Search

Recent advancements in Model-Based Reinforcement Learning (MBRL) have made it a powerful tool for visual control tasks. Despite improved data efficiency, it remains challenging to train MBRL agents with generalizable perception. Training in the presence of visual distractions is particularly difficult due to the high variation they introduce to representation learning. Building on DREAMER, a popular MBRL method, we propose a simple yet effective auxiliary task to facilitate representation learning in distracting environments. Under the assumption that task-relevant components of image observations are straightforward to identify with prior knowledge in a given task, we use a segmentation mask on image observations to only reconstruct task-relevant components. In doing so, we greatly reduce the complexity of representation learning by removing the need to encode task-irrelevant objects in the latent representation. Our method, Segmentation Dreamer (SD), can be used either with ground-truth masks easily accessible in simulation or by leveraging potentially imperfect segmentation foundation models. The latter is further improved by selectively applying the reconstruction loss to avoid providing misleading learning signals due to mask prediction errors. In modified DeepMind Control suite (DMC) and Meta-World tasks with added visual distractions, SD achieves significantly better sample efficiency and greater final performance than prior work. We find that SD is especially helpful in sparse reward tasks otherwise unsolvable by prior work, enabling the training of visually robust agents without the need for extensive reward engineering.

Shoeprints are a common type of evidence found at crime scenes and are used regularly in forensic investigations. However, existing methods cannot effectively employ deep learning techniques to match noisy and occluded crime-scene shoeprints to a shoe database due to a lack of training data. Moreover, all existing methods match crime-scene shoeprints to clean reference prints, yet our analysis shows matching to more informative tread depth maps yields better retrieval results. The matching task is further complicated by the necessity to identify similarities only in corresponding regions (heels, toes, etc) of prints and shoe treads. To overcome these challenges, we leverage shoe tread images from online retailers and utilize an off-the-shelf predictor to estimate depth maps and clean prints. Our method, named CriSp, matches crime-scene shoeprints to tread depth maps by training on this data. CriSp incorporates data augmentation to simulate crime-scene shoeprints, an encoder to learn spatially-aware features, and a masking module to ensure only visible regions of crime-scene prints affect retrieval results. To validate our approach, we introduce two validation sets by reprocessing existing datasets of crime-scene shoeprints and establish a benchmarking protocol for comparison. On this benchmark, CriSp significantly outperforms state-of-the-art methods in both automated shoeprint matching and image retrieval tailored to this task.

Egocentric sensors such as AR/VR devices capture human-object interactions and offer the potential to provide task-assistance by recalling 3D locations of objects of interest in the surrounding environment. This capability requires instance tracking in real-world 3D scenes from egocentric videos (IT3DEgo). We explore this problem by first introducing a new benchmark dataset, consisting of RGB and depth videos, per-frame camera pose, and instance-level annotations in both 2D camera and 3D world coordinates. We present an evaluation protocol which evaluates tracking performance in 3D coordinates with two settings for enrolling instances to track: (1) single-view online enrollment where an instance is specified on-the-fly based on the human wearer's interactions. and (2) multi-view pre-enrollment where images of an instance to be tracked are stored in memory ahead of time. To address IT3DEgo, we first re-purpose methods from relevant areas, e.g., single object tracking (SOT) -- running SOT methods to track instances in 2D frames and lifting them to 3D using camera pose and depth. We also present a simple method that leverages pretrained segmentation and detection models to generate proposals from RGB frames and match proposals with enrolled instance images. Our experiments show that our method (with no finetuning) significantly outperforms SOT-based approaches in the egocentric setting. We conclude by arguing that the problem of egocentric instance tracking is made easier by leveraging camera pose and using a 3D allocentric (world) coordinate representation., Comment: Accepted at CVPR 2024. Also presented at First Joint Egocentric Vision (EgoVis) Workshop @ CVPR 2024

We propose InCA, a lightweight method for transfer learning that cross-attends to any activation layer of a pre-trained model. During training, InCA uses a single forward pass to extract multiple activations, which are passed to external cross-attention adapters, trained anew and combined or selected for downstream tasks. We show that, even when selecting a single top-scoring adapter, InCA achieves performance comparable to full fine-tuning, at a cost comparable to fine-tuning just the last layer. For example, with a cross-attention probe 1.3% the size of a pre-trained ViT-L/16 model, we achieve performance within 0.2% of the full fine-tuning paragon at a computational training cost of 51% of the baseline, on average across 11 downstream classification. Unlike other forms of efficient adaptation, InCA does not require backpropagating through the pre-trained model, thus leaving its execution unaltered at both training and inference. The versatility of InCA is best illustrated in fine-grained tasks, which may require accessing information absent in the last layer but accessible in intermediate layer activations. Since the backbone is fixed, InCA allows parallel ensembling as well as parallel execution of multiple tasks. InCA achieves state-of-the-art performance in the ImageNet-to-Sketch multi-task benchmark., Comment: Accepted to NeurIPS 2023

