Georgia Tech Presenting 13 Papers at Premier Computer Vision Conference CVPR

A host of Georgia Tech students and faculty will travel to Salt Lake City this week to attend the conference on Computer Vision and Pattern Recognition (CVPR) 2018.

CVPR is the premier annual computer vision event and comprises a main conference and several co-located workshops and short courses. As in years past, faculty and students in the School of Interactive Computing (IC) and associated research units – the Center for Machine Learning at Georgia Tech (ML@GT), the GVU Center, and the Institute for Robotics and Intelligent Machines – will participate at all levels of the conference.

“CVPR is the top event in computer vision, and Georgia Tech has long had a substantial presence at the conference,” said Irfan Essa, IC professor and ML@GT director. “This year, we have a number of faculty and student researchers participating in the technical program and we’re excited to share our research with the rest of the community.”

More than 10 faculty members and many more student researchers sharing 13 papers in oral, spotlight, poster, and demo presentations will represent Georgia Tech at the five-day event.

The conference will take place June 18-22, with the main technical program set to begin on June 19. Essa will provide a workshop talk at the conference.

Below are titles and abstracts of Georgia Tech’s research being presented this week. The visualization below shows all of Georgia Tech’s research, as well as dates, times, and locations for the associated talks.

Georgia Tech at CVPR 2018

Interactive Classification for Deep Learning Interpretation (Angel Cabrera, Fred Hohman, Jason Lin, Polo Chau)

ABSTRACT: We present an interactive system enabling users to manipulate images to explore the robustness and sensitivity of deep learning image classifiers. Using modern web technologies to run in-browser inference, users can remove image features using inpainting algorithms and obtain new classifications in real time, which allows them to ask a variety of “what if” questions by experimentally modifying images and seeing how the model reacts. Our system allows users to compare and contrast what image regions humans and machine learning models use for classification, revealing a wide range of surprising results ranging from spectacular failures (e.g., a water bottle image becomes a concert when removing a person) to impressive resilience (e.g., a baseball player image remains correctly classified even without a glove or base).

3D-RCNN: Instance-Level 3D Object Reconstruction via Render-and-Compare (Abhijit Kundu, Yin Li, Jim Rehg)

ABSTRACT: We present a fast inverse-graphics framework for instance-level 3D scene understanding. We train a deep convolutional network that learns to map image regions to the full 3D shape and pose of all object instances in the image. Our method produces a compact 3D representation of the scene, which can be readily used for applications like autonomous driving. Many traditional 2D vision outputs, like instance segmentations and depth-maps, can be obtained by simply rendering our output 3D scene model. We exploit class-specific shape priors by learning a low dimensional shape-space from collections of CAD models. We present novel representations of shape and pose, that strive towards better 3D equivariance and generalization. In order to exploit rich supervisory signals in the form of 2D annotations like segmentation, we propose a differentiable Render-and-Compare loss that allows 3D shape and pose to be learned with 2D supervision. We evaluate our method on the challenging real-world datasets of Pascal3D+ and KITTI, where we achieve state-of-the-art results.

Embodied Question Answering (Abhishek Das, Samyak Datta, Georgia Gkioxari, Stefan Lee, Devi Parikh, Dhruv Batra)

ABSTRACT: We present a new AI task – Embodied Question Answering (EmbodiedQA) – where an agent is spawned at a random location in a 3D environment and asked a question (‘What color is the car?’). In order to answer, the agent must first intelligently navigate to explore the environment, gather information through first-person (egocentric) vision, and then answer the question (‘orange’). This challenging task requires a range of AI skills – active perception, language understanding, goal-driven navigation, commonsense reasoning, and grounding of language into actions. In this work, we develop the environments, end-to-end-trained reinforcement learning agents, and evaluation protocols for EmbodiedQA.

Attend and Interact: Higher-Order Object Interactions for Video Understanding (Chih-Yao Ma, Asim Kadav, Iain Melvin, Zsolt Kira, Ghassan AlRegib, Hans Peter Graf)

ABSTRACT: Human actions often involve complex interactions across several inter-related objects in the scene. However, existing approaches to fine-grained video understanding or visual relationship detection often rely on single object representation or pairwise object relationships. Furthermore, learning interactions across multiple objects in hundreds of frames for video is computationally infeasible and performance may suffer since a large combinatorial space has to be modeled. In this paper, we propose to efficiently learn higher-order interactions between arbitrary subgroups of objects for fine-grained video understanding. We demonstrate that modeling object interactions significantly improves accuracy for both action recognition and video captioning, while saving more than 3-times the computation over traditional pairwise relationships. The proposed method is validated on two large-scale datasets: Kinetics and ActivityNet Captions. Our SINet and SINet-Caption achieve state-of-the-art performances on both datasets even though the videos are sampled at a maximum of 1 FPS. To the best of our knowledge, this is the first work modeling object interactions on open domain large-scale video datasets, and we additionally model higher-order object interactions, which improves the performance with low computational costs.

