Search

Current vision models typically maintain a fixed correspondence between their representation structure and image space. Each layer comprises a set of tokens arranged "on-the-grid," which biases patches or tokens to encode information at a specific spatio(-temporal) location. In this work we present Moving Off-the-Grid (MooG), a self-supervised video representation model that offers an alternative approach, allowing tokens to move "off-the-grid" to better enable them to represent scene elements consistently, even as they move across the image plane through time. By using a combination of cross-attention and positional embeddings we disentangle the representation structure and image structure. We find that a simple self-supervised objective--next frame prediction--trained on video data, results in a set of latent tokens which bind to specific scene structures and track them as they move. We demonstrate the usefulness of MooG's learned representation both qualitatively and quantitatively by training readouts on top of the learned representation on a variety of downstream tasks. We show that MooG can provide a strong foundation for different vision tasks when compared to "on-the-grid" baselines., Comment: Accepted to NeurIPS 2024 (spotlight). Project page: https://moog-paper.github.io/

Visual understanding of the world goes beyond the semantics and flat structure of individual images. In this work, we aim to capture both the 3D structure and dynamics of real-world scenes from monocular real-world videos. Our Dynamic Scene Transformer (DyST) model leverages recent work in neural scene representation to learn a latent decomposition of monocular real-world videos into scene content, per-view scene dynamics, and camera pose. This separation is achieved through a novel co-training scheme on monocular videos and our new synthetic dataset DySO. DyST learns tangible latent representations for dynamic scenes that enable view generation with separate control over the camera and the content of the scene., Comment: ICLR 2024 spotlight. Project website: https://dyst-paper.github.io/

Recent progress in 3D scene understanding enables scalable learning of representations across large datasets of diverse scenes. As a consequence, generalization to unseen scenes and objects, rendering novel views from just a single or a handful of input images, and controllable scene generation that supports editing, is now possible. However, training jointly on a large number of scenes typically compromises rendering quality when compared to single-scene optimized models such as NeRFs. In this paper, we leverage recent progress in diffusion models to equip 3D scene representation learning models with the ability to render high-fidelity novel views, while retaining benefits such as object-level scene editing to a large degree. In particular, we propose DORSal, which adapts a video diffusion architecture for 3D scene generation conditioned on frozen object-centric slot-based representations of scenes. On both complex synthetic multi-object scenes and on the real-world large-scale Street View dataset, we show that DORSal enables scalable neural rendering of 3D scenes with object-level editing and improves upon existing approaches., Comment: Accepted to ICLR 2024. Project page: https://www.sjoerdvansteenkiste.com/dorsal

Self-supervised methods for learning object-centric representations have recently been applied successfully to various datasets. This progress is largely fueled by slot-based methods, whose ability to cluster visual scenes into meaningful objects holds great promise for compositional generalization and downstream learning. In these methods, the number of slots (clusters) $K$ is typically chosen to match the number of ground-truth objects in the data, even though this quantity is unknown in real-world settings. Indeed, the sensitivity of slot-based methods to $K$, and how this affects their learned correspondence to objects in the data has largely been ignored in the literature. In this work, we address this issue through a systematic study of slot-based methods. We propose using analogs to precision and recall based on the Adjusted Rand Index to accurately quantify model behavior over a large range of $K$. We find that, especially during training, incorrect choices of $K$ do not yield the desired object decomposition and, in fact, cause substantial oversegmentation or merging of separate objects (undersegmentation). We demonstrate that the choice of the objective function and incorporating instance-level annotations can moderately mitigate this behavior while still falling short of fully resolving this issue. Indeed, we show how this issue persists across multiple methods and datasets and stress its importance for future slot-based models.

The Scene Representation Transformer (SRT) is a recent method to render novel views at interactive rates. Since SRT uses camera poses with respect to an arbitrarily chosen reference camera, it is not invariant to the order of the input views. As a result, SRT is not directly applicable to large-scale scenes where the reference frame would need to be changed regularly. In this work, we propose Relative Pose Attention SRT (RePAST): Instead of fixing a reference frame at the input, we inject pairwise relative camera pose information directly into the attention mechanism of the Transformers. This leads to a model that is by definition invariant to the choice of any global reference frame, while still retaining the full capabilities of the original method. Empirical results show that adding this invariance to the model does not lead to a loss in quality. We believe that this is a step towards applying fully latent transformer-based rendering methods to large-scale scenes.

