Pedro O. Pinheiro

Ewa M. Nowara, Pedro O. Pinheiro, Sai Pooja Mahajan et al.

We present NEBULA, the first latent 3D generative model for scalable generation of large molecular libraries around a seed compound of interest. Such libraries are crucial for scientific discovery, but it remains challenging to generate large numbers of high quality samples efficiently. 3D-voxel-based methods have recently shown great promise for generating high quality samples de novo from random noise (Pinheiro et al., 2023). However, sampling in 3D-voxel space is computationally expensive and use in library generation is prohibitively slow. Here, we instead perform neural empirical Bayes sampling (Saremi & Hyvarinen, 2019) in the learned latent space of a vector-quantized variational autoencoder. NEBULA generates large molecular libraries nearly an order of magnitude faster than existing methods without sacrificing sample quality. Moreover, NEBULA generalizes better to unseen drug-like molecules, as demonstrated on two public datasets and multiple recently released drugs. We expect the approach herein to be highly enabling for machine learning-based drug discovery. The code is available at https://github.com/prescient-design/nebula

Pedro O. Pinheiro, Joshua Rackers, Joseph Kleinhenz et al.

We propose a new score-based approach to generate 3D molecules represented as atomic densities on regular grids. First, we train a denoising neural network that learns to map from a smooth distribution of noisy molecules to the distribution of real molecules. Then, we follow the neural empirical Bayes framework (Saremi and Hyvarinen, 19) and generate molecules in two steps: (i) sample noisy density grids from a smooth distribution via underdamped Langevin Markov chain Monte Carlo, and (ii) recover the "clean" molecule by denoising the noisy grid with a single step. Our method, VoxMol, generates molecules in a fundamentally different way than the current state of the art (ie, diffusion models applied to atom point clouds). It differs in terms of the data representation, the noise model, the network architecture and the generative modeling algorithm. Our experiments show that VoxMol captures the distribution of drug-like molecules better than state of the art, while being faster to generate samples.

Pedro O. Pinheiro, Arian Jamasb, Omar Mahmood et al.

We present VoxBind, a new score-based generative model for 3D molecules conditioned on protein structures. Our approach represents molecules as 3D atomic density grids and leverages a 3D voxel-denoising network for learning and generation. We extend the neural empirical Bayes formalism (Saremi & Hyvarinen, 2019) to the conditional setting and generate structure-conditioned molecules with a two-step procedure: (i) sample noisy molecules from the Gaussian-smoothed conditional distribution with underdamped Langevin MCMC using the learned score function and (ii) estimate clean molecules from the noisy samples with single-step denoising. Compared to the current state of the art, our model is simpler to train, significantly faster to sample from, and achieves better results on extensive in silico benchmarks -- the generated molecules are more diverse, exhibit fewer steric clashes, and bind with higher affinity to protein pockets. The code is available at https://github.com/genentech/voxbind/.

Matthieu Kirchmeyer, Pedro O. Pinheiro, Emma Willett et al.

Generative models for structure-based drug design are often limited to a specific modality, restricting their broader applicability. To address this challenge, we introduce FuncBind, a framework based on computer vision to generate target-conditioned, all-atom molecules across atomic systems. FuncBind uses neural fields to represent molecules as continuous atomic densities and employs score-based generative models with modern architectures adapted from the computer vision literature. This modality-agnostic representation allows a single unified model to be trained on diverse atomic systems, from small to large molecules, and handle variable atom/residue counts, including non-canonical amino acids. FuncBind achieves competitive in silico performance in generating small molecules, macrocyclic peptides, and antibody complementarity-determining region loops, conditioned on target structures. FuncBind also generated in vitro novel antibody binders via de novo redesign of the complementarity-determining region H3 loop of two chosen co-crystal structures. As a final contribution, we introduce a new dataset and benchmark for structure-conditioned macrocyclic peptide generation. The code is available at https://github.com/prescient-design/funcbind.

