach to tackle this problem that is based on an active strategy for generating box proposals that starts from a set of seed boxes, which are uniformly distributed on the image, and then progressively moves its attention on the promising image areas where it is more likely to discover well localized bounding box proposals. We call our approach AttractioNet and a core component of it is a CNN-based category agnostic object location refinement module that is capable of yielding accurate and robust bounding box predictions regardless of the object category. We extensively evaluate our AttractioNet approach on several image datasets (i.e. COCO, PASCAL, ImageNet detection and NYU-Depth V2 datasets) reporting on all of them state-of-the-art results that surpass the previous work in the field by a significant margin and also providing strong empirical evidence that our approach is capable to generalize to unseen categories. Furthermore, we evaluate our AttractioNet proposals in the context of the object detection task using a VGG16-Net based detector and the achieved detection performance on COCO manages to significantly surpass all other VGG16-Net based detectors while even being competitive with a heavily tuned ResNet-101 based detector. Code as well as box proposals computed for several datasets are available at:: https://github.com/gidariss/AttractioNet.

Sergey Zagoruyko, Nikos Komodakis

Deep residual networks were shown to be able to scale up to thousands of layers and still have improving performance. However, each fraction of a percent of improved accuracy costs nearly doubling the number of layers, and so training very deep residual networks has a problem of diminishing feature reuse, which makes these networks very slow to train. To tackle these problems, in this paper we conduct a detailed experimental study on the architecture of ResNet blocks, based on which we propose a novel architecture where we decrease depth and increase width of residual networks. We call the resulting network structures wide residual networks (WRNs) and show that these are far superior over their commonly used thin and very deep counterparts. For example, we demonstrate that even a simple 16-layer-deep wide residual network outperforms in accuracy and efficiency all previous deep residual networks, including thousand-layer-deep networks, achieving new state-of-the-art results on CIFAR, SVHN, COCO, and significant improvements on ImageNet. Our code and models are available at https://github.com/szagoruyko/wide-residual-networks

Theodoros Kouzelis, Ioannis Kakogeorgiou, Spyros Gidaris et al.

Latent generative models have emerged as a leading approach for high-quality image synthesis. These models rely on an autoencoder to compress images into a latent space, followed by a generative model to learn the latent distribution. We identify that existing autoencoders lack equivariance to semantic-preserving transformations like scaling and rotation, resulting in complex latent spaces that hinder generative performance. To address this, we propose EQ-VAE, a simple regularization approach that enforces equivariance in the latent space, reducing its complexity without degrading reconstruction quality. By finetuning pre-trained autoencoders with EQ-VAE, we enhance the performance of several state-of-the-art generative models, including DiT, SiT, REPA and MaskGIT, achieving a 7 speedup on DiT-XL/2 with only five epochs of SD-VAE fine-tuning. EQ-VAE is compatible with both continuous and discrete autoencoders, thus offering a versatile enhancement for a wide range of latent generative models. Project page and code: https://eq-vae.github.io/.

Theodoros Kouzelis, Efstathios Karypidis, Ioannis Kakogeorgiou et al.

Latent diffusion models (LDMs) dominate high-quality image generation, yet integrating representation learning with generative modeling remains a challenge. We introduce a novel generative image modeling framework that seamlessly bridges this gap by leveraging a diffusion model to jointly model low-level image latents (from a variational autoencoder) and high-level semantic features (from a pretrained self-supervised encoder like DINO). Our latent-semantic diffusion approach learns to generate coherent image-feature pairs from pure noise, significantly enhancing both generative quality and training efficiency, all while requiring only minimal modifications to standard Diffusion Transformer architectures. By eliminating the need for complex distillation objectives, our unified design simplifies training and unlocks a powerful new inference strategy: Representation Guidance, which leverages learned semantics to steer and refine image generation. Evaluated in both conditional and unconditional settings, our method delivers substantial improvements in image quality and training convergence speed, establishing a new direction for representation-aware generative modeling. Project page and code: https://representationdiffusion.github.io

Marius Schmidt-Mengin, Alexis Benichoux, Shibeshih Belachew et al.