Robust, real-time perception of 3D world is essential to the autonomous vehicle. We introduce an end-to-end surround camera perception system, named NVAutoNet, for self-driving. NVAutoNet is a multi-task, multi-camera network which takes a variable set of time-synced camera images as input and produces a rich collection of 3D signals such as sizes, orientations, locations of obstacles, parking spaces and free-spaces, etc. NVAutoNet is modular and end-to-end: 1) the outputs can be consumed directly by downstream modules without any post-processing such as clustering and fusion -- improving speed of model deployment and in-car testing 2) the whole network training is done in one single stage -- improving speed of model improvement and iterations. The network is carefully designed to have high accuracy while running at 53 fps on NVIDIA Orin SoC (system-on-a-chip). The network is robust to sensor mounting variations (within some tolerances) and can be quickly customized for different vehicle types via efficient model fine-tuning.

Large language models excel at a wide range of complex tasks. However, enabling general inference in the real world, e.g., for robotics problems, raises the challenge of grounding. We propose embodied language models to directly incorporate real-world continuous sensor modalities into language models and thereby establish the link between words and percepts. Input to our embodied language model are multi-modal sentences that interleave visual, continuous state estimation, and textual input encodings. We train these encodings end-to-end, in conjunction with a pre-trained large language model, for multiple embodied tasks including sequential robotic manipulation planning, visual question answering, and captioning. Our evaluations show that PaLM-E, a single large embodied multimodal model, can address a variety of embodied reasoning tasks, from a variety of observation modalities, on multiple embodiments, and further, exhibits positive transfer: the model benefits from diverse joint training across internet-scale language, vision, and visual-language domains. Our largest model, PaLM-E-562B with 562B parameters, in addition to being trained on robotics tasks, is a visual-language generalist with state-of-the-art performance on OK-VQA, and retains generalist language capabilities with increasing scale.

Automatically discovering composable abstractions from raw perceptual data is a long-standing challenge in machine learning. Recent slot-based neural networks that learn about objects in a self-supervised manner have made exciting progress in this direction. However, they typically fall short at adequately capturing spatial symmetries present in the visual world, which leads to sample inefficiency, such as when entangling object appearance and pose. In this paper, we present a simple yet highly effective method for incorporating spatial symmetries via slot-centric reference frames. We incorporate equivariance to per-object pose transformations into the attention and generation mechanism of Slot Attention by translating, scaling, and rotating position encodings. These changes result in little computational overhead, are easy to implement, and can result in large gains in terms of data efficiency and overall improvements to object discovery. We evaluate our method on a wide range of synthetic object discovery benchmarks namely CLEVR, Tetrominoes, CLEVRTex, Objects Room and MultiShapeNet, and show promising improvements on the challenging real-world Waymo Open dataset., Comment: Accepted at ICML 2023. Project page: https://invariantsa.github.io/

Inferring the structure of 3D scenes from 2D observations is a fundamental challenge in computer vision. Recently popularized approaches based on neural scene representations have achieved tremendous impact and have been applied across a variety of applications. One of the major remaining challenges in this space is training a single model which can provide latent representations which effectively generalize beyond a single scene. Scene Representation Transformer (SRT) has shown promise in this direction, but scaling it to a larger set of diverse scenes is challenging and necessitates accurately posed ground truth data. To address this problem, we propose RUST (Really Unposed Scene representation Transformer), a pose-free approach to novel view synthesis trained on RGB images alone. Our main insight is that one can train a Pose Encoder that peeks at the target image and learns a latent pose embedding which is used by the decoder for view synthesis. We perform an empirical investigation into the learned latent pose structure and show that it allows meaningful test-time camera transformations and accurate explicit pose readouts. Perhaps surprisingly, RUST achieves similar quality as methods which have access to perfect camera pose, thereby unlocking the potential for large-scale training of amortized neural scene representations., Comment: CVPR 2023 Highlight. Project website: https://rust-paper.github.io/

A compositional understanding of the world in terms of objects and their geometry in 3D space is considered a cornerstone of human cognition. Facilitating the learning of such a representation in neural networks holds promise for substantially improving labeled data efficiency. As a key step in this direction, we make progress on the problem of learning 3D-consistent decompositions of complex scenes into individual objects in an unsupervised fashion. We introduce Object Scene Representation Transformer (OSRT), a 3D-centric model in which individual object representations naturally emerge through novel view synthesis. OSRT scales to significantly more complex scenes with larger diversity of objects and backgrounds than existing methods. At the same time, it is multiple orders of magnitude faster at compositional rendering thanks to its light field parametrization and the novel Slot Mixer decoder. We believe this work will not only accelerate future architecture exploration and scaling efforts, but it will also serve as a useful tool for both object-centric as well as neural scene representation learning communities., Comment: Accepted at NeurIPS '22. Project page: https://osrt-paper.github.io/