Matthieu Kirchmeyer, Pedro O. Pinheiro, Saeed Saremi

We introduce a new representation for 3D molecules based on their continuous atomic density fields. Using this representation, we propose a new model based on walk-jump sampling for unconditional 3D molecule generation in the continuous space using neural fields. Our model, FuncMol, encodes molecular fields into latent codes using a conditional neural field, samples noisy codes from a Gaussian-smoothed distribution with Langevin MCMC (walk), denoises these samples in a single step (jump), and finally decodes them into molecular fields. FuncMol performs all-atom generation of 3D molecules without assumptions on the molecular structure and scales well with the size of molecules, unlike most approaches. Our method achieves competitive results on drug-like molecules and easily scales to macro-cyclic peptides, with at least one order of magnitude faster sampling. The code is available at https://github.com/prescient-design/funcmol.

Konrad Zolna, Michal Zajac, Negar Rostamzadeh et al.

Neural networks are prone to adversarial attacks. In general, such attacks deteriorate the quality of the input by either slightly modifying most of its pixels, or by occluding it with a patch. In this paper, we propose a method that keeps the image unchanged and only adds an adversarial framing on the border of the image. We show empirically that our method is able to successfully attack state-of-the-art methods on both image and video classification problems. Notably, the proposed method results in a universal attack which is very fast at test time. Source code can be found at https://github.com/zajaczajac/adv_framing .

Patricia Suriana, Joshua A. Rackers, Ewa M. Nowara et al.

Machine learning models for 3D molecular property prediction typically rely on atom-based representations, which may overlook subtle physical information. Electron density maps -- the direct output of X-ray crystallography and cryo-electron microscopy -- offer a continuous, physically grounded alternative. We compare three voxel-based input types for 3D convolutional neural networks (CNNs): atom types, raw electron density, and density gradient magnitude, across two molecular tasks -- protein-ligand binding affinity prediction (PDBbind) and quantum property prediction (QM9). We focus on voxel-based CNNs because electron density is inherently volumetric, and voxel grids provide the most natural representation for both experimental and computed densities. On PDBbind, all representations perform similarly with full data, but in low-data regimes, density-based inputs outperform atom types, while a shape-based baseline performs comparably -- suggesting that spatial occupancy dominates this task. On QM9, where labels are derived from Density Functional Theory (DFT) but input densities from a lower-level method (XTB), density-based inputs still outperform atom-based ones at scale, reflecting the rich structural and electronic information encoded in density. Overall, these results highlight the task- and regime-dependent strengths of density-derived inputs, improving data efficiency in affinity prediction and accuracy in quantum property modeling.

Sai Rajeswar, Cyril Ibrahim, Nitin Surya et al.

Robots in many real-world settings have access to force/torque sensors in their gripper and tactile sensing is often necessary in tasks that involve contact-rich motion. In this work, we leverage surprise from mismatches in touch feedback to guide exploration in hard sparse-reward reinforcement learning tasks. Our approach, Touch-based Curiosity (ToC), learns what visible objects interactions are supposed to "feel" like. We encourage exploration by rewarding interactions where the expectation and the experience don't match. In our proposed method, an initial task-independent exploration phase is followed by an on-task learning phase, in which the original interactions are relabeled with on-task rewards. We test our approach on a range of touch-intensive robot arm tasks (e.g. pushing objects, opening doors), which we also release as part of this work. Across multiple experiments in a simulated setting, we demonstrate that our method is able to learn these difficult tasks through sparse reward and curiosity alone. We compare our cross-modal approach to single-modality (touch- or vision-only) approaches as well as other curiosity-based methods and find that our method performs better and is more sample-efficient.

Pedro O. Pinheiro, Amjad Almahairi, Ryan Y. Benmalek et al.