Shoe tread impressions are one of the most common types of evidence left at crime scenes. However, the utility of such evidence is limited by the lack of databases of footwear prints that cover the large and growing number of distinct shoe models. Moreover, the database is preferred to contain the 3D shape, or depth, of shoe-tread photos so as to allow for extracting shoeprints to match a query (crime-scene) print. We propose to address this gap by leveraging shoe-tread photos collected by online retailers. The core challenge is to predict depth maps for these photos. As they do not have ground-truth 3D shapes allowing for training depth predictors, we exploit synthetic data that does. We develop a method termed ShoeRinsics that learns to predict depth by leveraging a mix of fully supervised synthetic data and unsupervised retail image data. In particular, we find domain adaptation and intrinsic image decomposition techniques effectively mitigate the synthetic-real domain gap and yield significantly better depth prediction. To validate our method, we introduce 2 validation sets consisting of shoe-tread image and print pairs and define a benchmarking protocol to quantify the quality of predicted depth. On this benchmark, ShoeRinsics outperforms existing methods of depth prediction and synthetic-to-real domain adaptation., Comment: published in WACV 2023; 8 pages including 11 figures and 3 tables; contains reference and appendix

Nonparametric based methods have recently shown promising results in reconstructing human bodies from monocular images while model-based methods can help correct these estimates and improve prediction. However, estimating model parameters from global image features may lead to noticeable misalignment between the estimated meshes and image evidence. To address this issue and leverage the best of both worlds, we propose a framework of three consecutive modules. A dense map prediction module explicitly establishes the dense UV correspondence between the image evidence and each part of the body model. The inverse kinematics module refines the key point prediction and generates a posed template mesh. Finally, a UV inpainting module relies on the corresponding feature, prediction and the posed template, and completes the predictions of occluded body shape. Our framework leverages the best of non-parametric and model-based methods and is also robust to partial occlusion. Experiments demonstrate that our framework outperforms existing 3D human estimation methods on multiple public benchmarks.

Adapting pre-trained models with broad capabilities has become standard practice for learning a wide range of downstream tasks. The typical approach of fine-tuning different models for each task is performant, but incurs a substantial memory cost. To efficiently learn multiple downstream tasks we introduce Task Adaptive Parameter Sharing (TAPS), a general method for tuning a base model to a new task by adaptively modifying a small, task-specific subset of layers. This enables multi-task learning while minimizing resources used and competition between tasks. TAPS solves a joint optimization problem which determines which layers to share with the base model and the value of the task-specific weights. Further, a sparsity penalty on the number of active layers encourages weight sharing with the base model. Compared to other methods, TAPS retains high accuracy on downstream tasks while introducing few task-specific parameters. Moreover, TAPS is agnostic to the model architecture and requires only minor changes to the training scheme. We evaluate our method on a suite of fine-tuning tasks and architectures (ResNet, DenseNet, ViT) and show that it achieves state-of-the-art performance while being simple to implement., Comment: CVPR 2022 Camera Ready. 15 pages, 11 figures

Reference-guided image inpainting restores image pixels by leveraging the content from another single reference image. The primary challenge is how to precisely place the pixels from the reference image into the hole region. Therefore, understanding the 3D geometry that relates pixels between two views is a crucial step towards building a better model. Given the complexity of handling various types of reference images, we focus on the scenario where the images are captured by freely moving the same camera around. Compared to the previous work, we propose a principled approach that does not make heuristic assumptions about the planarity of the scene. We leverage a monocular depth estimate and predict relative pose between cameras, then align the reference image to the target by a differentiable 3D reprojection and a joint optimization of relative pose and depth map scale and offset. Our approach achieves state-of-the-art performance on both RealEstate10K and MannequinChallenge dataset with large baselines, complex geometry and extreme camera motions. We experimentally verify our approach is also better at handling large holes., Comment: Accepted to WACV 2023

Natural language instruction following tasks serve as a valuable test-bed for grounded language and robotics research. However, data collection for these tasks is expensive and end-to-end approaches suffer from data inefficiency. We propose the structuring of language, acting, and visual tasks into separate modules that can be trained independently. Using a Language, Action, and Vision (LAV) framework removes the dependence of action and vision modules on instruction following datasets, making them more efficient to train. We also present a preliminary evaluation of LAV on the ALFRED task for visual and interactive instruction following.