Don’t Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering (Aishwarya Agrawal, Dhruv Batra, Devi Parikh, Aniruddha Kembhavi)

ABSTRACT: A number of studies have found that today’s Visual Question Answering (VQA) models are heavily driven by superficial correlations in the training data and lack sufficient image grounding. To encourage the development of models geared toward the latter, we propose a new setting for VQA where for every question type, train and test sets have different prior distributions of answers. Specifically, we present new splits of the VQA v1 and VQA v2 datasets, which we call Visual Question Answering under Changing Priors (VQACP v1 and VQA-CP v2 respectively). First, we evaluate several existing VQA models under this new setting and show that their performance degrades significantly compared to the original VQA setting. Second, we propose a novel Grounded Visual Question Answering model (GVQA) that contains inductive biases and restrictions in the architecture specifically designed to prevent the model from ‘cheating’ by primarily relying on priors in the training data. Specifically, GVQA explicitly disentangles the recognition of visual concepts present in the image from the identification of plausible answer space for a given question, enabling the model to more robustly generalize across different distributions of answers. GVQA is built off an existing VQA model – Stacked Attention Networks (SAN). Our experiments demonstrate that GVQA significantly outperforms SAN on both VQA-CP v1 and VQA-CP v2 datasets. Interestingly, it also outperforms more powerful VQA models such as Multimodal Compact Bilinear Pooling (MCB) in several cases. GVQA offers strengths complementary to SAN when trained and evaluated on the original VQA v1 and VQA v2 datasets. Finally, GVQA is more transparent and interpretable than existing VQA models.

Mobile Video Object Detection With Temporally-Aware Feature Maps (Mason Liu, Menglong Zhu)

ABSTRACT: This paper introduces an online model for object detection in videos designed to run in real-time on low-powered mobile and embedded devices. Our approach combines fast single-image object detection with convolutional long short-term memory (LSTM) layers to create an interweaved recurrent-convolutional architecture. Additionally, we propose an efficient Bottleneck-LSTM layer that significantly reduces computational cost compared to regular LSTMs. Our network achieves temporal awareness by using Bottleneck-LSTMs to refine and propagate feature maps across frames. This approach is substantially faster than existing detection methods in video, outperforming the fastest single-frame models in model size and computational cost while attaining accuracy comparable to much more expensive single-frame models on the Imagenet VID 2015 dataset. Our model reaches a real-time inference speed of up to 15 FPS on a mobile CPU.

Decoupled Networks (Weiyang Liu, Zhen Liu, Zhiding Yu, Bo Dai, Rongmei Lin, Yisen Wang, Jim Rehg, Le Song)

ABSTRACT: Inner product-based convolution has been a central component of convolutional neural networks (CNNs) and the key to learning visual representations. Inspired by the observation that CNN-learned features are naturally decoupled with the norm of features corresponding to the intra-class variation and the angle corresponding to the semantic difference, we propose a generic decoupled learning framework which models the intra-class variation and semantic difference independently. Specifically, we first reparametrize the inner product to a decoupled form and then generalize it to the decoupled convolution operator which serves as the building block of our decoupled networks. We present several effective instances of the decoupled convolution operator. Each decoupled operator is well motivated and has an intuitive geometric interpretation. Based on these decoupled operators, we further propose to directly learn the operator from data. Extensive experiments show that such decoupled reparameterization renders significant performance gain with easier convergence and stronger robustness.

Geometry-Aware Learning of Maps for Camera Localization (Samarth Brahmbhatt, Jinwei Gu, Kihwan Kim, James Hays, Jan Kautz)

ABSTRACT: Maps are a key component in image-based camera localization and visual SLAM systems: they are used to establish geometric constraints between images, correct drift in relative pose estimation, and relocalize cameras after lost tracking. The exact definitions of maps, however, are often application-specific and hand-crafted for different scenarios (e.g. 3D landmarks, lines, planes, bags of visual words). We propose to represent maps as a deep neural net called MapNet, which enables learning a data-driven map representation. Unlike prior work on learning maps, MapNet exploits cheap and ubiquitous sensory inputs like visual odometry and GPS in addition to images and fuses them together for camera localization. Geometric constraints expressed by these inputs, which have traditionally been used in bundle adjustment or pose-graph optimization, are formulated as loss terms in MapNet training and also used during inference. In addition to directly improving localization accuracy, this allows us to update the MapNet (i.e., maps) in a self-supervised manner using additional unlabeled video sequences from the scene. We also propose a novel parameterization for camera rotation which is better suited for deep-learning based camera pose regression. Experimental results on both the indoor 7-Scenes dataset and the outdoor Oxford RobotCar dataset show significant performance improvement over prior work.