Current visual detectors, though impressive within their training distribution, often fail to parse out-of-distribution scenes into their constituent entities. Recent test-time adaptation methods use auxiliary self-supervised losses to adapt the network parameters to each test example independently and have shown promising results towards generalization outside the training distribution for the task of image classification. In our work, we find evidence that these losses are insufficient for the task of scene decomposition, without also considering architectural inductive biases. Recent slot-centric generative models attempt to decompose scenes into entities in a self-supervised manner by reconstructing pixels. Drawing upon these two lines of work, we propose Slot-TTA, a semi-supervised slot-centric scene decomposition model that at test time is adapted per scene through gradient descent on reconstruction or cross-view synthesis objectives. We evaluate Slot-TTA across multiple input modalities, images or 3D point clouds, and show substantial out-of-distribution performance improvements against state-of-the-art supervised feed-forward detectors, and alternative test-time adaptation methods., Comment: Accepted at ICML 2023. Project website at https://slot-tta.github.io/

Data is the driving force of machine learning, with the amount and quality of training data often being more important for the performance of a system than architecture and training details. But collecting, processing and annotating real data at scale is difficult, expensive, and frequently raises additional privacy, fairness and legal concerns. Synthetic data is a powerful tool with the potential to address these shortcomings: 1) it is cheap 2) supports rich ground-truth annotations 3) offers full control over data and 4) can circumvent or mitigate problems regarding bias, privacy and licensing. Unfortunately, software tools for effective data generation are less mature than those for architecture design and training, which leads to fragmented generation efforts. To address these problems we introduce Kubric, an open-source Python framework that interfaces with PyBullet and Blender to generate photo-realistic scenes, with rich annotations, and seamlessly scales to large jobs distributed over thousands of machines, and generating TBs of data. We demonstrate the effectiveness of Kubric by presenting a series of 13 different generated datasets for tasks ranging from studying 3D NeRF models to optical flow estimation. We release Kubric, the used assets, all of the generation code, as well as the rendered datasets for reuse and modification., Comment: 21 pages, CVPR2022

Neural Radiance Fields (NeRF) have emerged as a powerful representation for the task of novel view synthesis due to their simplicity and state-of-the-art performance. Though NeRF can produce photorealistic renderings of unseen viewpoints when many input views are available, its performance drops significantly when this number is reduced. We observe that the majority of artifacts in sparse input scenarios are caused by errors in the estimated scene geometry, and by divergent behavior at the start of training. We address this by regularizing the geometry and appearance of patches rendered from unobserved viewpoints, and annealing the ray sampling space during training. We additionally use a normalizing flow model to regularize the color of unobserved viewpoints. Our model outperforms not only other methods that optimize over a single scene, but in many cases also conditional models that are extensively pre-trained on large multi-view datasets., Comment: Project page available at https://m-niemeyer.github.io/regnerf/index.html

We present NeSF, a method for producing 3D semantic fields from posed RGB images alone. In place of classical 3D representations, our method builds on recent work in implicit neural scene representations wherein 3D structure is captured by point-wise functions. We leverage this methodology to recover 3D density fields upon which we then train a 3D semantic segmentation model supervised by posed 2D semantic maps. Despite being trained on 2D signals alone, our method is able to generate 3D-consistent semantic maps from novel camera poses and can be queried at arbitrary 3D points. Notably, NeSF is compatible with any method producing a density field, and its accuracy improves as the quality of the density field improves. Our empirical analysis demonstrates comparable quality to competitive 2D and 3D semantic segmentation baselines on complex, realistically rendered synthetic scenes. Our method is the first to offer truly dense 3D scene segmentations requiring only 2D supervision for training, and does not require any semantic input for inference on novel scenes. We encourage the readers to visit the project website., Comment: Project website: https://nesf3d.github.io/. Updated with minor edits to text