Traditionally, distillation has been used to train a student model to emulate the input/output functionality of a teacher. A more useful goal than emulation, yet under-explored, is for the student to learn feature representations that transfer well to future tasks. However, we observe that standard distillation of task-specific teachers actually *reduces* the transferability of student representations to downstream tasks. We show that a multi-head, multi-task distillation method using an unlabeled proxy dataset and a generalist teacher is sufficient to consolidate representations from task-specific teacher(s) and improve downstream performance, outperforming the teacher(s) and the strong baseline of ImageNet pretrained features. Our method can also combine the representational knowledge of multiple teachers trained on one or multiple domains into a single model, whose representation is improved on all teachers' domain(s).

Temporal action segmentation is a task to classify each frame in the video with an action label. However, it is quite expensive to annotate every frame in a large corpus of videos to construct a comprehensive supervised training dataset. Thus in this work we propose an unsupervised method, namely SSCAP, that operates on a corpus of unlabeled videos and predicts a likely set of temporal segments across the videos. SSCAP leverages Self-Supervised learning to extract distinguishable features and then applies a novel Co-occurrence Action Parsing algorithm to not only capture the correlation among sub-actions underlying the structure of activities, but also estimate the temporal path of the sub-actions in an accurate and general way. We evaluate on both classic datasets (Breakfast, 50Salads) and the emerging fine-grained action dataset (FineGym) with more complex activity structures and similar sub-actions. Results show that SSCAP achieves state-of-the-art performance on all datasets and can even outperform some weakly-supervised approaches, demonstrating its effectiveness and generalizability., Comment: WACV 2022 camera ready

Fine-tuning from a collection of models pre-trained on different domains (a "model zoo") is emerging as a technique to improve test accuracy in the low-data regime. However, model selection, i.e. how to pre-select the right model to fine-tune from a model zoo without performing any training, remains an open topic. We use a linearized framework to approximate fine-tuning, and introduce two new baselines for model selection -- Label-Gradient and Label-Feature Correlation. Since all model selection algorithms in the literature have been tested on different use-cases and never compared directly, we introduce a new comprehensive benchmark for model selection comprising of: i) A model zoo of single and multi-domain models, and ii) Many target tasks. Our benchmark highlights accuracy gain with model zoo compared to fine-tuning Imagenet models. We show our model selection baseline can select optimal models to fine-tune in few selections and has the highest ranking correlation to fine-tuning accuracy compared to existing algorithms., Comment: 14 pages

We present a plug-in replacement for batch normalization (BN) called exponential moving average normalization (EMAN), which improves the performance of existing student-teacher based self- and semi-supervised learning techniques. Unlike the standard BN, where the statistics are computed within each batch, EMAN, used in the teacher, updates its statistics by exponential moving average from the BN statistics of the student. This design reduces the intrinsic cross-sample dependency of BN and enhances the generalization of the teacher. EMAN improves strong baselines for self-supervised learning by 4-6/1-2 points and semi-supervised learning by about 7/2 points, when 1%/10% supervised labels are available on ImageNet. These improvements are consistent across methods, network architectures, training duration, and datasets, demonstrating the general effectiveness of this technique. The code is available at https://github.com/amazon-research/exponential-moving-average-normalization., Comment: accepted by CVPR21 as Oral presentation

Monocular depth predictors are typically trained on large-scale training sets which are naturally biased w.r.t the distribution of camera poses. As a result, trained predictors fail to make reliable depth predictions for testing examples captured under uncommon camera poses. To address this issue, we propose two novel techniques that exploit the camera pose during training and prediction. First, we introduce a simple perspective-aware data augmentation that synthesizes new training examples with more diverse views by perturbing the existing ones in a geometrically consistent manner. Second, we propose a conditional model that exploits the per-image camera pose as prior knowledge by encoding it as a part of the input. We show that jointly applying the two methods improves depth prediction on images captured under uncommon and even never-before-seen camera poses. We show that our methods improve performance when applied to a range of different predictor architectures. Lastly, we show that explicitly encoding the camera pose distribution improves the generalization performance of a synthetically trained depth predictor when evaluated on real images., Comment: Accepted at CVPR2021, Oral

A system capturing the association between video frames and textual queries offer great potential for better video analysis. However, training such a system in a fully supervised way inevitably demands a meticulously curated video dataset with temporal-textual annotations. Therefore we provide a Weak-Supervised alternative with our proposed Referring Attention mechanism to learn temporal-textual association (dubbed WSRA). The weak supervision is simply a textual expression (e.g., short phrases or sentences) at video level, indicating this video contains relevant frames. The referring attention is our designed mechanism acting as a scoring function for grounding the given queries over frames temporally. It consists of multiple novel losses and sampling strategies for better training. The principle in our designed mechanism is to fully exploit 1) the weak supervision by considering informative and discriminative cues from intra-video segments anchored with the textual query, 2) multiple queries compared to the single video, and 3) cross-video visual similarities. We validate our WSRA through extensive experiments for temporally grounding by languages, demonstrating that it outperforms the state-of-the-art weakly-supervised methods notably., Comment: 12 pages, 6 figures