Annotating lots of 3D medical images for training segmentation models is time-consuming. The goal of weakly supervised semantic segmentation is to train segmentation models without using any ground truth segmentation masks. Our work addresses the case where only image-level categorical labels, indicating the presence or absence of a particular region of interest (such as tumours or lesions), are available. Most existing methods rely on class activation mapping (CAM). We propose a novel approach, ToNNO, which is based on the Tomographic reconstruction of a Neural Network's Output. Our technique extracts stacks of slices with different angles from the input 3D volume, feeds these slices to a 2D encoder, and applies the inverse Radon transform in order to reconstruct a 3D heatmap of the encoder's predictions. This generic method allows to perform dense prediction tasks on 3D volumes using any 2D image encoder. We apply it to weakly supervised medical image segmentation by training the 2D encoder to output high values for slices containing the regions of interest. We test it on four large scale medical image datasets and outperform 2D CAM methods. We then extend ToNNO by combining tomographic reconstruction with CAM methods, proposing Averaged CAM and Tomographic CAM, which obtain even better results.

Spyros Gidaris, Andrei Bursuc, Nikos Komodakis et al.

Self-supervised representation learning targets to learn convnet-based image representations from unlabeled data. Inspired by the success of NLP methods in this area, in this work we propose a self-supervised approach based on spatially dense image descriptions that encode discrete visual concepts, here called visual words. To build such discrete representations, we quantize the feature maps of a first pre-trained self-supervised convnet, over a k-means based vocabulary. Then, as a self-supervised task, we train another convnet to predict the histogram of visual words of an image (i.e., its Bag-of-Words representation) given as input a perturbed version of that image. The proposed task forces the convnet to learn perturbation-invariant and context-aware image features, useful for downstream image understanding tasks. We extensively evaluate our method and demonstrate very strong empirical results, e.g., our pre-trained self-supervised representations transfer better on detection task and similarly on classification over classes "unseen" during pre-training, when compared to the supervised case. This also shows that the process of image discretization into visual words can provide the basis for very powerful self-supervised approaches in the image domain, thus allowing further connections to be made to related methods from the NLP domain that have been extremely successful so far.

Himalaya Jain, Spyros Gidaris, Nikos Komodakis et al.

Knowledge distillation refers to the process of training a compact student network to achieve better accuracy by learning from a high capacity teacher network. Most of the existing knowledge distillation methods direct the student to follow the teacher by matching the teacher's output, feature maps or their distribution. In this work, we propose a novel way to achieve this goal: by distilling the knowledge through a quantized space. According to our method, the teacher's feature maps are quantized to represent the main visual concepts encompassed in the feature maps. The student is then asked to predict the quantized representation, which thus forms the task that the student uses to learn from the teacher. Despite its simplicity, we show that our approach is able to yield results that improve the state of the art on knowledge distillation. To that end, we provide an extensive evaluation across several network architectures and most commonly used benchmark datasets.

Aakanksha Rana, Praveer Singh, Giuseppe Valenzise et al.

A computationally fast tone mapping operator (TMO) that can quickly adapt to a wide spectrum of high dynamic range (HDR) content is quintessential for visualization on varied low dynamic range (LDR) output devices such as movie screens or standard displays. Existing TMOs can successfully tone-map only a limited number of HDR content and require an extensive parameter tuning to yield the best subjective-quality tone-mapped output. In this paper, we address this problem by proposing a fast, parameter-free and scene-adaptable deep tone mapping operator (DeepTMO) that yields a high-resolution and high-subjective quality tone mapped output. Based on conditional generative adversarial network (cGAN), DeepTMO not only learns to adapt to vast scenic-content (e.g., outdoor, indoor, human, structures, etc.) but also tackles the HDR related scene-specific challenges such as contrast and brightness, while preserving the fine-grained details. We explore 4 possible combinations of Generator-Discriminator architectural designs to specifically address some prominent issues in HDR related deep-learning frameworks like blurring, tiling patterns and saturation artifacts. By exploring different influences of scales, loss-functions and normalization layers under a cGAN setting, we conclude with adopting a multi-scale model for our task. To further leverage on the large-scale availability of unlabeled HDR data, we train our network by generating targets using an objective HDR quality metric, namely Tone Mapping Image Quality Index (TMQI). We demonstrate results both quantitatively and qualitatively, and showcase that our DeepTMO generates high-resolution, high-quality output images over a large spectrum of real-world scenes. Finally, we evaluate the perceived quality of our results by conducting a pair-wise subjective study which confirms the versatility of our method.