A classical problem in computer vision is to infer a 3D scene representation from few images that can be used to render novel views at interactive rates. Previous work focuses on reconstructing pre-defined 3D representations, e.g. textured meshes, or implicit representations, e.g. radiance fields, and often requires input images with precise camera poses and long processing times for each novel scene. In this work, we propose the Scene Representation Transformer (SRT), a method which processes posed or unposed RGB images of a new area, infers a "set-latent scene representation", and synthesises novel views, all in a single feed-forward pass. To calculate the scene representation, we propose a generalization of the Vision Transformer to sets of images, enabling global information integration, and hence 3D reasoning. An efficient decoder transformer parameterizes the light field by attending into the scene representation to render novel views. Learning is supervised end-to-end by minimizing a novel-view reconstruction error. We show that this method outperforms recent baselines in terms of PSNR and speed on synthetic datasets, including a new dataset created for the paper. Further, we demonstrate that SRT scales to support interactive visualization and semantic segmentation of real-world outdoor environments using Street View imagery., Comment: Accepted to CVPR 2022, Project website: https://srt-paper.github.io/

We present a learning-based method for synthesizing novel views of complex scenes using only unstructured collections of in-the-wild photographs. We build on Neural Radiance Fields (NeRF), which uses the weights of a multilayer perceptron to model the density and color of a scene as a function of 3D coordinates. While NeRF works well on images of static subjects captured under controlled settings, it is incapable of modeling many ubiquitous, real-world phenomena in uncontrolled images, such as variable illumination or transient occluders. We introduce a series of extensions to NeRF to address these issues, thereby enabling accurate reconstructions from unstructured image collections taken from the internet. We apply our system, dubbed NeRF-W, to internet photo collections of famous landmarks, and demonstrate temporally consistent novel view renderings that are significantly closer to photorealism than the prior state of the art., Comment: Project website: https://nerf-w.github.io. Ricardo Martin-Brualla, Noha Radwan, and Mehdi S. M. Sajjadi contributed equally to this work. Updated with results for three additional scenes

Variational Autoencoders (VAEs) provide a theoretically-backed and popular framework for deep generative models. However, learning a VAE from data poses still unanswered theoretical questions and considerable practical challenges. In this work, we propose an alternative framework for generative modeling that is simpler, easier to train, and deterministic, yet has many of the advantages of VAEs. We observe that sampling a stochastic encoder in a Gaussian VAE can be interpreted as simply injecting noise into the input of a deterministic decoder. We investigate how substituting this kind of stochasticity, with other explicit and implicit regularization schemes, can lead to an equally smooth and meaningful latent space without forcing it to conform to an arbitrarily chosen prior. To retrieve a generative mechanism to sample new data, we introduce an ex-post density estimation step that can be readily applied also to existing VAEs, improving their sample quality. We show, in a rigorous empirical study, that the proposed regularized deterministic autoencoders are able to generate samples that are comparable to, or better than, those of VAEs and more powerful alternatives when applied to images as well as to structured data such as molecules. \footnote{An implementation is available at: \url{https://github.com/ParthaEth/Regularized_autoencoders-RAE-}}, Comment: Partha Ghosh and Mehdi S. M. Sajjadi contributed equally to this work

With the advent of perceptual loss functions, new possibilities in super-resolution have emerged, and we currently have models that successfully generate near-photorealistic high-resolution images from their low-resolution observations. Up to now, however, such approaches have been exclusively limited to single image super-resolution. The application of perceptual loss functions on video processing still entails several challenges, mostly related to the lack of temporal consistency of the generated images, i.e., flickering artifacts. In this work, we present a novel adversarial recurrent network for video upscaling that is able to produce realistic textures in a temporally consistent way. The proposed architecture naturally leverages information from previous frames due to its recurrent architecture, i.e. the input to the generator is composed of the low-resolution image and, additionally, the warped output of the network at the previous step. Together with a video discriminator, we also propose additional loss functions to further reinforce temporal consistency in the generated sequences. The experimental validation of our algorithm shows the effectiveness of our approach which obtains images with high perceptual quality and improved temporal consistency., Comment: Major revision and improvement of the manuscript: New network architecture, new loss function and extended experiments