The nematode Caenorhabditis elegans (C. elegans) serves as an important model organism in a wide variety of biological studies. In this paper we introduce a pipeline for automated analysis of C. elegans imagery for the purpose of studying life-span, health-span and the underlying genetic determinants of aging. Our system detects and segments the worm, and predicts body coordinates at each pixel location inside the worm. These coordinates provide dense correspondence across individual animals to allow for meaningful comparative analysis. We show that a model pre-trained to perform body-coordinate regression extracts rich features that can be used to predict the age of individual worms with high accuracy. This lays the ground for future research in quantifying the relation between organs' physiologic and biochemical state, and individual life/health-span., Comment: Computer Vision for Microscopy Image Analysis (CVMI) 2020

Monocular estimation of 3d human pose has attracted increased attention with the availability of large ground-truth motion capture datasets. However, the diversity of training data available is limited and it is not clear to what extent methods generalize outside the specific datasets they are trained on. In this work we carry out a systematic study of the diversity and biases present in specific datasets and its effect on cross-dataset generalization across a compendium of 5 pose datasets. We specifically focus on systematic differences in the distribution of camera viewpoints relative to a body-centered coordinate frame. Based on this observation, we propose an auxiliary task of predicting the camera viewpoint in addition to pose. We find that models trained to jointly predict viewpoint and pose systematically show significantly improved cross-dataset generalization., Comment: http://wangzheallen.github.io/cross-dataset-generalization

Leveraging synthetically rendered data offers great potential to improve monocular depth estimation and other geometric estimation tasks, but closing the synthetic-real domain gap is a non-trivial and important task. While much recent work has focused on unsupervised domain adaptation, we consider a more realistic scenario where a large amount of synthetic training data is supplemented by a small set of real images with ground-truth. In this setting, we find that existing domain translation approaches are difficult to train and offer little advantage over simple baselines that use a mix of real and synthetic data. A key failure mode is that real-world images contain novel objects and clutter not present in synthetic training. This high-level domain shift isn't handled by existing image translation models. Based on these observations, we develop an attention module that learns to identify and remove difficult out-of-domain regions in real images in order to improve depth prediction for a model trained primarily on synthetic data. We carry out extensive experiments to validate our attend-remove-complete approach (ARC) and find that it significantly outperforms state-of-the-art domain adaptation methods for depth prediction. Visualizing the removed regions provides interpretable insights into the synthetic-real domain gap., Comment: camera-ready version, CVPR2020

We describe a latent approach that learns to detect actions in long sequences given training videos with only whole-video class labels. Our approach makes use of two innovations to attention-modeling in weakly-supervised learning. First, and most notably, our framework uses an attention model to extract both foreground and background frames whose appearance is explicitly modeled. Most prior works ignore the background, but we show that modeling it allows our system to learn a richer notion of actions and their temporal extents. Second, we combine bottom-up, class-agnostic attention modules with top-down, class-specific activation maps, using the latter as form of self-supervision for the former. Doing so allows our model to learn a more accurate model of attention without explicit temporal supervision. These modifications lead to 10% AP@IoU=0.5 improvement over existing systems on THUMOS14. Our proposed weaklysupervised system outperforms recent state-of-the-arts by at least 4.3% AP@IoU=0.5. Finally, we demonstrate that weakly-supervised learning can be used to aggressively scale-up learning to in-the-wild, uncurated Instagram videos. The addition of these videos significantly improves localization performance of our weakly-supervised model, Comment: To appear at ICCV 2019

Full 3D estimation of human pose from a single image remains a challenging task despite many recent advances. In this paper, we explore the hypothesis that strong prior information about scene geometry can be used to improve pose estimation accuracy. To tackle this question empirically, we have assembled a novel $\textbf{Geometric Pose Affordance}$ dataset, consisting of multi-view imagery of people interacting with a variety of rich 3D environments. We utilized a commercial motion capture system to collect gold-standard estimates of pose and construct accurate geometric 3D CAD models of the scene itself. To inject prior knowledge of scene constraints into existing frameworks for pose estimation from images, we introduce a novel, view-based representation of scene geometry, a $\textbf{multi-layer depth map}$, which employs multi-hit ray tracing to concisely encode multiple surface entry and exit points along each camera view ray direction. We propose two different mechanisms for integrating multi-layer depth information pose estimation: input as encoded ray features used in lifting 2D pose to full 3D, and secondly as a differentiable loss that encourages learned models to favor geometrically consistent pose estimates. We show experimentally that these techniques can improve the accuracy of 3D pose estimates, particularly in the presence of occlusion and complex scene geometry., Comment: $\href{https://wangzheallen.github.io/GPA.html}{Project Page}$, in submission to CVIU