Contrastive self-supervised learning has emerged as a promising approach to unsupervised visual representation learning. In general, these methods learn global (image-level) representations that are invariant to different views (i.e., compositions of data augmentation) of the same image. However, many visual understanding tasks require dense (pixel-level) representations. In this paper, we propose View-Agnostic Dense Representation (VADeR) for unsupervised learning of dense representations. VADeR learns pixelwise representations by forcing local features to remain constant over different viewing conditions. Specifically, this is achieved through pixel-level contrastive learning: matching features (that is, features that describes the same location of the scene on different views) should be close in an embedding space, while non-matching features should be apart. VADeR provides a natural representation for dense prediction tasks and transfers well to downstream tasks. Our method outperforms ImageNet supervised pretraining (and strong unsupervised baselines) in multiple dense prediction tasks.

Arantxa Casanova, Pedro O. Pinheiro, Negar Rostamzadeh et al.

Learning-based approaches for semantic segmentation have two inherent challenges. First, acquiring pixel-wise labels is expensive and time-consuming. Second, realistic segmentation datasets are highly unbalanced: some categories are much more abundant than others, biasing the performance to the most represented ones. In this paper, we are interested in focusing human labelling effort on a small subset of a larger pool of data, minimizing this effort while maximizing performance of a segmentation model on a hold-out set. We present a new active learning strategy for semantic segmentation based on deep reinforcement learning (RL). An agent learns a policy to select a subset of small informative image regions -- opposed to entire images -- to be labeled, from a pool of unlabeled data. The region selection decision is made based on predictions and uncertainties of the segmentation model being trained. Our method proposes a new modification of the deep Q-network (DQN) formulation for active learning, adapting it to the large-scale nature of semantic segmentation problems. We test the proof of concept in CamVid and provide results in the large-scale dataset Cityscapes. On Cityscapes, our deep RL region-based DQN approach requires roughly 30% less additional labeled data than our most competitive baseline to reach the same performance. Moreover, we find that our method asks for more labels of under-represented categories compared to the baselines, improving their performance and helping to mitigate class imbalance.

Jae Hyun Lim, Pedro O. Pinheiro, Negar Rostamzadeh et al.

For embodied agents to infer representations of the underlying 3D physical world they inhabit, they should efficiently combine multisensory cues from numerous trials, e.g., by looking at and touching objects. Despite its importance, multisensory 3D scene representation learning has received less attention compared to the unimodal setting. In this paper, we propose the Generative Multisensory Network (GMN) for learning latent representations of 3D scenes which are partially observable through multiple sensory modalities. We also introduce a novel method, called the Amortized Product-of-Experts, to improve the computational efficiency and the robustness to unseen combinations of modalities at test time. Experimental results demonstrate that the proposed model can efficiently infer robust modality-invariant 3D-scene representations from arbitrary combinations of modalities and perform accurate cross-modal generation. To perform this exploration, we also develop the Multisensory Embodied 3D-Scene Environment (MESE).

Issam H. Laradji, Negar Rostamzadeh, Pedro O. Pinheiro et al.

Instance segmentation methods often require costly per-pixel labels. We propose a method that only requires point-level annotations. During training, the model only has access to a single pixel label per object, yet the task is to output full segmentation masks. To address this challenge, we construct a network with two branches: (1) a localization network (L-Net) that predicts the location of each object; and (2) an embedding network (E-Net) that learns an embedding space where pixels of the same object are close. The segmentation masks for the located objects are obtained by grouping pixels with similar embeddings. At training time, while L-Net only requires point-level annotations, E-Net uses pseudo-labels generated by a class-agnostic object proposal method. We evaluate our approach on PASCAL VOC, COCO, KITTI and CityScapes datasets. The experiments show that our method (1) obtains competitive results compared to fully-supervised methods in certain scenarios; (2) outperforms fully- and weakly- supervised methods with a fixed annotation budget; and (3) is a first strong baseline for instance segmentation with point-level supervision.