Recent advances in generative modeling have led to an increased interest in the study of statistical divergences as means of model comparison. Commonly used evaluation methods, such as the Frechet Inception Distance (FID), correlate well with the perceived quality of samples and are sensitive to mode dropping. However, these metrics are unable to distinguish between different failure cases since they only yield one-dimensional scores. We propose a novel definition of precision and recall for distributions which disentangles the divergence into two separate dimensions. The proposed notion is intuitive, retains desirable properties, and naturally leads to an efficient algorithm that can be used to evaluate generative models. We relate this notion to total variation as well as to recent evaluation metrics such as Inception Score and FID. To demonstrate the practical utility of the proposed approach we perform an empirical study on several variants of Generative Adversarial Networks and Variational Autoencoders. In an extensive set of experiments we show that the proposed metric is able to disentangle the quality of generated samples from the coverage of the target distribution., Comment: NIPS 2018

Generative adversarial networks (GANs) have been shown to produce realistic samples from high-dimensional distributions, but training them is considered hard. A possible explanation for training instabilities is the inherent imbalance between the networks: While the discriminator is trained directly on both real and fake samples, the generator only has control over the fake samples it produces since the real data distribution is fixed by the choice of a given dataset. We propose a simple modification that gives the generator control over the real samples which leads to a tempered learning process for both generator and discriminator. The real data distribution passes through a lens before being revealed to the discriminator, balancing the generator and discriminator by gradually revealing more detailed features necessary to produce high-quality results. The proposed module automatically adjusts the learning process to the current strength of the networks, yet is generic and easy to add to any GAN variant. In a number of experiments, we show that this can improve quality, stability and/or convergence speed across a range of different GAN architectures (DCGAN, LSGAN, WGAN-GP)., Comment: accepted to ICML 2018

Recent advances in video super-resolution have shown that convolutional neural networks combined with motion compensation are able to merge information from multiple low-resolution (LR) frames to generate high-quality images. Current state-of-the-art methods process a batch of LR frames to generate a single high-resolution (HR) frame and run this scheme in a sliding window fashion over the entire video, effectively treating the problem as a large number of separate multi-frame super-resolution tasks. This approach has two main weaknesses: 1) Each input frame is processed and warped multiple times, increasing the computational cost, and 2) each output frame is estimated independently conditioned on the input frames, limiting the system's ability to produce temporally consistent results. In this work, we propose an end-to-end trainable frame-recurrent video super-resolution framework that uses the previously inferred HR estimate to super-resolve the subsequent frame. This naturally encourages temporally consistent results and reduces the computational cost by warping only one image in each step. Furthermore, due to its recurrent nature, the proposed method has the ability to assimilate a large number of previous frames without increased computational demands. Extensive evaluations and comparisons with previous methods validate the strengths of our approach and demonstrate that the proposed framework is able to significantly outperform the current state of the art., Comment: Accepted at CVPR 2018

We present a neighborhood similarity layer (NSL) which induces appearance invariance in a network when used in conjunction with convolutional layers. We are motivated by the observation that, even though convolutional networks have low generalization error, their generalization capability does not extend to samples which are not represented by the training data. For instance, while novel appearances of learned concepts pose no problem for the human visual system, feedforward convolutional networks are generally not successful in such situations. Motivated by the Gestalt principle of grouping with respect to similarity, the proposed NSL transforms its input feature map using the feature vectors at each pixel as a frame of reference, i.e. center of attention, for its surrounding neighborhood. This transformation is spatially varying, hence not a convolution. It is differentiable; therefore, networks including the proposed layer can be trained in an end-to-end manner. We analyze the invariance of NSL to significant changes in appearance that are not represented in the training data. We also demonstrate its advantages for digit recognition, semantic labeling and cell detection problems.

Single image super-resolution is the task of inferring a high-resolution image from a single low-resolution input. Traditionally, the performance of algorithms for this task is measured using pixel-wise reconstruction measures such as peak signal-to-noise ratio (PSNR) which have been shown to correlate poorly with the human perception of image quality. As a result, algorithms minimizing these metrics tend to produce over-smoothed images that lack high-frequency textures and do not look natural despite yielding high PSNR values. We propose a novel application of automated texture synthesis in combination with a perceptual loss focusing on creating realistic textures rather than optimizing for a pixel-accurate reproduction of ground truth images during training. By using feed-forward fully convolutional neural networks in an adversarial training setting, we achieve a significant boost in image quality at high magnification ratios. Extensive experiments on a number of datasets show the effectiveness of our approach, yielding state-of-the-art results in both quantitative and qualitative benchmarks., Comment: main paper and supplementary material