Computer Vision applications often require a textual grounding module with precision, interpretability, and resilience to counterfactual inputs/queries. To achieve high grounding precision, current textual grounding methods heavily rely on large-scale training data with manual annotations at the pixel level. Such annotations are expensive to obtain and thus severely narrow the model's scope of real-world applications. Moreover, most of these methods sacrifice interpretability, generalizability, and they neglect the importance of being resilient to counterfactual inputs. To address these issues, we propose a visual grounding system which is 1) end-to-end trainable in a weakly supervised fashion with only image-level annotations, and 2) counterfactually resilient owing to the modular design. Specifically, we decompose textual descriptions into three levels: entity, semantic attribute, color information, and perform compositional grounding progressively. We validate our model through a series of experiments and demonstrate its improvement over the state-of-the-art methods. In particular, our model's performance not only surpasses other weakly/un-supervised methods and even approaches the strongly supervised ones, but also is interpretable for decision making and performs much better in face of counterfactual classes than all the others., Comment: 13 pages, 12 figures, IEEE Conference on Computer Vision and Pattern Recognition, 2019

We introduce multigrid Predictive Filter Flow (mgPFF), a framework for unsupervised learning on videos. The mgPFF takes as input a pair of frames and outputs per-pixel filters to warp one frame to the other. Compared to optical flow used for warping frames, mgPFF is more powerful in modeling sub-pixel movement and dealing with corruption (e.g., motion blur). We develop a multigrid coarse-to-fine modeling strategy that avoids the requirement of learning large filters to capture large displacement. This allows us to train an extremely compact model (4.6MB) which operates in a progressive way over multiple resolutions with shared weights. We train mgPFF on unsupervised, free-form videos and show that mgPFF is able to not only estimate long-range flow for frame reconstruction and detect video shot transitions, but also readily amendable for video object segmentation and pose tracking, where it substantially outperforms the published state-of-the-art without bells and whistles. Moreover, owing to mgPFF's nature of per-pixel filter prediction, we have the unique opportunity to visualize how each pixel is evolving during solving these tasks, thus gaining better interpretability., Comment: webpage (https://www.ics.uci.edu/~skong2/mgpff.html)

Dynamic scenes that contain both object motion and egomotion are a challenge for monocular visual odometry (VO). Another issue with monocular VO is the scale ambiguity, i.e. these methods cannot estimate scene depth and camera motion in real scale. Here, we propose a learning based approach to predict camera motion parameters directly from optic flow, by marginalizing depthmap variations and outliers. This is achieved by learning a sparse overcomplete basis set of egomotion in an autoencoder network, which is able to eliminate irrelevant components of optic flow for the task of camera parameter or motionfield estimation. The model is trained using a sparsity regularizer and a supervised egomotion loss, and achieves the state-of-the-art performances on trajectory prediction and camera rotation prediction tasks on KITTI and Virtual KITTI datasets, respectively. The sparse latent space egomotion representation learned by the model is robust and requires only 5% of the hidden layer neurons to maintain the best trajectory prediction accuracy on KITTI dataset. Additionally, in presence of depth information, the proposed method demonstrates faithful object velocity prediction for wide range of object sizes and speeds by global compensation of predicted egomotion and a divisive normalization procedure., Comment: With supplementary material

We tackle the problem of automatically reconstructing a complete 3D model of a scene from a single RGB image. This challenging task requires inferring the shape of both visible and occluded surfaces. Our approach utilizes viewer-centered, multi-layer representation of scene geometry adapted from recent methods for single object shape completion. To improve the accuracy of view-centered representations for complex scenes, we introduce a novel "Epipolar Feature Transformer" that transfers convolutional network features from an input view to other virtual camera viewpoints, and thus better covers the 3D scene geometry. Unlike existing approaches that first detect and localize objects in 3D, and then infer object shape using category-specific models, our approach is fully convolutional, end-to-end differentiable, and avoids the resolution and memory limitations of voxel representations. We demonstrate the advantages of multi-layer depth representations and epipolar feature transformers on the reconstruction of a large database of indoor scenes., Comment: Accepted at ICCV 2019. Paper title changed. Project web page: https://research.dshin.org/iccv19/multi-layer-depth

We introduce a method to provide vectorial representations of visual classification tasks which can be used to reason about the nature of those tasks and their relations. Given a dataset with ground-truth labels and a loss function defined over those labels, we process images through a "probe network" and compute an embedding based on estimates of the Fisher information matrix associated with the probe network parameters. This provides a fixed-dimensional embedding of the task that is independent of details such as the number of classes and does not require any understanding of the class label semantics. We demonstrate that this embedding is capable of predicting task similarities that match our intuition about semantic and taxonomic relations between different visual tasks (e.g., tasks based on classifying different types of plants are similar) We also demonstrate the practical value of this framework for the meta-task of selecting a pre-trained feature extractor for a new task. We present a simple meta-learning framework for learning a metric on embeddings that is capable of predicting which feature extractors will perform well. Selecting a feature extractor with task embedding obtains a performance close to the best available feature extractor, while costing substantially less than exhaustively training and evaluating on all available feature extractors.