Spyros Gidaris, Andrei Bursuc, Nikos Komodakis et al.

Few-shot learning and self-supervised learning address different facets of the same problem: how to train a model with little or no labeled data. Few-shot learning aims for optimization methods and models that can learn efficiently to recognize patterns in the low data regime. Self-supervised learning focuses instead on unlabeled data and looks into it for the supervisory signal to feed high capacity deep neural networks. In this work we exploit the complementarity of these two domains and propose an approach for improving few-shot learning through self-supervision. We use self-supervision as an auxiliary task in a few-shot learning pipeline, enabling feature extractors to learn richer and more transferable visual representations while still using few annotated samples. Through self-supervision, our approach can be naturally extended towards using diverse unlabeled data from other datasets in the few-shot setting. We report consistent improvements across an array of architectures, datasets and self-supervision techniques.

Edouard Oyallon, Sergey Zagoruyko, Gabriel Huang et al.

Scattering networks are a class of designed Convolutional Neural Networks (CNNs) with fixed weights. We argue they can serve as generic representations for modelling images. In particular, by working in scattering space, we achieve competitive results both for supervised and unsupervised learning tasks, while making progress towards constructing more interpretable CNNs. For supervised learning, we demonstrate that the early layers of CNNs do not necessarily need to be learned, and can be replaced with a scattering network instead. Indeed, using hybrid architectures, we achieve the best results with predefined representations to-date, while being competitive with end-to-end learned CNNs. Specifically, even applying a shallow cascade of small-windowed scattering coefficients followed by 1$\times$1-convolutions results in AlexNet accuracy on the ILSVRC2012 classification task. Moreover, by combining scattering networks with deep residual networks, we achieve a single-crop top-5 error of 11.4% on ILSVRC2012. Also, we show they can yield excellent performance in the small sample regime on CIFAR-10 and STL-10 datasets, exceeding their end-to-end counterparts, through their ability to incorporate geometrical priors. For unsupervised learning, scattering coefficients can be a competitive representation that permits image recovery. We use this fact to train hybrid GANs to generate images. Finally, we empirically analyze several properties related to stability and reconstruction of images from scattering coefficients.

Martin Simonovsky, Nikos Komodakis

Deep learning on graphs has become a popular research topic with many applications. However, past work has concentrated on learning graph embedding tasks, which is in contrast with advances in generative models for images and text. Is it possible to transfer this progress to the domain of graphs? We propose to sidestep hurdles associated with linearization of such discrete structures by having a decoder output a probabilistic fully-connected graph of a predefined maximum size directly at once. Our method is formulated as a variational autoencoder. We evaluate on the challenging task of molecule generation.

Hariprasad Kannan, Nikos Komodakis, Nikos Paragios

Linear programming relaxations are central to {\sc map} inference in discrete Markov Random Fields. The ability to properly solve the Lagrangian dual is a critical component of such methods. In this paper, we study the benefit of using Newton-type methods to solve the Lagrangian dual of a smooth version of the problem. We investigate their ability to achieve superior convergence behavior and to better handle the ill-conditioned nature of the formulation, as compared to first order methods. We show that it is indeed possible to efficiently apply a trust region Newton method for a broad range of {\sc map} inference problems. In this paper we propose a provably convergent and efficient framework that includes (i) excellent compromise between computational complexity and precision concerning the Hessian matrix construction, (ii) a damping strategy that aids efficient optimization, (iii) a truncation strategy coupled with a generic pre-conditioner for Conjugate Gradients, (iv) efficient sum-product computation for sparse clique potentials. Results for higher-order Markov Random Fields demonstrate the potential of this approach.