Kris Y. Hong, Pedro O. Pinheiro, Scott Weichenthal

Here we present a new method of estimating global variations in outdoor PM$_{2.5}$ concentrations using satellite images combined with ground-level measurements and deep convolutional neural networks. Specifically, new deep learning models were trained over the global PM$_{2.5}$ concentration range ($<$1-436 $μ$g/m$^3$) using a large database of satellite images paired with ground level PM$_{2.5}$ measurements available from the World Health Organization. Final model selection was based on a systematic evaluation of well-known architectures for the convolutional base including InceptionV3, Xception, and VGG16. The Xception architecture performed best and the final global model had a root mean square error (RMSE) value of 13.01 $μ$g/m$^3$ (R$^2$=0.75) in the disjoint test set. The predictive performance of our new global model (called IMAGE-PM$_{2.5}$) is similar to the current state-of-the-art model used in the Global Burden of Disease study but relies only on satellite images as input. As a result, the IMAGE-PM$_{2.5}$ model offers a fast, cost-effective means of estimating global variations in long-term average PM$_{2.5}$ concentrations and may be particularly useful for regions without ground monitoring data or detailed emissions inventories. The IMAGE-PM$_{2.5}$ model can be used as a stand-alone method of global exposure estimation or incorporated into more complex hierarchical model structures.

Boris N. Oreshkin, Negar Rostamzadeh, Pedro O. Pinheiro et al.

We address the problem of learning fine-grained cross-modal representations. We propose an instance-based deep metric learning approach in joint visual and textual space. The key novelty of this paper is that it shows that using per-image semantic supervision leads to substantial improvement in zero-shot performance over using class-only supervision. On top of that, we provide a probabilistic justification for a metric rescaling approach that solves a very common problem in the generalized zero-shot learning setting, i.e., classifying test images from unseen classes as one of the classes seen during training. We evaluate our approach on two fine-grained zero-shot learning datasets: CUB and FLOWERS. We find that on the generalized zero-shot classification task CLAREL consistently outperforms the existing approaches on both datasets.

Konrad Zolna, Negar Rostamzadeh, Yoshua Bengio et al.

Imitation learning is an effective alternative approach to learn a policy when the reward function is sparse. In this paper, we consider a challenging setting where an agent and an expert use different actions from each other. We assume that the agent has access to a sparse reward function and state-only expert observations. We propose a method which gradually balances between the imitation learning cost and the reinforcement learning objective. In addition, this method adapts the agent's policy based on either mimicking expert behavior or maximizing sparse reward. We show, through navigation scenarios, that (i) an agent is able to efficiently leverage sparse rewards to outperform standard state-only imitation learning, (ii) it can learn a policy even when its actions are different from the expert, and (iii) the performance of the agent is not bounded by that of the expert, due to the optimized usage of sparse rewards.

Chen Xing, Negar Rostamzadeh, Boris N. Oreshkin et al.

Metric-based meta-learning techniques have successfully been applied to few-shot classification problems. In this paper, we propose to leverage cross-modal information to enhance metric-based few-shot learning methods. Visual and semantic feature spaces have different structures by definition. For certain concepts, visual features might be richer and more discriminative than text ones. While for others, the inverse might be true. Moreover, when the support from visual information is limited in image classification, semantic representations (learned from unsupervised text corpora) can provide strong prior knowledge and context to help learning. Based on these two intuitions, we propose a mechanism that can adaptively combine information from both modalities according to new image categories to be learned. Through a series of experiments, we show that by this adaptive combination of the two modalities, our model outperforms current uni-modality few-shot learning methods and modality-alignment methods by a large margin on all benchmarks and few-shot scenarios tested. Experiments also show that our model can effectively adjust its focus on the two modalities. The improvement in performance is particularly large when the number of shots is very small.