We propose a simple, interpretable framework for solving a wide range of image reconstruction problems such as denoising and deconvolution. Given a corrupted input image, the model synthesizes a spatially varying linear filter which, when applied to the input image, reconstructs the desired output. The model parameters are learned using supervised or self-supervised training. We test this model on three tasks: non-uniform motion blur removal, lossy-compression artifact reduction and single image super resolution. We demonstrate that our model substantially outperforms state-of-the-art methods on all these tasks and is significantly faster than optimization-based approaches to deconvolution. Unlike models that directly predict output pixel values, the predicted filter flow is controllable and interpretable, which we demonstrate by visualizing the space of predicted filters for different tasks., Comment: https://www.ics.uci.edu/~skong2/pff.html

Much recent work on visual recognition aims to scale up learning to massive, noisily-annotated datasets. We address the problem of scaling- up the evaluation of such models to large-scale datasets with noisy labels. Current protocols for doing so require a human user to either vet (re-annotate) a small fraction of the test set and ignore the rest, or else correct errors in annotation as they are found through manual inspection of results. In this work, we re-formulate the problem as one of active testing, and examine strategies for efficiently querying a user so as to obtain an accu- rate performance estimate with minimal vetting. We demonstrate the effectiveness of our proposed active testing framework on estimating two performance metrics, Precision@K and mean Average Precision, for two popular computer vision tasks, multi-label classification and instance segmentation. We further show that our approach is able to save significant human annotation effort and is more robust than alternative evaluation protocols., Comment: accepted to ICML 2018

In this paper, we propose a novel self-supervised learning model for estimating continuous ego-motion from video. Our model learns to estimate camera motion by watching RGBD or RGB video streams and determining translational and rotation velocities that correctly predict the appearance of future frames. Our approach differs from other recent work on self-supervised structure-from-motion in its use of a continuous motion formulation and representation of rigid motion fields rather than direct prediction of camera parameters. To make estimation robust in dynamic environments with multiple moving objects, we introduce a simple two-component segmentation process that isolates the rigid background environment from dynamic scene elements. We demonstrate state-of-the-art accuracy of the self-trained model on several benchmark ego-motion datasets and highlight the ability of the model to provide superior rotational accuracy and handling of non-rigid scene motions.

Training deep networks that generalize to a wide range of variations in test data is essential to building accurate and robust image classifiers. One standard strategy is to apply data augmentation to synthetically enlarge the training set. However, data augmentation is essentially a brute-force method which generates uniform samples from some pre-defined set of transformations. In this paper, we propose a principled approach to train networks with significantly improved resistance to large variations between training and testing data. This is achieved by embedding a learnable transformation module into the introspective network, which is a convolutional neural network (CNN) classifier empowered with generative capabilities. Our approach alternates between synthesizing pseudo-negative samples and transformed positive examples based on the current model, and optimizing model predictions on these synthesized samples. Experimental results verify that our approach significantly improves the ability of deep networks to resist large variations between training and testing data and achieves classification accuracy improvements on several benchmark datasets, including MNIST, affNIST, SVHN, CIFAR-10 and miniImageNet., Comment: camera-ready version, WACV 2020

To achieve parsimonious inference in per-pixel labeling tasks with a limited computational budget, we propose a \emph{Pixel-wise Attentional Gating} unit (\emph{PAG}) that learns to selectively process a subset of spatial locations at each layer of a deep convolutional network. PAG is a generic, architecture-independent, problem-agnostic mechanism that can be readily "plugged in" to an existing model with fine-tuning. We utilize PAG in two ways: 1) learning spatially varying pooling fields that improve model performance without the extra computation cost associated with multi-scale pooling, and 2) learning a dynamic computation policy for each pixel to decrease total computation while maintaining accuracy. We extensively evaluate PAG on a variety of per-pixel labeling tasks, including semantic segmentation, boundary detection, monocular depth and surface normal estimation. We demonstrate that PAG allows competitive or state-of-the-art performance on these tasks. Our experiments show that PAG learns dynamic spatial allocation of computation over the input image which provides better performance trade-offs compared to related approaches (e.g., truncating deep models or dynamically skipping whole layers). Generally, we observe PAG can reduce computation by $10\%$ without noticeable loss in accuracy and performance degrades gracefully when imposing stronger computational constraints., Comment: https://www.ics.uci.edu/~skong2/PAG.html