Diego Marcos, Michele Volpi, Nikos Komodakis et al.

In many computer vision tasks, we expect a particular behavior of the output with respect to rotations of the input image. If this relationship is explicitly encoded, instead of treated as any other variation, the complexity of the problem is decreased, leading to a reduction in the size of the required model. In this paper, we propose the Rotation Equivariant Vector Field Networks (RotEqNet), a Convolutional Neural Network (CNN) architecture encoding rotation equivariance, invariance and covariance. Each convolutional filter is applied at multiple orientations and returns a vector field representing magnitude and angle of the highest scoring orientation at every spatial location. We develop a modified convolution operator relying on this representation to obtain deep architectures. We test RotEqNet on several problems requiring different responses with respect to the inputs' rotation: image classification, biomedical image segmentation, orientation estimation and patch matching. In all cases, we show that RotEqNet offers extremely compact models in terms of number of parameters and provides results in line to those of networks orders of magnitude larger.

Spyros Gidaris, Nikos Komodakis

Pixel wise image labeling is an interesting and challenging problem with great significance in the computer vision community. In order for a dense labeling algorithm to be able to achieve accurate and precise results, it has to consider the dependencies that exist in the joint space of both the input and the output variables. An implicit approach for modeling those dependencies is by training a deep neural network that, given as input an initial estimate of the output labels and the input image, it will be able to predict a new refined estimate for the labels. In this context, our work is concerned with what is the optimal architecture for performing the label improvement task. We argue that the prior approaches of either directly predicting new label estimates or predicting residual corrections w.r.t. the initial labels with feed-forward deep network architectures are sub-optimal. Instead, we propose a generic architecture that decomposes the label improvement task to three steps: 1) detecting the initial label estimates that are incorrect, 2) replacing the incorrect labels with new ones, and finally 3) refining the renewed labels by predicting residual corrections w.r.t. them. Furthermore, we explore and compare various other alternative architectures that consist of the aforementioned Detection, Replace, and Refine components. We extensively evaluate the examined architectures in the challenging task of dense disparity estimation (stereo matching) and we report both quantitative and qualitative results on three different datasets. Finally, our dense disparity estimation network that implements the proposed generic architecture, achieves state-of-the-art results in the KITTI 2015 test surpassing prior approaches by a significant margin.

Martin Simonovsky, Benjamín Gutiérrez-Becker, Diana Mateus et al.

Multimodal registration is a challenging problem in medical imaging due the high variability of tissue appearance under different imaging modalities. The crucial component here is the choice of the right similarity measure. We make a step towards a general learning-based solution that can be adapted to specific situations and present a metric based on a convolutional neural network. Our network can be trained from scratch even from a few aligned image pairs. The metric is validated on intersubject deformable registration on a dataset different from the one used for training, demonstrating good generalization. In this task, we outperform mutual information by a significant margin.

Martin Simonovsky, Nikos Komodakis

The focus of our work is speeding up evaluation of deep neural networks in retrieval scenarios, where conventional architectures may spend too much time on negative examples. We propose to replace a monolithic network with our novel cascade of feature-sharing deep classifiers, called OnionNet, where subsequent stages may add both new layers as well as new feature channels to the previous ones. Importantly, intermediate feature maps are shared among classifiers, preventing them from the necessity of being recomputed. To accomplish this, the model is trained end-to-end in a principled way under a joint loss. We validate our approach in theory and on a synthetic benchmark. As a result demonstrated in three applications (patch matching, object detection, and image retrieval), our cascade can operate significantly faster than both monolithic networks and traditional cascades without sharing at the cost of marginal decrease in precision.