Pedro O. Pinheiro, Negar Rostamzadeh, Sungjin Ahn

Single-view 3D shape reconstruction is an important but challenging problem, mainly for two reasons. First, as shape annotation is very expensive to acquire, current methods rely on synthetic data, in which ground-truth 3D annotation is easy to obtain. However, this results in domain adaptation problem when applied to natural images. The second challenge is that there are multiple shapes that can explain a given 2D image. In this paper, we propose a framework to improve over these challenges using adversarial training. On one hand, we impose domain confusion between natural and synthetic image representations to reduce the distribution gap. On the other hand, we impose the reconstruction to be `realistic' by forcing it to lie on a (learned) manifold of realistic object shapes. Our experiments show that these constraints improve performance by a large margin over baseline reconstruction models. We achieve results competitive with the state of the art with a much simpler architecture.

Issam H. Laradji, Negar Rostamzadeh, Pedro O. Pinheiro et al.

Object counting is an important task in computer vision due to its growing demand in applications such as surveillance, traffic monitoring, and counting everyday objects. State-of-the-art methods use regression-based optimization where they explicitly learn to count the objects of interest. These often perform better than detection-based methods that need to learn the more difficult task of predicting the location, size, and shape of each object. However, we propose a detection-based method that does not need to estimate the size and shape of the objects and that outperforms regression-based methods. Our contributions are three-fold: (1) we propose a novel loss function that encourages the network to output a single blob per object instance using point-level annotations only; (2) we design two methods for splitting large predicted blobs between object instances; and (3) we show that our method achieves new state-of-the-art results on several challenging datasets including the Pascal VOC and the Penguins dataset. Our method even outperforms those that use stronger supervision such as depth features, multi-point annotations, and bounding-box labels.

Pedro O. Pinheiro

The objective of unsupervised domain adaptation is to leverage features from a labeled source domain and learn a classifier for an unlabeled target domain, with a similar but different data distribution. Most deep learning approaches to domain adaptation consist of two steps: (i) learn features that preserve a low risk on labeled samples (source domain) and (ii) make the features from both domains to be as indistinguishable as possible, so that a classifier trained on the source can also be applied on the target domain. In general, the classifiers in step (i) consist of fully-connected layers applied directly on the indistinguishable features learned in (ii). In this paper, we propose a different way to do the classification, using similarity learning. The proposed method learns a pairwise similarity function in which classification can be performed by computing similarity between prototype representations of each category. The domain-invariant features and the categorical prototype representations are learned jointly and in an end-to-end fashion. At inference time, images from the target domain are compared to the prototypes and the label associated with the one that best matches the image is outputed. The approach is simple, scalable and effective. We show that our model achieves state-of-the-art performance in different unsupervised domain adaptation scenarios.

Sergey Zagoruyko, Adam Lerer, Tsung-Yi Lin et al.

The recent COCO object detection dataset presents several new challenges for object detection. In particular, it contains objects at a broad range of scales, less prototypical images, and requires more precise localization. To address these challenges, we test three modifications to the standard Fast R-CNN object detector: (1) skip connections that give the detector access to features at multiple network layers, (2) a foveal structure to exploit object context at multiple object resolutions, and (3) an integral loss function and corresponding network adjustment that improve localization. The result of these modifications is that information can flow along multiple paths in our network, including through features from multiple network layers and from multiple object views. We refer to our modified classifier as a "MultiPath" network. We couple our MultiPath network with DeepMask object proposals, which are well suited for localization and small objects, and adapt our pipeline to predict segmentation masks in addition to bounding boxes. The combined system improves results over the baseline Fast R-CNN detector with Selective Search by 66% overall and by 4x on small objects. It placed second in both the COCO 2015 detection and segmentation challenges.

Pedro O. Pinheiro, Tsung-Yi Lin, Ronan Collobert et al.

Object segmentation requires both object-level information and low-level pixel data. This presents a challenge for feedforward networks: lower layers in convolutional nets capture rich spatial information, while upper layers encode object-level knowledge but are invariant to factors such as pose and appearance. In this work we propose to augment feedforward nets for object segmentation with a novel top-down refinement approach. The resulting bottom-up/top-down architecture is capable of efficiently generating high-fidelity object masks. Similarly to skip connections, our approach leverages features at all layers of the net. Unlike skip connections, our approach does not attempt to output independent predictions at each layer. Instead, we first output a coarse `mask encoding' in a feedforward pass, then refine this mask encoding in a top-down pass utilizing features at successively lower layers. The approach is simple, fast, and effective. Building on the recent DeepMask network for generating object proposals, we show accuracy improvements of 10-20% in average recall for various setups. Additionally, by optimizing the overall network architecture, our approach, which we call SharpMask, is 50% faster than the original DeepMask network (under .8s per image).