Automated facial expression analysis has a variety of applications in human-computer interaction. Traditional methods mainly analyze prototypical facial expressions of no more than eight discrete emotions as a classification task. However, in practice, spontaneous facial expressions in naturalistic environment can represent not only a wide range of emotions, but also different intensities within an emotion family. In such situation, these methods are not reliable or adequate. In this paper, we propose to train deep convolutional neural networks (CNNs) to analyze facial expressions explainable in a dimensional emotion model. The proposed method accommodates not only a set of basic emotion expressions, but also a full range of other emotions and subtle emotion intensities that we both feel in ourselves and perceive in others in our daily life. Specifically, we first mapped facial expressions into dimensional measures so that we transformed facial expression analysis from a classification problem to a regression one. We then tested our CNN-based methods for facial expression regression and these methods demonstrated promising performance. Moreover, we improved our method by a bilinear pooling which encodes second-order statistics of features. We showed such bilinear-CNN models significantly outperformed their respective baselines., Comment: code: http://www.ics.uci.edu/~skong2/DimensionalEmotionModel.html

The goal of this paper is to compare surface-based and volumetric 3D object shape representations, as well as viewer-centered and object-centered reference frames for single-view 3D shape prediction. We propose a new algorithm for predicting depth maps from multiple viewpoints, with a single depth or RGB image as input. By modifying the network and the way models are evaluated, we can directly compare the merits of voxels vs. surfaces and viewer-centered vs. object-centered for familiar vs. unfamiliar objects, as predicted from RGB or depth images. Among our findings, we show that surface-based methods outperform voxel representations for objects from novel classes and produce higher resolution outputs. We also find that using viewer-centered coordinates is advantageous for novel objects, while object-centered representations are better for more familiar objects. Interestingly, the coordinate frame significantly affects the shape representation learned, with object-centered placing more importance on implicitly recognizing the object category and viewer-centered producing shape representations with less dependence on category recognition., Comment: CVPR 2018

We investigate the problem of automatically determining what type of shoe left an impression found at a crime scene. This recognition problem is made difficult by the variability in types of crime scene evidence (ranging from traces of dust or oil on hard surfaces to impressions made in soil) and the lack of comprehensive databases of shoe outsole tread patterns. We find that mid-level features extracted by pre-trained convolutional neural nets are surprisingly effective descriptors for this specialized domains. However, the choice of similarity measure for matching exemplars to a query image is essential to good performance. For matching multi-channel deep features, we propose the use of multi-channel normalized cross-correlation and analyze its effectiveness. Our proposed metric significantly improves performance in matching crime scene shoeprints to laboratory test impressions. We also show its effectiveness in other cross-domain image retrieval problems: matching facade images to segmentation labels and aerial photos to map images. Finally, we introduce a discriminatively trained variant and fine-tune our system through our proposed metric, obtaining state-of-the-art performance.

Visual question answering (VQA) is of significant interest due to its potential to be a strong test of image understanding systems and to probe the connection between language and vision. Despite much recent progress, general VQA is far from a solved problem. In this paper, we focus on the VQA multiple-choice task, and provide some good practices for designing an effective VQA model that can capture language-vision interactions and perform joint reasoning. We explore mechanisms of incorporating part-of-speech (POS) tag guided attention, convolutional n-grams, triplet attention interactions between the image, question and candidate answer, and structured learning for triplets based on image-question pairs. We evaluate our models on two popular datasets: Visual7W and VQA Real Multiple Choice. Our final model achieves the state-of-the-art performance of 68.2% on Visual7W, and a very competitive performance of 69.6% on the test-standard split of VQA Real Multiple Choice., Comment: 8 pages, 5 figures, state-of-the-art VQA system; https://github.com/wangzheallen/STL-VQA

We introduce a differentiable, end-to-end trainable framework for solving pixel-level grouping problems such as instance segmentation consisting of two novel components. First, we regress pixels into a hyper-spherical embedding space so that pixels from the same group have high cosine similarity while those from different groups have similarity below a specified margin. We analyze the choice of embedding dimension and margin, relating them to theoretical results on the problem of distributing points uniformly on the sphere. Second, to group instances, we utilize a variant of mean-shift clustering, implemented as a recurrent neural network parameterized by kernel bandwidth. This recurrent grouping module is differentiable, enjoys convergent dynamics and probabilistic interpretability. Backpropagating the group-weighted loss through this module allows learning to focus on only correcting embedding errors that won't be resolved during subsequent clustering. Our framework, while conceptually simple and theoretically abundant, is also practically effective and computationally efficient. We demonstrate substantial improvements over state-of-the-art instance segmentation for object proposal generation, as well as demonstrating the benefits of grouping loss for classification tasks such as boundary detection and semantic segmentation.