Spyros Gidaris, Nikos Komodakis

We propose a novel object localization methodology with the purpose of boosting the localization accuracy of state-of-the-art object detection systems. Our model, given a search region, aims at returning the bounding box of an object of interest inside this region. To accomplish its goal, it relies on assigning conditional probabilities to each row and column of this region, where these probabilities provide useful information regarding the location of the boundaries of the object inside the search region and allow the accurate inference of the object bounding box under a simple probabilistic framework. For implementing our localization model, we make use of a convolutional neural network architecture that is properly adapted for this task, called LocNet. We show experimentally that LocNet achieves a very significant improvement on the mAP for high IoU thresholds on PASCAL VOC2007 test set and that it can be very easily coupled with recent state-of-the-art object detection systems, helping them to boost their performance. Finally, we demonstrate that our detection approach can achieve high detection accuracy even when it is given as input a set of sliding windows, thus proving that it is independent of box proposal methods.

Spyros Gidaris, Nikos Komodakis

We propose an object detection system that relies on a multi-region deep convolutional neural network (CNN) that also encodes semantic segmentation-aware features. The resulting CNN-based representation aims at capturing a diverse set of discriminative appearance factors and exhibits localization sensitivity that is essential for accurate object localization. We exploit the above properties of our recognition module by integrating it on an iterative localization mechanism that alternates between scoring a box proposal and refining its location with a deep CNN regression model. Thanks to the efficient use of our modules, we detect objects with very high localization accuracy. On the detection challenges of PASCAL VOC2007 and PASCAL VOC2012 we achieve mAP of 78.2% and 73.9% correspondingly, surpassing any other published work by a significant margin.

Sergey Zagoruyko, Nikos Komodakis

In this paper we show how to learn directly from image data (i.e., without resorting to manually-designed features) a general similarity function for comparing image patches, which is a task of fundamental importance for many computer vision problems. To encode such a function, we opt for a CNN-based model that is trained to account for a wide variety of changes in image appearance. To that end, we explore and study multiple neural network architectures, which are specifically adapted to this task. We show that such an approach can significantly outperform the state-of-the-art on several problems and benchmark datasets.

Nikos Komodakis, Jean-Christophe Pesquet

Optimization methods are at the core of many problems in signal/image processing, computer vision, and machine learning. For a long time, it has been recognized that looking at the dual of an optimization problem may drastically simplify its solution. Deriving efficient strategies which jointly brings into play the primal and the dual problems is however a more recent idea which has generated many important new contributions in the last years. These novel developments are grounded on recent advances in convex analysis, discrete optimization, parallel processing, and non-smooth optimization with emphasis on sparsity issues. In this paper, we aim at presenting the principles of primal-dual approaches, while giving an overview of numerical methods which have been proposed in different contexts. We show the benefits which can be drawn from primal-dual algorithms both for solving large-scale convex optimization problems and discrete ones, and we provide various application examples to illustrate their usefulness.

Jörg H. Kappes, Bjoern Andres, Fred A. Hamprecht et al.

Szeliski et al. published an influential study in 2006 on energy minimization methods for Markov Random Fields (MRF). This study provided valuable insights in choosing the best optimization technique for certain classes of problems. While these insights remain generally useful today, the phenomenal success of random field models means that the kinds of inference problems that have to be solved changed significantly. Specifically, the models today often include higher order interactions, flexible connectivity structures, large la\-bel-spaces of different cardinalities, or learned energy tables. To reflect these changes, we provide a modernized and enlarged study. We present an empirical comparison of 32 state-of-the-art optimization techniques on a corpus of 2,453 energy minimization instances from diverse applications in computer vision. To ensure reproducibility, we evaluate all methods in the OpenGM 2 framework and report extensive results regarding runtime and solution quality. Key insights from our study agree with the results of Szeliski et al. for the types of models they studied. However, on new and challenging types of models our findings disagree and suggest that polyhedral methods and integer programming solvers are competitive in terms of runtime and solution quality over a large range of model types.