Pedro O. Pinheiro, Ronan Collobert, Piotr Dollar

Recent object detection systems rely on two critical steps: (1) a set of object proposals is predicted as efficiently as possible, and (2) this set of candidate proposals is then passed to an object classifier. Such approaches have been shown they can be fast, while achieving the state of the art in detection performance. In this paper, we propose a new way to generate object proposals, introducing an approach based on a discriminative convolutional network. Our model is trained jointly with two objectives: given an image patch, the first part of the system outputs a class-agnostic segmentation mask, while the second part of the system outputs the likelihood of the patch being centered on a full object. At test time, the model is efficiently applied on the whole test image and generates a set of segmentation masks, each of them being assigned with a corresponding object likelihood score. We show that our model yields significant improvements over state-of-the-art object proposal algorithms. In particular, compared to previous approaches, our model obtains substantially higher object recall using fewer proposals. We also show that our model is able to generalize to unseen categories it has not seen during training. Unlike all previous approaches for generating object masks, we do not rely on edges, superpixels, or any other form of low-level segmentation.

Rémi Lebret, Pedro O. Pinheiro, Ronan Collobert

Generating a novel textual description of an image is an interesting problem that connects computer vision and natural language processing. In this paper, we present a simple model that is able to generate descriptive sentences given a sample image. This model has a strong focus on the syntax of the descriptions. We train a purely bilinear model that learns a metric between an image representation (generated from a previously trained Convolutional Neural Network) and phrases that are used to described them. The system is then able to infer phrases from a given image sample. Based on caption syntax statistics, we propose a simple language model that can produce relevant descriptions for a given test image using the phrases inferred. Our approach, which is considerably simpler than state-of-the-art models, achieves comparable results in two popular datasets for the task: Flickr30k and the recently proposed Microsoft COCO.

Remi Lebret, Pedro O. Pinheiro, Ronan Collobert

Generating a novel textual description of an image is an interesting problem that connects computer vision and natural language processing. In this paper, we present a simple model that is able to generate descriptive sentences given a sample image. This model has a strong focus on the syntax of the descriptions. We train a purely bilinear model that learns a metric between an image representation (generated from a previously trained Convolutional Neural Network) and phrases that are used to described them. The system is then able to infer phrases from a given image sample. Based on caption syntax statistics, we propose a simple language model that can produce relevant descriptions for a given test image using the phrases inferred. Our approach, which is considerably simpler than state-of-the-art models, achieves comparable results on the recently release Microsoft COCO dataset.

Pedro O. Pinheiro, Ronan Collobert

We are interested in inferring object segmentation by leveraging only object class information, and by considering only minimal priors on the object segmentation task. This problem could be viewed as a kind of weakly supervised segmentation task, and naturally fits the Multiple Instance Learning (MIL) framework: every training image is known to have (or not) at least one pixel corresponding to the image class label, and the segmentation task can be rewritten as inferring the pixels belonging to the class of the object (given one image, and its object class). We propose a Convolutional Neural Network-based model, which is constrained during training to put more weight on pixels which are important for classifying the image. We show that at test time, the model has learned to discriminate the right pixels well enough, such that it performs very well on an existing segmentation benchmark, by adding only few smoothing priors. Our system is trained using a subset of the Imagenet dataset and the segmentation experiments are performed on the challenging Pascal VOC dataset (with no fine-tuning of the model on Pascal VOC). Our model beats the state of the art results in weakly supervised object segmentation task by a large margin. We also compare the performance of our model with state of the art fully-supervised segmentation approaches.