Light field photography captures rich structural information that may facilitate a number of traditional image processing and computer vision tasks. A crucial ingredient in such endeavors is accurate depth recovery. We present a novel framework that allows the recovery of a high quality continuous depth map from light field data. To this end we propose a generative model of a light field that is fully parametrized by its corresponding depth map. The model allows for the integration of powerful regularization techniques such as a non-local means prior, facilitating accurate depth map estimation., Comment: German Conference on Pattern Recognition (GCPR) 2016

Effective convolutional neural networks are trained on large sets of labeled data. However, creating large labeled datasets is a very costly and time-consuming task. Semi-supervised learning uses unlabeled data to train a model with higher accuracy when there is a limited set of labeled data available. In this paper, we consider the problem of semi-supervised learning with convolutional neural networks. Techniques such as randomized data augmentation, dropout and random max-pooling provide better generalization and stability for classifiers that are trained using gradient descent. Multiple passes of an individual sample through the network might lead to different predictions due to the non-deterministic behavior of these techniques. We propose an unsupervised loss function that takes advantage of the stochastic nature of these methods and minimizes the difference between the predictions of multiple passes of a training sample through the network. We evaluate the proposed method on several benchmark datasets., Comment: 9 pages, 2 figures, 5 tables

In this paper we consider the problem of semi-supervised learning with deep Convolutional Neural Networks (ConvNets). Semi-supervised learning is motivated on the observation that unlabeled data is cheap and can be used to improve the accuracy of classifiers. In this paper we propose an unsupervised regularization term that explicitly forces the classifier's prediction for multiple classes to be mutually-exclusive and effectively guides the decision boundary to lie on the low density space between the manifolds corresponding to different classes of data. Our proposed approach is general and can be used with any backpropagation-based learning method. We show through different experiments that our method can improve the object recognition performance of ConvNets using unlabeled data., Comment: 5 pages, 1 figures, ICIP 2016

We introduce a novel unsupervised loss function for learning semantic segmentation with deep convolutional neural nets (ConvNet) when densely labeled training images are not available. More specifically, the proposed loss function penalizes the L1-norm of the gradient of the label probability vector image , i.e. total variation, produced by the ConvNet. This can be seen as a regularization term that promotes piecewise smoothness of the label probability vector image produced by the ConvNet during learning. The unsupervised loss function is combined with a supervised loss in a semi-supervised setting to learn ConvNets that can achieve high semantic segmentation accuracy even when only a tiny percentage of the pixels in the training images are labeled. We demonstrate significant improvements over the purely supervised setting in the Weizmann horse, Stanford background and Sift Flow datasets. Furthermore, we show that using the proposed piecewise smoothness constraint in the learning phase significantly outperforms post-processing results from a purely supervised approach with Markov Random Fields (MRF). Finally, we note that the framework we introduce is general and can be used to learn to label other types of structures such as curvilinear structures by modifying the unsupervised loss function accordingly.

Peer grading is the process of students reviewing each others' work, such as homework submissions, and has lately become a popular mechanism used in massive open online courses (MOOCs). Intrigued by this idea, we used it in a course on algorithms and data structures at the University of Hamburg. Throughout the whole semester, students repeatedly handed in submissions to exercises, which were then evaluated both by teaching assistants and by a peer grading mechanism, yielding a large dataset of teacher and peer grades. We applied different statistical and machine learning methods to aggregate the peer grades in order to come up with accurate final grades for the submissions (supervised and unsupervised, methods based on numeric scores and ordinal rankings). Surprisingly, none of them improves over the baseline of using the mean peer grade as the final grade. We discuss a number of possible explanations for these results and present a thorough analysis of the generated dataset., Comment: Published at the Third Annual ACM Conference on Learning at Scale L@S

Artificial neural networks are powerful pattern classifiers; however, they have been surpassed in accuracy by methods such as support vector machines and random forests that are also easier to use and faster to train. Backpropagation, which is used to train artificial neural networks, suffers from the herd effect problem which leads to long training times and limit classification accuracy. We use the disjunctive normal form and approximate the boolean conjunction operations with products to construct a novel network architecture. The proposed model can be trained by minimizing an error function and it allows an effective and intuitive initialization which solves the herd-effect problem associated with backpropagation. This leads to state-of-the art classification accuracy and fast training times. In addition, our model can be jointly optimized with convolutional features in an unified structure leading to state-of-the-art results on computer vision problems with fast convergence rates. A GPU implementation of LDNN with optional convolutional features is also available