Iterative Learning With Open-Set Noisy Labels (Yisen Wang, Weiyang Liu, Xingjun Ma, James Bailey, Hongyuan Zha, Le Song, Shu-Tao Xia)

ABSTRACT: Large-scale datasets possessing clean label annotations are crucial for training Convolutional Neural Networks (CNNs). However, labeling large-scale data can be very costly and error-prone, and even high-quality datasets are likely to contain noisy (incorrect) labels. Existing works usually employ a closed-set assumption, whereby the samples associated with noisy labels possess a true class contained within the set of known classes in the training data. However, such an assumption is too restrictive for many applications, since samples associated with noisy labels might in fact possess a true class that is not present in the training data. We refer to this more complex scenario as the open-set noisy label problem and show that it is nontrivial in order to make accurate predictions. To address this problem, we propose a novel iterative learning framework for training CNNs on datasets with open-set noisy labels. Our approach detects noisy labels and learns deep discriminative features in an iterative fashion. To benefit from the noisy label detection, we design a Siamese network to encourage clean labels and noisy labels to be dissimilar. A reweighting module is also applied to simultaneously emphasize the learning from clean labels and reduce the effect caused by noisy labels. Experiments on CIFAR-10, ImageNet and real-world noisy (web-search) datasets demonstrate that our proposed model can robustly train CNNs in the presence of a high proportion of open-set as well as closed-set noisy labels.

Neural Baby Talk (Jiasen Lu, Jianwei Yang, Dhruv Batra, Devi Parikh)

ABSTRACT: We introduce a novel framework for image captioning that can produce natural language explicitly grounded in entities that object detectors find in the image. Our approach reconciles classical slot filling approaches (that are generally better grounded in images) with modern neural captioning approaches (that are generally more natural sounding and accurate). Our approach first generates a sentence ‘template’ with slot locations explicitly tied to specific image regions. These slots are then filled in by visual concepts identified in the regions by object detectors. The entire architecture (sentence template generation and slot filling with object detectors) is end-to-end differentiable. We verify the effectiveness of our proposed model on different image captioning tasks. On standard image captioning and novel object captioning, our model reaches state-of-the-art on both COCO and Flickr30k datasets. We also demonstrate that our model has unique advantages when the train and test distributions of scene compositions – and hence language priors of associated captions – are different.

TextureGAN: Controlling Deep Image Synthesis With Texture Patches (Wenqi Xian, Patsorn Sangkloy, Varun Agrawal, Amit Raj, Jingwan Lu, Chen Fang, Fisher Yu, James Hays)

ABSTRACT: In this paper, we investigate deep image synthesis guided by sketch, color, and texture. Previous image synthesis methods can be controlled by sketch and color strokes but we are the first to examine texture control. We allow a user to place a texture patch on a sketch at arbitrary locations and scales to control the desired output texture. Our generative network learns to synthesize objects consistent with these texture suggestions. To achieve this, we develop a local texture loss in addition to adversarial and content loss to train the generative network. We conduct experiments using sketches generated from real images and textures sampled from a separate texture database and results show that our proposed algorithm is able to generate plausible images that are faithful to user controls. Ablation studies show that our proposed pipeline can generate more realistic images than adapting existing methods directly

SktechyGAN: Towards Diverse and Realistic Sketch to Image Synthesis (Wengling Chen, James Hays)

ABSTRACT: Synthesizing realistic images from human drawn sketches is a challenging problem in computer graphics and vision. Existing approaches either need exact edge maps, or rely on retrieval of existing photographs. In this work, we propose a novel Generative Adversarial Network (GAN) approach that synthesizes plausible images from 50 categories including motorcycles, horses and couches. We demonstrate a data augmentation technique for sketches which is fully automatic, and we show that the augmented data is helpful to our task. We introduce a new network building block suitable for both the generator and discriminator which improves the information flow by injecting the input image at multiple scales. Compared to state-of-the-art image translation methods, our approach generates more realistic images and achieves significantly higher Inception Scores.

MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks (Ariel Gordon, Elad Eban, Ofir Nachum, Bo Chen, Hao Wu, Tien-Ju Yang, Edward Choi)

ABSTRACT: We present MorphNet, an approach to automate the design of neural network structures. MorphNet iteratively shrinks and expands a network, shrinking via a resourceweighted sparsifying regularizer on activations and expanding via a uniform multiplicative factor on all layers. In contrast to previous approaches, our method is scalable to large networks, adaptable to specific resource constraints (e.g. the number of floating-point operations per inference), and capable of increasing the network’s performance. When applied to standard network architectures on a wide variety of datasets, our approach discovers novel structures in each domain, obtaining higher performance while respecting the resource constraint.