In this paper, we explore an efficient variant of convolutional sparse coding with unit norm code vectors where reconstruction quality is evaluated using an inner product (cosine distance). To use these codes for discriminative classification, we describe a model we term Energy-Based Spherical Sparse Coding (EB-SSC) in which the hypothesized class label introduces a learned linear bias into the coding step. We evaluate and visualize performance of stacking this encoder to make a deep layered model for image classification.

Objects may appear at arbitrary scales in perspective images of a scene, posing a challenge for recognition systems that process images at a fixed resolution. We propose a depth-aware gating module that adaptively selects the pooling field size in a convolutional network architecture according to the object scale (inversely proportional to the depth) so that small details are preserved for distant objects while larger receptive fields are used for those nearby. The depth gating signal is provided by stereo disparity or estimated directly from monocular input. We integrate this depth-aware gating into a recurrent convolutional neural network to perform semantic segmentation. Our recurrent module iteratively refines the segmentation results, leveraging the depth and semantic predictions from the previous iterations. Through extensive experiments on four popular large-scale RGB-D datasets, we demonstrate this approach achieves competitive semantic segmentation performance with a model which is substantially more compact. We carry out extensive analysis of this architecture including variants that operate on monocular RGB but use depth as side-information during training, unsupervised gating as a generic attentional mechanism, and multi-resolution gating. We find that gated pooling for joint semantic segmentation and depth yields state-of-the-art results for quantitative monocular depth estimation.

Feature point matching for camera localization suffers from scalability problems. Even when feature descriptors associated with 3D scene points are locally unique, as coverage grows, similar or repeated features become increasingly common. As a result, the standard distance ratio-test used to identify reliable image feature points is overly restrictive and rejects many good candidate matches. We propose a simple coarse-to-fine strategy that uses conservative approximations to robust local ratio-tests that can be computed efficiently using global approximate k-nearest neighbor search. We treat these forward matches as votes in camera pose space and use them to prioritize back-matching within candidate camera pose clusters, exploiting feature co-visibility captured by clustering the 3D model camera pose graph. This approach achieves state-of-the-art camera localization results on a variety of popular benchmarks, outperforming several methods that use more complicated data structures and that make more restrictive assumptions on camera pose. We also carry out diagnostic analyses on a difficult test dataset containing globally repetitive structure that suggest our approach successfully adapts to the challenges of large-scale image localization.

Pooling second-order local feature statistics to form a high-dimensional bilinear feature has been shown to achieve state-of-the-art performance on a variety of fine-grained classification tasks. To address the computational demands of high feature dimensionality, we propose to represent the covariance features as a matrix and apply a low-rank bilinear classifier. The resulting classifier can be evaluated without explicitly computing the bilinear feature map which allows for a large reduction in the compute time as well as decreasing the effective number of parameters to be learned. To further compress the model, we propose classifier co-decomposition that factorizes the collection of bilinear classifiers into a common factor and compact per-class terms. The co-decomposition idea can be deployed through two convolutional layers and trained in an end-to-end architecture. We suggest a simple yet effective initialization that avoids explicitly first training and factorizing the larger bilinear classifiers. Through extensive experiments, we show that our model achieves state-of-the-art performance on several public datasets for fine-grained classification trained with only category labels. Importantly, our final model is an order of magnitude smaller than the recently proposed compact bilinear model, and three orders smaller than the standard bilinear CNN model.

We describe an end-to-end framework for learning parameters of min-cost flow multi-target tracking problem with quadratic trajectory interactions including suppression of overlapping tracks and contextual cues about cooccurrence of different objects. Our approach utilizes structured prediction with a tracking-specific loss function to learn the complete set of model parameters. In this learning framework, we evaluate two different approaches to finding an optimal set of tracks under a quadratic model objective, one based on an LP relaxation and the other based on novel greedy variants of dynamic programming that handle pairwise interactions. We find the greedy algorithms achieve almost equivalent accuracy to the LP relaxation while being up to 10x faster than a commercial LP solver. We evaluate trained models on three challenging benchmarks. Surprisingly, we find that with proper parameter learning, our simple data association model without explicit appearance/motion reasoning is able to achieve comparable or better accuracy than many state-of-the-art methods that use far more complex motion features or appearance affinity metric learning., Comment: arXiv admin note: text overlap with arXiv:1412.2066